diff --git a/base/common/logger_useful.h b/base/common/logger_useful.h index c89ec63ef22..ad56ef7e857 100644 --- a/base/common/logger_useful.h +++ b/base/common/logger_useful.h @@ -15,15 +15,27 @@ using Poco::Message; using DB::LogsLevel; using DB::CurrentThread; -/// Logs a message to a specified logger with that level. -#define LOG_IMPL(logger, priority, PRIORITY, ...) do \ +namespace +{ + template constexpr size_t numArgs(Ts &&...) { return sizeof...(Ts); } + template constexpr auto firstArg(T && x, Ts &&...) { return std::forward(x); } +} + + +/// Logs a message to a specified logger with that level. +/// If more than one argument is provided, +/// the first argument is interpreted as template with {}-substitutions +/// and the latter arguments treat as values to substitute. +/// If only one argument is provided, it is threat as message without substitutions. + +#define LOG_IMPL(logger, priority, PRIORITY, ...) do \ { \ const bool is_clients_log = (CurrentThread::getGroup() != nullptr) && \ (CurrentThread::getGroup()->client_logs_level >= (priority)); \ if ((logger)->is((PRIORITY)) || is_clients_log) \ { \ - std::string formatted_message = fmt::format(__VA_ARGS__); \ + std::string formatted_message = numArgs(__VA_ARGS__) > 1 ? fmt::format(__VA_ARGS__) : firstArg(__VA_ARGS__); \ if (auto channel = (logger)->getChannel()) \ { \ std::string file_function; \ diff --git a/cmake/autogenerated_versions.txt b/cmake/autogenerated_versions.txt new file mode 100644 index 00000000000..72959d3c1d8 --- /dev/null +++ b/cmake/autogenerated_versions.txt @@ -0,0 +1,9 @@ +# This strings autochanged from release_lib.sh: +SET(VERSION_REVISION 54435) +SET(VERSION_MAJOR 20) +SET(VERSION_MINOR 5) +SET(VERSION_PATCH 1) +SET(VERSION_GITHASH 91df18a906dcffdbee6816e5389df6c65f86e35f) +SET(VERSION_DESCRIBE v20.5.1.1-prestable) +SET(VERSION_STRING 20.5.1.1) +# end of autochange diff --git a/cmake/protobuf_generate_cpp.cmake b/cmake/protobuf_generate_cpp.cmake index 40ec3c8e681..cc2502e5eeb 100644 --- a/cmake/protobuf_generate_cpp.cmake +++ b/cmake/protobuf_generate_cpp.cmake @@ -55,6 +55,7 @@ function(protobuf_generate_cpp_impl SRCS HDRS MODES OUTPUT_FILE_EXTS PLUGIN) endif() set (intermediate_dir ${CMAKE_CURRENT_BINARY_DIR}/intermediate) + file (MAKE_DIRECTORY ${intermediate_dir}) set (protoc_args) foreach (mode ${MODES}) @@ -112,16 +113,21 @@ if (PROTOBUF_GENERATE_CPP_SCRIPT_MODE) set (intermediate_dir ${DIR}/intermediate) set (intermediate_output "${intermediate_dir}/${FILENAME}") - if (COMPILER_ID STREQUAL "GNU") + if (COMPILER_ID MATCHES "Clang") + set (pragma_push "#pragma clang diagnostic push\n") + set (pragma_pop "#pragma clang diagnostic pop\n") + set (pragma_disable_warnings "#pragma clang diagnostic ignored \"-Weverything\"\n") + elseif (COMPILER_ID MATCHES "GNU") set (pragma_push "#pragma GCC diagnostic push\n") set (pragma_pop "#pragma GCC diagnostic pop\n") set (pragma_disable_warnings "#pragma GCC diagnostic ignored \"-Wall\"\n" "#pragma GCC diagnostic ignored \"-Wextra\"\n" - "#pragma GCC diagnostic ignored \"-Warray-bounds\"\n") - elseif (COMPILER_ID MATCHES "Clang") - set (pragma_push "#pragma clang diagnostic push\n") - set (pragma_pop "#pragma clang diagnostic pop\n") - set (pragma_disable_warnings "#pragma clang diagnostic ignored \"-Weverything\"\n") + "#pragma GCC diagnostic ignored \"-Warray-bounds\"\n" + "#pragma GCC diagnostic ignored \"-Wold-style-cast\"\n" + "#pragma GCC diagnostic ignored \"-Wshadow\"\n" + "#pragma GCC diagnostic ignored \"-Wsuggest-override\"\n" + "#pragma GCC diagnostic ignored \"-Wcast-qual\"\n" + "#pragma GCC diagnostic ignored \"-Wunused-parameter\"\n") endif() if (${FILENAME} MATCHES ".*\\.h") diff --git a/cmake/version.cmake b/cmake/version.cmake index 3f51f59cf0f..eea17f68c47 100644 --- a/cmake/version.cmake +++ b/cmake/version.cmake @@ -1,12 +1,4 @@ -# This strings autochanged from release_lib.sh: -set(VERSION_REVISION 54435) -set(VERSION_MAJOR 20) -set(VERSION_MINOR 5) -set(VERSION_PATCH 1) -set(VERSION_GITHASH 91df18a906dcffdbee6816e5389df6c65f86e35f) -set(VERSION_DESCRIBE v20.5.1.1-prestable) -set(VERSION_STRING 20.5.1.1) -# end of autochange +include(${CMAKE_SOURCE_DIR}/cmake/autogenerated_versions.txt) set(VERSION_EXTRA "" CACHE STRING "") set(VERSION_TWEAK "" CACHE STRING "") diff --git a/cmake/yandex/ya.make.versions.inc b/cmake/yandex/ya.make.versions.inc new file mode 100644 index 00000000000..3ac401cb108 --- /dev/null +++ b/cmake/yandex/ya.make.versions.inc @@ -0,0 +1,25 @@ +INCLUDE(${ARCADIA_ROOT}/clickhouse/cmake/autogenerated_versions.txt) + +# TODO: not sure if this is customizable per-binary +SET(VERSION_NAME "ClickHouse") + +# TODO: not quite sure how to replace dash with space in ya.make +SET(VERSION_FULL "${VERSION_NAME}-${VERSION_STRING}") + +CFLAGS (GLOBAL -DDBMS_NAME=\"ClickHouse\") +CFLAGS (GLOBAL -DDBMS_VERSION_MAJOR=${VERSION_MAJOR}) +CFLAGS (GLOBAL -DDBMS_VERSION_MINOR=${VERSION_MINOR}) +CFLAGS (GLOBAL -DDBMS_VERSION_PATCH=${VERSION_PATCH}) +CFLAGS (GLOBAL -DVERSION_FULL=\"\\\"${VERSION_FULL}\\\"\") +CFLAGS (GLOBAL -DVERSION_MAJOR=${VERSION_MAJOR}) +CFLAGS (GLOBAL -DVERSION_MINOR=${VERSION_MINOR}) +CFLAGS (GLOBAL -DVERSION_PATCH=${VERSION_PATCH}) + +# TODO: not supported yet, not sure if ya.make supports arithmetics. +CFLAGS (GLOBAL -DVERSION_INTEGER=0) + +CFLAGS (GLOBAL -DVERSION_NAME=\"\\\"${VERSION_NAME}\\\"\") +CFLAGS (GLOBAL -DVERSION_OFFICIAL=\"-arcadia\") +CFLAGS (GLOBAL -DVERSION_REVISION=${VERSION_REVISION}) +CFLAGS (GLOBAL -DVERSION_STRING=\"\\\"${VERSION_STRING}\\\"\") + diff --git a/contrib/cctz-cmake/CMakeLists.txt b/contrib/cctz-cmake/CMakeLists.txt index df9fd6aa61c..0837a366f20 100644 --- a/contrib/cctz-cmake/CMakeLists.txt +++ b/contrib/cctz-cmake/CMakeLists.txt @@ -618,7 +618,12 @@ if (USE_INTERNAL_CCTZ) add_library(tzdata STATIC ${TZ_OBJS}) set_target_properties(tzdata PROPERTIES LINKER_LANGUAGE C) - target_link_libraries(cctz -Wl,--whole-archive tzdata -Wl,--no-whole-archive) # whole-archive prevents symbols from being discarded + # whole-archive prevents symbols from being discarded for unknown reason + # CMake can shuffle each of target_link_libraries arguments with other + # libraries in linker command. To avoid this we hardcode whole-archive + # library into single string. + add_dependencies(cctz tzdata) + target_link_libraries(cctz INTERFACE "-Wl,--whole-archive $ -Wl,--no-whole-archive") endif () else () diff --git a/contrib/jemalloc b/contrib/jemalloc index cd2931ad9bb..ea6b3e973b4 160000 --- a/contrib/jemalloc +++ b/contrib/jemalloc @@ -1 +1 @@ -Subproject commit cd2931ad9bbd78208565716ab102e86d858c2fff +Subproject commit ea6b3e973b477b8061e0076bb257dbd7f3faa756 diff --git a/contrib/jemalloc-cmake/CMakeLists.txt b/contrib/jemalloc-cmake/CMakeLists.txt index 9081de593b8..63c5a5e66ea 100644 --- a/contrib/jemalloc-cmake/CMakeLists.txt +++ b/contrib/jemalloc-cmake/CMakeLists.txt @@ -17,7 +17,13 @@ if (ENABLE_JEMALLOC) # # By enabling percpu_arena number of arenas limited to number of CPUs and hence # this problem should go away. - set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu" CACHE STRING "Change default configuration string of JEMalloc" ) + set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0") + # CACHE variable is empty, to allow changing defaults without necessity + # to purge cache + set (JEMALLOC_CONFIG_MALLOC_CONF_OVERRIDE "" CACHE STRING "Change default configuration string of JEMalloc" ) + if (JEMALLOC_CONFIG_MALLOC_CONF_OVERRIDE) + set (JEMALLOC_CONFIG_MALLOC_CONF "${JEMALLOC_CONFIG_MALLOC_CONF_OVERRIDE}") + endif() message (STATUS "jemalloc malloc_conf: ${JEMALLOC_CONFIG_MALLOC_CONF}") set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/jemalloc") @@ -55,6 +61,7 @@ if (ENABLE_JEMALLOC) ${LIBRARY_DIR}/src/ticker.c ${LIBRARY_DIR}/src/tsd.c ${LIBRARY_DIR}/src/witness.c + ${LIBRARY_DIR}/src/safety_check.c ) if (OS_DARWIN) list(APPEND SRCS ${LIBRARY_DIR}/src/zone.c) @@ -89,6 +96,8 @@ if (ENABLE_JEMALLOC) endif () target_compile_options(jemalloc PRIVATE -Wno-redundant-decls) + # for RTLD_NEXT + target_compile_options(jemalloc PRIVATE -D_GNU_SOURCE) else () find_library(LIBRARY_JEMALLOC jemalloc) find_path(INCLUDE_JEMALLOC jemalloc/jemalloc.h) diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_defs.h similarity index 84% rename from contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h rename to contrib/jemalloc-cmake/include/jemalloc/jemalloc_defs.h index d1389237a77..6a03a231a0e 100644 --- a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h +++ b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_defs.h @@ -5,6 +5,12 @@ /* Defined if alloc_size attribute is supported. */ #define JEMALLOC_HAVE_ATTR_ALLOC_SIZE +/* Defined if format_arg(...) attribute is supported. */ +#define JEMALLOC_HAVE_ATTR_FORMAT_ARG + +/* Defined if format(gnu_printf, ...) attribute is supported. */ +#define JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF + /* Defined if format(printf, ...) attribute is supported. */ #define JEMALLOC_HAVE_ATTR_FORMAT_PRINTF diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_macros.h b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_macros.h similarity index 87% rename from contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_macros.h rename to contrib/jemalloc-cmake/include/jemalloc/jemalloc_macros.h index 7432f1cda53..34235894285 100644 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_macros.h +++ b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_macros.h @@ -4,12 +4,13 @@ #include #include -#define JEMALLOC_VERSION "5.1.0-56-g41b7372eadee941b9164751b8d4963f915d3ceae" +#define JEMALLOC_VERSION "5.2.1-0-gea6b3e973b477b8061e0076bb257dbd7f3faa756" #define JEMALLOC_VERSION_MAJOR 5 -#define JEMALLOC_VERSION_MINOR 1 -#define JEMALLOC_VERSION_BUGFIX 0 -#define JEMALLOC_VERSION_NREV 56 -#define JEMALLOC_VERSION_GID "41b7372eadee941b9164751b8d4963f915d3ceae" +#define JEMALLOC_VERSION_MINOR 2 +#define JEMALLOC_VERSION_BUGFIX 1 +#define JEMALLOC_VERSION_NREV 0 +#define JEMALLOC_VERSION_GID "ea6b3e973b477b8061e0076bb257dbd7f3faa756" +#define JEMALLOC_VERSION_GID_IDENT ea6b3e973b477b8061e0076bb257dbd7f3faa756 #define MALLOCX_LG_ALIGN(la) ((int)(la)) #if LG_SIZEOF_PTR == 2 @@ -68,6 +69,7 @@ # define JEMALLOC_EXPORT __declspec(dllimport) # endif # endif +# define JEMALLOC_FORMAT_ARG(i) # define JEMALLOC_FORMAT_PRINTF(s, i) # define JEMALLOC_NOINLINE __declspec(noinline) # ifdef __cplusplus @@ -95,6 +97,11 @@ # ifndef JEMALLOC_EXPORT # define JEMALLOC_EXPORT JEMALLOC_ATTR(visibility("default")) # endif +# ifdef JEMALLOC_HAVE_ATTR_FORMAT_ARG +# define JEMALLOC_FORMAT_ARG(i) JEMALLOC_ATTR(__format_arg__(3)) +# else +# define JEMALLOC_FORMAT_ARG(i) +# endif # ifdef JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF # define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(gnu_printf, s, i)) # elif defined(JEMALLOC_HAVE_ATTR_FORMAT_PRINTF) diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_protos.h b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_protos.h similarity index 100% rename from contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_protos.h rename to contrib/jemalloc-cmake/include/jemalloc/jemalloc_protos.h diff --git a/contrib/jemalloc-cmake/include/jemalloc/jemalloc_rename.h b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_rename.h index a2ea2dd3533..2e94f7a0cc3 100644 --- a/contrib/jemalloc-cmake/include/jemalloc/jemalloc_rename.h +++ b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_rename.h @@ -17,6 +17,7 @@ # define je_malloc_stats_print malloc_stats_print # define je_malloc_usable_size malloc_usable_size # define je_mallocx mallocx +# define je_smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 # define je_nallocx nallocx # define je_posix_memalign posix_memalign # define je_rallocx rallocx diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_typedefs.h b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_typedefs.h similarity index 88% rename from contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_typedefs.h rename to contrib/jemalloc-cmake/include/jemalloc/jemalloc_typedefs.h index 1a58874306e..5f94f16f937 100644 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_typedefs.h +++ b/contrib/jemalloc-cmake/include/jemalloc/jemalloc_typedefs.h @@ -65,13 +65,13 @@ typedef bool (extent_merge_t)(extent_hooks_t *, void *, size_t, void *, size_t, bool, unsigned); struct extent_hooks_s { - extent_alloc_t *alloc; - extent_dalloc_t *dalloc; - extent_destroy_t *destroy; - extent_commit_t *commit; - extent_decommit_t *decommit; - extent_purge_t *purge_lazy; - extent_purge_t *purge_forced; - extent_split_t *split; - extent_merge_t *merge; + extent_alloc_t *alloc; + extent_dalloc_t *dalloc; + extent_destroy_t *destroy; + extent_commit_t *commit; + extent_decommit_t *decommit; + extent_purge_t *purge_lazy; + extent_purge_t *purge_forced; + extent_split_t *split; + extent_merge_t *merge; }; diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in index 089f1a773aa..cbd2740e1f1 100644 --- a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in @@ -1,12 +1,6 @@ /* include/jemalloc/internal/jemalloc_internal_defs.h. Generated from jemalloc_internal_defs.h.in by configure. */ #ifndef JEMALLOC_INTERNAL_DEFS_H_ #define JEMALLOC_INTERNAL_DEFS_H_ - - -#ifndef _GNU_SOURCE - #define _GNU_SOURCE -#endif - /* * If JEMALLOC_PREFIX is defined via --with-jemalloc-prefix, it will cause all * public APIs to be prefixed. This makes it possible, with some care, to use @@ -25,7 +19,7 @@ #define JEMALLOC_OVERRIDE___LIBC_MEMALIGN #define JEMALLOC_OVERRIDE___LIBC_REALLOC #define JEMALLOC_OVERRIDE___LIBC_VALLOC -#define JEMALLOC_OVERRIDE___POSIX_MEMALIGN +/* #undef JEMALLOC_OVERRIDE___POSIX_MEMALIGN */ /* * JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs. @@ -41,7 +35,7 @@ */ #define CPU_SPINWAIT /* 1 if CPU_SPINWAIT is defined, 0 otherwise. */ -#define HAVE_CPU_SPINWAIT 0 +#define HAVE_CPU_SPINWAIT 9 /* * Number of significant bits in virtual addresses. This may be less than the @@ -55,25 +49,13 @@ /* Defined if GCC __atomic atomics are available. */ #define JEMALLOC_GCC_ATOMIC_ATOMICS 1 +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_ATOMIC_ATOMICS 1 /* Defined if GCC __sync atomics are available. */ #define JEMALLOC_GCC_SYNC_ATOMICS 1 - -/* - * Defined if __sync_add_and_fetch(uint32_t *, uint32_t) and - * __sync_sub_and_fetch(uint32_t *, uint32_t) are available, despite - * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4 not being defined (which means the - * functions are defined in libgcc instead of being inlines). - */ -/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_4 */ - -/* - * Defined if __sync_add_and_fetch(uint64_t *, uint64_t) and - * __sync_sub_and_fetch(uint64_t *, uint64_t) are available, despite - * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8 not being defined (which means the - * functions are defined in libgcc instead of being inlines). - */ -/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_8 */ +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1 /* * Defined if __builtin_clz() and __builtin_clzl() are available. @@ -85,19 +67,13 @@ */ /* #undef JEMALLOC_OS_UNFAIR_LOCK */ -/* - * Defined if OSSpin*() functions are available, as provided by Darwin, and - * documented in the spinlock(3) manual page. - */ -/* #undef JEMALLOC_OSSPIN */ - /* Defined if syscall(2) is usable. */ #define JEMALLOC_USE_SYSCALL /* * Defined if secure_getenv(3) is available. */ -#define JEMALLOC_HAVE_SECURE_GETENV +// #define JEMALLOC_HAVE_SECURE_GETENV /* * Defined if issetugid(2) is available. @@ -243,6 +219,12 @@ #define JEMALLOC_INTERNAL_FFSL __builtin_ffsl #define JEMALLOC_INTERNAL_FFS __builtin_ffs +/* + * popcount*() functions to use for bitmapping. + */ +#define JEMALLOC_INTERNAL_POPCOUNTL __builtin_popcountl +#define JEMALLOC_INTERNAL_POPCOUNT __builtin_popcount + /* * If defined, explicitly attempt to more uniformly distribute large allocation * pointer alignments across all cache indices. @@ -297,7 +279,7 @@ * MADV_FREE, though typically with higher * system overhead. */ -// #define JEMALLOC_PURGE_MADVISE_FREE +#define JEMALLOC_PURGE_MADVISE_FREE #define JEMALLOC_PURGE_MADVISE_DONTNEED #define JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS @@ -379,4 +361,7 @@ */ #define JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE +/* Performs additional safety checks when defined. */ +/* #undef JEMALLOC_OPT_SAFETY_CHECKS */ + #endif /* JEMALLOC_INTERNAL_DEFS_H_ */ diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h index c150785fb4a..e5e34925b55 100644 --- a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h @@ -21,7 +21,7 @@ # include "jemalloc/jemalloc.h" #endif -#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN)) +#if defined(JEMALLOC_OSATOMIC) #include #endif @@ -161,7 +161,26 @@ static const bool config_log = false #endif ; -#ifdef JEMALLOC_HAVE_SCHED_GETCPU +/* + * Are extra safety checks enabled; things like checking the size of sized + * deallocations, double-frees, etc. + */ +static const bool config_opt_safety_checks = +#ifdef JEMALLOC_OPT_SAFETY_CHECKS + true +#elif defined(JEMALLOC_DEBUG) + /* + * This lets us only guard safety checks by one flag instead of two; fast + * checks can guard solely by config_opt_safety_checks and run in debug mode + * too. + */ + true +#else + false +#endif + ; + +#if defined(_WIN32) || defined(JEMALLOC_HAVE_SCHED_GETCPU) /* Currently percpu_arena depends on sched_getcpu. */ #define JEMALLOC_PERCPU_ARENA #endif diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h deleted file mode 100644 index 79b13337fbb..00000000000 --- a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h +++ /dev/null @@ -1,123 +0,0 @@ -#include -#include -#include -#include -#include - -#define JEMALLOC_VERSION "5.1.0-97-gcd2931ad9bbd78208565716ab102e86d858c2fff" -#define JEMALLOC_VERSION_MAJOR 5 -#define JEMALLOC_VERSION_MINOR 1 -#define JEMALLOC_VERSION_BUGFIX 0 -#define JEMALLOC_VERSION_NREV 97 -#define JEMALLOC_VERSION_GID "cd2931ad9bbd78208565716ab102e86d858c2fff" -#define JEMALLOC_VERSION_GID_IDENT cd2931ad9bbd78208565716ab102e86d858c2fff - -#define MALLOCX_LG_ALIGN(la) ((int)(la)) -#if LG_SIZEOF_PTR == 2 -# define MALLOCX_ALIGN(a) ((int)(ffs((int)(a))-1)) -#else -# define MALLOCX_ALIGN(a) \ - ((int)(((size_t)(a) < (size_t)INT_MAX) ? ffs((int)(a))-1 : \ - ffs((int)(((size_t)(a))>>32))+31)) -#endif -#define MALLOCX_ZERO ((int)0x40) -/* - * Bias tcache index bits so that 0 encodes "automatic tcache management", and 1 - * encodes MALLOCX_TCACHE_NONE. - */ -#define MALLOCX_TCACHE(tc) ((int)(((tc)+2) << 8)) -#define MALLOCX_TCACHE_NONE MALLOCX_TCACHE(-1) -/* - * Bias arena index bits so that 0 encodes "use an automatically chosen arena". - */ -#define MALLOCX_ARENA(a) ((((int)(a))+1) << 20) - -/* - * Use as arena index in "arena..{purge,decay,dss}" and - * "stats.arenas..*" mallctl interfaces to select all arenas. This - * definition is intentionally specified in raw decimal format to support - * cpp-based string concatenation, e.g. - * - * #define STRINGIFY_HELPER(x) #x - * #define STRINGIFY(x) STRINGIFY_HELPER(x) - * - * mallctl("arena." STRINGIFY(MALLCTL_ARENAS_ALL) ".purge", NULL, NULL, NULL, - * 0); - */ -#define MALLCTL_ARENAS_ALL 4096 -/* - * Use as arena index in "stats.arenas..*" mallctl interfaces to select - * destroyed arenas. - */ -#define MALLCTL_ARENAS_DESTROYED 4097 - -#if defined(__cplusplus) && defined(JEMALLOC_USE_CXX_THROW) -# define JEMALLOC_CXX_THROW throw() -#else -# define JEMALLOC_CXX_THROW -#endif - -#if defined(_MSC_VER) -# define JEMALLOC_ATTR(s) -# define JEMALLOC_ALIGNED(s) __declspec(align(s)) -# define JEMALLOC_ALLOC_SIZE(s) -# define JEMALLOC_ALLOC_SIZE2(s1, s2) -# ifndef JEMALLOC_EXPORT -# ifdef DLLEXPORT -# define JEMALLOC_EXPORT __declspec(dllexport) -# else -# define JEMALLOC_EXPORT __declspec(dllimport) -# endif -# endif -# define JEMALLOC_FORMAT_PRINTF(s, i) -# define JEMALLOC_NOINLINE __declspec(noinline) -# ifdef __cplusplus -# define JEMALLOC_NOTHROW __declspec(nothrow) -# else -# define JEMALLOC_NOTHROW -# endif -# define JEMALLOC_SECTION(s) __declspec(allocate(s)) -# define JEMALLOC_RESTRICT_RETURN __declspec(restrict) -# if _MSC_VER >= 1900 && !defined(__EDG__) -# define JEMALLOC_ALLOCATOR __declspec(allocator) -# else -# define JEMALLOC_ALLOCATOR -# endif -#elif defined(JEMALLOC_HAVE_ATTR) -# define JEMALLOC_ATTR(s) __attribute__((s)) -# define JEMALLOC_ALIGNED(s) JEMALLOC_ATTR(aligned(s)) -# ifdef JEMALLOC_HAVE_ATTR_ALLOC_SIZE -# define JEMALLOC_ALLOC_SIZE(s) JEMALLOC_ATTR(alloc_size(s)) -# define JEMALLOC_ALLOC_SIZE2(s1, s2) JEMALLOC_ATTR(alloc_size(s1, s2)) -# else -# define JEMALLOC_ALLOC_SIZE(s) -# define JEMALLOC_ALLOC_SIZE2(s1, s2) -# endif -# ifndef JEMALLOC_EXPORT -# define JEMALLOC_EXPORT JEMALLOC_ATTR(visibility("default")) -# endif -# ifdef JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF -# define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(gnu_printf, s, i)) -# elif defined(JEMALLOC_HAVE_ATTR_FORMAT_PRINTF) -# define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(printf, s, i)) -# else -# define JEMALLOC_FORMAT_PRINTF(s, i) -# endif -# define JEMALLOC_NOINLINE JEMALLOC_ATTR(noinline) -# define JEMALLOC_NOTHROW JEMALLOC_ATTR(nothrow) -# define JEMALLOC_SECTION(s) JEMALLOC_ATTR(section(s)) -# define JEMALLOC_RESTRICT_RETURN -# define JEMALLOC_ALLOCATOR -#else -# define JEMALLOC_ATTR(s) -# define JEMALLOC_ALIGNED(s) -# define JEMALLOC_ALLOC_SIZE(s) -# define JEMALLOC_ALLOC_SIZE2(s1, s2) -# define JEMALLOC_EXPORT -# define JEMALLOC_FORMAT_PRINTF(s, i) -# define JEMALLOC_NOINLINE -# define JEMALLOC_NOTHROW -# define JEMALLOC_SECTION(s) -# define JEMALLOC_RESTRICT_RETURN -# define JEMALLOC_ALLOCATOR -#endif diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h deleted file mode 100644 index 1a58874306e..00000000000 --- a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h +++ /dev/null @@ -1,77 +0,0 @@ -typedef struct extent_hooks_s extent_hooks_t; - -/* - * void * - * extent_alloc(extent_hooks_t *extent_hooks, void *new_addr, size_t size, - * size_t alignment, bool *zero, bool *commit, unsigned arena_ind); - */ -typedef void *(extent_alloc_t)(extent_hooks_t *, void *, size_t, size_t, bool *, - bool *, unsigned); - -/* - * bool - * extent_dalloc(extent_hooks_t *extent_hooks, void *addr, size_t size, - * bool committed, unsigned arena_ind); - */ -typedef bool (extent_dalloc_t)(extent_hooks_t *, void *, size_t, bool, - unsigned); - -/* - * void - * extent_destroy(extent_hooks_t *extent_hooks, void *addr, size_t size, - * bool committed, unsigned arena_ind); - */ -typedef void (extent_destroy_t)(extent_hooks_t *, void *, size_t, bool, - unsigned); - -/* - * bool - * extent_commit(extent_hooks_t *extent_hooks, void *addr, size_t size, - * size_t offset, size_t length, unsigned arena_ind); - */ -typedef bool (extent_commit_t)(extent_hooks_t *, void *, size_t, size_t, size_t, - unsigned); - -/* - * bool - * extent_decommit(extent_hooks_t *extent_hooks, void *addr, size_t size, - * size_t offset, size_t length, unsigned arena_ind); - */ -typedef bool (extent_decommit_t)(extent_hooks_t *, void *, size_t, size_t, - size_t, unsigned); - -/* - * bool - * extent_purge(extent_hooks_t *extent_hooks, void *addr, size_t size, - * size_t offset, size_t length, unsigned arena_ind); - */ -typedef bool (extent_purge_t)(extent_hooks_t *, void *, size_t, size_t, size_t, - unsigned); - -/* - * bool - * extent_split(extent_hooks_t *extent_hooks, void *addr, size_t size, - * size_t size_a, size_t size_b, bool committed, unsigned arena_ind); - */ -typedef bool (extent_split_t)(extent_hooks_t *, void *, size_t, size_t, size_t, - bool, unsigned); - -/* - * bool - * extent_merge(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a, - * void *addr_b, size_t size_b, bool committed, unsigned arena_ind); - */ -typedef bool (extent_merge_t)(extent_hooks_t *, void *, size_t, void *, size_t, - bool, unsigned); - -struct extent_hooks_s { - extent_alloc_t *alloc; - extent_dalloc_t *dalloc; - extent_destroy_t *destroy; - extent_commit_t *commit; - extent_decommit_t *decommit; - extent_purge_t *purge_lazy; - extent_purge_t *purge_forced; - extent_split_t *split; - extent_merge_t *merge; -}; diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in index 63f7f765023..d5cf0e719ef 100644 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in +++ b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in @@ -1,11 +1,6 @@ /* include/jemalloc/internal/jemalloc_internal_defs.h. Generated from jemalloc_internal_defs.h.in by configure. */ #ifndef JEMALLOC_INTERNAL_DEFS_H_ #define JEMALLOC_INTERNAL_DEFS_H_ - -#ifndef _GNU_SOURCE - #define _GNU_SOURCE -#endif - /* * If JEMALLOC_PREFIX is defined via --with-jemalloc-prefix, it will cause all * public APIs to be prefixed. This makes it possible, with some care, to use @@ -24,7 +19,7 @@ #define JEMALLOC_OVERRIDE___LIBC_MEMALIGN #define JEMALLOC_OVERRIDE___LIBC_REALLOC #define JEMALLOC_OVERRIDE___LIBC_VALLOC -#define JEMALLOC_OVERRIDE___POSIX_MEMALIGN +/* #undef JEMALLOC_OVERRIDE___POSIX_MEMALIGN */ /* * JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs. @@ -54,25 +49,13 @@ /* Defined if GCC __atomic atomics are available. */ #define JEMALLOC_GCC_ATOMIC_ATOMICS 1 +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_ATOMIC_ATOMICS 1 /* Defined if GCC __sync atomics are available. */ #define JEMALLOC_GCC_SYNC_ATOMICS 1 - -/* - * Defined if __sync_add_and_fetch(uint32_t *, uint32_t) and - * __sync_sub_and_fetch(uint32_t *, uint32_t) are available, despite - * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4 not being defined (which means the - * functions are defined in libgcc instead of being inlines). - */ -/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_4 */ - -/* - * Defined if __sync_add_and_fetch(uint64_t *, uint64_t) and - * __sync_sub_and_fetch(uint64_t *, uint64_t) are available, despite - * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8 not being defined (which means the - * functions are defined in libgcc instead of being inlines). - */ -/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_8 */ +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1 /* * Defined if __builtin_clz() and __builtin_clzl() are available. @@ -84,20 +67,13 @@ */ /* #undef JEMALLOC_OS_UNFAIR_LOCK */ -/* - * Defined if OSSpin*() functions are available, as provided by Darwin, and - * documented in the spinlock(3) manual page. - */ -/* #undef JEMALLOC_OSSPIN */ - /* Defined if syscall(2) is usable. */ #define JEMALLOC_USE_SYSCALL /* * Defined if secure_getenv(3) is available. */ -// Don't want dependency on newer GLIBC -//#define JEMALLOC_HAVE_SECURE_GETENV +// #define JEMALLOC_HAVE_SECURE_GETENV /* * Defined if issetugid(2) is available. @@ -160,6 +136,9 @@ /* JEMALLOC_STATS enables statistics calculation. */ #define JEMALLOC_STATS +/* JEMALLOC_EXPERIMENTAL_SMALLOCX_API enables experimental smallocx API. */ +/* #undef JEMALLOC_EXPERIMENTAL_SMALLOCX_API */ + /* JEMALLOC_PROF enables allocation profiling. */ /* #undef JEMALLOC_PROF */ @@ -240,6 +219,12 @@ #define JEMALLOC_INTERNAL_FFSL __builtin_ffsl #define JEMALLOC_INTERNAL_FFS __builtin_ffs +/* + * popcount*() functions to use for bitmapping. + */ +#define JEMALLOC_INTERNAL_POPCOUNTL __builtin_popcountl +#define JEMALLOC_INTERNAL_POPCOUNT __builtin_popcount + /* * If defined, explicitly attempt to more uniformly distribute large allocation * pointer alignments across all cache indices. @@ -252,6 +237,12 @@ */ /* #undef JEMALLOC_LOG */ +/* + * If defined, use readlinkat() (instead of readlink()) to follow + * /etc/malloc_conf. + */ +/* #undef JEMALLOC_READLINKAT */ + /* * Darwin (OS X) uses zones to work around Mach-O symbol override shortcomings. */ @@ -288,7 +279,7 @@ * MADV_FREE, though typically with higher * system overhead. */ -//#define JEMALLOC_PURGE_MADVISE_FREE +#define JEMALLOC_PURGE_MADVISE_FREE #define JEMALLOC_PURGE_MADVISE_DONTNEED #define JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS @@ -370,4 +361,7 @@ */ #define JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE +/* Performs additional safety checks when defined. */ +/* #undef JEMALLOC_OPT_SAFETY_CHECKS */ + #endif /* JEMALLOC_INTERNAL_DEFS_H_ */ diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_preamble.h b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_preamble.h index c150785fb4a..e5e34925b55 100644 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_preamble.h +++ b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_preamble.h @@ -21,7 +21,7 @@ # include "jemalloc/jemalloc.h" #endif -#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN)) +#if defined(JEMALLOC_OSATOMIC) #include #endif @@ -161,7 +161,26 @@ static const bool config_log = false #endif ; -#ifdef JEMALLOC_HAVE_SCHED_GETCPU +/* + * Are extra safety checks enabled; things like checking the size of sized + * deallocations, double-frees, etc. + */ +static const bool config_opt_safety_checks = +#ifdef JEMALLOC_OPT_SAFETY_CHECKS + true +#elif defined(JEMALLOC_DEBUG) + /* + * This lets us only guard safety checks by one flag instead of two; fast + * checks can guard solely by config_opt_safety_checks and run in debug mode + * too. + */ + true +#else + false +#endif + ; + +#if defined(_WIN32) || defined(JEMALLOC_HAVE_SCHED_GETCPU) /* Currently percpu_arena depends on sched_getcpu. */ #define JEMALLOC_PERCPU_ARENA #endif diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_defs.h b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_defs.h deleted file mode 100644 index d1389237a77..00000000000 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_defs.h +++ /dev/null @@ -1,43 +0,0 @@ -/* include/jemalloc/jemalloc_defs.h. Generated from jemalloc_defs.h.in by configure. */ -/* Defined if __attribute__((...)) syntax is supported. */ -#define JEMALLOC_HAVE_ATTR - -/* Defined if alloc_size attribute is supported. */ -#define JEMALLOC_HAVE_ATTR_ALLOC_SIZE - -/* Defined if format(printf, ...) attribute is supported. */ -#define JEMALLOC_HAVE_ATTR_FORMAT_PRINTF - -/* - * Define overrides for non-standard allocator-related functions if they are - * present on the system. - */ -#define JEMALLOC_OVERRIDE_MEMALIGN -#define JEMALLOC_OVERRIDE_VALLOC - -/* - * At least Linux omits the "const" in: - * - * size_t malloc_usable_size(const void *ptr); - * - * Match the operating system's prototype. - */ -#define JEMALLOC_USABLE_SIZE_CONST - -/* - * If defined, specify throw() for the public function prototypes when compiling - * with C++. The only justification for this is to match the prototypes that - * glibc defines. - */ -#define JEMALLOC_USE_CXX_THROW - -#ifdef _MSC_VER -# ifdef _WIN64 -# define LG_SIZEOF_PTR_WIN 3 -# else -# define LG_SIZEOF_PTR_WIN 2 -# endif -#endif - -/* sizeof(void *) == 2^LG_SIZEOF_PTR. */ -#define LG_SIZEOF_PTR 3 diff --git a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_protos.h b/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_protos.h deleted file mode 100644 index ff025e30fa7..00000000000 --- a/contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/jemalloc_protos.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * The je_ prefix on the following public symbol declarations is an artifact - * of namespace management, and should be omitted in application code unless - * JEMALLOC_NO_DEMANGLE is defined (see jemalloc_mangle.h). - */ -extern JEMALLOC_EXPORT const char *je_malloc_conf; -extern JEMALLOC_EXPORT void (*je_malloc_message)(void *cbopaque, - const char *s); - -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_malloc(size_t size) - JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1); -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_calloc(size_t num, size_t size) - JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2); -JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_posix_memalign(void **memptr, - size_t alignment, size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(nonnull(1)); -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_aligned_alloc(size_t alignment, - size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) - JEMALLOC_ALLOC_SIZE(2); -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_realloc(void *ptr, size_t size) - JEMALLOC_CXX_THROW JEMALLOC_ALLOC_SIZE(2); -JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_free(void *ptr) - JEMALLOC_CXX_THROW; - -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_mallocx(size_t size, int flags) - JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1); -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_rallocx(void *ptr, size_t size, - int flags) JEMALLOC_ALLOC_SIZE(2); -JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_xallocx(void *ptr, size_t size, - size_t extra, int flags); -JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_sallocx(const void *ptr, - int flags) JEMALLOC_ATTR(pure); -JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_dallocx(void *ptr, int flags); -JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_sdallocx(void *ptr, size_t size, - int flags); -JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_nallocx(size_t size, int flags) - JEMALLOC_ATTR(pure); - -JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctl(const char *name, - void *oldp, size_t *oldlenp, void *newp, size_t newlen); -JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlnametomib(const char *name, - size_t *mibp, size_t *miblenp); -JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlbymib(const size_t *mib, - size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen); -JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_malloc_stats_print( - void (*write_cb)(void *, const char *), void *je_cbopaque, - const char *opts); -JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_malloc_usable_size( - JEMALLOC_USABLE_SIZE_CONST void *ptr) JEMALLOC_CXX_THROW; - -#ifdef JEMALLOC_OVERRIDE_MEMALIGN -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_memalign(size_t alignment, size_t size) - JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc); -#endif - -#ifdef JEMALLOC_OVERRIDE_VALLOC -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN - void JEMALLOC_NOTHROW *je_valloc(size_t size) JEMALLOC_CXX_THROW - JEMALLOC_ATTR(malloc); -#endif diff --git a/docker/packager/deb/Dockerfile b/docker/packager/deb/Dockerfile index ae70bc8c594..786e6620eac 100644 --- a/docker/packager/deb/Dockerfile +++ b/docker/packager/deb/Dockerfile @@ -80,7 +80,9 @@ RUN apt-get --allow-unauthenticated update -y \ pigz \ moreutils \ libcctz-dev \ - libldap2-dev + libldap2-dev \ + libsasl2-dev \ + heimdal-multidev diff --git a/docker/server/Dockerfile b/docker/server/Dockerfile index 3ad20a9479c..93f192c3f3c 100644 --- a/docker/server/Dockerfile +++ b/docker/server/Dockerfile @@ -21,7 +21,7 @@ RUN apt-get update \ locales \ ca-certificates \ wget \ - tzata \ + tzdata \ && rm -rf \ /var/lib/apt/lists/* \ /var/cache/debconf \ diff --git a/docker/test/integration/runner/Dockerfile b/docker/test/integration/runner/Dockerfile index 53f41905f10..9c1fe66cf7b 100644 --- a/docker/test/integration/runner/Dockerfile +++ b/docker/test/integration/runner/Dockerfile @@ -36,7 +36,7 @@ RUN apt-get update \ ENV TZ=Europe/Moscow RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone -RUN pip install urllib3==1.23 pytest docker-compose==1.22.0 docker dicttoxml kazoo PyMySQL psycopg2==2.7.5 pymongo tzlocal kafka-python protobuf redis aerospike pytest-timeout minio rpm-confluent-schemaregistry grpcio grpcio-tools +RUN pip install urllib3==1.23 pytest docker-compose==1.22.0 docker dicttoxml kazoo PyMySQL psycopg2==2.7.5 pymongo tzlocal kafka-python protobuf redis aerospike pytest-timeout minio rpm-confluent-schemaregistry grpcio grpcio-tools cassandra-driver ENV DOCKER_CHANNEL stable ENV DOCKER_VERSION 17.09.1-ce diff --git a/docker/test/performance-comparison/compare.sh b/docker/test/performance-comparison/compare.sh index bf4599acb9a..209b36f59af 100755 --- a/docker/test/performance-comparison/compare.sh +++ b/docker/test/performance-comparison/compare.sh @@ -317,7 +317,7 @@ function report rm -r report ||: mkdir report report/tmp ||: -rm ./*.{rep,svg} test-times.tsv test-dump.tsv unstable.tsv unstable-query-ids.tsv unstable-query-metrics.tsv changed-perf.tsv unstable-tests.tsv unstable-queries.tsv bad-tests.tsv slow-on-client.tsv all-queries.tsv ||: +rm ./*.{rep,svg} test-times.tsv test-dump.tsv unstable.tsv unstable-query-ids.tsv unstable-query-metrics.tsv changed-perf.tsv unstable-tests.tsv unstable-queries.tsv bad-tests.tsv slow-on-client.tsv all-queries.tsv run-errors.tsv ||: build_log_column_definitions @@ -434,7 +434,7 @@ create table wall_clock engine Memory as select * from file('wall-clock-times.tsv', TSV, 'test text, real float, user float, system float'); create table slow_on_client_tsv engine File(TSV, 'report/slow-on-client.tsv') as - select client, server, floor(client/server, 3) p, query_display_name + select client, server, floor(client/server, 3) p, test, query_display_name from query_time left join query_display_names using (test, query_index) where p > 1.02 order by p desc; diff --git a/docker/test/performance-comparison/report.py b/docker/test/performance-comparison/report.py index b171603700d..866e78da098 100755 --- a/docker/test/performance-comparison/report.py +++ b/docker/test/performance-comparison/report.py @@ -189,7 +189,7 @@ if args.report == 'main': slow_on_client_rows = tsvRows('report/slow-on-client.tsv') error_tests += len(slow_on_client_rows) printSimpleTable('Slow on client', - ['Client time, s', 'Server time, s', 'Ratio', 'Query'], + ['Client time, s', 'Server time, s', 'Ratio', 'Test', 'Query'], slow_on_client_rows) def print_changes(): diff --git a/docker/test/stateful/Dockerfile b/docker/test/stateful/Dockerfile index e51efadf653..3aff49bf5a1 100644 --- a/docker/test/stateful/Dockerfile +++ b/docker/test/stateful/Dockerfile @@ -32,8 +32,8 @@ CMD dpkg -i package_folder/clickhouse-common-static_*.deb; \ ln -s /usr/share/clickhouse-test/config/decimals_dictionary.xml /etc/clickhouse-server/; \ ln -s /usr/share/clickhouse-test/config/macros.xml /etc/clickhouse-server/config.d/; \ ln -s /usr/lib/llvm-9/bin/llvm-symbolizer /usr/bin/llvm-symbolizer; \ - if [ -n $USE_DATABASE_ATOMIC ] && [ $USE_DATABASE_ATOMIC -eq 1 ]; then ln -s /usr/share/clickhouse-test/config/database_atomic_configd.xml /etc/clickhouse-server/config.d/; fi; \ - if [ -n $USE_DATABASE_ATOMIC ] && [ $USE_DATABASE_ATOMIC -eq 1 ]; then ln -s /usr/share/clickhouse-test/config/database_atomic_usersd.xml /etc/clickhouse-server/users.d/; fi; \ + if [[ -n "$USE_DATABASE_ATOMIC" ]] && [[ "$USE_DATABASE_ATOMIC" -eq 1 ]]; then ln -s /usr/share/clickhouse-test/config/database_atomic_configd.xml /etc/clickhouse-server/config.d/; fi; \ + if [[ -n "$USE_DATABASE_ATOMIC" ]] && [[ "$USE_DATABASE_ATOMIC" -eq 1 ]]; then ln -s /usr/share/clickhouse-test/config/database_atomic_usersd.xml /etc/clickhouse-server/users.d/; fi; \ echo "TSAN_OPTIONS='verbosity=1000 halt_on_error=1 history_size=7'" >> /etc/environment; \ echo "TSAN_SYMBOLIZER_PATH=/usr/lib/llvm-8/bin/llvm-symbolizer" >> /etc/environment; \ echo "UBSAN_OPTIONS='print_stacktrace=1'" >> /etc/environment; \ diff --git a/docker/test/stateless/Dockerfile b/docker/test/stateless/Dockerfile index 35a8a5a9d3d..41a53f8a3f5 100644 --- a/docker/test/stateless/Dockerfile +++ b/docker/test/stateless/Dockerfile @@ -78,9 +78,9 @@ CMD dpkg -i package_folder/clickhouse-common-static_*.deb; \ ln -s /usr/share/clickhouse-test/config/server.key /etc/clickhouse-server/; \ ln -s /usr/share/clickhouse-test/config/server.crt /etc/clickhouse-server/; \ ln -s /usr/share/clickhouse-test/config/dhparam.pem /etc/clickhouse-server/; \ - if [ -n $USE_POLYMORPHIC_PARTS ] && [ $USE_POLYMORPHIC_PARTS -eq 1 ]; then ln -s /usr/share/clickhouse-test/config/polymorphic_parts.xml /etc/clickhouse-server/config.d/; fi; \ - if [ -n $USE_DATABASE_ATOMIC ] && [ $USE_DATABASE_ATOMIC -eq 1 ]; then ln -s /usr/share/clickhouse-test/config/database_atomic_configd.xml /etc/clickhouse-server/config.d/; fi; \ - if [ -n $USE_DATABASE_ATOMIC ] && [ $USE_DATABASE_ATOMIC -eq 1 ]; then ln -s /usr/share/clickhouse-test/config/database_atomic_usersd.xml /etc/clickhouse-server/users.d/; fi; \ + if [[ -n "$USE_POLYMORPHIC_PARTS" ]] && [[ "$USE_POLYMORPHIC_PARTS" -eq 1 ]]; then ln -s /usr/share/clickhouse-test/config/polymorphic_parts.xml /etc/clickhouse-server/config.d/; fi; \ + if [[ -n "$USE_DATABASE_ATOMIC" ]] && [[ "$USE_DATABASE_ATOMIC" -eq 1 ]]; then ln -s /usr/share/clickhouse-test/config/database_atomic_configd.xml /etc/clickhouse-server/config.d/; fi; \ + if [[ -n "$USE_DATABASE_ATOMIC" ]] && [[ "$USE_DATABASE_ATOMIC" -eq 1 ]]; then ln -s /usr/share/clickhouse-test/config/database_atomic_usersd.xml /etc/clickhouse-server/users.d/; fi; \ ln -sf /usr/share/clickhouse-test/config/client_config.xml /etc/clickhouse-client/config.xml; \ service zookeeper start; sleep 5; \ service clickhouse-server start && sleep 5 && clickhouse-test --testname --shard --zookeeper $ADDITIONAL_OPTIONS $SKIP_TESTS_OPTION 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt diff --git a/docker/test/test_runner.sh b/docker/test/test_runner.sh index 76e142e61f9..561117492b0 100755 --- a/docker/test/test_runner.sh +++ b/docker/test/test_runner.sh @@ -12,7 +12,7 @@ readonly CLICKHOUSE_PACKAGES_ARG="${2}" CLICKHOUSE_SERVER_IMAGE="${3}" if [ ${CLICKHOUSE_PACKAGES_ARG} != ${NO_REBUILD_FLAG} ]; then - readonly CLICKHOUSE_PACKAGES_DIR="$(realpath ${2})" # or --no-rebuild + readonly CLICKHOUSE_PACKAGES_DIR="$(realpath ${2})" # or --no-rebuild fi @@ -26,19 +26,19 @@ fi # TODO: optionally mount most recent clickhouse-test and queries directory from local machine if [ ${CLICKHOUSE_PACKAGES_ARG} != ${NO_REBUILD_FLAG} ]; then - docker build \ - -f "${CLICKHOUSE_DOCKER_DIR}/test/stateless/clickhouse-statelest-test-runner.Dockerfile" \ - --target clickhouse-test-runner-base \ - -t clickhouse-test-runner-base:preinstall \ - "${CLICKHOUSE_DOCKER_DIR}/test/stateless" + docker build \ + -f "${CLICKHOUSE_DOCKER_DIR}/test/stateless/clickhouse-statelest-test-runner.Dockerfile" \ + --target clickhouse-test-runner-base \ + -t clickhouse-test-runner-base:preinstall \ + "${CLICKHOUSE_DOCKER_DIR}/test/stateless" - docker rm -f clickhouse-test-runner-installing-packages || true - docker run \ - -v "${CLICKHOUSE_PACKAGES_DIR}:/packages" \ - --name clickhouse-test-runner-installing-packages \ - clickhouse-test-runner-base:preinstall - docker commit clickhouse-test-runner-installing-packages clickhouse-statelest-test-runner:local - docker rm -f clickhouse-test-runner-installing-packages || true + docker rm -f clickhouse-test-runner-installing-packages || true + docker run \ + -v "${CLICKHOUSE_PACKAGES_DIR}:/packages" \ + --name clickhouse-test-runner-installing-packages \ + clickhouse-test-runner-base:preinstall + docker commit clickhouse-test-runner-installing-packages clickhouse-statelest-test-runner:local + docker rm -f clickhouse-test-runner-installing-packages || true fi # # Create a bind-volume to the clickhouse-test script file @@ -47,38 +47,38 @@ fi # Build server image (optional) from local packages if [ -z "${CLICKHOUSE_SERVER_IMAGE}" ]; then - CLICKHOUSE_SERVER_IMAGE="yandex/clickhouse-server:local" + CLICKHOUSE_SERVER_IMAGE="yandex/clickhouse-server:local" - if [ ${CLICKHOUSE_PACKAGES_ARG} != ${NO_REBUILD_FLAG} ]; then - docker build \ - -f "${CLICKHOUSE_DOCKER_DIR}/server/local.Dockerfile" \ - --target clickhouse-server-base \ - -t clickhouse-server-base:preinstall \ - "${CLICKHOUSE_DOCKER_DIR}/server" + if [ ${CLICKHOUSE_PACKAGES_ARG} != ${NO_REBUILD_FLAG} ]; then + docker build \ + -f "${CLICKHOUSE_DOCKER_DIR}/server/local.Dockerfile" \ + --target clickhouse-server-base \ + -t clickhouse-server-base:preinstall \ + "${CLICKHOUSE_DOCKER_DIR}/server" - docker rm -f clickhouse_server_base_installing_server || true - docker run -v "${CLICKHOUSE_PACKAGES_DIR}:/packages" \ - --name clickhouse_server_base_installing_server \ - clickhouse-server-base:preinstall - docker commit clickhouse_server_base_installing_server clickhouse-server-base:postinstall + docker rm -f clickhouse_server_base_installing_server || true + docker run -v "${CLICKHOUSE_PACKAGES_DIR}:/packages" \ + --name clickhouse_server_base_installing_server \ + clickhouse-server-base:preinstall + docker commit clickhouse_server_base_installing_server clickhouse-server-base:postinstall - docker build \ - -f "${CLICKHOUSE_DOCKER_DIR}/server/local.Dockerfile" \ - --target clickhouse-server \ - -t "${CLICKHOUSE_SERVER_IMAGE}" \ - "${CLICKHOUSE_DOCKER_DIR}/server" - fi + docker build \ + -f "${CLICKHOUSE_DOCKER_DIR}/server/local.Dockerfile" \ + --target clickhouse-server \ + -t "${CLICKHOUSE_SERVER_IMAGE}" \ + "${CLICKHOUSE_DOCKER_DIR}/server" + fi fi docker rm -f test-runner || true docker-compose down CLICKHOUSE_SERVER_IMAGE="${CLICKHOUSE_SERVER_IMAGE}" \ - docker-compose -f "${CLICKHOUSE_DOCKER_DIR}/test/test_runner_docker_compose.yaml" \ - create \ - --build --force-recreate + docker-compose -f "${CLICKHOUSE_DOCKER_DIR}/test/test_runner_docker_compose.yaml" \ + create \ + --build --force-recreate CLICKHOUSE_SERVER_IMAGE="${CLICKHOUSE_SERVER_IMAGE}" \ - docker-compose -f "${CLICKHOUSE_DOCKER_DIR}/test/test_runner_docker_compose.yaml" \ - run \ - --name test-runner \ - test-runner + docker-compose -f "${CLICKHOUSE_DOCKER_DIR}/test/test_runner_docker_compose.yaml" \ + run \ + --name test-runner \ + test-runner diff --git a/docs/en/interfaces/formats.md b/docs/en/interfaces/formats.md index 4697fbca7e1..a08f2db7149 100644 --- a/docs/en/interfaces/formats.md +++ b/docs/en/interfaces/formats.md @@ -37,6 +37,8 @@ The supported formats are: | [Avro](#data-format-avro) | ✔ | ✔ | | [AvroConfluent](#data-format-avro-confluent) | ✔ | ✗ | | [Parquet](#data-format-parquet) | ✔ | ✔ | +| [Arrow](#data-format-arrow) | ✔ | ✔ | +| [ArrowStream](#data-format-arrow-stream) | ✔ | ✔ | | [ORC](#data-format-orc) | ✔ | ✗ | | [RowBinary](#rowbinary) | ✔ | ✔ | | [RowBinaryWithNamesAndTypes](#rowbinarywithnamesandtypes) | ✔ | ✔ | @@ -985,9 +987,9 @@ See also [how to read/write length-delimited protobuf messages in popular langua ## Avro {#data-format-avro} -[Apache Avro](http://avro.apache.org/) is a row-oriented data serialization framework developed within Apache’s Hadoop project. +[Apache Avro](https://avro.apache.org/) is a row-oriented data serialization framework developed within Apache’s Hadoop project. -ClickHouse Avro format supports reading and writing [Avro data files](http://avro.apache.org/docs/current/spec.html#Object+Container+Files). +ClickHouse Avro format supports reading and writing [Avro data files](https://avro.apache.org/docs/current/spec.html#Object+Container+Files). ### Data Types Matching {#data_types-matching} @@ -1009,7 +1011,7 @@ The table below shows supported data types and how they match ClickHouse [data t | `long (timestamp-millis)` \* | [DateTime64(3)](../sql-reference/data-types/datetime.md) | `long (timestamp-millis)` \* | | `long (timestamp-micros)` \* | [DateTime64(6)](../sql-reference/data-types/datetime.md) | `long (timestamp-micros)` \* | -\* [Avro logical types](http://avro.apache.org/docs/current/spec.html#Logical+Types) +\* [Avro logical types](https://avro.apache.org/docs/current/spec.html#Logical+Types) Unsupported Avro data types: `record` (non-root), `map` @@ -1095,7 +1097,7 @@ SELECT * FROM topic1_stream; ## Parquet {#data-format-parquet} -[Apache Parquet](http://parquet.apache.org/) is a columnar storage format widespread in the Hadoop ecosystem. ClickHouse supports read and write operations for this format. +[Apache Parquet](https://parquet.apache.org/) is a columnar storage format widespread in the Hadoop ecosystem. ClickHouse supports read and write operations for this format. ### Data Types Matching {#data_types-matching-2} @@ -1141,6 +1143,16 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Parquet" > {some_ To exchange data with Hadoop, you can use [HDFS table engine](../engines/table-engines/integrations/hdfs.md). +## Arrow {#data-format-arrow} + +[Apache Arrow](https://arrow.apache.org/) comes with two built-in columnar storage formats. ClickHouse supports read and write operations for these formats. + +`Arrow` is Apache Arrow's "file mode" format. It is designed for in-memory random access. + +## ArrowStream {#data-format-arrow-stream} + +`ArrowStream` is Apache Arrow's "stream mode" format. It is designed for in-memory stream processing. + ## ORC {#data-format-orc} [Apache ORC](https://orc.apache.org/) is a columnar storage format widespread in the Hadoop ecosystem. You can only insert data in this format to ClickHouse. diff --git a/docs/en/interfaces/third-party/integrations.md b/docs/en/interfaces/third-party/integrations.md index 5e9e8f841bf..716e774871b 100644 --- a/docs/en/interfaces/third-party/integrations.md +++ b/docs/en/interfaces/third-party/integrations.md @@ -25,6 +25,7 @@ toc_title: Integrations - Message queues - [Kafka](https://kafka.apache.org) - [clickhouse\_sinker](https://github.com/housepower/clickhouse_sinker) (uses [Go client](https://github.com/ClickHouse/clickhouse-go/)) + - [stream-loader-clickhouse](https://github.com/adform/stream-loader) - Stream processing - [Flink](https://flink.apache.org) - [flink-clickhouse-sink](https://github.com/ivi-ru/flink-clickhouse-sink) diff --git a/docs/en/introduction/adopters.md b/docs/en/introduction/adopters.md index 8868522e977..4daadf32be6 100644 --- a/docs/en/introduction/adopters.md +++ b/docs/en/introduction/adopters.md @@ -41,6 +41,7 @@ toc_title: Adopters | [Integros](https://integros.com){.favicon} | Platform for video services | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) | | [Kodiak Data](https://www.kodiakdata.com/){.favicon} | Clouds | Main product | — | — | [Slides in Engish, April 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup13/kodiak_data.pdf) | | [Kontur](https://kontur.ru){.favicon} | Software Development | Metrics | — | — | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY) | +| [Lawrence Berkeley National Laboratory](https://www.lbl.gov){.favicon} | Research | Traffic analysis | 1 server | 11.8 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) | | [LifeStreet](https://lifestreet.com/){.favicon} | Ad network | Main product | 75 servers (3 replicas) | 5.27 PiB | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/) | | [Mail.ru Cloud Solutions](https://mcs.mail.ru/){.favicon} | Cloud services | Main product | — | — | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#) | | [MessageBird](https://www.messagebird.com){.favicon} | Telecommunications | Statistics | — | — | [Slides in English, November 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup20/messagebird.pdf) | diff --git a/docs/en/operations/server-configuration-parameters/settings.md b/docs/en/operations/server-configuration-parameters/settings.md index 93acf3cae7a..5961c701283 100644 --- a/docs/en/operations/server-configuration-parameters/settings.md +++ b/docs/en/operations/server-configuration-parameters/settings.md @@ -586,11 +586,11 @@ If the table doesn’t exist, ClickHouse will create it. If the structure of the ``` -## query\_thread\_log {#server_configuration_parameters-query-thread-log} +## query\_thread\_log {#server_configuration_parameters-query_thread_log} Setting for logging threads of queries received with the [log\_query\_threads=1](../settings/settings.md#settings-log-query-threads) setting. -Queries are logged in the [system.query\_thread\_log](../../operations/system-tables.md#system_tables-query-thread-log) table, not in a separate file. You can change the name of the table in the `table` parameter (see below). +Queries are logged in the [system.query\_thread\_log](../../operations/system-tables.md#system_tables-query_thread_log) table, not in a separate file. You can change the name of the table in the `table` parameter (see below). Use the following parameters to configure logging: diff --git a/docs/en/operations/settings/settings.md b/docs/en/operations/settings/settings.md index 909ba7bf876..880f0ffedb1 100644 --- a/docs/en/operations/settings/settings.md +++ b/docs/en/operations/settings/settings.md @@ -404,6 +404,35 @@ Possible values: Default value: 0. +## partial_merge_join_optimizations {#partial_merge_join_optimizations} + +Disables optimizations in partial merge join algorithm for [JOIN](../../sql-reference/statements/select/join.md) queries. + +By default, this setting enables improvements that could lead to wrong results. If you see suspicious results in your queries, disable optimizations by this setting. Optimizations can be different in different versions of the ClickHouse server. + +Possible values: + +- 0 — Optimizations disabled. +- 1 — Optimizations enabled. + +Default value: 1. + +## partial_merge_join_rows_in_right_blocks {#partial_merge_join_rows_in_right_blocks} + +Limits sizes of right-hand join data blocks in partial merge join algorithm for [JOIN](../../sql-reference/statements/select/join.md) queries. + +ClickHouse server: + +1. Splits right-hand join data into blocks with up to the specified number of rows. +2. Indexes each block with their minimum and maximum values +3. Unloads prepared blocks to disk if possible. + +Possible values: + +- Any positive integer. Recommended range of values: [1000, 100000]. + +Default value: 65536. + ## any_join_distinct_right_table_keys {#any_join_distinct_right_table_keys} Enables legacy ClickHouse server behavior in `ANY INNER|LEFT JOIN` operations. @@ -569,7 +598,7 @@ log_queries_min_type='EXCEPTION_WHILE_PROCESSING' Setting up query threads logging. -Queries’ threads runned by ClickHouse with this setup are logged according to the rules in the [query\_thread\_log](../server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) server configuration parameter. +Queries’ threads runned by ClickHouse with this setup are logged according to the rules in the [query\_thread\_log](../server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server configuration parameter. Example: diff --git a/docs/en/operations/system-tables.md b/docs/en/operations/system-tables.md index cc5456f5324..f364d4e3068 100644 --- a/docs/en/operations/system-tables.md +++ b/docs/en/operations/system-tables.md @@ -5,7 +5,7 @@ toc_title: System Tables # System Tables {#system-tables} -## Introduction +## Introduction {#system-tables-introduction} System tables provide information about: @@ -18,9 +18,12 @@ System tables: - Available only for reading data. - Can't be dropped or altered, but can be detached. -The `metric_log`, `query_log`, `query_thread_log`, `trace_log` system tables store data in a storage filesystem. Other system tables store their data in RAM. ClickHouse server creates such system tables at the start. +Most of system tables store their data in RAM. ClickHouse server creates such system tables at the start. -### Sources of System Metrics +The [metric_log](#system_tables-metric_log), [query_log](#system_tables-query_log), [query_thread_log](#system_tables-query_thread_log), [trace_log](#system_tables-trace_log) system tables store data in a storage filesystem. You can alter them or remove from a disk manually. If you remove one of that tables from a disk, the ClickHouse server creates the table again at the time of the next recording. A storage period for these tables is not limited, and ClickHouse server doesn't delete their data automatically. You need to organize removing of outdated logs by yourself. For example, you can use [TTL](../sql-reference/statements/alter.md#manipulations-with-table-ttl) settings for removing outdated log records. + + +### Sources of System Metrics {#system-tables-sources-of-system-metrics} For collecting system metrics ClickHouse server uses: @@ -587,97 +590,150 @@ Columns: - `source_file` (LowCardinality(String)) — Source file from which the logging was done. - `source_line` (UInt64) — Source line from which the logging was done. -## system.query\_log {#system_tables-query_log} +## system.query_log {#system_tables-query_log} -Contains information about execution of queries. For each query, you can see processing start time, duration of processing, error messages and other information. +Contains information about executed queries, for example, start time, duration of processing, error messages. !!! note "Note" The table doesn’t contain input data for `INSERT` queries. -ClickHouse creates this table only if the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server parameter is specified. This parameter sets the logging rules, such as the logging interval or the name of the table the queries will be logged in. +You can change settings of queries logging in the [query_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) section of the server configuration. -To enable query logging, set the [log\_queries](settings/settings.md#settings-log-queries) parameter to 1. For details, see the [Settings](settings/settings.md) section. +You can disable queries logging by setting [log_queries = 0](settings/settings.md#settings-log-queries). We don't recommend to turn off logging because information in this table is important for solving issues. + +The flushing period of logs is set in `flush_interval_milliseconds` parameter of the [query_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server settings section. To force flushing logs, use the [SYSTEM FLUSH LOGS](../sql-reference/statements/system.md#query_language-system-flush_logs) query. + +ClickHouse doesn't delete logs from the table automatically. See [Introduction](#system-tables-introduction) for more details. The `system.query_log` table registers two kinds of queries: 1. Initial queries that were run directly by the client. 2. Child queries that were initiated by other queries (for distributed query execution). For these types of queries, information about the parent queries is shown in the `initial_*` columns. +Each query creates one or two rows in the `query_log` table, depending on the status (see the `type` column) of the query: + +1. If the query execution was successful, two rows with the `QueryStart` and `QueryFinish` types are created . +2. If an error occurred during query processing, two events with the `QueryStart` and `ExceptionWhileProcessing` types are created . +3. If an error occurred before launching the query, a single event with the `ExceptionBeforeStart` type is created. + Columns: -- `type` (`Enum8`) — Type of event that occurred when executing the query. Values: +- `type` ([Enum8](../sql-reference/data-types/enum.md)) — Type of an event that occurred when executing the query. Values: - `'QueryStart' = 1` — Successful start of query execution. - `'QueryFinish' = 2` — Successful end of query execution. - `'ExceptionBeforeStart' = 3` — Exception before the start of query execution. - `'ExceptionWhileProcessing' = 4` — Exception during the query execution. -- `event_date` (Date) — Query starting date. -- `event_time` (DateTime) — Query starting time. -- `query_start_time` (DateTime) — Start time of query execution. -- `query_duration_ms` (UInt64) — Duration of query execution. -- `read_rows` (UInt64) — Number of read rows. -- `read_bytes` (UInt64) — Number of read bytes. -- `written_rows` (UInt64) — For `INSERT` queries, the number of written rows. For other queries, the column value is 0. -- `written_bytes` (UInt64) — For `INSERT` queries, the number of written bytes. For other queries, the column value is 0. -- `result_rows` (UInt64) — Number of rows in the result. -- `result_bytes` (UInt64) — Number of bytes in the result. -- `memory_usage` (UInt64) — Memory consumption by the query. -- `query` (String) — Query string. -- `exception` (String) — Exception message. -- `stack_trace` (String) — Stack trace (a list of methods called before the error occurred). An empty string, if the query is completed successfully. -- `is_initial_query` (UInt8) — Query type. Possible values: +- `event_date` ([Date](../sql-reference/data-types/date.md)) — Query starting date. +- `event_time` ([DateTime](../sql-reference/data-types/datetime.md)) — Query starting time. +- `query_start_time` ([DateTime](../sql-reference/data-types/datetime.md)) — Start time of query execution. +- `query_duration_ms` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Duration of query execution in milliseconds. +- `read_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number or rows read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_rows` includes the total number of rows read at all replicas. Each replica sends it's `read_rows` value, and the server-initiator of the query summarize all received and local values. The cache volumes doesn't affect this value. +- `read_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number or bytes read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_bytes` includes the total number of rows read at all replicas. Each replica sends it's `read_bytes` value, and the server-initiator of the query summarize all received and local values. The cache volumes doesn't affect this value. +- `written_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written rows. For other queries, the column value is 0. +- `written_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written bytes. For other queries, the column value is 0. +- `result_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of rows in a result of the `SELECT` query, or a number of rows in the `INSERT` query. +- `result_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — RAM volume in bytes used to store a query result. +- `memory_usage` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Memory consumption by the query. +- `query` ([String](../sql-reference/data-types/string.md)) — Query string. +- `exception` ([String](../sql-reference/data-types/string.md)) — Exception message. +- `exception_code` ([Int32](../sql-reference/data-types/int-uint.md)) — Code of an exception. +- `stack_trace` ([String](../sql-reference/data-types/string.md)) — [Stack trace](https://en.wikipedia.org/wiki/Stack_trace). An empty string, if the query was completed successfully. +- `is_initial_query` ([UInt8](../sql-reference/data-types/int-uint.md)) — Query type. Possible values: - 1 — Query was initiated by the client. - - 0 — Query was initiated by another query for distributed query execution. -- `user` (String) — Name of the user who initiated the current query. -- `query_id` (String) — ID of the query. -- `address` (IPv6) — IP address that was used to make the query. -- `port` (UInt16) — The client port that was used to make the query. -- `initial_user` (String) — Name of the user who ran the initial query (for distributed query execution). -- `initial_query_id` (String) — ID of the initial query (for distributed query execution). -- `initial_address` (IPv6) — IP address that the parent query was launched from. -- `initial_port` (UInt16) — The client port that was used to make the parent query. -- `interface` (UInt8) — Interface that the query was initiated from. Possible values: + - 0 — Query was initiated by another query as part of distributed query execution. +- `user` ([String](../sql-reference/data-types/string.md)) — Name of the user who initiated the current query. +- `query_id` ([String](../sql-reference/data-types/string.md)) — ID of the query. +- `address` ([IPv6](../sql-reference/data-types/domains/ipv6.md)) — IP address that was used to make the query. +- `port` ([UInt16](../sql-reference/data-types/int-uint.md)) — The client port that was used to make the query. +- `initial_user` ([String](../sql-reference/data-types/string.md)) — Name of the user who ran the initial query (for distributed query execution). +- `initial_query_id` ([String](../sql-reference/data-types/string.md)) — ID of the initial query (for distributed query execution). +- `initial_address` ([IPv6](../sql-reference/data-types/domains/ipv6.md)) — IP address that the parent query was launched from. +- `initial_port` ([UInt16](../sql-reference/data-types/int-uint.md)) — The client port that was used to make the parent query. +- `interface` ([UInt8](../sql-reference/data-types/int-uint.md)) — Interface that the query was initiated from. Possible values: - 1 — TCP. - 2 — HTTP. -- `os_user` (String) — OS’s username who runs [clickhouse-client](../interfaces/cli.md). -- `client_hostname` (String) — Hostname of the client machine where the [clickhouse-client](../interfaces/cli.md) or another TCP client is run. -- `client_name` (String) — The [clickhouse-client](../interfaces/cli.md) or another TCP client name. -- `client_revision` (UInt32) — Revision of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_major` (UInt32) — Major version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_minor` (UInt32) — Minor version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_patch` (UInt32) — Patch component of the [clickhouse-client](../interfaces/cli.md) or another TCP client version. +- `os_user` ([String](../sql-reference/data-types/string.md)) — Operating system username who runs [clickhouse-client](../interfaces/cli.md). +- `client_hostname` ([String](../sql-reference/data-types/string.md)) — Hostname of the client machine where the [clickhouse-client](../interfaces/cli.md) or another TCP client is run. +- `client_name` ([String](../sql-reference/data-types/string.md)) — The [clickhouse-client](../interfaces/cli.md) or another TCP client name. +- `client_revision` ([UInt32](../sql-reference/data-types/int-uint.md)) — Revision of the [clickhouse-client](../interfaces/cli.md) or another TCP client. +- `client_version_major` ([UInt32](../sql-reference/data-types/int-uint.md)) — Major version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. +- `client_version_minor` ([UInt32](../sql-reference/data-types/int-uint.md)) — Minor version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. +- `client_version_patch` ([UInt32](../sql-reference/data-types/int-uint.md)) — Patch component of the [clickhouse-client](../interfaces/cli.md) or another TCP client version. - `http_method` (UInt8) — HTTP method that initiated the query. Possible values: - 0 — The query was launched from the TCP interface. - 1 — `GET` method was used. - 2 — `POST` method was used. -- `http_user_agent` (String) — The `UserAgent` header passed in the HTTP request. -- `quota_key` (String) — The “quota key” specified in the [quotas](quotas.md) setting (see `keyed`). -- `revision` (UInt32) — ClickHouse revision. -- `thread_numbers` (Array(UInt32)) — Number of threads that are participating in query execution. -- `ProfileEvents.Names` (Array(String)) — Counters that measure different metrics. The description of them could be found in the table [system.events](#system_tables-events) -- `ProfileEvents.Values` (Array(UInt64)) — Values of metrics that are listed in the `ProfileEvents.Names` column. -- `Settings.Names` (Array(String)) — Names of settings that were changed when the client ran the query. To enable logging changes to settings, set the `log_query_settings` parameter to 1. -- `Settings.Values` (Array(String)) — Values of settings that are listed in the `Settings.Names` column. +- `http_user_agent` ([String](../sql-reference/data-types/string.md)) — The `UserAgent` header passed in the HTTP request. +- `quota_key` ([String](../sql-reference/data-types/string.md)) — The “quota key” specified in the [quotas](quotas.md) setting (see `keyed`). +- `revision` ([UInt32](../sql-reference/data-types/int-uint.md)) — ClickHouse revision. +- `thread_numbers` ([Array(UInt32)](../sql-reference/data-types/array.md)) — Number of threads that are participating in query execution. +- `ProfileEvents.Names` ([Array(String)](../sql-reference/data-types/array.md)) — Counters that measure different metrics. The description of them could be found in the table [system.events](#system_tables-events) +- `ProfileEvents.Values` ([Array(UInt64)](../sql-reference/data-types/array.md)) — Values of metrics that are listed in the `ProfileEvents.Names` column. +- `Settings.Names` ([Array(String)](../sql-reference/data-types/array.md)) — Names of settings that were changed when the client ran the query. To enable logging changes to settings, set the `log_query_settings` parameter to 1. +- `Settings.Values` ([Array(String)](../sql-reference/data-types/array.md)) — Values of settings that are listed in the `Settings.Names` column. -Each query creates one or two rows in the `query_log` table, depending on the status of the query: +**Example** -1. If the query execution is successful, two events with types 1 and 2 are created (see the `type` column). -2. If an error occurred during query processing, two events with types 1 and 4 are created. -3. If an error occurred before launching the query, a single event with type 3 is created. +``` sql +SELECT * FROM system.query_log LIMIT 1 FORMAT Vertical; +``` -By default, logs are added to the table at intervals of 7.5 seconds. You can set this interval in the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server setting (see the `flush_interval_milliseconds` parameter). To flush the logs forcibly from the memory buffer into the table, use the `SYSTEM FLUSH LOGS` query. +``` text +Row 1: +────── +type: QueryStart +event_date: 2020-05-13 +event_time: 2020-05-13 14:02:28 +query_start_time: 2020-05-13 14:02:28 +query_duration_ms: 0 +read_rows: 0 +read_bytes: 0 +written_rows: 0 +written_bytes: 0 +result_rows: 0 +result_bytes: 0 +memory_usage: 0 +query: SELECT 1 +exception_code: 0 +exception: +stack_trace: +is_initial_query: 1 +user: default +query_id: 5e834082-6f6d-4e34-b47b-cd1934f4002a +address: ::ffff:127.0.0.1 +port: 57720 +initial_user: default +initial_query_id: 5e834082-6f6d-4e34-b47b-cd1934f4002a +initial_address: ::ffff:127.0.0.1 +initial_port: 57720 +interface: 1 +os_user: bayonet +client_hostname: clickhouse.ru-central1.internal +client_name: ClickHouse client +client_revision: 54434 +client_version_major: 20 +client_version_minor: 4 +client_version_patch: 1 +http_method: 0 +http_user_agent: +quota_key: +revision: 54434 +thread_ids: [] +ProfileEvents.Names: [] +ProfileEvents.Values: [] +Settings.Names: ['use_uncompressed_cache','load_balancing','log_queries','max_memory_usage'] +Settings.Values: ['0','random','1','10000000000'] -When the table is deleted manually, it will be automatically created on the fly. Note that all the previous logs will be deleted. +``` +**See Also** -!!! note "Note" - The storage period for logs is unlimited. Logs aren’t automatically deleted from the table. You need to organize the removal of outdated logs yourself. +- [system.query_thread_log](#system_tables-query_thread_log) — This table contains information about each query execution thread. -You can specify an arbitrary partitioning key for the `system.query_log` table in the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server setting (see the `partition_by` parameter). - -## system.query\_thread\_log {#system_tables-query-thread-log} +## system.query_thread_log {#system_tables-query_thread_log} The table contains information about each query execution thread. -ClickHouse creates this table only if the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) server parameter is specified. This parameter sets the logging rules, such as the logging interval or the name of the table the queries will be logged in. +ClickHouse creates this table only if the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server parameter is specified. This parameter sets the logging rules, such as the logging interval or the name of the table the queries will be logged in. To enable query logging, set the [log\_query\_threads](settings/settings.md#settings-log-query-threads) parameter to 1. For details, see the [Settings](settings/settings.md) section. @@ -729,14 +785,14 @@ Columns: - `ProfileEvents.Names` (Array(String)) — Counters that measure different metrics for this thread. The description of them could be found in the table [system.events](#system_tables-events) - `ProfileEvents.Values` (Array(UInt64)) — Values of metrics for this thread that are listed in the `ProfileEvents.Names` column. -By default, logs are added to the table at intervals of 7.5 seconds. You can set this interval in the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) server setting (see the `flush_interval_milliseconds` parameter). To flush the logs forcibly from the memory buffer into the table, use the `SYSTEM FLUSH LOGS` query. +By default, logs are added to the table at intervals of 7.5 seconds. You can set this interval in the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server setting (see the `flush_interval_milliseconds` parameter). To flush the logs forcibly from the memory buffer into the table, use the `SYSTEM FLUSH LOGS` query. When the table is deleted manually, it will be automatically created on the fly. Note that all the previous logs will be deleted. !!! note "Note" The storage period for logs is unlimited. Logs aren’t automatically deleted from the table. You need to organize the removal of outdated logs yourself. -You can specify an arbitrary partitioning key for the `system.query_thread_log` table in the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) server setting (see the `partition_by` parameter). +You can specify an arbitrary partitioning key for the `system.query_thread_log` table in the [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server setting (see the `partition_by` parameter). ## system.trace\_log {#system_tables-trace_log} diff --git a/docs/en/sql-reference/functions/url-functions.md b/docs/en/sql-reference/functions/url-functions.md index 143bd42b08e..34477529649 100644 --- a/docs/en/sql-reference/functions/url-functions.md +++ b/docs/en/sql-reference/functions/url-functions.md @@ -117,6 +117,10 @@ Returns the part of the domain that includes top-level subdomains up to the “f For example, `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`. +### port(URL[, default_port = 0]) {#port} + +Returns the port or `default_port` if there is no port in the URL (or in case of validation error). + ### path {#path} Returns the path. Example: `/top/news.html` The path does not include the query string. diff --git a/docs/ru/operations/server-configuration-parameters/settings.md b/docs/ru/operations/server-configuration-parameters/settings.md index c664580c659..ccde7a945ac 100644 --- a/docs/ru/operations/server-configuration-parameters/settings.md +++ b/docs/ru/operations/server-configuration-parameters/settings.md @@ -574,11 +574,11 @@ ClickHouse проверит условия `min_part_size` и `min_part_size_rat ``` -## query\_thread\_log {#server_configuration_parameters-query-thread-log} +## query\_thread\_log {#server_configuration_parameters-query_thread_log} Настройка логирования потоков выполнения запросов, принятых с настройкой [log\_query\_threads=1](../settings/settings.md#settings-log-query-threads). -Запросы логируются не в отдельный файл, а в системную таблицу [system.query\_thread\_log](../../operations/server-configuration-parameters/settings.md#system_tables-query-thread-log). Вы можете изменить название этой таблицы в параметре `table` (см. ниже). +Запросы логируются не в отдельный файл, а в системную таблицу [system.query\_thread\_log](../../operations/server-configuration-parameters/settings.md#system_tables-query_thread_log). Вы можете изменить название этой таблицы в параметре `table` (см. ниже). При настройке логирования используются следующие параметры: diff --git a/docs/ru/operations/settings/settings.md b/docs/ru/operations/settings/settings.md index 56c3042bfa3..4dd43e9607b 100644 --- a/docs/ru/operations/settings/settings.md +++ b/docs/ru/operations/settings/settings.md @@ -536,7 +536,7 @@ log_queries=1 Установка логирования информации о потоках выполнения запроса. -Лог информации о потоках выполнения запросов, переданных в ClickHouse с этой установкой, записывается согласно правилам конфигурационного параметра сервера [query\_thread\_log](../server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log). +Лог информации о потоках выполнения запросов, переданных в ClickHouse с этой установкой, записывается согласно правилам конфигурационного параметра сервера [query\_thread\_log](../server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log). Пример: diff --git a/docs/ru/operations/system-tables.md b/docs/ru/operations/system-tables.md index ae0e67a4515..8954a484560 100644 --- a/docs/ru/operations/system-tables.md +++ b/docs/ru/operations/system-tables.md @@ -1,4 +1,7 @@ -# Системные таблицы {#sistemnye-tablitsy} +# Системные таблицы {#system-tables} + + +## Введение {#system-tables-introduction} Системные таблицы используются для реализации части функциональности системы, а также предоставляют доступ к информации о работе системы. Вы не можете удалить системную таблицу (хотя можете сделать DETACH). @@ -544,182 +547,156 @@ CurrentMetric_ReplicatedChecks: 0 - `source_file` (LowCardinality(String)) — Исходный файл, из которого была сделана запись. - `source_line` (UInt64) — Исходная строка, из которой была сделана запись. -## system.query\_log {#system_tables-query_log} +## system.query_log {#system_tables-query_log} -Содержит информацию о выполнении запросов. Для каждого запроса вы можете увидеть время начала обработки, продолжительность обработки, сообщения об ошибках и другую информацию. +Содержит информацию о выполняемых запросах, например, время начала обработки, продолжительность обработки, сообщения об ошибках. !!! note "Внимание" Таблица не содержит входных данных для запросов `INSERT`. -ClickHouse создаёт таблицу только в том случае, когда установлен конфигурационный параметр сервера [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log). Параметр задаёт правила ведения лога, такие как интервал логирования или имя таблицы, в которую будут логгироваться запросы. +Настойки логгирования можно изменить в секции серверной конфигурации [query_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log). -Чтобы включить логирование, задайте значение параметра [log\_queries](settings/settings.md#settings-log-queries) равным 1. Подробности смотрите в разделе [Настройки](settings/settings.md#settings). +Можно отключить логгирование настройкой [log_queries = 0](settings/settings.md#settings-log-queries). По-возможности, не отключайте логгирование, поскольку информация из таблицы важна при решении проблем. + +Период сброса логов в таблицу задаётся параметром `flush_interval_milliseconds` в конфигурационной секции [query_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log). Чтобы принудительно записать логи из буффера памяти в таблицу, используйте запрос [SYSTEM FLUSH LOGS](../sql-reference/statements/system.md#query_language-system-flush_logs). + +ClickHouse не удаляет логи из таблица автоматически. Смотрите [Введение](#system-tables-introduction). + +Можно указать произвольный ключ партиционирования для таблицы `system.query_log` в конфигурации [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) (параметр `partition_by`). + + + +Если таблицу удалить вручную, она создается заново автоматически «на лету». При этом все логи на момент удаления таблицы будут убраны. Таблица `system.query_log` содержит информацию о двух видах запросов: 1. Первоначальные запросы, которые были выполнены непосредственно клиентом. 2. Дочерние запросы, инициированные другими запросами (для выполнения распределенных запросов). Для дочерних запросов информация о первоначальном запросе содержится в столбцах `initial_*`. +В зависимости от статуса (столбец `type`) каждый запрос создаёт одну или две строки в таблице `query_log`: + +1. Если запрос выполнен успешно, создаются два события типа `QueryStart` и `QueryFinish`. +2. Если во время обработки запроса возникла ошибка, создаются два события с типами `QueryStart` и `ExceptionWhileProcessing`. +3. Если ошибка произошла ещё до запуска запроса, создается одно событие с типом `ExceptionBeforeStart`. + Столбцы: -- `type` (`Enum8`) — тип события, произошедшего при выполнении запроса. Значения: +- `type` ([Enum8](../sql-reference/data-types/enum.md)) — тип события, произошедшего при выполнении запроса. Значения: - `'QueryStart' = 1` — успешное начало выполнения запроса. - `'QueryFinish' = 2` — успешное завершение выполнения запроса. - `'ExceptionBeforeStart' = 3` — исключение перед началом обработки запроса. - `'ExceptionWhileProcessing' = 4` — исключение во время обработки запроса. -- `event_date` (Date) — дата начала запроса. -- `event_time` (DateTime) — время начала запроса. -- `query_start_time` (DateTime) — время начала обработки запроса. -- `query_duration_ms` (UInt64) — длительность обработки запроса. -- `read_rows` (UInt64) — количество прочитанных строк. -- `read_bytes` (UInt64) — количество прочитанных байтов. -- `written_rows` (UInt64) — количество записанных строк для запросов `INSERT`. Для других запросов, значение столбца 0. -- `written_bytes` (UInt64) — объём записанных данных в байтах для запросов `INSERT`. Для других запросов, значение столбца 0. -- `result_rows` (UInt64) — количество строк в результате. -- `result_bytes` (UInt64) — объём результата в байтах. -- `memory_usage` (UInt64) — потребление RAM запросом. -- `query` (String) — текст запроса. -- `exception` (String) — сообщение исключения, если запрос завершился по исключению. -- `stack_trace` (String) — трассировка (список функций, последовательно вызванных перед ошибкой). Пустая строка, если запрос успешно завершен. -- `is_initial_query` (UInt8) — вид запроса. Возможные значения: +- `event_date` ([Date](../sql-reference/data-types/date.md)) — дата начала запроса. +- `event_time` ([DateTime](../sql-reference/data-types/datetime.md)) — время начала запроса. +- `query_start_time` ([DateTime](../sql-reference/data-types/datetime.md)) — время начала обработки запроса. +- `query_duration_ms` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — длительность выполнения запроса в миллисекундах. +- `read_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Общее количество строк, считанных из всех таблиц и табличных функций, участвующих в запросе. Включает в себя обычные подзапросы, подзапросы для `IN` и `JOIN`. Для распределенных запросов `read_rows` включает в себя общее количество строк, прочитанных на всех репликах. Каждая реплика передает собственное значение `read_rows`, а сервер-инициатор запроса суммирует все полученные и локальные значения. Объемы кэша не учитываюся. +- `read_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — Общее количество байтов, считанных из всех таблиц и табличных функций, участвующих в запросе. Включает в себя обычные подзапросы, подзапросы для `IN` и `JOIN`. Для распределенных запросов `read_bytes` включает в себя общее количество байтов, прочитанных на всех репликах. Каждая реплика передает собственное значение `read_bytes`, а сервер-инициатор запроса суммирует все полученные и локальные значения. Объемы кэша не учитываюся. +- `written_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — количество записанных строк для запросов `INSERT`. Для других запросов, значение столбца 0. +- `written_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — объём записанных данных в байтах для запросов `INSERT`. Для других запросов, значение столбца 0. +- `result_rows` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — количество строк в результате запроса `SELECT` или количество строк в запросе `INSERT`. +- `result_bytes` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — объём RAM в байтах, использованный для хранения результата запроса. +- `memory_usage` ([UInt64](../sql-reference/data-types/int-uint.md#uint-ranges)) — потребление RAM запросом. +- `query` ([String](../sql-reference/data-types/string.md)) — текст запроса. +- `exception` ([String](../sql-reference/data-types/string.md)) — сообщение исключения, если запрос завершился по исключению. +- `exception_code` ([Int32](../sql-reference/data-types/int-uint.md)) — код исключения. +- `stack_trace` ([String](../sql-reference/data-types/string.md)) — [stack trace](https://en.wikipedia.org/wiki/Stack_trace). Пустая строка, если запрос успешно завершен. +- `is_initial_query` ([UInt8](../sql-reference/data-types/int-uint.md)) — вид запроса. Возможные значения: - 1 — запрос был инициирован клиентом. - - 0 — запрос был инициирован другим запросом при распределенном запросе. -- `user` (String) — пользователь, запустивший текущий запрос. -- `query_id` (String) — ID запроса. -- `address` (IPv6) — IP адрес, с которого пришел запрос. -- `port` (UInt16) — порт, с которого клиент сделал запрос -- `initial_user` (String) — пользователь, запустивший первоначальный запрос (для распределенных запросов). -- `initial_query_id` (String) — ID родительского запроса. -- `initial_address` (IPv6) — IP адрес, с которого пришел родительский запрос. -- `initial_port` (UInt16) — порт, с которого клиент сделал родительский запрос. -- `interface` (UInt8) — интерфейс, с которого ушёл запрос. Возможные значения: + - 0 — запрос был инициирован другим запросом при выполнении распределенного запроса. +- `user` ([String](../sql-reference/data-types/string.md)) — пользователь, запустивший текущий запрос. +- `query_id` ([String](../sql-reference/data-types/string.md)) — ID запроса. +- `address` ([IPv6](../sql-reference/data-types/domains/ipv6.md)) — IP адрес, с которого пришел запрос. +- `port` ([UInt16](../sql-reference/data-types/int-uint.md)) — порт, с которого клиент сделал запрос +- `initial_user` ([String](../sql-reference/data-types/string.md)) — пользователь, запустивший первоначальный запрос (для распределенных запросов). +- `initial_query_id` ([String](../sql-reference/data-types/string.md)) — ID родительского запроса. +- `initial_address` ([IPv6](../sql-reference/data-types/domains/ipv6.md)) — IP адрес, с которого пришел родительский запрос. +- `initial_port` ([UInt16](../sql-reference/data-types/int-uint.md)) — порт, с которого клиент сделал родительский запрос. +- `interface` ([UInt8](../sql-reference/data-types/int-uint.md)) — интерфейс, с которого ушёл запрос. Возможные значения: - 1 — TCP. - 2 — HTTP. -- `os_user` (String) — имя пользователя в OS, который запустил [clickhouse-client](../interfaces/cli.md). -- `client_hostname` (String) — имя сервера, с которого присоединился [clickhouse-client](../interfaces/cli.md) или другой TCP клиент. -- `client_name` (String) — [clickhouse-client](../interfaces/cli.md) или другой TCP клиент. -- `client_revision` (UInt32) — ревизия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. -- `client_version_major` (UInt32) — старшая версия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. -- `client_version_minor` (UInt32) — младшая версия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. -- `client_version_patch` (UInt32) — патч [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. -- `http_method` (UInt8) — HTTP метод, инициировавший запрос. Возможные значения: +- `os_user` ([String](../sql-reference/data-types/string.md)) — имя пользователя операционной системы, который запустил [clickhouse-client](../interfaces/cli.md). +- `client_hostname` ([String](../sql-reference/data-types/string.md)) — имя сервера, с которого присоединился [clickhouse-client](../interfaces/cli.md) или другой TCP клиент. +- `client_name` ([String](../sql-reference/data-types/string.md)) — [clickhouse-client](../interfaces/cli.md) или другой TCP клиент. +- `client_revision` ([UInt32](../sql-reference/data-types/int-uint.md)) — ревизия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. +- `client_version_major` ([UInt32](../sql-reference/data-types/int-uint.md)) — старшая версия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. +- `client_version_minor` ([UInt32](../sql-reference/data-types/int-uint.md)) — младшая версия [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. +- `client_version_patch` ([UInt32](../sql-reference/data-types/int-uint.md)) — патч [clickhouse-client](../interfaces/cli.md) или другого TCP клиента. +- `http_method` ([UInt8](../sql-reference/data-types/int-uint.md)) — HTTP метод, инициировавший запрос. Возможные значения: - 0 — запрос запущен с интерфейса TCP. - 1 — `GET`. - 2 — `POST`. -- `http_user_agent` (String) — HTTP заголовок `UserAgent`. -- `quota_key` (String) — «ключ квоты» из настроек [квот](quotas.md) (см. `keyed`). -- `revision` (UInt32) — ревизия ClickHouse. -- `thread_numbers` (Array(UInt32)) — количество потоков, участвующих в обработке запросов. -- `ProfileEvents.Names` (Array(String)) — Счетчики для изменения различных метрик. Описание метрик можно получить из таблицы [system.events](#system_tables-events)(\#system\_tables-events -- `ProfileEvents.Values` (Array(UInt64)) — метрики, перечисленные в столбце `ProfileEvents.Names`. -- `Settings.Names` (Array(String)) — имена настроек, которые меняются, когда клиент выполняет запрос. Чтобы разрешить логирование изменений настроек, установите параметр `log_query_settings` равным 1. -- `Settings.Values` (Array(String)) — Значения настроек, которые перечислены в столбце `Settings.Names`. +- `http_user_agent` ([String](../sql-reference/data-types/string.md)) — HTTP заголовок `UserAgent`. +- `quota_key` ([String](../sql-reference/data-types/string.md)) — «ключ квоты» из настроек [квот](quotas.md) (см. `keyed`). +- `revision` ([UInt32](../sql-reference/data-types/int-uint.md)) — ревизия ClickHouse. +- `thread_numbers` ([Array(UInt32)](../sql-reference/data-types/array.md)) — количество потоков, участвующих в обработке запросов. +- `ProfileEvents.Names` ([Array(String)](../sql-reference/data-types/array.md)) — Счетчики для изменения различных метрик. Описание метрик можно получить из таблицы [system.events](#system_tables-events)(\#system\_tables-events +- `ProfileEvents.Values` ([Array(UInt64)](../sql-reference/data-types/array.md)) — метрики, перечисленные в столбце `ProfileEvents.Names`. +- `Settings.Names` ([Array(String)](../sql-reference/data-types/array.md)) — имена настроек, которые меняются, когда клиент выполняет запрос. Чтобы разрешить логирование изменений настроек, установите параметр `log_query_settings` равным 1. +- `Settings.Values` ([Array(String)](../sql-reference/data-types/array.md)) — Значения настроек, которые перечислены в столбце `Settings.Names`. -Каждый запрос создаёт одну или две строки в таблице `query_log`, в зависимости от статуса запроса: +**Пример** -1. Если запрос выполнен успешно, создаются два события типа 1 и 2 (смотрите столбец `type`). -2. Если во время обработки запроса произошла ошибка, создаются два события с типами 1 и 4. -3. Если ошибка произошла до запуска запроса, создается одно событие с типом 3. +``` sql +SELECT * FROM system.query_log LIMIT 1 FORMAT Vertical; +``` -По умолчанию, строки добавляются в таблицу логирования с интервалом в 7,5 секунд. Можно задать интервал в конфигурационном параметре сервера [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) (смотрите параметр `flush_interval_milliseconds`). Чтобы принудительно записать логи из буффера памяти в таблицу, используйте запрос `SYSTEM FLUSH LOGS`. +``` text +Row 1: +────── +type: QueryStart +event_date: 2020-05-13 +event_time: 2020-05-13 14:02:28 +query_start_time: 2020-05-13 14:02:28 +query_duration_ms: 0 +read_rows: 0 +read_bytes: 0 +written_rows: 0 +written_bytes: 0 +result_rows: 0 +result_bytes: 0 +memory_usage: 0 +query: SELECT 1 +exception_code: 0 +exception: +stack_trace: +is_initial_query: 1 +user: default +query_id: 5e834082-6f6d-4e34-b47b-cd1934f4002a +address: ::ffff:127.0.0.1 +port: 57720 +initial_user: default +initial_query_id: 5e834082-6f6d-4e34-b47b-cd1934f4002a +initial_address: ::ffff:127.0.0.1 +initial_port: 57720 +interface: 1 +os_user: bayonet +client_hostname: clickhouse.ru-central1.internal +client_name: ClickHouse client +client_revision: 54434 +client_version_major: 20 +client_version_minor: 4 +client_version_patch: 1 +http_method: 0 +http_user_agent: +quota_key: +revision: 54434 +thread_ids: [] +ProfileEvents.Names: [] +ProfileEvents.Values: [] +Settings.Names: ['use_uncompressed_cache','load_balancing','log_queries','max_memory_usage'] +Settings.Values: ['0','random','1','10000000000'] -Если таблицу удалить вручную, она пересоздастся автоматически «на лету». При этом все логи на момент удаления таблицы будут удалены. +``` +**Смотрите также** -!!! note "Примечание" - Срок хранения логов не ограничен. Логи не удаляются из таблицы автоматически. Вам необходимо самостоятельно организовать удаление устаревших логов. +- [system.query_thread_log](#system_tables-query_thread_log) — в этой таблице содержится информация о цепочке каждого выполненного запроса. -Можно указать произвольный ключ партиционирования для таблицы `system.query_log` в конфигурации [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) (параметр `partition_by`). - -## system.query\_log {#system_tables-query_log} - -Contains information about execution of queries. For each query, you can see processing start time, duration of processing, error messages and other information. - -!!! note "Note" - The table doesn’t contain input data for `INSERT` queries. - -ClickHouse creates this table only if the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server parameter is specified. This parameter sets the logging rules, such as the logging interval or the name of the table the queries will be logged in. - -To enable query logging, set the [log\_queries](settings/settings.md#settings-log-queries) parameter to 1. For details, see the [Settings](settings/settings.md) section. - -The `system.query_log` table registers two kinds of queries: - -1. Initial queries that were run directly by the client. -2. Child queries that were initiated by other queries (for distributed query execution). For these types of queries, information about the parent queries is shown in the `initial_*` columns. - -Columns: - -- `type` (`Enum8`) — Type of event that occurred when executing the query. Values: - - `'QueryStart' = 1` — Successful start of query execution. - - `'QueryFinish' = 2` — Successful end of query execution. - - `'ExceptionBeforeStart' = 3` — Exception before the start of query execution. - - `'ExceptionWhileProcessing' = 4` — Exception during the query execution. -- `event_date` (Date) — Query starting date. -- `event_time` (DateTime) — Query starting time. -- `query_start_time` (DateTime) — Start time of query execution. -- `query_duration_ms` (UInt64) — Duration of query execution. -- `read_rows` (UInt64) — Number of read rows. -- `read_bytes` (UInt64) — Number of read bytes. -- `written_rows` (UInt64) — For `INSERT` queries, the number of written rows. For other queries, the column value is 0. -- `written_bytes` (UInt64) — For `INSERT` queries, the number of written bytes. For other queries, the column value is 0. -- `result_rows` (UInt64) — Number of rows in the result. -- `result_bytes` (UInt64) — Number of bytes in the result. -- `memory_usage` (UInt64) — Memory consumption by the query. -- `query` (String) — Query string. -- `exception` (String) — Exception message. -- `stack_trace` (String) — Stack trace (a list of methods called before the error occurred). An empty string, if the query is completed successfully. -- `is_initial_query` (UInt8) — Query type. Possible values: - - 1 — Query was initiated by the client. - - 0 — Query was initiated by another query for distributed query execution. -- `user` (String) — Name of the user who initiated the current query. -- `query_id` (String) — ID of the query. -- `address` (IPv6) — IP address that was used to make the query. -- `port` (UInt16) — The client port that was used to make the query. -- `initial_user` (String) — Name of the user who ran the initial query (for distributed query execution). -- `initial_query_id` (String) — ID of the initial query (for distributed query execution). -- `initial_address` (IPv6) — IP address that the parent query was launched from. -- `initial_port` (UInt16) — The client port that was used to make the parent query. -- `interface` (UInt8) — Interface that the query was initiated from. Possible values: - - 1 — TCP. - - 2 — HTTP. -- `os_user` (String) — OS’s username who runs [clickhouse-client](../interfaces/cli.md). -- `client_hostname` (String) — Hostname of the client machine where the [clickhouse-client](../interfaces/cli.md) or another TCP client is run. -- `client_name` (String) — The [clickhouse-client](../interfaces/cli.md) or another TCP client name. -- `client_revision` (UInt32) — Revision of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_major` (UInt32) — Major version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_minor` (UInt32) — Minor version of the [clickhouse-client](../interfaces/cli.md) or another TCP client. -- `client_version_patch` (UInt32) — Patch component of the [clickhouse-client](../interfaces/cli.md) or another TCP client version. -- `http_method` (UInt8) — HTTP method that initiated the query. Possible values: - - 0 — The query was launched from the TCP interface. - - 1 — `GET` method was used. - - 2 — `POST` method was used. -- `http_user_agent` (String) — The `UserAgent` header passed in the HTTP request. -- `quota_key` (String) — The «quota key» specified in the [quotas](quotas.md) setting (see `keyed`). -- `revision` (UInt32) — ClickHouse revision. -- `thread_numbers` (Array(UInt32)) — Number of threads that are participating in query execution. -- `ProfileEvents.Names` (Array(String)) — Counters that measure different metrics. The description of them could be found in the table [system.events](#system_tables-events) -- `ProfileEvents.Values` (Array(UInt64)) — Values of metrics that are listed in the `ProfileEvents.Names` column. -- `Settings.Names` (Array(String)) — Names of settings that were changed when the client ran the query. To enable logging changes to settings, set the `log_query_settings` parameter to 1. -- `Settings.Values` (Array(String)) — Values of settings that are listed in the `Settings.Names` column. - -Each query creates one or two rows in the `query_log` table, depending on the status of the query: - -1. If the query execution is successful, two events with types 1 and 2 are created (see the `type` column). -2. If an error occurred during query processing, two events with types 1 and 4 are created. -3. If an error occurred before launching the query, a single event with type 3 is created. - -By default, logs are added to the table at intervals of 7.5 seconds. You can set this interval in the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server setting (see the `flush_interval_milliseconds` parameter). To flush the logs forcibly from the memory buffer into the table, use the `SYSTEM FLUSH LOGS` query. - -When the table is deleted manually, it will be automatically created on the fly. Note that all the previous logs will be deleted. - -!!! note "Note" - The storage period for logs is unlimited. Logs aren’t automatically deleted from the table. You need to organize the removal of outdated logs yourself. - -You can specify an arbitrary partitioning key for the `system.query_log` table in the [query\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server setting (see the `partition_by` parameter). -\#\# system.query\_thread\_log {\#system\_tables-query-thread-log} +## system.query_thread_log {#system_tables-query_thread_log} Содержит информацию о каждом потоке выполняемых запросов. -ClickHouse создаёт таблицу только в том случае, когда установлен конфигурационный параметр сервера [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log). Параметр задаёт правила ведения лога, такие как интервал логирования или имя таблицы, в которую будут логгироваться запросы. +ClickHouse создаёт таблицу только в том случае, когда установлен конфигурационный параметр сервера [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log). Параметр задаёт правила ведения лога, такие как интервал логирования или имя таблицы, в которую будут логгироваться запросы. Чтобы включить логирование, задайте значение параметра [log\_query\_threads](settings/settings.md#settings-log-query-threads) равным 1. Подробности смотрите в разделе [Настройки](settings/settings.md#settings). @@ -770,16 +747,16 @@ ClickHouse создаёт таблицу только в том случае, к - `ProfileEvents.Names` (Array(String)) — Счетчики для изменения различных метрик для данного потока. Описание метрик можно получить из таблицы [system.events](#system_tables-events)(\#system\_tables-events - `ProfileEvents.Values` (Array(UInt64)) — метрики для данного потока, перечисленные в столбце `ProfileEvents.Names`. -По умолчанию, строки добавляются в таблицу логирования с интервалом в 7,5 секунд. Можно задать интервал в конфигурационном параметре сервера [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) (смотрите параметр `flush_interval_milliseconds`). Чтобы принудительно записать логи из буффера памяти в таблицу, используйте запрос `SYSTEM FLUSH LOGS`. +По умолчанию, строки добавляются в таблицу логирования с интервалом в 7,5 секунд. Можно задать интервал в конфигурационном параметре сервера [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) (смотрите параметр `flush_interval_milliseconds`). Чтобы принудительно записать логи из буффера памяти в таблицу, используйте запрос `SYSTEM FLUSH LOGS`. Если таблицу удалить вручную, она пересоздастся автоматически «на лету». При этом все логи на момент удаления таблицы будут удалены. !!! note "Примечание" Срок хранения логов не ограничен. Логи не удаляются из таблицы автоматически. Вам необходимо самостоятельно организовать удаление устаревших логов. -Можно указать произвольный ключ партиционирования для таблицы `system.query_log` в конфигурации [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query-thread-log) (параметр `partition_by`). +Можно указать произвольный ключ партиционирования для таблицы `system.query_log` в конфигурации [query\_thread\_log](server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) (параметр `partition_by`). -## system.query_thread_log {#system_tables-query-thread-log} +## system.query_thread_log {#system_tables-query_thread_log} Содержит информацию о каждом потоке исполнения запроса. diff --git a/docs/ru/whats-new/extended-roadmap.md b/docs/ru/whats-new/extended-roadmap.md index b7756f7fb79..20ebe28fe5b 100644 --- a/docs/ru/whats-new/extended-roadmap.md +++ b/docs/ru/whats-new/extended-roadmap.md @@ -73,10 +73,10 @@ Upd. Включено для системных таблиц. Q1. Закоммичено, но есть технический долг, который исправляется сейчас. Готово. Нет, не готово - там всё ещё технический долг. -### 1.9. Использование TTL для прореживания данных {#ispolzovanie-ttl-dlia-prorezhivaniia-dannykh} +### 1.9. + Использование TTL для прореживания данных {#ispolzovanie-ttl-dlia-prorezhivaniia-dannykh} Будет делать Сорокин Николай, ВШЭ и Яндекс. -Upd. Есть pull request. +Upd. Есть pull request. Upd. Сделано. Сейчас пользователь может задать в таблице выражение, которое определяет, сколько времени хранятся данные. Обычно это выражение задаётся относительно значения столбца с датой - например: удалять данные через три месяца. https://clickhouse.tech/docs/ru/operations/table_engines/mergetree/\#table_engine-mergetree-ttl @@ -124,7 +124,7 @@ Q2. Upd. Олег будет делать только часть про HDFS. Upd. Реализация поверх S3 является рабочей на уровне PoC. -### 1.13. Ускорение запросов с FINAL {#uskorenie-zaprosov-s-final} +### 1.13. + Ускорение запросов с FINAL {#uskorenie-zaprosov-s-final} Требует 2.1. Делает [Николай Кочетов](https://github.com/KochetovNicolai). Нужно для Яндекс.Метрики. Q2. Upd: PR [#10463](https://github.com/ClickHouse/ClickHouse/pull/10463) @@ -203,10 +203,11 @@ Upd. SharedContext вынесен из Context. Upd. В очереди. Иван Лежанкин. -### 2.9. Логгировние в format-стиле {#loggirovnie-v-format-stile} +### 2.9. + Логгировние в format-стиле {#loggirovnie-v-format-stile} -Делает [Иван Лежанкин](https://github.com/abyss7). Низкий приоритет. -[\#6049](https://github.com/ClickHouse/ClickHouse/issues/6049#issuecomment-570836998) +[#6049](https://github.com/ClickHouse/ClickHouse/issues/6049#issuecomment-570836998) + +Сделано. ### 2.10. Запрашивать у таблиц не столбцы, а срезы {#zaprashivat-u-tablits-ne-stolbtsy-a-srezy} @@ -282,24 +283,20 @@ Upd. Сейчас обсуждается, как сделать другую з ### 4.3. Ограничение числа одновременных скачиваний с реплик {#ogranichenie-chisla-odnovremennykh-skachivanii-s-replik} -Дмитрий Григорьев, ВШЭ. Изначально делал Олег Алексеенков, но пока решение не готово, хотя там не так уж много доделывать. ### 4.4. Ограничение сетевой полосы при репликации {#ogranichenie-setevoi-polosy-pri-replikatsii} -Дмитрий Григорьев, ВШЭ. Нужно для Метрики. +Нужно для Метрики. ### 4.5. Возможность продолжить передачу куска данных при репликации после сбоя {#vozmozhnost-prodolzhit-peredachu-kuska-dannykh-pri-replikatsii-posle-sboia} -Дмитрий Григорьев, ВШЭ. - ### 4.6. p2p передача для GLOBAL подзапросов {#p2p-peredacha-dlia-global-podzaprosov} ### 4.7. Ленивая загрузка множеств для IN и JOIN с помощью k/v запросов {#lenivaia-zagruzka-mnozhestv-dlia-in-i-join-s-pomoshchiu-kv-zaprosov} ### 4.8. Разделить background pool для fetch и merge {#razdelit-background-pool-dlia-fetch-i-merge} -Дмитрий Григорьев, ВШЭ. В очереди. Исправить проблему, что восстанавливающаяся реплика перестаёт мержить. Частично компенсируется 4.3. @@ -329,6 +326,7 @@ Upd. Сделано. Эффективность работы под вопрос Метрика, БК, Маркет, Altinity уже используют более свежие версии чем LTS. Upd. Появилась вторая версия LTS - 20.3. + ## 6. Инструментирование {#instrumentirovanie} ### 6.1. + Исправления сэмплирующего профайлера запросов {#ispravleniia-sempliruiushchego-profailera-zaprosov} @@ -425,11 +423,11 @@ Upd. Рассмотрели все проверки подряд. UBSan включен в функциональных тестах, но не включен в интеграционных тестах. Требует 7.7. -### 7.11. Включение \*San в unit тестах {#vkliuchenie-san-v-unit-testakh} +### 7.11. + Включение \*San в unit тестах {#vkliuchenie-san-v-unit-testakh} У нас мало unit тестов по сравнению с функциональными тестами и их использование не обязательно. Но они всё-равно важны и нет причин не запускать их под всеми видами sanitizers. -Илья Яцишин. +Илья Яцишин. Сделано. ### 7.12. Показывать тестовое покрытие нового кода в PR {#pokazyvat-testovoe-pokrytie-novogo-koda-v-pr} @@ -528,6 +526,8 @@ Upd. Есть сборки, [пример](https://clickhouse-builds.s3.yandex.n Дарья Петрова, УрФУ. +Рабочий прототип: https://pulls-dashboard-demo.herokuapp.com/dashboard/ClickHouse/ClickHouse + Над ClickHouse одновременно работает большое количество разработчиков, которые оформляют свои изменения в виде pull requests. Когда непомерженных pull requests много, то возникает сложность с организацией работы - непонятно, на какой pull request смотреть в первую очередь. Предлагается реализовать простое одностраничное веб-приложение, в котором отображается список pull requests со следующей информацией: @@ -627,6 +627,7 @@ Upd. Готово (все директории кроме contrib). ### 7.32. Обфускация продакшен запросов {#obfuskatsiia-prodakshen-zaprosov} Роман Ильговский. Нужно для Яндекс.Метрики. +Есть pull request, почти готово: https://github.com/ClickHouse/ClickHouse/pull/10973 Имея SQL запрос, требуется вывести структуру таблиц, на которых этот запрос будет выполнен, и заполнить эти таблицы случайными данными, такими, что результат этого запроса зависит от выбора подмножества данных. @@ -1397,11 +1398,11 @@ Constraints позволяют задать выражение, истиннос Василий Морозов, Арслан Гумеров, Альберт Кидрачев, ВШЭ. В прошлом году задачу начинал делать другой человек, но не добился достаточного прогресса. -1. Оптимизация top sort. ++ 1. Оптимизация top sort. В ClickHouse используется неоптимальный вариант top sort. Суть его в том, что из каждого блока достаётся top N записей, а затем, все блоки мержатся. Но доставание top N записей у каждого следующего блока бессмысленно, если мы знаем, что из них в глобальный top N войдёт меньше. Конечно нужно реализовать вариацию на тему priority queue (heap) с быстрым пропуском целых блоков, если ни одна строка не попадёт в накопленный top. -2. Рекурсивный вариант сортировки по кортежам. ++ 2. Рекурсивный вариант сортировки по кортежам. Для сортировки по кортежам используется обычная сортировка с компаратором, который в цикле по элементам кортежа делает виртуальные вызовы `IColumn::compareAt`. Это неоптимально - как из-за короткого цикла по неизвестному в compile-time количеству элементов, так и из-за виртуальных вызовов. Чтобы обойтись без виртуальных вызовов, есть метод `IColumn::getPermutation`. Он используется в случае сортировки по одному столбцу. Есть вариант, что в случае сортировки по кортежу, что-то похожее тоже можно применить… например, сделать метод `updatePermutation`, принимающий аргументы offset и limit, и допереставляющий перестановку в диапазоне значений, в которых предыдущий столбец имел равные значения. diff --git a/docs/tools/requirements.txt b/docs/tools/requirements.txt index 4d4e9f98780..d9ea19ff389 100644 --- a/docs/tools/requirements.txt +++ b/docs/tools/requirements.txt @@ -21,7 +21,7 @@ mkdocs-htmlproofer-plugin==0.0.3 mkdocs-macros-plugin==0.4.9 nltk==3.5 nose==1.3.7 -protobuf==3.12.1 +protobuf==3.12.2 numpy==1.18.4 Pygments==2.5.2 pymdown-extensions==7.1 diff --git a/programs/client/CMakeLists.txt b/programs/client/CMakeLists.txt index 11ade559a8d..e273123afe0 100644 --- a/programs/client/CMakeLists.txt +++ b/programs/client/CMakeLists.txt @@ -6,14 +6,9 @@ set(CLICKHOUSE_CLIENT_SOURCES set(CLICKHOUSE_CLIENT_LINK PRIVATE clickhouse_common_config clickhouse_functions clickhouse_aggregate_functions clickhouse_common_io clickhouse_parsers string_utils ${Boost_PROGRAM_OPTIONS_LIBRARY}) -include(CheckSymbolExists) -check_symbol_exists(readpassphrase readpassphrase.h HAVE_READPASSPHRASE) -configure_file(config_client.h.in ${ConfigIncludePath}/config_client.h) - -if(NOT HAVE_READPASSPHRASE) - add_subdirectory(readpassphrase) - list(APPEND CLICKHOUSE_CLIENT_LINK PRIVATE readpassphrase) -endif() +# Always use internal readpassphrase +add_subdirectory(readpassphrase) +list(APPEND CLICKHOUSE_CLIENT_LINK PRIVATE readpassphrase) clickhouse_program_add(client) diff --git a/programs/client/Client.cpp b/programs/client/Client.cpp index d6cac7a7b02..afc8f9a72b1 100644 --- a/programs/client/Client.cpp +++ b/programs/client/Client.cpp @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include @@ -77,6 +76,10 @@ #include #include +#if !defined(ARCADIA_BUILD) +# include +#endif + #ifndef __clang__ #pragma GCC optimize("-fno-var-tracking-assignments") #endif diff --git a/programs/client/ConnectionParameters.cpp b/programs/client/ConnectionParameters.cpp index f0ef3ae5694..d8b4d0f1add 100644 --- a/programs/client/ConnectionParameters.cpp +++ b/programs/client/ConnectionParameters.cpp @@ -9,7 +9,7 @@ #include #include #include -#include +#include "readpassphrase/readpassphrase.h" namespace DB { diff --git a/programs/client/config_client.h.in b/programs/client/config_client.h.in deleted file mode 100644 index 5ad788ff54c..00000000000 --- a/programs/client/config_client.h.in +++ /dev/null @@ -1,3 +0,0 @@ -#pragma once - -#cmakedefine HAVE_READPASSPHRASE diff --git a/programs/client/readpassphrase/CMakeLists.txt b/programs/client/readpassphrase/CMakeLists.txt index a10b54c377d..dd1bf2c91b9 100644 --- a/programs/client/readpassphrase/CMakeLists.txt +++ b/programs/client/readpassphrase/CMakeLists.txt @@ -1,13 +1,7 @@ - # wget https://raw.githubusercontent.com/openssh/openssh-portable/master/openbsd-compat/readpassphrase.c # wget https://raw.githubusercontent.com/openssh/openssh-portable/master/openbsd-compat/readpassphrase.h -set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wno-unused-result -Wno-reserved-id-macro") +add_library(readpassphrase readpassphrase.c) -configure_file(includes.h.in ${CMAKE_CURRENT_BINARY_DIR}/include/includes.h) -add_library(readpassphrase ${CMAKE_CURRENT_SOURCE_DIR}/readpassphrase.c) -set_target_properties(readpassphrase - PROPERTIES LINKER_LANGUAGE C - ) -# . to allow #include -target_include_directories(readpassphrase PUBLIC . ${CMAKE_CURRENT_BINARY_DIR}/include) +set_target_properties(readpassphrase PROPERTIES LINKER_LANGUAGE C) +target_compile_options(readpassphrase PRIVATE -Wno-unused-result -Wno-reserved-id-macro) diff --git a/programs/client/readpassphrase/includes.h.in b/programs/client/readpassphrase/includes.h similarity index 79% rename from programs/client/readpassphrase/includes.h.in rename to programs/client/readpassphrase/includes.h index 44580d1ed95..3ca5eb2bff8 100644 --- a/programs/client/readpassphrase/includes.h.in +++ b/programs/client/readpassphrase/includes.h @@ -1,6 +1,6 @@ #pragma once -#cmakedefine HAVE_READPASSPHRASE +/* #undef HAVE_READPASSPHRASE */ #if !defined(HAVE_READPASSPHRASE) # ifndef _PATH_TTY diff --git a/programs/client/readpassphrase/readpassphrase.c b/programs/client/readpassphrase/readpassphrase.c index 243701239bf..21b48e7efc3 100644 --- a/programs/client/readpassphrase/readpassphrase.c +++ b/programs/client/readpassphrase/readpassphrase.c @@ -25,13 +25,11 @@ #include "includes.h" -#ifndef HAVE_READPASSPHRASE - #include #include #include #include -#include +#include "readpassphrase.h" #include #include #include @@ -193,19 +191,7 @@ restart: } //DEF_WEAK(readpassphrase); -#if 0 -char * -getpass(const char *prompt) -{ - static char buf[_PASSWORD_LEN + 1]; - - return(readpassphrase(prompt, buf, sizeof(buf), RPP_ECHO_OFF)); -} -#endif - static void handler(int s) { - signo[s] = 1; } -#endif /* HAVE_READPASSPHRASE */ diff --git a/programs/client/readpassphrase/readpassphrase.h b/programs/client/readpassphrase/readpassphrase.h index 0782a1773ea..399eb7b062c 100644 --- a/programs/client/readpassphrase/readpassphrase.h +++ b/programs/client/readpassphrase/readpassphrase.h @@ -23,39 +23,22 @@ /* OPENBSD ORIGINAL: include/readpassphrase.h */ #pragma once -// #ifndef _READPASSPHRASE_H_ -// #define _READPASSPHRASE_H_ -//#include "includes.h" -#include "config_client.h" - -// Should not be included on BSD systems, but if it happen... -#ifdef HAVE_READPASSPHRASE -# include_next +#if defined(__cplusplus) +extern "C" { #endif -#ifndef HAVE_READPASSPHRASE -# ifdef __cplusplus -extern "C" { -# endif - - -# define RPP_ECHO_OFF 0x00 /* Turn off echo (default). */ -# define RPP_ECHO_ON 0x01 /* Leave echo on. */ -# define RPP_REQUIRE_TTY 0x02 /* Fail if there is no tty. */ -# define RPP_FORCELOWER 0x04 /* Force input to lower case. */ -# define RPP_FORCEUPPER 0x08 /* Force input to upper case. */ -# define RPP_SEVENBIT 0x10 /* Strip the high bit from input. */ -# define RPP_STDIN 0x20 /* Read from stdin, not /dev/tty */ +#define RPP_ECHO_OFF 0x00 /* Turn off echo (default). */ +#define RPP_ECHO_ON 0x01 /* Leave echo on. */ +#define RPP_REQUIRE_TTY 0x02 /* Fail if there is no tty. */ +#define RPP_FORCELOWER 0x04 /* Force input to lower case. */ +#define RPP_FORCEUPPER 0x08 /* Force input to upper case. */ +#define RPP_SEVENBIT 0x10 /* Strip the high bit from input. */ +#define RPP_STDIN 0x20 /* Read from stdin, not /dev/tty */ char * readpassphrase(const char *, char *, size_t, int); -# ifdef __cplusplus +#if defined(__cplusplus) } -# endif - - -#endif /* HAVE_READPASSPHRASE */ - -// #endif /* !_READPASSPHRASE_H_ */ +#endif diff --git a/programs/client/readpassphrase/ya.make b/programs/client/readpassphrase/ya.make new file mode 100644 index 00000000000..80ad197e5d4 --- /dev/null +++ b/programs/client/readpassphrase/ya.make @@ -0,0 +1,7 @@ +LIBRARY() + +SRCS( + readpassphrase.c +) + +END() diff --git a/programs/copier/ClusterCopier.cpp b/programs/copier/ClusterCopier.cpp index d50b89738aa..227ce9eb715 100644 --- a/programs/copier/ClusterCopier.cpp +++ b/programs/copier/ClusterCopier.cpp @@ -1293,7 +1293,7 @@ TaskStatus ClusterCopier::processPartitionPieceTaskImpl( local_context.setSettings(task_cluster->settings_pull); local_context.setSetting("skip_unavailable_shards", true); - Block block = getBlockWithAllStreamData(InterpreterFactory::get(query_select_ast, local_context)->execute().in); + Block block = getBlockWithAllStreamData(InterpreterFactory::get(query_select_ast, local_context)->execute().getInputStream()); count = (block) ? block.safeGetByPosition(0).column->getUInt(0) : 0; } @@ -1403,7 +1403,7 @@ TaskStatus ClusterCopier::processPartitionPieceTaskImpl( BlockIO io_select = InterpreterFactory::get(query_select_ast, context_select)->execute(); BlockIO io_insert = InterpreterFactory::get(query_insert_ast, context_insert)->execute(); - input = io_select.in; + input = io_select.getInputStream(); output = io_insert.out; } @@ -1690,7 +1690,7 @@ std::set ClusterCopier::getShardPartitions(const ConnectionTimeouts & ti Context local_context = context; local_context.setSettings(task_cluster->settings_pull); - Block block = getBlockWithAllStreamData(InterpreterFactory::get(query_ast, local_context)->execute().in); + Block block = getBlockWithAllStreamData(InterpreterFactory::get(query_ast, local_context)->execute().getInputStream()); std::set res; if (block) @@ -1735,7 +1735,7 @@ const auto & settings = context.getSettingsRef(); Context local_context = context; local_context.setSettings(task_cluster->settings_pull); - return InterpreterFactory::get(query_ast, local_context)->execute().in->read().rows() != 0; + return InterpreterFactory::get(query_ast, local_context)->execute().getInputStream()->read().rows() != 0; } bool ClusterCopier::checkPresentPartitionPiecesOnCurrentShard(const ConnectionTimeouts & timeouts, @@ -1774,7 +1774,7 @@ bool ClusterCopier::checkPresentPartitionPiecesOnCurrentShard(const ConnectionTi Context local_context = context; local_context.setSettings(task_cluster->settings_pull); - auto result = InterpreterFactory::get(query_ast, local_context)->execute().in->read().rows(); + auto result = InterpreterFactory::get(query_ast, local_context)->execute().getInputStream()->read().rows(); if (result != 0) LOG_DEBUG(log, "Partition {} piece number {} is PRESENT on shard {}", partition_quoted_name, std::to_string(current_piece_number), task_shard.getDescription()); else diff --git a/programs/copier/ClusterCopierApp.cpp b/programs/copier/ClusterCopierApp.cpp index 9b1393204d4..ce4bf94589e 100644 --- a/programs/copier/ClusterCopierApp.cpp +++ b/programs/copier/ClusterCopierApp.cpp @@ -114,7 +114,7 @@ void ClusterCopierApp::mainImpl() registerDisks(); static const std::string default_database = "_local"; - DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared(default_database)); + DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared(default_database, *context)); context->setCurrentDatabase(default_database); /// Initialize query scope just in case. diff --git a/programs/local/LocalServer.cpp b/programs/local/LocalServer.cpp index 01acf250b1b..eb78c049825 100644 --- a/programs/local/LocalServer.cpp +++ b/programs/local/LocalServer.cpp @@ -118,13 +118,13 @@ void LocalServer::tryInitPath() } -static void attachSystemTables() +static void attachSystemTables(const Context & context) { DatabasePtr system_database = DatabaseCatalog::instance().tryGetDatabase(DatabaseCatalog::SYSTEM_DATABASE); if (!system_database) { /// TODO: add attachTableDelayed into DatabaseMemory to speedup loading - system_database = std::make_shared(DatabaseCatalog::SYSTEM_DATABASE); + system_database = std::make_shared(DatabaseCatalog::SYSTEM_DATABASE, context); DatabaseCatalog::instance().attachDatabase(DatabaseCatalog::SYSTEM_DATABASE, system_database); } @@ -202,7 +202,7 @@ try * if such tables will not be dropped, clickhouse-server will not be able to load them due to security reasons. */ std::string default_database = config().getString("default_database", "_local"); - DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared(default_database)); + DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared(default_database, *context)); context->setCurrentDatabase(default_database); applyCmdOptions(); @@ -213,14 +213,14 @@ try LOG_DEBUG(log, "Loading metadata from {}", context->getPath()); loadMetadataSystem(*context); - attachSystemTables(); + attachSystemTables(*context); loadMetadata(*context); DatabaseCatalog::instance().loadDatabases(); LOG_DEBUG(log, "Loaded metadata."); } else { - attachSystemTables(); + attachSystemTables(*context); } processQueries(); diff --git a/programs/main.cpp b/programs/main.cpp index 2eb226d3c00..382a104b798 100644 --- a/programs/main.cpp +++ b/programs/main.cpp @@ -8,11 +8,8 @@ #include #include /// pair -#if __has_include("config_tools.h") -#include "config_tools.h" -#endif -#if __has_include("config_core.h") -#include "config_core.h" +#if !defined(ARCADIA_BUILD) +# include "config_tools.h" #endif #include @@ -22,31 +19,31 @@ /// Universal executable for various clickhouse applications -#if ENABLE_CLICKHOUSE_SERVER || !defined(ENABLE_CLICKHOUSE_SERVER) +#if ENABLE_CLICKHOUSE_SERVER int mainEntryClickHouseServer(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_CLIENT || !defined(ENABLE_CLICKHOUSE_CLIENT) +#if ENABLE_CLICKHOUSE_CLIENT int mainEntryClickHouseClient(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_LOCAL || !defined(ENABLE_CLICKHOUSE_LOCAL) +#if ENABLE_CLICKHOUSE_LOCAL int mainEntryClickHouseLocal(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_BENCHMARK || !defined(ENABLE_CLICKHOUSE_BENCHMARK) +#if ENABLE_CLICKHOUSE_BENCHMARK int mainEntryClickHouseBenchmark(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG || !defined(ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG) +#if ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG int mainEntryClickHouseExtractFromConfig(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_COMPRESSOR || !defined(ENABLE_CLICKHOUSE_COMPRESSOR) +#if ENABLE_CLICKHOUSE_COMPRESSOR int mainEntryClickHouseCompressor(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_FORMAT || !defined(ENABLE_CLICKHOUSE_FORMAT) +#if ENABLE_CLICKHOUSE_FORMAT int mainEntryClickHouseFormat(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_COPIER || !defined(ENABLE_CLICKHOUSE_COPIER) +#if ENABLE_CLICKHOUSE_COPIER int mainEntryClickHouseClusterCopier(int argc, char ** argv); #endif -#if ENABLE_CLICKHOUSE_OBFUSCATOR || !defined(ENABLE_CLICKHOUSE_OBFUSCATOR) +#if ENABLE_CLICKHOUSE_OBFUSCATOR int mainEntryClickHouseObfuscator(int argc, char ** argv); #endif @@ -60,31 +57,31 @@ using MainFunc = int (*)(int, char**); /// Add an item here to register new application std::pair clickhouse_applications[] = { -#if ENABLE_CLICKHOUSE_LOCAL || !defined(ENABLE_CLICKHOUSE_LOCAL) +#if ENABLE_CLICKHOUSE_LOCAL {"local", mainEntryClickHouseLocal}, #endif -#if ENABLE_CLICKHOUSE_CLIENT || !defined(ENABLE_CLICKHOUSE_CLIENT) +#if ENABLE_CLICKHOUSE_CLIENT {"client", mainEntryClickHouseClient}, #endif -#if ENABLE_CLICKHOUSE_BENCHMARK || !defined(ENABLE_CLICKHOUSE_BENCHMARK) +#if ENABLE_CLICKHOUSE_BENCHMARK {"benchmark", mainEntryClickHouseBenchmark}, #endif -#if ENABLE_CLICKHOUSE_SERVER || !defined(ENABLE_CLICKHOUSE_SERVER) +#if ENABLE_CLICKHOUSE_SERVER {"server", mainEntryClickHouseServer}, #endif -#if ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG || !defined(ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG) +#if ENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG {"extract-from-config", mainEntryClickHouseExtractFromConfig}, #endif -#if ENABLE_CLICKHOUSE_COMPRESSOR || !defined(ENABLE_CLICKHOUSE_COMPRESSOR) +#if ENABLE_CLICKHOUSE_COMPRESSOR {"compressor", mainEntryClickHouseCompressor}, #endif -#if ENABLE_CLICKHOUSE_FORMAT || !defined(ENABLE_CLICKHOUSE_FORMAT) +#if ENABLE_CLICKHOUSE_FORMAT {"format", mainEntryClickHouseFormat}, #endif -#if ENABLE_CLICKHOUSE_COPIER || !defined(ENABLE_CLICKHOUSE_COPIER) +#if ENABLE_CLICKHOUSE_COPIER {"copier", mainEntryClickHouseClusterCopier}, #endif -#if ENABLE_CLICKHOUSE_OBFUSCATOR || !defined(ENABLE_CLICKHOUSE_OBFUSCATOR) +#if ENABLE_CLICKHOUSE_OBFUSCATOR {"obfuscator", mainEntryClickHouseObfuscator}, #endif }; @@ -127,9 +124,10 @@ enum class InstructionFail SSSE3 = 2, SSE4_1 = 3, SSE4_2 = 4, - AVX = 5, - AVX2 = 6, - AVX512 = 7 + POPCNT = 5, + AVX = 6, + AVX2 = 7, + AVX512 = 8 }; const char * instructionFailToString(InstructionFail fail) @@ -146,6 +144,8 @@ const char * instructionFailToString(InstructionFail fail) return "SSE4.1"; case InstructionFail::SSE4_2: return "SSE4.2"; + case InstructionFail::POPCNT: + return "POPCNT"; case InstructionFail::AVX: return "AVX"; case InstructionFail::AVX2: @@ -189,6 +189,16 @@ void checkRequiredInstructionsImpl(volatile InstructionFail & fail) __asm__ volatile ("pcmpgtq %%xmm0, %%xmm0" : : : "xmm0"); #endif + /// Defined by -msse4.2 +#if defined(__POPCNT__) + fail = InstructionFail::POPCNT; + { + uint64_t a = 0; + uint64_t b = 0; + __asm__ volatile ("popcnt %1, %0" : "=r"(a) :"r"(b) :); + } +#endif + #if defined(__AVX__) fail = InstructionFail::AVX; __asm__ volatile ("vaddpd %%ymm0, %%ymm0, %%ymm0" : : : "ymm0"); diff --git a/programs/server/CMakeLists.txt b/programs/server/CMakeLists.txt index 026bb0bfeb2..1563f5ac51e 100644 --- a/programs/server/CMakeLists.txt +++ b/programs/server/CMakeLists.txt @@ -1,21 +1,6 @@ set(CLICKHOUSE_SERVER_SOURCES - ${CMAKE_CURRENT_SOURCE_DIR}/HTTPHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/HTTPHandlerFactory.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/InterserverIOHTTPHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/MetricsTransmitter.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/NotFoundHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/PrometheusMetricsWriter.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/PrometheusRequestHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/ReplicasStatusHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/StaticRequestHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/Server.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/TCPHandler.cpp -) - -set(CLICKHOUSE_SERVER_SOURCES - ${CLICKHOUSE_SERVER_SOURCES} - ${CMAKE_CURRENT_SOURCE_DIR}/MySQLHandler.cpp - ${CMAKE_CURRENT_SOURCE_DIR}/MySQLHandlerFactory.cpp + MetricsTransmitter.cpp + Server.cpp ) set (CLICKHOUSE_SERVER_LINK diff --git a/programs/server/Server.cpp b/programs/server/Server.cpp index c1a520030f4..29096327a71 100644 --- a/programs/server/Server.cpp +++ b/programs/server/Server.cpp @@ -53,13 +53,13 @@ #include #include #include -#include "HTTPHandlerFactory.h" +#include #include "MetricsTransmitter.h" #include -#include "TCPHandlerFactory.h" +#include #include #include -#include "MySQLHandlerFactory.h" +#include #if !defined(ARCADIA_BUILD) # include "config_core.h" @@ -236,6 +236,14 @@ int Server::main(const std::vector & /*args*/) if (ThreadFuzzer::instance().isEffective()) LOG_WARNING(log, "ThreadFuzzer is enabled. Application will run slowly and unstable."); +#if !defined(NDEBUG) || !defined(__OPTIMIZE__) + LOG_WARNING(log, "Server was built in debug mode. It will work slowly."); +#endif + +#if defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) + LOG_WARNING(log, "Server was built with sanitizer. It will work slowly."); +#endif + /** Context contains all that query execution is dependent: * settings, available functions, data types, aggregate functions, databases... */ diff --git a/programs/server/Server.h b/programs/server/Server.h index ffd89df6af4..ad9e51c881c 100644 --- a/programs/server/Server.h +++ b/programs/server/Server.h @@ -1,6 +1,6 @@ #pragma once -#include "IServer.h" +#include #include diff --git a/programs/server/ya.make b/programs/server/ya.make index 2c74c01c7cb..2e13267f715 100644 --- a/programs/server/ya.make +++ b/programs/server/ya.make @@ -11,19 +11,8 @@ PEERDIR( SRCS( clickhouse-server.cpp - HTTPHandler.cpp - HTTPHandlerFactory.cpp - InterserverIOHTTPHandler.cpp MetricsTransmitter.cpp - MySQLHandler.cpp - MySQLHandlerFactory.cpp - NotFoundHandler.cpp - PrometheusMetricsWriter.cpp - PrometheusRequestHandler.cpp - ReplicasStatusHandler.cpp - StaticRequestHandler.cpp Server.cpp - TCPHandler.cpp ) END() diff --git a/programs/ya.make b/programs/ya.make index 6c773c312b8..f4a61850212 100644 --- a/programs/ya.make +++ b/programs/ya.make @@ -1,3 +1,27 @@ -RECURSE( - server +PROGRAM(clickhouse) + +CFLAGS( + -DENABLE_CLICKHOUSE_CLIENT + -DENABLE_CLICKHOUSE_EXTRACT_FROM_CONFIG + -DENABLE_CLICKHOUSE_SERVER ) + +PEERDIR( + clickhouse/base/daemon + clickhouse/base/loggers + clickhouse/programs/client/readpassphrase + clickhouse/src +) + +SRCS( + main.cpp + + client/Client.cpp + client/ConnectionParameters.cpp + client/Suggest.cpp + extract-from-config/ExtractFromConfig.cpp + server/Server.cpp + server/MetricsTransmitter.cpp +) + +END() diff --git a/src/Access/Authentication.cpp b/src/Access/Authentication.cpp index f435d6e6336..cb2c9e7a256 100644 --- a/src/Access/Authentication.cpp +++ b/src/Access/Authentication.cpp @@ -7,8 +7,8 @@ namespace DB { namespace ErrorCodes { - extern const int LOGICAL_ERROR; extern const int BAD_ARGUMENTS; + extern const int NOT_IMPLEMENTED; } @@ -36,8 +36,11 @@ Authentication::Digest Authentication::getPasswordDoubleSHA1() const case DOUBLE_SHA1_PASSWORD: return password_hash; + + case MAX_TYPE: + break; } - throw Exception("Unknown authentication type: " + std::to_string(static_cast(type)), ErrorCodes::LOGICAL_ERROR); + throw Exception("getPasswordDoubleSHA1(): authentication type " + toString(type) + " not supported", ErrorCodes::NOT_IMPLEMENTED); } @@ -71,8 +74,11 @@ bool Authentication::isCorrectPassword(const String & password_) const return encodeSHA1(first_sha1) == password_hash; } + + case MAX_TYPE: + break; } - throw Exception("Unknown authentication type: " + std::to_string(static_cast(type)), ErrorCodes::LOGICAL_ERROR); + throw Exception("Cannot check if the password is correct for authentication type " + toString(type), ErrorCodes::NOT_IMPLEMENTED); } } diff --git a/src/Access/Authentication.h b/src/Access/Authentication.h index 3f16dc56de3..c410a101cdd 100644 --- a/src/Access/Authentication.h +++ b/src/Access/Authentication.h @@ -5,6 +5,7 @@ #include #include #include +#include namespace DB @@ -14,6 +15,7 @@ namespace ErrorCodes extern const int SUPPORT_IS_DISABLED; extern const int BAD_ARGUMENTS; extern const int LOGICAL_ERROR; + extern const int NOT_IMPLEMENTED; } @@ -35,6 +37,15 @@ public: /// SHA1(SHA1(password)). /// This kind of hash is used by the `mysql_native_password` authentication plugin. DOUBLE_SHA1_PASSWORD, + + MAX_TYPE, + }; + + struct TypeInfo + { + const char * const raw_name; + const String name; /// Lowercased with underscores, e.g. "sha256_password". + static const TypeInfo & get(Type type_); }; using Digest = std::vector; @@ -85,6 +96,48 @@ private: }; +inline const Authentication::TypeInfo & Authentication::TypeInfo::get(Type type_) +{ + static constexpr auto make_info = [](const char * raw_name_) + { + String init_name = raw_name_; + boost::to_lower(init_name); + return TypeInfo{raw_name_, std::move(init_name)}; + }; + + switch (type_) + { + case NO_PASSWORD: + { + static const auto info = make_info("NO_PASSWORD"); + return info; + } + case PLAINTEXT_PASSWORD: + { + static const auto info = make_info("PLAINTEXT_PASSWORD"); + return info; + } + case SHA256_PASSWORD: + { + static const auto info = make_info("SHA256_PASSWORD"); + return info; + } + case DOUBLE_SHA1_PASSWORD: + { + static const auto info = make_info("DOUBLE_SHA1_PASSWORD"); + return info; + } + case MAX_TYPE: break; + } + throw Exception("Unknown authentication type: " + std::to_string(static_cast(type_)), ErrorCodes::LOGICAL_ERROR); +} + +inline String toString(Authentication::Type type_) +{ + return Authentication::TypeInfo::get(type_).raw_name; +} + + inline Authentication::Digest Authentication::encodeSHA256(const std::string_view & text [[maybe_unused]]) { #if USE_SSL @@ -122,8 +175,10 @@ inline void Authentication::setPassword(const String & password_) case DOUBLE_SHA1_PASSWORD: return setPasswordHashBinary(encodeDoubleSHA1(password_)); + + case MAX_TYPE: break; } - throw Exception("Unknown authentication type: " + std::to_string(static_cast(type)), ErrorCodes::LOGICAL_ERROR); + throw Exception("setPassword(): authentication type " + toString(type) + " not supported", ErrorCodes::NOT_IMPLEMENTED); } @@ -186,8 +241,10 @@ inline void Authentication::setPasswordHashBinary(const Digest & hash) password_hash = hash; return; } + + case MAX_TYPE: break; } - throw Exception("Unknown authentication type: " + std::to_string(static_cast(type)), ErrorCodes::LOGICAL_ERROR); + throw Exception("setPasswordHashBinary(): authentication type " + toString(type) + " not supported", ErrorCodes::NOT_IMPLEMENTED); } } diff --git a/src/Access/ExtendedRoleSet.cpp b/src/Access/ExtendedRoleSet.cpp index a29ee40380c..a8e674b3722 100644 --- a/src/Access/ExtendedRoleSet.cpp +++ b/src/Access/ExtendedRoleSet.cpp @@ -68,15 +68,27 @@ void ExtendedRoleSet::init(const ASTExtendedRoleSet & ast, const AccessControlMa { all = ast.all; - auto name_to_id = [id_mode{ast.id_mode}, manager](const String & name) -> UUID + auto name_to_id = [&ast, manager](const String & name) -> UUID { - if (id_mode) + if (ast.id_mode) return parse(name); assert(manager); - auto id = manager->find(name); - if (id) - return *id; - return manager->getID(name); + if (ast.can_contain_users && ast.can_contain_roles) + { + auto id = manager->find(name); + if (id) + return *id; + return manager->getID(name); + } + else if (ast.can_contain_users) + { + return manager->getID(name); + } + else + { + assert(ast.can_contain_roles); + return manager->getID(name); + } }; if (!ast.names.empty() && !all) diff --git a/src/Access/MultipleAccessStorage.cpp b/src/Access/MultipleAccessStorage.cpp index 0dd1f142f31..9b80c16e487 100644 --- a/src/Access/MultipleAccessStorage.cpp +++ b/src/Access/MultipleAccessStorage.cpp @@ -143,6 +143,14 @@ const IAccessStorage & MultipleAccessStorage::getStorage(const UUID & id) const return const_cast(this)->getStorage(id); } +void MultipleAccessStorage::addStorage(std::unique_ptr nested_storage) +{ + /// Note that IStorage::storage_name is not changed. It is ok as this method + /// is considered as a temporary solution allowing third-party Arcadia applications + /// using CH as a library to register their own access storages. Do not remove + /// this method without providing any alternative :) + nested_storages.emplace_back(std::move(nested_storage)); +} AccessEntityPtr MultipleAccessStorage::readImpl(const UUID & id) const { diff --git a/src/Access/MultipleAccessStorage.h b/src/Access/MultipleAccessStorage.h index ec8c8f2a101..06fb3d45c05 100644 --- a/src/Access/MultipleAccessStorage.h +++ b/src/Access/MultipleAccessStorage.h @@ -25,6 +25,8 @@ public: const Storage & getStorage(const UUID & id) const; Storage & getStorage(const UUID & id); + void addStorage(std::unique_ptr nested_storage); + Storage & getStorageByIndex(size_t i) { return *(nested_storages[i]); } const Storage & getStorageByIndex(size_t i) const { return *(nested_storages[i]); } diff --git a/src/AggregateFunctions/AggregateFunctionEntropy.h b/src/AggregateFunctions/AggregateFunctionEntropy.h index 7586cebd8ec..ff233a5ac93 100644 --- a/src/AggregateFunctions/AggregateFunctionEntropy.h +++ b/src/AggregateFunctions/AggregateFunctionEntropy.h @@ -23,18 +23,10 @@ struct EntropyData { using Weight = UInt64; - using HashingMap = HashMap< - Value, Weight, - HashCRC32, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory) * (1 << 3)>>; + using HashingMap = HashMapWithStackMemory, 4>; /// For the case of pre-hashed values. - using TrivialMap = HashMap< - Value, Weight, - UInt128TrivialHash, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory) * (1 << 3)>>; + using TrivialMap = HashMapWithStackMemory; using Map = std::conditional_t, TrivialMap, HashingMap>; diff --git a/src/AggregateFunctions/AggregateFunctionGroupUniqArray.h b/src/AggregateFunctions/AggregateFunctionGroupUniqArray.h index 9dbf2c921c2..88b1c87f526 100644 --- a/src/AggregateFunctions/AggregateFunctionGroupUniqArray.h +++ b/src/AggregateFunctions/AggregateFunctionGroupUniqArray.h @@ -28,12 +28,7 @@ template struct AggregateFunctionGroupUniqArrayData { /// When creating, the hash table must be small. - using Set = HashSet< - T, - DefaultHash, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory - >; + using Set = HashSetWithStackMemory, 4>; Set value; }; @@ -126,9 +121,10 @@ public: /// Generic implementation, it uses serialized representation as object descriptor. struct AggregateFunctionGroupUniqArrayGenericData { - static constexpr size_t INIT_ELEMS = 2; /// adjustable - static constexpr size_t ELEM_SIZE = sizeof(HashSetCellWithSavedHash); - using Set = HashSetWithSavedHash, HashTableAllocatorWithStackMemory>; + static constexpr size_t INITIAL_SIZE_DEGREE = 3; /// adjustable + + using Set = HashSetWithSavedHashWithStackMemory; Set value; }; diff --git a/src/AggregateFunctions/AggregateFunctionTopK.h b/src/AggregateFunctions/AggregateFunctionTopK.h index 9c5e62bb6d7..23eb0e7ff09 100644 --- a/src/AggregateFunctions/AggregateFunctionTopK.h +++ b/src/AggregateFunctions/AggregateFunctionTopK.h @@ -23,13 +23,8 @@ namespace DB template struct AggregateFunctionTopKData { - using Set = SpaceSaving - < - T, - HashCRC32, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory - >; + using Set = SpaceSaving>; + Set value; }; @@ -109,13 +104,7 @@ public: /// Generic implementation, it uses serialized representation as object descriptor. struct AggregateFunctionTopKGenericData { - using Set = SpaceSaving - < - StringRef, - StringRefHash, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory - >; + using Set = SpaceSaving; Set value; }; diff --git a/src/AggregateFunctions/QuantileExactWeighted.h b/src/AggregateFunctions/QuantileExactWeighted.h index 6053bddc947..666dbd6b622 100644 --- a/src/AggregateFunctions/QuantileExactWeighted.h +++ b/src/AggregateFunctions/QuantileExactWeighted.h @@ -33,12 +33,7 @@ struct QuantileExactWeighted using Hasher = std::conditional_t, Int128Hash, HashCRC32>; /// When creating, the hash table must be small. - using Map = HashMap< - UnderlyingType, Weight, - Hasher, - HashTableGrower<4>, - HashTableAllocatorWithStackMemory) * (1 << 3)> - >; + using Map = HashMapWithStackMemory; Map map; diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index f720b5c1c85..c3208228388 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -58,6 +58,7 @@ add_subdirectory (TableFunctions) add_subdirectory (Processors) add_subdirectory (Formats) add_subdirectory (Compression) +add_subdirectory (Server) set(dbms_headers) @@ -149,6 +150,7 @@ add_object_library(clickhouse_storages_distributed Storages/Distributed) add_object_library(clickhouse_storages_mergetree Storages/MergeTree) add_object_library(clickhouse_storages_liveview Storages/LiveView) add_object_library(clickhouse_client Client) +add_object_library(clickhouse_server Server) add_object_library(clickhouse_formats Formats) add_object_library(clickhouse_processors Processors) add_object_library(clickhouse_processors_executors Processors/Executors) diff --git a/src/Common/Allocator.h b/src/Common/Allocator.h index 9add9299430..43d7e67c4bb 100644 --- a/src/Common/Allocator.h +++ b/src/Common/Allocator.h @@ -278,13 +278,15 @@ private: /** Allocator with optimization to place small memory ranges in automatic memory. */ -template +template class AllocatorWithStackMemory : private Base { private: - alignas(Alignment) char stack_memory[N]; + alignas(Alignment) char stack_memory[_initial_bytes]; public: + static constexpr size_t initial_bytes = _initial_bytes; + /// Do not use boost::noncopyable to avoid the warning about direct base /// being inaccessible due to ambiguity, when derived classes are also /// noncopiable (-Winaccessible-base). @@ -295,10 +297,10 @@ public: void * alloc(size_t size) { - if (size <= N) + if (size <= initial_bytes) { if constexpr (Base::clear_memory) - memset(stack_memory, 0, N); + memset(stack_memory, 0, initial_bytes); return stack_memory; } @@ -307,18 +309,18 @@ public: void free(void * buf, size_t size) { - if (size > N) + if (size > initial_bytes) Base::free(buf, size); } void * realloc(void * buf, size_t old_size, size_t new_size) { /// Was in stack_memory, will remain there. - if (new_size <= N) + if (new_size <= initial_bytes) return buf; /// Already was big enough to not fit in stack_memory. - if (old_size > N) + if (old_size > initial_bytes) return Base::realloc(buf, old_size, new_size, Alignment); /// Was in stack memory, but now will not fit there. @@ -330,10 +332,20 @@ public: protected: static constexpr size_t getStackThreshold() { - return N; + return initial_bytes; } }; +// A constant that gives the number of initially available bytes in +// the allocator. Used to check that this number is in sync with the +// initial size of array or hash table that uses the allocator. +template +constexpr size_t allocatorInitialBytes = 0; + +template +constexpr size_t allocatorInitialBytes> = initial_bytes; + #if !__clang__ #pragma GCC diagnostic pop diff --git a/src/Common/CurrentMetrics.h b/src/Common/CurrentMetrics.h index b87504ef49a..a3bac96a16c 100644 --- a/src/Common/CurrentMetrics.h +++ b/src/Common/CurrentMetrics.h @@ -94,6 +94,12 @@ namespace CurrentMetrics amount = new_amount; } + void sub(Value value = 1) + { + what->fetch_sub(value, std::memory_order_relaxed); + amount -= value; + } + /// Subtract value before destructor. void destroy() { diff --git a/src/Common/HashTable/ClearableHashMap.h b/src/Common/HashTable/ClearableHashMap.h index 4370f6b6dc7..fda01dcf4bc 100644 --- a/src/Common/HashTable/ClearableHashMap.h +++ b/src/Common/HashTable/ClearableHashMap.h @@ -43,3 +43,14 @@ public: this->m_size = 0; } }; + +template +using ClearableHashMapWithStackMemory = ClearableHashMap< + Key, + Mapped, + Hash, + HashTableGrower, + HashTableAllocatorWithStackMemory< + (1ULL << initial_size_degree) + * sizeof(ClearableHashMapCell)>>; diff --git a/src/Common/HashTable/ClearableHashSet.h b/src/Common/HashTable/ClearableHashSet.h index 824ec9d8e5f..dc057afacd8 100644 --- a/src/Common/HashTable/ClearableHashSet.h +++ b/src/Common/HashTable/ClearableHashSet.h @@ -84,3 +84,15 @@ public: this->m_size = 0; } }; + +template +using ClearableHashSetWithStackMemory = ClearableHashSet< + Key, + Hash, + HashTableGrower, + HashTableAllocatorWithStackMemory< + (1ULL << initial_size_degree) + * sizeof( + ClearableHashTableCell< + Key, + HashTableCell>)>>; diff --git a/src/Common/HashTable/HashMap.h b/src/Common/HashTable/HashMap.h index cdc4a003af8..3ecbd9f263c 100644 --- a/src/Common/HashTable/HashMap.h +++ b/src/Common/HashTable/HashMap.h @@ -239,3 +239,14 @@ template < typename Grower = HashTableGrower<>, typename Allocator = HashTableAllocator> using HashMapWithSavedHash = HashMapTable, Hash, Grower, Allocator>; + +template +using HashMapWithStackMemory = HashMapTable< + Key, + HashMapCellWithSavedHash, + Hash, + HashTableGrower, + HashTableAllocatorWithStackMemory< + (1ULL << initial_size_degree) + * sizeof(HashMapCellWithSavedHash)>>; diff --git a/src/Common/HashTable/HashSet.h b/src/Common/HashTable/HashSet.h index c1970e898a1..c79e05073fc 100644 --- a/src/Common/HashTable/HashSet.h +++ b/src/Common/HashTable/HashSet.h @@ -93,6 +93,14 @@ template > using HashSet = HashSetTable, Hash, Grower, Allocator>; +template +using HashSetWithStackMemory = HashSet< + Key, + Hash, + HashTableGrower, + HashTableAllocatorWithStackMemory< + (1ULL << initial_size_degree) + * sizeof(HashTableCell)>>; template < @@ -102,3 +110,12 @@ template typename Allocator = HashTableAllocator > using HashSetWithSavedHash = HashSetTable, Hash, Grower, Allocator>; + +template +using HashSetWithSavedHashWithStackMemory = HashSetWithSavedHash< + Key, + Hash, + HashTableGrower, + HashTableAllocatorWithStackMemory< + (1ULL << initial_size_degree) + * sizeof(HashSetCellWithSavedHash)>>; diff --git a/src/Common/HashTable/HashTable.h b/src/Common/HashTable/HashTable.h index 58b7cd81901..528e719c05b 100644 --- a/src/Common/HashTable/HashTable.h +++ b/src/Common/HashTable/HashTable.h @@ -208,6 +208,7 @@ struct HashTableGrower /// The state of this structure is enough to get the buffer size of the hash table. UInt8 size_degree = initial_size_degree; + static constexpr auto initial_count = 1ULL << initial_size_degree; /// The size of the hash table in the cells. size_t bufSize() const { return 1ULL << size_degree; } @@ -255,6 +256,7 @@ struct HashTableGrower template struct HashTableFixedGrower { + static constexpr auto initial_count = 1ULL << key_bits; size_t bufSize() const { return 1ULL << key_bits; } size_t place(size_t x) const { return x; } /// You could write __builtin_unreachable(), but the compiler does not optimize everything, and it turns out less efficiently. @@ -309,6 +311,7 @@ struct ZeroValueStorage }; +// The HashTable template < typename Key, @@ -324,6 +327,14 @@ class HashTable : protected Cell::State, protected ZeroValueStorage /// empty base optimization { +public: + // If we use an allocator with inline memory, check that the initial + // size of the hash table is in sync with the amount of this memory. + static constexpr size_t initial_buffer_bytes + = Grower::initial_count * sizeof(Cell); + static_assert(allocatorInitialBytes == 0 + || allocatorInitialBytes == initial_buffer_bytes); + protected: friend class const_iterator; friend class iterator; diff --git a/src/Common/HashTable/HashTableAllocator.h b/src/Common/HashTable/HashTableAllocator.h index 99f9c979685..47e3fdfc4b6 100644 --- a/src/Common/HashTable/HashTableAllocator.h +++ b/src/Common/HashTable/HashTableAllocator.h @@ -10,5 +10,5 @@ */ using HashTableAllocator = Allocator; -template -using HashTableAllocatorWithStackMemory = AllocatorWithStackMemory; +template +using HashTableAllocatorWithStackMemory = AllocatorWithStackMemory; diff --git a/src/Common/MemoryStatisticsOS.cpp b/src/Common/MemoryStatisticsOS.cpp index adc5bf5d904..6082d23cbd0 100644 --- a/src/Common/MemoryStatisticsOS.cpp +++ b/src/Common/MemoryStatisticsOS.cpp @@ -9,6 +9,7 @@ #include #include #include +#include namespace DB @@ -19,6 +20,7 @@ namespace ErrorCodes extern const int FILE_DOESNT_EXIST; extern const int CANNOT_OPEN_FILE; extern const int CANNOT_READ_FROM_FILE_DESCRIPTOR; + extern const int CANNOT_CLOSE_FILE; } static constexpr auto filename = "/proc/self/statm"; @@ -35,7 +37,18 @@ MemoryStatisticsOS::MemoryStatisticsOS() MemoryStatisticsOS::~MemoryStatisticsOS() { if (0 != ::close(fd)) - tryLogCurrentException(__PRETTY_FUNCTION__); + { + try + { + throwFromErrno( + "File descriptor for \"" + std::string(filename) + "\" could not be closed. " + "Something seems to have gone wrong. Inspect errno.", ErrorCodes::CANNOT_CLOSE_FILE); + } + catch (const ErrnoException &) + { + DB::tryLogCurrentException(__PRETTY_FUNCTION__); + } + } } MemoryStatisticsOS::Data MemoryStatisticsOS::get() const diff --git a/src/Common/MemoryTracker.cpp b/src/Common/MemoryTracker.cpp index 082b78682a2..16d166c191b 100644 --- a/src/Common/MemoryTracker.cpp +++ b/src/Common/MemoryTracker.cpp @@ -49,11 +49,13 @@ MemoryTracker::~MemoryTracker() void MemoryTracker::logPeakMemoryUsage() const { + const auto * description = description_ptr.load(std::memory_order_relaxed); LOG_DEBUG(&Logger::get("MemoryTracker"), "Peak memory usage{}: {}.", (description ? " " + std::string(description) : ""), formatReadableSizeWithBinarySuffix(peak)); } void MemoryTracker::logMemoryUsage(Int64 current) const { + const auto * description = description_ptr.load(std::memory_order_relaxed); LOG_DEBUG(&Logger::get("MemoryTracker"), "Current memory usage{}: {}.", (description ? " " + std::string(description) : ""), formatReadableSizeWithBinarySuffix(current)); } @@ -85,7 +87,7 @@ void MemoryTracker::alloc(Int64 size) std::stringstream message; message << "Memory tracker"; - if (description) + if (const auto * description = description_ptr.load(std::memory_order_relaxed)) message << " " << description; message << ": fault injected. Would use " << formatReadableSizeWithBinarySuffix(will_be) << " (attempt to allocate chunk of " << size << " bytes)" @@ -117,7 +119,7 @@ void MemoryTracker::alloc(Int64 size) std::stringstream message; message << "Memory limit"; - if (description) + if (const auto * description = description_ptr.load(std::memory_order_relaxed)) message << " " << description; message << " exceeded: would use " << formatReadableSizeWithBinarySuffix(will_be) << " (attempt to allocate chunk of " << size << " bytes)" diff --git a/src/Common/MemoryTracker.h b/src/Common/MemoryTracker.h index 23f32b051b2..8af683ae790 100644 --- a/src/Common/MemoryTracker.h +++ b/src/Common/MemoryTracker.h @@ -35,7 +35,7 @@ private: CurrentMetrics::Metric metric = CurrentMetrics::end(); /// This description will be used as prefix into log messages (if isn't nullptr) - const char * description = nullptr; + std::atomic description_ptr = nullptr; void updatePeak(Int64 will_be); void logMemoryUsage(Int64 current) const; @@ -114,9 +114,9 @@ public: metric = metric_; } - void setDescription(const char * description_) + void setDescription(const char * description) { - description = description_; + description_ptr.store(description, std::memory_order_relaxed); } /// Reset the accumulated data diff --git a/src/Common/PODArray.h b/src/Common/PODArray.h index acbcb73dc2c..9ab1c64d3b9 100644 --- a/src/Common/PODArray.h +++ b/src/Common/PODArray.h @@ -85,6 +85,11 @@ protected: static_assert(pad_left <= empty_pod_array_size && "Left Padding exceeds empty_pod_array_size. Is the element size too large?"); + // If we are using allocator with inline memory, the minimal size of + // array must be in sync with the size of this memory. + static_assert(allocatorInitialBytes == 0 + || allocatorInitialBytes == initial_bytes); + char * c_start = null; /// Does not include pad_left. char * c_end = null; char * c_end_of_storage = null; /// Does not include pad_right. diff --git a/src/Common/ProcfsMetricsProvider.cpp b/src/Common/ProcfsMetricsProvider.cpp index 633558a7b67..fcc4124aa85 100644 --- a/src/Common/ProcfsMetricsProvider.cpp +++ b/src/Common/ProcfsMetricsProvider.cpp @@ -7,6 +7,7 @@ #include #include +#include #include #include @@ -22,6 +23,7 @@ namespace ErrorCodes { extern const int FILE_DOESNT_EXIST; extern const int CANNOT_OPEN_FILE; + extern const int CANNOT_CLOSE_FILE; extern const int CANNOT_READ_FROM_FILE_DESCRIPTOR; } @@ -39,6 +41,20 @@ namespace errno == ENOENT ? ErrorCodes::FILE_DOESNT_EXIST : ErrorCodes::CANNOT_OPEN_FILE); } +inline void emitErrorMsgWithFailedToCloseFile(const std::string & filename) +{ + try + { + throwFromErrno( + "File descriptor for \"" + filename + "\" could not be closed. " + "Something seems to have gone wrong. Inspect errno.", ErrorCodes::CANNOT_CLOSE_FILE); + } + catch (const ErrnoException &) + { + DB::tryLogCurrentException(__PRETTY_FUNCTION__); + } +} + ssize_t readFromFD(const int fd, const char * filename, char * buf, size_t buf_size) { ssize_t res = 0; @@ -100,11 +116,11 @@ ProcfsMetricsProvider::ProcfsMetricsProvider(const pid_t /*tid*/) ProcfsMetricsProvider::~ProcfsMetricsProvider() { if (stats_version >= 3 && 0 != ::close(thread_io_fd)) - tryLogCurrentException(__PRETTY_FUNCTION__); + emitErrorMsgWithFailedToCloseFile(thread_io); if (0 != ::close(thread_stat_fd)) - tryLogCurrentException(__PRETTY_FUNCTION__); + emitErrorMsgWithFailedToCloseFile(thread_stat); if (0 != ::close(thread_schedstat_fd)) - tryLogCurrentException(__PRETTY_FUNCTION__); + emitErrorMsgWithFailedToCloseFile(thread_schedstat); } diff --git a/src/Common/SpaceSaving.h b/src/Common/SpaceSaving.h index 9ad7f6275d6..56063340240 100644 --- a/src/Common/SpaceSaving.h +++ b/src/Common/SpaceSaving.h @@ -67,9 +67,7 @@ private: template < typename TKey, - typename Hash = DefaultHash, - typename Grower = HashTableGrower<>, - typename Allocator = HashTableAllocator + typename Hash = DefaultHash > class SpaceSaving { @@ -380,7 +378,7 @@ private: counter_map[counter->key] = counter; } - using CounterMap = HashMap; + using CounterMap = HashMapWithStackMemory; CounterMap counter_map; std::vector counter_list; diff --git a/src/Common/tests/gtest_global_context.h b/src/Common/tests/gtest_global_context.h index 05f60e01774..b6529f09b46 100644 --- a/src/Common/tests/gtest_global_context.h +++ b/src/Common/tests/gtest_global_context.h @@ -11,15 +11,15 @@ struct ContextHolder : shared_context(DB::Context::createShared()) , context(DB::Context::createGlobal(shared_context.get())) { + context.makeGlobalContext(); + context.setPath("./"); } ContextHolder(ContextHolder &&) = default; }; -inline ContextHolder getContext() +inline const ContextHolder & getContext() { - ContextHolder holder; - holder.context.makeGlobalContext(); - holder.context.setPath("./"); + static ContextHolder holder; return holder; } diff --git a/src/Common/tests/gtest_log.cpp b/src/Common/tests/gtest_log.cpp new file mode 100644 index 00000000000..a1e532f92e6 --- /dev/null +++ b/src/Common/tests/gtest_log.cpp @@ -0,0 +1,19 @@ +#include +#include +#include +#include + +#include +#include +#include + + +TEST(Logger, Log) +{ + Poco::Logger::root().setLevel("none"); + Poco::Logger::root().setChannel(Poco::AutoPtr(new Poco::NullChannel())); + Logger * log = &Logger::get("Log"); + + /// This test checks that we don't pass this string to fmtlib, because it is the only argument. + EXPECT_NO_THROW(LOG_INFO(log, "Hello {} World")); +} diff --git a/src/Common/tests/pod_array.cpp b/src/Common/tests/pod_array.cpp index de15b485411..6e9634ba3cf 100644 --- a/src/Common/tests/pod_array.cpp +++ b/src/Common/tests/pod_array.cpp @@ -18,9 +18,9 @@ static void test1() { using namespace DB; - static constexpr size_t initial_size = 8; - static constexpr size_t stack_threshold = 32; - using Array = PODArray, stack_threshold>>; + static constexpr size_t initial_bytes = 32; + using Array = PODArray, initial_bytes>>; bool res = true; @@ -139,9 +139,9 @@ static void test2() { using namespace DB; - static constexpr size_t initial_size = 8; - static constexpr size_t stack_threshold = 32; - using Array = PODArray, stack_threshold>>; + static constexpr size_t initial_bytes = 32; + using Array = PODArray, initial_bytes>>; bool res = true; @@ -389,9 +389,9 @@ static void test3() { using namespace DB; - static constexpr size_t initial_size = 8; - static constexpr size_t stack_threshold = 32; - using Array = PODArray, stack_threshold>>; + static constexpr size_t initial_bytes = 32; + using Array = PODArray, initial_bytes>>; bool res = true; diff --git a/src/Common/ya.make b/src/Common/ya.make index c0178f3d310..83a419212bd 100644 --- a/src/Common/ya.make +++ b/src/Common/ya.make @@ -18,17 +18,7 @@ PEERDIR( contrib/restricted/ryu ) -# TODO: stub for config_version.h -CFLAGS (GLOBAL -DDBMS_NAME=\"ClickHouse\") -CFLAGS (GLOBAL -DDBMS_VERSION_MAJOR=0) -CFLAGS (GLOBAL -DDBMS_VERSION_MINOR=0) -CFLAGS (GLOBAL -DDBMS_VERSION_PATCH=0) -CFLAGS (GLOBAL -DVERSION_FULL=\"ClickHouse\") -CFLAGS (GLOBAL -DVERSION_INTEGER=0) -CFLAGS (GLOBAL -DVERSION_NAME=\"ClickHouse\") -CFLAGS (GLOBAL -DVERSION_OFFICIAL=\"\\\(arcadia\\\)\") -CFLAGS (GLOBAL -DVERSION_REVISION=0) -CFLAGS (GLOBAL -DVERSION_STRING=\"Unknown\") +INCLUDE(${ARCADIA_ROOT}/clickhouse/cmake/yandex/ya.make.versions.inc) SRCS( ActionLock.cpp diff --git a/src/Core/ExternalTable.cpp b/src/Core/ExternalTable.cpp index 62a99cea97e..5ec6980dbfa 100644 --- a/src/Core/ExternalTable.cpp +++ b/src/Core/ExternalTable.cpp @@ -164,7 +164,7 @@ void ExternalTablesHandler::handlePart(const Poco::Net::MessageHeader & header, /// Create table NamesAndTypesList columns = sample_block.getNamesAndTypesList(); - auto temporary_table = TemporaryTableHolder(context, ColumnsDescription{columns}); + auto temporary_table = TemporaryTableHolder(context, ColumnsDescription{columns}, {}); auto storage = temporary_table.getTable(); context.addExternalTable(data->table_name, std::move(temporary_table)); BlockOutputStreamPtr output = storage->write(ASTPtr(), context); diff --git a/src/Core/Settings.h b/src/Core/Settings.h index 8122a10951d..57b382ba4bd 100644 --- a/src/Core/Settings.h +++ b/src/Core/Settings.h @@ -127,7 +127,7 @@ struct Settings : public SettingsCollection M(SettingBool, force_optimize_skip_unused_shards_no_nested, false, "Do not apply force_optimize_skip_unused_shards for nested Distributed tables.", 0) \ \ M(SettingBool, input_format_parallel_parsing, true, "Enable parallel parsing for some data formats.", 0) \ - M(SettingUInt64, min_chunk_bytes_for_parallel_parsing, (1024 * 1024), "The minimum chunk size in bytes, which each thread will parse in parallel.", 0) \ + M(SettingUInt64, min_chunk_bytes_for_parallel_parsing, (10 * 1024 * 1024), "The minimum chunk size in bytes, which each thread will parse in parallel.", 0) \ \ M(SettingUInt64, merge_tree_min_rows_for_concurrent_read, (20 * 8192), "If at least as many lines are read from one file, the reading can be parallelized.", 0) \ M(SettingUInt64, merge_tree_min_bytes_for_concurrent_read, (24 * 10 * 1024 * 1024), "If at least as many bytes are read from one file, the reading can be parallelized.", 0) \ @@ -157,7 +157,7 @@ struct Settings : public SettingsCollection M(SettingUInt64, priority, 0, "Priority of the query. 1 - the highest, higher value - lower priority; 0 - do not use priorities.", 0) \ M(SettingInt64, os_thread_priority, 0, "If non zero - set corresponding 'nice' value for query processing threads. Can be used to adjust query priority for OS scheduler.", 0) \ \ - M(SettingBool, log_queries, 0, "Log requests and write the log to the system table.", 0) \ + M(SettingBool, log_queries, 1, "Log requests and write the log to the system table.", 0) \ M(SettingLogQueriesType, log_queries_min_type, QueryLogElementType::QUERY_START, "query_log minimal type to log, possible values (from low to high): QUERY_START, QUERY_FINISH, EXCEPTION_BEFORE_START, EXCEPTION_WHILE_PROCESSING.", 0) \ M(SettingUInt64, log_queries_cut_to_length, 100000, "If query length is greater than specified threshold (in bytes), then cut query when writing to query log. Also limit length of printed query in ordinary text log.", 0) \ \ @@ -438,6 +438,7 @@ struct Settings : public SettingsCollection M(SettingUInt64, mark_cache_min_lifetime, 0, "Obsolete setting, does nothing. Will be removed after 2020-05-31", 0) \ M(SettingBool, partial_merge_join, false, "Obsolete. Use join_algorithm='prefer_partial_merge' instead.", 0) \ M(SettingUInt64, max_memory_usage_for_all_queries, 0, "Obsolete. Will be removed after 2020-10-20", 0) \ + M(SettingBool, experimental_use_processors, true, "Obsolete setting, does nothing. Will be removed after 2020-11-29.", 0) \ DECLARE_SETTINGS_COLLECTION(LIST_OF_SETTINGS) diff --git a/src/DataStreams/BlocksBlockInputStream.h b/src/DataStreams/BlocksBlockInputStream.h index 6301a92b6a4..3062a24a44c 100644 --- a/src/DataStreams/BlocksBlockInputStream.h +++ b/src/DataStreams/BlocksBlockInputStream.h @@ -13,6 +13,7 @@ limitations under the License. */ #include #include +#include namespace DB @@ -38,7 +39,12 @@ protected: Block res = *it; ++it; - return Chunk(res.getColumns(), res.rows()); + + auto info = std::make_shared(); + info->bucket_num = res.info.bucket_num; + info->is_overflows = res.info.is_overflows; + + return Chunk(res.getColumns(), res.rows(), std::move(info)); } private: diff --git a/src/DataStreams/InputStreamFromASTInsertQuery.cpp b/src/DataStreams/InputStreamFromASTInsertQuery.cpp index 3b4946e4bc9..47b61294da3 100644 --- a/src/DataStreams/InputStreamFromASTInsertQuery.cpp +++ b/src/DataStreams/InputStreamFromASTInsertQuery.cpp @@ -58,7 +58,7 @@ InputStreamFromASTInsertQuery::InputStreamFromASTInsertQuery( if (context.getSettingsRef().input_format_defaults_for_omitted_fields && ast_insert_query->table_id && !input_function) { - StoragePtr storage = DatabaseCatalog::instance().getTable(ast_insert_query->table_id); + StoragePtr storage = DatabaseCatalog::instance().getTable(ast_insert_query->table_id, context); auto column_defaults = storage->getColumns().getDefaults(); if (!column_defaults.empty()) res_stream = std::make_shared(res_stream, column_defaults, context); diff --git a/src/DataStreams/NullAndDoCopyBlockInputStream.h b/src/DataStreams/NullAndDoCopyBlockInputStream.h index 8fe05c387a3..8bfb3538f3a 100644 --- a/src/DataStreams/NullAndDoCopyBlockInputStream.h +++ b/src/DataStreams/NullAndDoCopyBlockInputStream.h @@ -21,19 +21,10 @@ class NullAndDoCopyBlockInputStream : public IBlockInputStream { public: NullAndDoCopyBlockInputStream(const BlockInputStreamPtr & input_, BlockOutputStreamPtr output_) + : input(std::move(input_)) + , output(std::move(output_)) { - input_streams.push_back(input_); - output_streams.push_back(output_); - - for (auto & input_stream : input_streams) - children.push_back(input_stream); - } - - NullAndDoCopyBlockInputStream(const BlockInputStreams & input_, BlockOutputStreams & output_) - : input_streams(input_), output_streams(output_) - { - for (auto & input_stream : input_) - children.push_back(input_stream); + children.push_back(input); } /// Suppress readPrefix and readSuffix, because they are called by copyData. @@ -53,16 +44,13 @@ protected: /// If query was cancelled, it will be processed by child streams. /// Part of the data will be processed. - if (input_streams.size() == 1 && output_streams.size() == 1) - copyData(*input_streams.at(0), *output_streams.at(0)); - else - copyData(input_streams, output_streams); + copyData(*input, *output); return Block(); } private: - BlockInputStreams input_streams; - BlockOutputStreams output_streams; + BlockInputStreamPtr input; + BlockOutputStreamPtr output; }; } diff --git a/src/DataStreams/PushingToViewsBlockOutputStream.cpp b/src/DataStreams/PushingToViewsBlockOutputStream.cpp index 7f730b5fd3f..a4f0b58adeb 100644 --- a/src/DataStreams/PushingToViewsBlockOutputStream.cpp +++ b/src/DataStreams/PushingToViewsBlockOutputStream.cpp @@ -59,7 +59,7 @@ PushingToViewsBlockOutputStream::PushingToViewsBlockOutputStream( for (const auto & database_table : dependencies) { - auto dependent_table = DatabaseCatalog::instance().getTable(database_table); + auto dependent_table = DatabaseCatalog::instance().getTable(database_table, context); ASTPtr query; BlockOutputStreamPtr out; @@ -274,7 +274,7 @@ void PushingToViewsBlockOutputStream::process(const Block & block, size_t view_n StorageValues::create( storage->getStorageID(), storage->getColumns(), block, storage->getVirtuals())); select.emplace(view.query, local_context, SelectQueryOptions()); - in = std::make_shared(select->execute().in); + in = std::make_shared(select->execute().getInputStream()); /// Squashing is needed here because the materialized view query can generate a lot of blocks /// even when only one block is inserted into the parent table (e.g. if the query is a GROUP BY diff --git a/src/DataStreams/TTLBlockInputStream.cpp b/src/DataStreams/TTLBlockInputStream.cpp index d2d5d6a92f9..c6542763533 100644 --- a/src/DataStreams/TTLBlockInputStream.cpp +++ b/src/DataStreams/TTLBlockInputStream.cpp @@ -5,6 +5,8 @@ #include #include #include +#include +#include namespace DB { @@ -36,7 +38,7 @@ TTLBlockInputStream::TTLBlockInputStream( const auto & column_defaults = storage_columns.getDefaults(); ASTPtr default_expr_list = std::make_shared(); - for (const auto & [name, _] : storage.column_ttl_entries_by_name) + for (const auto & [name, _] : storage.getColumnTTLs()) { auto it = column_defaults.find(name); if (it != column_defaults.end()) @@ -67,6 +69,32 @@ TTLBlockInputStream::TTLBlockInputStream( default_expr_list, storage.getColumns().getAllPhysical()); defaults_expression = ExpressionAnalyzer{default_expr_list, syntax_result, storage.global_context}.getActions(true); } + + if (storage.hasRowsTTL() && storage.getRowsTTL().mode == TTLMode::GROUP_BY) + { + current_key_value.resize(storage.getRowsTTL().group_by_keys.size()); + + ColumnNumbers keys; + for (const auto & key : storage.getRowsTTL().group_by_keys) + keys.push_back(header.getPositionByName(key)); + agg_key_columns.resize(storage.getRowsTTL().group_by_keys.size()); + + AggregateDescriptions aggregates = storage.getRowsTTL().aggregate_descriptions; + for (auto & descr : aggregates) + if (descr.arguments.empty()) + for (const auto & name : descr.argument_names) + descr.arguments.push_back(header.getPositionByName(name)); + agg_aggregate_columns.resize(storage.getRowsTTL().aggregate_descriptions.size()); + + const Settings & settings = storage.global_context.getSettingsRef(); + + Aggregator::Params params(header, keys, aggregates, + false, settings.max_rows_to_group_by, settings.group_by_overflow_mode, + SettingUInt64(0), SettingUInt64(0), + settings.max_bytes_before_external_group_by, settings.empty_result_for_aggregation_by_empty_set, + storage.global_context.getTemporaryVolume(), settings.max_threads, settings.min_free_disk_space_for_temporary_data); + aggregator = std::make_unique(params); + } } bool TTLBlockInputStream::isTTLExpired(time_t ttl) const @@ -77,7 +105,8 @@ bool TTLBlockInputStream::isTTLExpired(time_t ttl) const Block TTLBlockInputStream::readImpl() { /// Skip all data if table ttl is expired for part - if (storage.hasRowsTTL() && isTTLExpired(old_ttl_infos.table_ttl.max)) + if (storage.hasRowsTTL() && !storage.getRowsTTL().where_expression && + storage.getRowsTTL().mode != TTLMode::GROUP_BY && isTTLExpired(old_ttl_infos.table_ttl.max)) { rows_removed = data_part->rows_count; return {}; @@ -85,7 +114,16 @@ Block TTLBlockInputStream::readImpl() Block block = children.at(0)->read(); if (!block) + { + if (aggregator && !agg_result.empty()) + { + MutableColumns result_columns = header.cloneEmptyColumns(); + finalizeAggregates(result_columns); + block = header.cloneWithColumns(std::move(result_columns)); + } + return block; + } if (storage.hasRowsTTL() && (force || isTTLExpired(old_ttl_infos.table_ttl.min))) removeRowsWithExpiredTableTTL(block); @@ -113,36 +151,149 @@ void TTLBlockInputStream::readSuffixImpl() void TTLBlockInputStream::removeRowsWithExpiredTableTTL(Block & block) { - storage.rows_ttl_entry.expression->execute(block); + const auto & rows_ttl = storage.getRowsTTL(); + + rows_ttl.expression->execute(block); + if (rows_ttl.where_expression) + rows_ttl.where_expression->execute(block); const IColumn * ttl_column = - block.getByName(storage.rows_ttl_entry.result_column).column.get(); + block.getByName(rows_ttl.result_column).column.get(); + + const IColumn * where_result_column = storage.getRowsTTL().where_expression ? + block.getByName(storage.getRowsTTL().where_result_column).column.get() : nullptr; const auto & column_names = header.getNames(); - MutableColumns result_columns; - result_columns.reserve(column_names.size()); - for (auto it = column_names.begin(); it != column_names.end(); ++it) + if (!aggregator) { - const IColumn * values_column = block.getByName(*it).column.get(); - MutableColumnPtr result_column = values_column->cloneEmpty(); - result_column->reserve(block.rows()); + MutableColumns result_columns; + result_columns.reserve(column_names.size()); + for (auto it = column_names.begin(); it != column_names.end(); ++it) + { + const IColumn * values_column = block.getByName(*it).column.get(); + MutableColumnPtr result_column = values_column->cloneEmpty(); + result_column->reserve(block.rows()); + for (size_t i = 0; i < block.rows(); ++i) + { + UInt32 cur_ttl = getTimestampByIndex(ttl_column, i); + bool where_filter_passed = !where_result_column || where_result_column->getBool(i); + if (!isTTLExpired(cur_ttl) || !where_filter_passed) + { + new_ttl_infos.table_ttl.update(cur_ttl); + result_column->insertFrom(*values_column, i); + } + else if (it == column_names.begin()) + ++rows_removed; + } + result_columns.emplace_back(std::move(result_column)); + } + block = header.cloneWithColumns(std::move(result_columns)); + } + else + { + MutableColumns result_columns = header.cloneEmptyColumns(); + MutableColumns aggregate_columns = header.cloneEmptyColumns(); + + size_t rows_aggregated = 0; + size_t current_key_start = 0; + size_t rows_with_current_key = 0; for (size_t i = 0; i < block.rows(); ++i) { UInt32 cur_ttl = getTimestampByIndex(ttl_column, i); - if (!isTTLExpired(cur_ttl)) + bool where_filter_passed = !where_result_column || where_result_column->getBool(i); + bool ttl_expired = isTTLExpired(cur_ttl) && where_filter_passed; + + bool same_as_current = true; + for (size_t j = 0; j < storage.getRowsTTL().group_by_keys.size(); ++j) + { + const String & key_column = storage.getRowsTTL().group_by_keys[j]; + const IColumn * values_column = block.getByName(key_column).column.get(); + if (!same_as_current || (*values_column)[i] != current_key_value[j]) + { + values_column->get(i, current_key_value[j]); + same_as_current = false; + } + } + if (!same_as_current) + { + if (rows_with_current_key) + calculateAggregates(aggregate_columns, current_key_start, rows_with_current_key); + finalizeAggregates(result_columns); + + current_key_start = rows_aggregated; + rows_with_current_key = 0; + } + + if (ttl_expired) + { + ++rows_with_current_key; + ++rows_aggregated; + for (const auto & name : column_names) + { + const IColumn * values_column = block.getByName(name).column.get(); + auto & column = aggregate_columns[header.getPositionByName(name)]; + column->insertFrom(*values_column, i); + } + } + else { new_ttl_infos.table_ttl.update(cur_ttl); - result_column->insertFrom(*values_column, i); + for (const auto & name : column_names) + { + const IColumn * values_column = block.getByName(name).column.get(); + auto & column = result_columns[header.getPositionByName(name)]; + column->insertFrom(*values_column, i); + } } - else if (it == column_names.begin()) - ++rows_removed; } - result_columns.emplace_back(std::move(result_column)); - } - block = header.cloneWithColumns(std::move(result_columns)); + if (rows_with_current_key) + calculateAggregates(aggregate_columns, current_key_start, rows_with_current_key); + + block = header.cloneWithColumns(std::move(result_columns)); + } +} + +void TTLBlockInputStream::calculateAggregates(const MutableColumns & aggregate_columns, size_t start_pos, size_t length) +{ + Columns aggregate_chunk; + aggregate_chunk.reserve(aggregate_columns.size()); + for (const auto & name : header.getNames()) + { + const auto & column = aggregate_columns[header.getPositionByName(name)]; + ColumnPtr chunk_column = column->cut(start_pos, length); + aggregate_chunk.emplace_back(std::move(chunk_column)); + } + aggregator->executeOnBlock(aggregate_chunk, length, agg_result, agg_key_columns, + agg_aggregate_columns, agg_no_more_keys); +} + +void TTLBlockInputStream::finalizeAggregates(MutableColumns & result_columns) +{ + if (!agg_result.empty()) + { + auto aggregated_res = aggregator->convertToBlocks(agg_result, true, 1); + for (auto & agg_block : aggregated_res) + { + for (const auto & it : storage.getRowsTTL().set_parts) + it.expression->execute(agg_block); + for (const auto & name : storage.getRowsTTL().group_by_keys) + { + const IColumn * values_column = agg_block.getByName(name).column.get(); + auto & result_column = result_columns[header.getPositionByName(name)]; + result_column->insertRangeFrom(*values_column, 0, agg_block.rows()); + } + for (const auto & it : storage.getRowsTTL().set_parts) + { + const IColumn * values_column = agg_block.getByName(it.expression_result_column_name).column.get(); + auto & result_column = result_columns[header.getPositionByName(it.column_name)]; + result_column->insertRangeFrom(*values_column, 0, agg_block.rows()); + } + } + } + agg_result.invalidate(); } void TTLBlockInputStream::removeValuesWithExpiredColumnTTL(Block & block) @@ -155,7 +306,7 @@ void TTLBlockInputStream::removeValuesWithExpiredColumnTTL(Block & block) } std::vector columns_to_remove; - for (const auto & [name, ttl_entry] : storage.column_ttl_entries_by_name) + for (const auto & [name, ttl_entry] : storage.getColumnTTLs()) { /// If we read not all table columns. E.g. while mutation. if (!block.has(name)) @@ -216,7 +367,7 @@ void TTLBlockInputStream::removeValuesWithExpiredColumnTTL(Block & block) void TTLBlockInputStream::updateMovesTTL(Block & block) { std::vector columns_to_remove; - for (const auto & ttl_entry : storage.move_ttl_entries) + for (const auto & ttl_entry : storage.getMoveTTLs()) { auto & new_ttl_info = new_ttl_infos.moves_ttl[ttl_entry.result_column]; diff --git a/src/DataStreams/TTLBlockInputStream.h b/src/DataStreams/TTLBlockInputStream.h index 3896e5232f8..c6ffa95cd75 100644 --- a/src/DataStreams/TTLBlockInputStream.h +++ b/src/DataStreams/TTLBlockInputStream.h @@ -3,6 +3,7 @@ #include #include #include +#include #include @@ -39,6 +40,13 @@ private: time_t current_time; bool force; + std::unique_ptr aggregator; + std::vector current_key_value; + AggregatedDataVariants agg_result; + ColumnRawPtrs agg_key_columns; + Aggregator::AggregateColumns agg_aggregate_columns; + bool agg_no_more_keys = false; + IMergeTreeDataPart::TTLInfos old_ttl_infos; IMergeTreeDataPart::TTLInfos new_ttl_infos; NameSet empty_columns; @@ -59,6 +67,12 @@ private: /// Removes rows with expired table ttl and computes new ttl_infos for part void removeRowsWithExpiredTableTTL(Block & block); + // Calculate aggregates of aggregate_columns into agg_result + void calculateAggregates(const MutableColumns & aggregate_columns, size_t start_pos, size_t length); + + /// Finalize agg_result into result_columns + void finalizeAggregates(MutableColumns & result_columns); + /// Updates TTL for moves void updateMovesTTL(Block & block); diff --git a/src/DataStreams/copyData.cpp b/src/DataStreams/copyData.cpp index fd4bfab28d8..a0651999034 100644 --- a/src/DataStreams/copyData.cpp +++ b/src/DataStreams/copyData.cpp @@ -1,9 +1,6 @@ -#include #include #include #include -#include -#include #include @@ -55,79 +52,6 @@ void copyDataImpl(IBlockInputStream & from, IBlockOutputStream & to, TCancelCall inline void doNothing(const Block &) {} -namespace -{ - - -struct ParallelInsertsHandler -{ - using CencellationHook = std::function; - - explicit ParallelInsertsHandler(BlockOutputStreams & output_streams, CencellationHook cancellation_hook_, size_t num_threads) - : outputs(output_streams.size()), cancellation_hook(std::move(cancellation_hook_)) - { - exceptions.resize(num_threads); - - for (auto & output : output_streams) - outputs.push(output.get()); - } - - void onBlock(Block & block, size_t /*thread_num*/) - { - IBlockOutputStream * out = nullptr; - - outputs.pop(out); - out->write(block); - outputs.push(out); - } - - void onFinishThread(size_t /*thread_num*/) {} - void onFinish() {} - - void onException(std::exception_ptr & exception, size_t thread_num) - { - exceptions[thread_num] = exception; - cancellation_hook(); - } - - void rethrowFirstException() - { - for (auto & exception : exceptions) - if (exception) - std::rethrow_exception(exception); - } - - ConcurrentBoundedQueue outputs; - std::vector exceptions; - CencellationHook cancellation_hook; -}; - -} - -static void copyDataImpl(BlockInputStreams & inputs, BlockOutputStreams & outputs) -{ - for (auto & output : outputs) - output->writePrefix(); - - using Processor = ParallelInputsProcessor; - Processor * processor_ptr = nullptr; - - ParallelInsertsHandler handler(outputs, [&processor_ptr]() { processor_ptr->cancel(false); }, inputs.size()); - ParallelInputsProcessor processor(inputs, nullptr, inputs.size(), handler); - processor_ptr = &processor; - - processor.process(); - processor.wait(); - handler.rethrowFirstException(); - - /// readPrefix is called in ParallelInputsProcessor. - for (auto & input : inputs) - input->readSuffix(); - - for (auto & output : outputs) - output->writeSuffix(); -} - void copyData(IBlockInputStream & from, IBlockOutputStream & to, std::atomic * is_cancelled) { auto is_cancelled_pred = [is_cancelled] () @@ -138,11 +62,6 @@ void copyData(IBlockInputStream & from, IBlockOutputStream & to, std::atomic & is_cancelled) { copyDataImpl(from, to, is_cancelled, doNothing); diff --git a/src/DataStreams/copyData.h b/src/DataStreams/copyData.h index ae72dbd2421..f2bce8f411b 100644 --- a/src/DataStreams/copyData.h +++ b/src/DataStreams/copyData.h @@ -16,8 +16,6 @@ class Block; */ void copyData(IBlockInputStream & from, IBlockOutputStream & to, std::atomic * is_cancelled = nullptr); -void copyData(BlockInputStreams & inputs, BlockOutputStreams & outputs); - void copyData(IBlockInputStream & from, IBlockOutputStream & to, const std::function & is_cancelled); void copyData(IBlockInputStream & from, IBlockOutputStream & to, const std::function & is_cancelled, diff --git a/src/DataStreams/tests/union_stream2.cpp b/src/DataStreams/tests/union_stream2.cpp index 6e0997e7f72..5b84d89a435 100644 --- a/src/DataStreams/tests/union_stream2.cpp +++ b/src/DataStreams/tests/union_stream2.cpp @@ -35,7 +35,7 @@ try Names column_names; column_names.push_back("WatchID"); - StoragePtr table = DatabaseCatalog::instance().getTable({"default", "hits6"}); + StoragePtr table = DatabaseCatalog::instance().getTable({"default", "hits6"}, context); QueryProcessingStage::Enum stage = table->getQueryProcessingStage(context); auto pipes = table->read(column_names, {}, context, stage, settings.max_block_size, settings.max_threads); diff --git a/src/Databases/DatabaseAtomic.cpp b/src/Databases/DatabaseAtomic.cpp index 27a2441cec6..ed875f5fff4 100644 --- a/src/Databases/DatabaseAtomic.cpp +++ b/src/Databases/DatabaseAtomic.cpp @@ -288,15 +288,15 @@ void DatabaseAtomic::assertCanBeDetached(bool cleenup) "because some tables are still in use. Retry later.", ErrorCodes::DATABASE_NOT_EMPTY); } -DatabaseTablesIteratorPtr DatabaseAtomic::getTablesIterator(const IDatabase::FilterByNameFunction & filter_by_table_name) +DatabaseTablesIteratorPtr DatabaseAtomic::getTablesIterator(const Context & context, const IDatabase::FilterByNameFunction & filter_by_table_name) { - auto base_iter = DatabaseWithOwnTablesBase::getTablesIterator(filter_by_table_name); + auto base_iter = DatabaseWithOwnTablesBase::getTablesIterator(context, filter_by_table_name); return std::make_unique(std::move(typeid_cast(*base_iter))); } UUID DatabaseAtomic::tryGetTableUUID(const String & table_name) const { - if (auto table = tryGetTable(table_name)) + if (auto table = tryGetTable(table_name, global_context)) return table->getStorageID().uuid; return UUIDHelpers::Nil; } diff --git a/src/Databases/DatabaseAtomic.h b/src/Databases/DatabaseAtomic.h index 84297a42843..71428fdb420 100644 --- a/src/Databases/DatabaseAtomic.h +++ b/src/Databases/DatabaseAtomic.h @@ -42,7 +42,7 @@ public: void drop(const Context & /*context*/) override; - DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name) override; + DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name) override; void loadStoredObjects(Context & context, bool has_force_restore_data_flag) override; diff --git a/src/Databases/DatabaseDictionary.cpp b/src/Databases/DatabaseDictionary.cpp index 81bcbf7bc6b..c4c74f8e70c 100644 --- a/src/Databases/DatabaseDictionary.cpp +++ b/src/Databases/DatabaseDictionary.cpp @@ -50,18 +50,18 @@ Tables DatabaseDictionary::listTables(const FilterByNameFunction & filter_by_nam return tables; } -bool DatabaseDictionary::isTableExist(const String & table_name) const +bool DatabaseDictionary::isTableExist(const String & table_name, const Context &) const { return global_context.getExternalDictionariesLoader().getCurrentStatus(table_name) != ExternalLoader::Status::NOT_EXIST; } -StoragePtr DatabaseDictionary::tryGetTable(const String & table_name) const +StoragePtr DatabaseDictionary::tryGetTable(const String & table_name, const Context &) const { auto load_result = global_context.getExternalDictionariesLoader().getLoadResult(table_name); return createStorageDictionary(getDatabaseName(), load_result); } -DatabaseTablesIteratorPtr DatabaseDictionary::getTablesIterator(const FilterByNameFunction & filter_by_table_name) +DatabaseTablesIteratorPtr DatabaseDictionary::getTablesIterator(const Context &, const FilterByNameFunction & filter_by_table_name) { return std::make_unique(listTables(filter_by_table_name)); } @@ -71,7 +71,7 @@ bool DatabaseDictionary::empty() const return !global_context.getExternalDictionariesLoader().hasObjects(); } -ASTPtr DatabaseDictionary::getCreateTableQueryImpl(const String & table_name, bool throw_on_error) const +ASTPtr DatabaseDictionary::getCreateTableQueryImpl(const String & table_name, const Context &, bool throw_on_error) const { String query; { diff --git a/src/Databases/DatabaseDictionary.h b/src/Databases/DatabaseDictionary.h index bf10dc134bd..b61c85033e8 100644 --- a/src/Databases/DatabaseDictionary.h +++ b/src/Databases/DatabaseDictionary.h @@ -29,11 +29,11 @@ public: return "Dictionary"; } - bool isTableExist(const String & table_name) const override; + bool isTableExist(const String & table_name, const Context & context) const override; - StoragePtr tryGetTable(const String & table_name) const override; + StoragePtr tryGetTable(const String & table_name, const Context & context) const override; - DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name) override; + DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name) override; bool empty() const override; @@ -44,7 +44,7 @@ public: void shutdown() override; protected: - ASTPtr getCreateTableQueryImpl(const String & table_name, bool throw_on_error) const override; + ASTPtr getCreateTableQueryImpl(const String & table_name, const Context & context, bool throw_on_error) const override; private: mutable std::mutex mutex; diff --git a/src/Databases/DatabaseFactory.cpp b/src/Databases/DatabaseFactory.cpp index 21feb122da1..f27bc509ebe 100644 --- a/src/Databases/DatabaseFactory.cpp +++ b/src/Databases/DatabaseFactory.cpp @@ -82,7 +82,7 @@ DatabasePtr DatabaseFactory::getImpl( else if (engine_name == "Atomic") return std::make_shared(database_name, metadata_path, context); else if (engine_name == "Memory") - return std::make_shared(database_name); + return std::make_shared(database_name, context); else if (engine_name == "Dictionary") return std::make_shared(database_name, context); diff --git a/src/Databases/DatabaseLazy.cpp b/src/Databases/DatabaseLazy.cpp index 51ee664a42a..11e5272110e 100644 --- a/src/Databases/DatabaseLazy.cpp +++ b/src/Databases/DatabaseLazy.cpp @@ -132,7 +132,7 @@ StoragePtr DatabaseLazy::tryGetTable(const String & table_name) const return loadTable(table_name); } -DatabaseTablesIteratorPtr DatabaseLazy::getTablesIterator(const FilterByNameFunction & filter_by_table_name) +DatabaseTablesIteratorPtr DatabaseLazy::getTablesIterator(const Context &, const FilterByNameFunction & filter_by_table_name) { std::lock_guard lock(mutex); Strings filtered_tables; diff --git a/src/Databases/DatabaseLazy.h b/src/Databases/DatabaseLazy.h index 4306e61b37b..2e24b687be5 100644 --- a/src/Databases/DatabaseLazy.h +++ b/src/Databases/DatabaseLazy.h @@ -51,13 +51,15 @@ public: time_t getObjectMetadataModificationTime(const String & table_name) const override; - bool isTableExist(const String & table_name) const override; + bool isTableExist(const String & table_name, const Context &) const override { return isTableExist(table_name); } + bool isTableExist(const String & table_name) const; - StoragePtr tryGetTable(const String & table_name) const override; + StoragePtr tryGetTable(const String & table_name, const Context &) const override { return tryGetTable(table_name); } + StoragePtr tryGetTable(const String & table_name) const; bool empty() const override; - DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name) override; + DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name) override; void attachTable(const String & table_name, const StoragePtr & table, const String & relative_table_path) override; diff --git a/src/Databases/DatabaseMemory.cpp b/src/Databases/DatabaseMemory.cpp index 84fec6bcc22..52b1f889943 100644 --- a/src/Databases/DatabaseMemory.cpp +++ b/src/Databases/DatabaseMemory.cpp @@ -16,8 +16,8 @@ namespace ErrorCodes extern const int UNKNOWN_TABLE; } -DatabaseMemory::DatabaseMemory(const String & name_) - : DatabaseWithOwnTablesBase(name_, "DatabaseMemory(" + name_ + ")") +DatabaseMemory::DatabaseMemory(const String & name_, const Context & context) + : DatabaseWithOwnTablesBase(name_, "DatabaseMemory(" + name_ + ")", context) , data_path("data/" + escapeForFileName(database_name) + "/") {} @@ -64,7 +64,7 @@ ASTPtr DatabaseMemory::getCreateDatabaseQuery() const return create_query; } -ASTPtr DatabaseMemory::getCreateTableQueryImpl(const String & table_name, bool throw_on_error) const +ASTPtr DatabaseMemory::getCreateTableQueryImpl(const String & table_name, const Context &, bool throw_on_error) const { std::lock_guard lock{mutex}; auto it = create_queries.find(table_name); @@ -80,7 +80,7 @@ ASTPtr DatabaseMemory::getCreateTableQueryImpl(const String & table_name, bool t UUID DatabaseMemory::tryGetTableUUID(const String & table_name) const { - if (auto table = tryGetTable(table_name)) + if (auto table = tryGetTable(table_name, global_context)) return table->getStorageID().uuid; return UUIDHelpers::Nil; } diff --git a/src/Databases/DatabaseMemory.h b/src/Databases/DatabaseMemory.h index ad34c4d9097..40cc808e42b 100644 --- a/src/Databases/DatabaseMemory.h +++ b/src/Databases/DatabaseMemory.h @@ -19,7 +19,7 @@ namespace DB class DatabaseMemory final : public DatabaseWithOwnTablesBase { public: - DatabaseMemory(const String & name_); + DatabaseMemory(const String & name_, const Context & context); String getEngineName() const override { return "Memory"; } @@ -34,7 +34,7 @@ public: const String & table_name, bool no_delay) override; - ASTPtr getCreateTableQueryImpl(const String & name, bool throw_on_error) const override; + ASTPtr getCreateTableQueryImpl(const String & name, const Context & context, bool throw_on_error) const override; ASTPtr getCreateDatabaseQuery() const override; /// DatabaseMemory allows to create tables, which store data on disk. diff --git a/src/Databases/DatabaseMySQL.cpp b/src/Databases/DatabaseMySQL.cpp index cbd3261975a..5d4b81014f9 100644 --- a/src/Databases/DatabaseMySQL.cpp +++ b/src/Databases/DatabaseMySQL.cpp @@ -89,7 +89,7 @@ bool DatabaseMySQL::empty() const return true; } -DatabaseTablesIteratorPtr DatabaseMySQL::getTablesIterator(const FilterByNameFunction & filter_by_table_name) +DatabaseTablesIteratorPtr DatabaseMySQL::getTablesIterator(const Context &, const FilterByNameFunction & filter_by_table_name) { Tables tables; std::lock_guard lock(mutex); @@ -103,12 +103,12 @@ DatabaseTablesIteratorPtr DatabaseMySQL::getTablesIterator(const FilterByNameFun return std::make_unique(tables); } -bool DatabaseMySQL::isTableExist(const String & name) const +bool DatabaseMySQL::isTableExist(const String & name, const Context &) const { - return bool(tryGetTable(name)); + return bool(tryGetTable(name, global_context)); } -StoragePtr DatabaseMySQL::tryGetTable(const String & mysql_table_name) const +StoragePtr DatabaseMySQL::tryGetTable(const String & mysql_table_name, const Context &) const { std::lock_guard lock(mutex); @@ -155,7 +155,7 @@ static ASTPtr getCreateQueryFromStorage(const StoragePtr & storage, const ASTPtr return create_table_query; } -ASTPtr DatabaseMySQL::getCreateTableQueryImpl(const String & table_name, bool throw_on_error) const +ASTPtr DatabaseMySQL::getCreateTableQueryImpl(const String & table_name, const Context &, bool throw_on_error) const { std::lock_guard lock(mutex); @@ -501,7 +501,7 @@ void DatabaseMySQL::createTable(const Context &, const String & table_name, cons /// XXX: hack /// In order to prevent users from broken the table structure by executing attach table database_name.table_name (...) /// we should compare the old and new create_query to make them completely consistent - const auto & origin_create_query = getCreateTableQuery(table_name); + const auto & origin_create_query = getCreateTableQuery(table_name, global_context); origin_create_query->as()->attach = true; if (queryToString(origin_create_query) != queryToString(create_query)) diff --git a/src/Databases/DatabaseMySQL.h b/src/Databases/DatabaseMySQL.h index a43da5d1762..70d8dc81e0f 100644 --- a/src/Databases/DatabaseMySQL.h +++ b/src/Databases/DatabaseMySQL.h @@ -32,13 +32,13 @@ public: bool empty() const override; - DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name) override; + DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name) override; ASTPtr getCreateDatabaseQuery() const override; - bool isTableExist(const String & name) const override; + bool isTableExist(const String & name, const Context & context) const override; - StoragePtr tryGetTable(const String & name) const override; + StoragePtr tryGetTable(const String & name, const Context & context) const override; time_t getObjectMetadataModificationTime(const String & name) const override; @@ -59,7 +59,7 @@ public: void attachTable(const String & table_name, const StoragePtr & storage, const String & relative_table_path) override; protected: - ASTPtr getCreateTableQueryImpl(const String & name, bool throw_on_error) const override; + ASTPtr getCreateTableQueryImpl(const String & name, const Context & context, bool throw_on_error) const override; private: const Context & global_context; diff --git a/src/Databases/DatabaseOnDisk.cpp b/src/Databases/DatabaseOnDisk.cpp index 70f86b19f1f..1b542c7a1ff 100644 --- a/src/Databases/DatabaseOnDisk.cpp +++ b/src/Databases/DatabaseOnDisk.cpp @@ -123,10 +123,9 @@ String getObjectDefinitionFromCreateQuery(const ASTPtr & query) } DatabaseOnDisk::DatabaseOnDisk(const String & name, const String & metadata_path_, const String & data_path_, const String & logger, const Context & context) - : DatabaseWithOwnTablesBase(name, logger) + : DatabaseWithOwnTablesBase(name, logger, context) , metadata_path(metadata_path_) , data_path(data_path_) - , global_context(context.getGlobalContext()) { Poco::File(context.getPath() + data_path).createDirectories(); Poco::File(metadata_path).createDirectories(); @@ -160,7 +159,7 @@ void DatabaseOnDisk::createTable( throw Exception("Dictionary " + backQuote(getDatabaseName()) + "." + backQuote(table_name) + " already exists.", ErrorCodes::DICTIONARY_ALREADY_EXISTS); - if (isTableExist(table_name)) + if (isTableExist(table_name, global_context)) throw Exception("Table " + backQuote(getDatabaseName()) + "." + backQuote(table_name) + " already exists.", ErrorCodes::TABLE_ALREADY_EXISTS); if (create.attach_short_syntax) @@ -267,7 +266,7 @@ void DatabaseOnDisk::renameTable( String table_metadata_path; ASTPtr attach_query; /// DatabaseLazy::detachTable may return nullptr even if table exists, so we need tryGetTable for this case. - StoragePtr table = tryGetTable(table_name); + StoragePtr table = tryGetTable(table_name, global_context); detachTable(table_name); try { @@ -304,10 +303,10 @@ void DatabaseOnDisk::renameTable( Poco::File(table_metadata_path).remove(); } -ASTPtr DatabaseOnDisk::getCreateTableQueryImpl(const String & table_name, bool throw_on_error) const +ASTPtr DatabaseOnDisk::getCreateTableQueryImpl(const String & table_name, const Context &, bool throw_on_error) const { ASTPtr ast; - bool has_table = tryGetTable(table_name) != nullptr; + bool has_table = tryGetTable(table_name, global_context) != nullptr; auto table_metadata_path = getObjectMetadataPath(table_name); try { diff --git a/src/Databases/DatabaseOnDisk.h b/src/Databases/DatabaseOnDisk.h index 75609e231af..d4fb9b2aa17 100644 --- a/src/Databases/DatabaseOnDisk.h +++ b/src/Databases/DatabaseOnDisk.h @@ -76,6 +76,7 @@ protected: ASTPtr getCreateTableQueryImpl( const String & table_name, + const Context & context, bool throw_on_error) const override; ASTPtr getCreateQueryFromMetadata(const String & metadata_path, bool throw_on_error) const; @@ -85,7 +86,6 @@ protected: const String metadata_path; const String data_path; - const Context & global_context; }; } diff --git a/src/Databases/DatabaseWithDictionaries.cpp b/src/Databases/DatabaseWithDictionaries.cpp index 0d49078bd08..e0f2aa9286b 100644 --- a/src/Databases/DatabaseWithDictionaries.cpp +++ b/src/Databases/DatabaseWithDictionaries.cpp @@ -127,7 +127,7 @@ void DatabaseWithDictionaries::createDictionary(const Context & context, const S "Dictionary " + backQuote(getDatabaseName()) + "." + backQuote(dictionary_name) + " already exists.", ErrorCodes::DICTIONARY_ALREADY_EXISTS); - if (isTableExist(dictionary_name)) + if (isTableExist(dictionary_name, global_context)) throw Exception("Table " + backQuote(getDatabaseName()) + "." + backQuote(dictionary_name) + " already exists.", ErrorCodes::TABLE_ALREADY_EXISTS); diff --git a/src/Databases/DatabasesCommon.cpp b/src/Databases/DatabasesCommon.cpp index 5ad4fa20690..2a2ca1841cf 100644 --- a/src/Databases/DatabasesCommon.cpp +++ b/src/Databases/DatabasesCommon.cpp @@ -1,5 +1,6 @@ #include #include +#include #include #include #include @@ -18,18 +19,18 @@ namespace ErrorCodes extern const int UNKNOWN_TABLE; } -DatabaseWithOwnTablesBase::DatabaseWithOwnTablesBase(const String & name_, const String & logger) - : IDatabase(name_), log(&Logger::get(logger)) +DatabaseWithOwnTablesBase::DatabaseWithOwnTablesBase(const String & name_, const String & logger, const Context & context) + : IDatabase(name_), log(&Logger::get(logger)), global_context(context.getGlobalContext()) { } -bool DatabaseWithOwnTablesBase::isTableExist(const String & table_name) const +bool DatabaseWithOwnTablesBase::isTableExist(const String & table_name, const Context &) const { std::lock_guard lock(mutex); return tables.find(table_name) != tables.end(); } -StoragePtr DatabaseWithOwnTablesBase::tryGetTable(const String & table_name) const +StoragePtr DatabaseWithOwnTablesBase::tryGetTable(const String & table_name, const Context &) const { std::lock_guard lock(mutex); auto it = tables.find(table_name); @@ -38,7 +39,7 @@ StoragePtr DatabaseWithOwnTablesBase::tryGetTable(const String & table_name) con return {}; } -DatabaseTablesIteratorPtr DatabaseWithOwnTablesBase::getTablesIterator(const FilterByNameFunction & filter_by_table_name) +DatabaseTablesIteratorPtr DatabaseWithOwnTablesBase::getTablesIterator(const Context &, const FilterByNameFunction & filter_by_table_name) { std::lock_guard lock(mutex); if (!filter_by_table_name) diff --git a/src/Databases/DatabasesCommon.h b/src/Databases/DatabasesCommon.h index e195fc59ce9..4238fd30137 100644 --- a/src/Databases/DatabasesCommon.h +++ b/src/Databases/DatabasesCommon.h @@ -19,9 +19,9 @@ class Context; class DatabaseWithOwnTablesBase : public IDatabase { public: - bool isTableExist(const String & table_name) const override; + bool isTableExist(const String & table_name, const Context & context) const override; - StoragePtr tryGetTable(const String & table_name) const override; + StoragePtr tryGetTable(const String & table_name, const Context & context) const override; bool empty() const override; @@ -29,18 +29,19 @@ public: StoragePtr detachTable(const String & table_name) override; - DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name) override; + DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name) override; void shutdown() override; - virtual ~DatabaseWithOwnTablesBase() override; + ~DatabaseWithOwnTablesBase() override; protected: mutable std::mutex mutex; Tables tables; Poco::Logger * log; + const Context & global_context; - DatabaseWithOwnTablesBase(const String & name_, const String & logger); + DatabaseWithOwnTablesBase(const String & name_, const String & logger, const Context & context); void attachTableUnlocked(const String & table_name, const StoragePtr & table, std::unique_lock & lock); StoragePtr detachTableUnlocked(const String & table_name, std::unique_lock & lock); diff --git a/src/Databases/IDatabase.h b/src/Databases/IDatabase.h index 24147a0e7c5..3d108cfd91c 100644 --- a/src/Databases/IDatabase.h +++ b/src/Databases/IDatabase.h @@ -130,7 +130,7 @@ public: virtual void loadStoredObjects(Context & /*context*/, bool /*has_force_restore_data_flag*/) {} /// Check the existence of the table. - virtual bool isTableExist(const String & name) const = 0; + virtual bool isTableExist(const String & name, const Context & context) const = 0; /// Check the existence of the dictionary virtual bool isDictionaryExist(const String & /*name*/) const @@ -139,7 +139,7 @@ public: } /// Get the table for work. Return nullptr if there is no table. - virtual StoragePtr tryGetTable(const String & name) const = 0; + virtual StoragePtr tryGetTable(const String & name, const Context & context) const = 0; virtual UUID tryGetTableUUID(const String & /*table_name*/) const { return UUIDHelpers::Nil; } @@ -147,7 +147,7 @@ public: /// Get an iterator that allows you to pass through all the tables. /// It is possible to have "hidden" tables that are not visible when passing through, but are visible if you get them by name using the functions above. - virtual DatabaseTablesIteratorPtr getTablesIterator(const FilterByNameFunction & filter_by_table_name = {}) = 0; + virtual DatabaseTablesIteratorPtr getTablesIterator(const Context & context, const FilterByNameFunction & filter_by_table_name = {}) = 0; /// Get an iterator to pass through all the dictionaries. virtual DatabaseDictionariesIteratorPtr getDictionariesIterator([[maybe_unused]] const FilterByNameFunction & filter_by_dictionary_name = {}) @@ -249,14 +249,14 @@ public: } /// Get the CREATE TABLE query for the table. It can also provide information for detached tables for which there is metadata. - ASTPtr tryGetCreateTableQuery(const String & name) const noexcept + ASTPtr tryGetCreateTableQuery(const String & name, const Context & context) const noexcept { - return getCreateTableQueryImpl(name, false); + return getCreateTableQueryImpl(name, context, false); } - ASTPtr getCreateTableQuery(const String & name) const + ASTPtr getCreateTableQuery(const String & name, const Context & context) const { - return getCreateTableQueryImpl(name, true); + return getCreateTableQueryImpl(name, context, true); } /// Get the CREATE DICTIONARY query for the dictionary. Returns nullptr if dictionary doesn't exists. @@ -304,7 +304,7 @@ public: virtual ~IDatabase() {} protected: - virtual ASTPtr getCreateTableQueryImpl(const String & /*name*/, bool throw_on_error) const + virtual ASTPtr getCreateTableQueryImpl(const String & /*name*/, const Context & /*context*/, bool throw_on_error) const { if (throw_on_error) throw Exception("There is no SHOW CREATE TABLE query for Database" + getEngineName(), ErrorCodes::CANNOT_GET_CREATE_TABLE_QUERY); diff --git a/src/Dictionaries/CacheDictionary.inc.h b/src/Dictionaries/CacheDictionary.inc.h index 71f3f1857ce..27064d113e6 100644 --- a/src/Dictionaries/CacheDictionary.inc.h +++ b/src/Dictionaries/CacheDictionary.inc.h @@ -302,37 +302,33 @@ void CacheDictionary::getItemsString( /// Request new values sync. /// We have request both cache_not_found_ids and cache_expired_ids. - if (!cache_not_found_ids.empty()) + std::vector required_ids; + required_ids.reserve(cache_not_found_ids.size() + cache_expired_ids.size()); + std::transform( + std::begin(cache_not_found_ids), std::end(cache_not_found_ids), + std::back_inserter(required_ids), [](auto & pair) { return pair.first; }); + std::transform( + std::begin(cache_expired_ids), std::end(cache_expired_ids), + std::back_inserter(required_ids), [](auto & pair) { return pair.first; }); + + auto on_cell_updated = [&] (const auto id, const auto cell_idx) { - std::vector required_ids; - required_ids.reserve(cache_not_found_ids.size() + cache_expired_ids.size()); - std::transform( - std::begin(cache_not_found_ids), std::end(cache_not_found_ids), - std::back_inserter(required_ids), [](auto & pair) { return pair.first; }); - std::transform( - std::begin(cache_expired_ids), std::end(cache_expired_ids), - std::back_inserter(required_ids), [](auto & pair) { return pair.first; }); + const auto attribute_value = attribute_array[cell_idx]; - auto on_cell_updated = [&] (const auto id, const auto cell_idx) - { - const auto attribute_value = attribute_array[cell_idx]; + map[id] = String{attribute_value}; + total_length += (attribute_value.size + 1) * cache_not_found_ids[id].size(); + }; - map[id] = String{attribute_value}; - total_length += (attribute_value.size + 1) * cache_not_found_ids[id].size(); - }; + auto on_id_not_found = [&] (const auto id, const auto) + { + for (const auto row : cache_not_found_ids[id]) + total_length += get_default(row).size + 1; + }; - auto on_id_not_found = [&] (const auto id, const auto) - { - for (const auto row : cache_not_found_ids[id]) - total_length += get_default(row).size + 1; - }; - - auto update_unit_ptr = std::make_shared(required_ids, on_cell_updated, on_id_not_found); - - tryPushToUpdateQueueOrThrow(update_unit_ptr); - waitForCurrentUpdateFinish(update_unit_ptr); - } + auto update_unit_ptr = std::make_shared(required_ids, on_cell_updated, on_id_not_found); + tryPushToUpdateQueueOrThrow(update_unit_ptr); + waitForCurrentUpdateFinish(update_unit_ptr); out->getChars().reserve(total_length); for (const auto row : ext::range(0, ext::size(ids))) diff --git a/src/Dictionaries/ya.make b/src/Dictionaries/ya.make index e47b55d5254..e30a22a372c 100644 --- a/src/Dictionaries/ya.make +++ b/src/Dictionaries/ya.make @@ -24,8 +24,8 @@ SRCS( ComplexKeyCacheDictionary_generate3.cpp ComplexKeyCacheDictionary_setAttributeValue.cpp ComplexKeyCacheDictionary_setDefaultAttributeValue.cpp - ComplexKeyHashedDictionary.cpp ComplexKeyDirectDictionary.cpp + ComplexKeyHashedDictionary.cpp DictionaryBlockInputStreamBase.cpp DictionaryFactory.cpp DictionarySourceFactory.cpp diff --git a/src/Formats/ProtobufReader.cpp b/src/Formats/ProtobufReader.cpp index d8302771002..d76b048c1e9 100644 --- a/src/Formats/ProtobufReader.cpp +++ b/src/Formats/ProtobufReader.cpp @@ -32,11 +32,12 @@ namespace BITS32 = 5, }; - // The following condition must always be true: - // any_cursor_position < min(END_OF_VARINT, END_OF_GROUP) - // This inequation helps to check conditions in SimpleReader. - constexpr UInt64 END_OF_VARINT = static_cast(-1); - constexpr UInt64 END_OF_GROUP = static_cast(-2); + // The following conditions must always be true: + // any_cursor_position > END_OF_VARINT + // any_cursor_position > END_OF_GROUP + // Those inequations helps checking conditions in ProtobufReader::SimpleReader. + constexpr Int64 END_OF_VARINT = -1; + constexpr Int64 END_OF_GROUP = -2; Int64 decodeZigZag(UInt64 n) { return static_cast((n >> 1) ^ (~(n & 1) + 1)); } @@ -77,7 +78,7 @@ void ProtobufReader::SimpleReader::endMessage(bool ignore_errors) if (!current_message_level) return; - UInt64 root_message_end = (current_message_level == 1) ? current_message_end : parent_message_ends.front(); + Int64 root_message_end = (current_message_level == 1) ? current_message_end : parent_message_ends.front(); if (cursor != root_message_end) { if (cursor < root_message_end) @@ -95,6 +96,9 @@ void ProtobufReader::SimpleReader::endMessage(bool ignore_errors) void ProtobufReader::SimpleReader::startNestedMessage() { assert(current_message_level >= 1); + if ((cursor > field_end) && (field_end != END_OF_GROUP)) + throwUnknownFormat(); + // Start reading a nested message which is located inside a length-delimited field // of another message. parent_message_ends.emplace_back(current_message_end); @@ -146,7 +150,7 @@ bool ProtobufReader::SimpleReader::readFieldNumber(UInt32 & field_number) throwUnknownFormat(); } - if (cursor >= current_message_end) + if ((cursor >= current_message_end) && (current_message_end != END_OF_GROUP)) return false; UInt64 varint = readVarint(); @@ -196,11 +200,17 @@ bool ProtobufReader::SimpleReader::readFieldNumber(UInt32 & field_number) bool ProtobufReader::SimpleReader::readUInt(UInt64 & value) { + if (field_end == END_OF_VARINT) + { + value = readVarint(); + field_end = cursor; + return true; + } + if (unlikely(cursor >= field_end)) return false; + value = readVarint(); - if (field_end == END_OF_VARINT) - field_end = cursor; return true; } @@ -227,6 +237,7 @@ bool ProtobufReader::SimpleReader::readFixed(T & value) { if (unlikely(cursor >= field_end)) return false; + readBinary(&value, sizeof(T)); return true; } diff --git a/src/Formats/ProtobufReader.h b/src/Formats/ProtobufReader.h index a50c2f202f0..7c3c19ba376 100644 --- a/src/Formats/ProtobufReader.h +++ b/src/Formats/ProtobufReader.h @@ -124,12 +124,12 @@ private: void ignoreGroup(); ReadBuffer & in; - UInt64 cursor; + Int64 cursor; size_t current_message_level; - UInt64 current_message_end; - std::vector parent_message_ends; - UInt64 field_end; - UInt64 last_string_pos; + Int64 current_message_end; + std::vector parent_message_ends; + Int64 field_end; + Int64 last_string_pos; }; class IConverter diff --git a/src/Functions/FunctionJoinGet.cpp b/src/Functions/FunctionJoinGet.cpp index d6be2469759..a4569684e7f 100644 --- a/src/Functions/FunctionJoinGet.cpp +++ b/src/Functions/FunctionJoinGet.cpp @@ -43,7 +43,7 @@ static auto getJoin(const ColumnsWithTypeAndName & arguments, const Context & co ++dot; } String table_name = join_name.substr(dot); - auto table = DatabaseCatalog::instance().getTable({database_name, table_name}); + auto table = DatabaseCatalog::instance().getTable({database_name, table_name}, context); auto storage_join = std::dynamic_pointer_cast(table); if (!storage_join) throw Exception{"Table " + join_name + " should have engine StorageJoin", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT}; diff --git a/src/Functions/URL/port.cpp b/src/Functions/URL/port.cpp new file mode 100644 index 00000000000..e703da2602b --- /dev/null +++ b/src/Functions/URL/port.cpp @@ -0,0 +1,129 @@ +#include +#include +#include +#include +#include +#include +#include +#include "domain.h" + + +namespace DB +{ + +namespace ErrorCodes +{ + extern const int ILLEGAL_COLUMN; + extern const int ILLEGAL_TYPE_OF_ARGUMENT; + extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH; +} + +struct FunctionPort : public IFunction +{ + static constexpr auto name = "port"; + static FunctionPtr create(const Context &) { return std::make_shared(); } + + String getName() const override { return name; } + bool isVariadic() const override { return true; } + size_t getNumberOfArguments() const override { return 0; } + bool useDefaultImplementationForConstants() const override { return true; } + ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {1}; } + + DataTypePtr getReturnTypeImpl(const ColumnsWithTypeAndName & arguments) const override + { + if (arguments.size() != 1 && arguments.size() != 2) + throw Exception("Number of arguments for function " + getName() + " doesn't match: passed " + + std::to_string(arguments.size()) + ", should be 1 or 2", + ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + + if (!WhichDataType(arguments[0].type).isString()) + throw Exception("Illegal type " + arguments[0].type->getName() + " of first argument of function " + getName() + ". Must be String.", + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + + if (arguments.size() == 2 && !WhichDataType(arguments[1].type).isUInt16()) + throw Exception("Illegal type " + arguments[1].type->getName() + " of second argument of function " + getName() + ". Must be UInt16.", + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + + return std::make_shared(); + } + + + void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t) override + { + UInt16 default_port = 0; + if (arguments.size() == 2) + { + const auto * port_column = checkAndGetColumn(block.getByPosition(arguments[1]).column.get()); + if (!port_column) + throw Exception("Second argument for function " + getName() + " must be constant UInt16", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + default_port = port_column->getValue(); + } + + const ColumnPtr url_column = block.getByPosition(arguments[0]).column; + if (const ColumnString * url_strs = checkAndGetColumn(url_column.get())) + { + auto col_res = ColumnVector::create(); + typename ColumnVector::Container & vec_res = col_res->getData(); + vec_res.resize(url_column->size()); + + vector(default_port, url_strs->getChars(), url_strs->getOffsets(), vec_res); + block.getByPosition(result).column = std::move(col_res); + } + else + throw Exception( + "Illegal column " + block.getByPosition(arguments[0]).column->getName() + " of argument of function " + getName(), + ErrorCodes::ILLEGAL_COLUMN); +} + +private: + static void vector(UInt16 default_port, const ColumnString::Chars & data, const ColumnString::Offsets & offsets, PaddedPODArray & res) + { + size_t size = offsets.size(); + + ColumnString::Offset prev_offset = 0; + for (size_t i = 0; i < size; ++i) + { + res[i] = extractPort(default_port, data, prev_offset, offsets[i] - prev_offset - 1); + prev_offset = offsets[i]; + } +} + + static UInt16 extractPort(UInt16 default_port, const ColumnString::Chars & buf, size_t offset, size_t size) + { + const char * p = reinterpret_cast(&buf[0]) + offset; + const char * end = p + size; + + StringRef host = getURLHost(p, size); + if (!host.size) + return default_port; + if (host.size == size) + return default_port; + + p = host.data + host.size; + if (*p++ != ':') + return default_port; + + Int64 port = default_port; + while (p < end) + { + if (*p == '/') + break; + if (!isNumericASCII(*p)) + return default_port; + + port = (port * 10) + (*p - '0'); + if (port < 0 || port > UInt16(-1)) + return default_port; + ++p; + } + return port; + } +}; + +void registerFunctionPort(FunctionFactory & factory) +{ + factory.registerFunction(); +} + +} + diff --git a/src/Functions/URL/registerFunctionsURL.cpp b/src/Functions/URL/registerFunctionsURL.cpp index 66a847185f3..9ba5261f728 100644 --- a/src/Functions/URL/registerFunctionsURL.cpp +++ b/src/Functions/URL/registerFunctionsURL.cpp @@ -8,6 +8,7 @@ void registerFunctionDomain(FunctionFactory & factory); void registerFunctionDomainWithoutWWW(FunctionFactory & factory); void registerFunctionFirstSignificantSubdomain(FunctionFactory & factory); void registerFunctionTopLevelDomain(FunctionFactory & factory); +void registerFunctionPort(FunctionFactory & factory); void registerFunctionPath(FunctionFactory & factory); void registerFunctionPathFull(FunctionFactory & factory); void registerFunctionQueryString(FunctionFactory & factory); @@ -33,6 +34,7 @@ void registerFunctionsURL(FunctionFactory & factory) registerFunctionDomainWithoutWWW(factory); registerFunctionFirstSignificantSubdomain(factory); registerFunctionTopLevelDomain(factory); + registerFunctionPort(factory); registerFunctionPath(factory); registerFunctionPathFull(factory); registerFunctionQueryString(factory); diff --git a/src/Functions/array/arrayDistinct.cpp b/src/Functions/array/arrayDistinct.cpp index d24de638865..bb26567e8a5 100644 --- a/src/Functions/array/arrayDistinct.cpp +++ b/src/Functions/array/arrayDistinct.cpp @@ -153,10 +153,8 @@ bool FunctionArrayDistinct::executeNumber( if (nullable_col) src_null_map = &nullable_col->getNullMapData(); - using Set = ClearableHashSet, - HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(T)>>; + using Set = ClearableHashSetWithStackMemory, + INITIAL_SIZE_DEGREE>; Set set; @@ -201,10 +199,8 @@ bool FunctionArrayDistinct::executeString( ColumnString & res_data_column_string = typeid_cast(res_data_col); - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using Set = ClearableHashSetWithStackMemory; const PaddedPODArray * src_null_map = nullptr; @@ -249,8 +245,8 @@ void FunctionArrayDistinct::executeHashed( ColumnArray::Offsets & res_offsets, const ColumnNullable * nullable_col) { - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Set = ClearableHashSetWithStackMemory; const PaddedPODArray * src_null_map = nullptr; diff --git a/src/Functions/array/arrayEnumerateExtended.h b/src/Functions/array/arrayEnumerateExtended.h index 69db59e698e..e2f83ae8826 100644 --- a/src/Functions/array/arrayEnumerateExtended.h +++ b/src/Functions/array/arrayEnumerateExtended.h @@ -64,36 +64,41 @@ private: template struct MethodOneNumber { - using Set = ClearableHashMap, HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(T)>>; + using Set = ClearableHashMapWithStackMemory, + INITIAL_SIZE_DEGREE>; + using Method = ColumnsHashing::HashMethodOneNumber; }; struct MethodString { - using Set = ClearableHashMap, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using Set = ClearableHashMapWithStackMemory; + using Method = ColumnsHashing::HashMethodString; }; struct MethodFixedString { - using Set = ClearableHashMap, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using Set = ClearableHashMapWithStackMemory; + using Method = ColumnsHashing::HashMethodFixedString; }; struct MethodFixed { - using Set = ClearableHashMap, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Set = ClearableHashMapWithStackMemory; + using Method = ColumnsHashing::HashMethodKeysFixed; }; struct MethodHashed { - using Set = ClearableHashMap, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Set = ClearableHashMapWithStackMemory; + using Method = ColumnsHashing::HashMethodHashed; }; diff --git a/src/Functions/array/arrayEnumerateRanked.h b/src/Functions/array/arrayEnumerateRanked.h index 133f5d7cb81..c021b5fbfd1 100644 --- a/src/Functions/array/arrayEnumerateRanked.h +++ b/src/Functions/array/arrayEnumerateRanked.h @@ -308,12 +308,9 @@ void FunctionArrayEnumerateRankedExtended::executeMethodImpl( const size_t depth_to_look = arrays_depths.max_array_depth; const auto & offsets = *offsets_by_depth[depth_to_look - 1]; - using Map = ClearableHashMap< - UInt128, - UInt32, - UInt128TrivialHash, - HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Map = ClearableHashMapWithStackMemory; + Map indices; std::vector indices_by_depth(depth_to_look); diff --git a/src/Functions/array/arrayIntersect.cpp b/src/Functions/array/arrayIntersect.cpp index cccad7c7a03..24db3c0cd08 100644 --- a/src/Functions/array/arrayIntersect.cpp +++ b/src/Functions/array/arrayIntersect.cpp @@ -418,16 +418,15 @@ void FunctionArrayIntersect::executeImpl(Block & block, const ColumnNumbers & ar TypeListNativeNumbers::forEach(NumberExecutor(arrays, not_nullable_nested_return_type, result_column)); TypeListDecimalNumbers::forEach(DecimalExecutor(arrays, not_nullable_nested_return_type, result_column)); - using DateMap = ClearableHashMap, - HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(DataTypeDate::FieldType)>>; + using DateMap = ClearableHashMapWithStackMemory, INITIAL_SIZE_DEGREE>; - using DateTimeMap = ClearableHashMap, - HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(DataTypeDateTime::FieldType)>>; + using DateTimeMap = ClearableHashMapWithStackMemory< + DataTypeDateTime::FieldType, size_t, + DefaultHash, INITIAL_SIZE_DEGREE>; - using StringMap = ClearableHashMap, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using StringMap = ClearableHashMapWithStackMemory; if (!result_column) { @@ -455,8 +454,8 @@ void FunctionArrayIntersect::executeImpl(Block & block, const ColumnNumbers & ar template void FunctionArrayIntersect::NumberExecutor::operator()() { - using Map = ClearableHashMap, HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(T)>>; + using Map = ClearableHashMapWithStackMemory, + INITIAL_SIZE_DEGREE>; if (!result && typeid_cast *>(data_type.get())) result = execute, true>(arrays, ColumnVector::create()); @@ -465,8 +464,8 @@ void FunctionArrayIntersect::NumberExecutor::operator()() template void FunctionArrayIntersect::DecimalExecutor::operator()() { - using Map = ClearableHashMap, HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(T)>>; + using Map = ClearableHashMapWithStackMemory, + INITIAL_SIZE_DEGREE>; if (!result) if (auto * decimal = typeid_cast *>(data_type.get())) diff --git a/src/Functions/array/arrayUniq.cpp b/src/Functions/array/arrayUniq.cpp index 02129781c13..d9a44f6d8d3 100644 --- a/src/Functions/array/arrayUniq.cpp +++ b/src/Functions/array/arrayUniq.cpp @@ -66,36 +66,41 @@ private: template struct MethodOneNumber { - using Set = ClearableHashSet, HashTableGrower, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(T)>>; + using Set = ClearableHashSetWithStackMemory, + INITIAL_SIZE_DEGREE>; + using Method = ColumnsHashing::HashMethodOneNumber; }; struct MethodString { - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using Set = ClearableHashSetWithStackMemory; + using Method = ColumnsHashing::HashMethodString; }; struct MethodFixedString { - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(StringRef)>>; + using Set = ClearableHashSetWithStackMemory; + using Method = ColumnsHashing::HashMethodFixedString; }; struct MethodFixed { - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Set = ClearableHashSetWithStackMemory; + using Method = ColumnsHashing::HashMethodKeysFixed; }; struct MethodHashed { - using Set = ClearableHashSet, - HashTableAllocatorWithStackMemory<(1ULL << INITIAL_SIZE_DEGREE) * sizeof(UInt128)>>; + using Set = ClearableHashSetWithStackMemory; + using Method = ColumnsHashing::HashMethodHashed; }; diff --git a/src/Functions/hasColumnInTable.cpp b/src/Functions/hasColumnInTable.cpp index 03e5a4513db..b9ec2b84837 100644 --- a/src/Functions/hasColumnInTable.cpp +++ b/src/Functions/hasColumnInTable.cpp @@ -113,7 +113,7 @@ void FunctionHasColumnInTable::executeImpl(Block & block, const ColumnNumbers & bool has_column; if (host_name.empty()) { - const StoragePtr & table = DatabaseCatalog::instance().getTable({database_name, table_name}); + const StoragePtr & table = DatabaseCatalog::instance().getTable({database_name, table_name}, global_context); has_column = table->getColumns().hasPhysical(column_name); } else diff --git a/src/Functions/ya.make b/src/Functions/ya.make index ddb1d27b398..bbbf13d360b 100644 --- a/src/Functions/ya.make +++ b/src/Functions/ya.make @@ -171,7 +171,6 @@ SRCS( FunctionsRound.cpp FunctionsStringArray.cpp FunctionsStringSimilarity.cpp - FunctionUnixTimestamp64.h GatherUtils/concat.cpp GatherUtils/createArraySink.cpp GatherUtils/createArraySource.cpp @@ -285,10 +284,10 @@ SRCS( rand64.cpp randConstant.cpp rand.cpp + randomFixedString.cpp randomPrintableASCII.cpp randomString.cpp randomStringUTF8.cpp - randomFixedString.cpp regexpQuoteMeta.cpp registerFunctionsArithmetic.cpp registerFunctionsComparison.cpp @@ -308,8 +307,8 @@ SRCS( registerFunctionsStringRegexp.cpp registerFunctionsStringSearch.cpp registerFunctionsTuple.cpp - registerFunctionsVisitParam.cpp registerFunctionsUnixTimestamp64.cpp + registerFunctionsVisitParam.cpp reinterpretAsFixedString.cpp reinterpretAsString.cpp reinterpretStringAs.cpp @@ -390,10 +389,10 @@ SRCS( toTime.cpp toTimeZone.cpp toTypeName.cpp - toValidUTF8.cpp toUnixTimestamp64Micro.cpp toUnixTimestamp64Milli.cpp toUnixTimestamp64Nano.cpp + toValidUTF8.cpp toYear.cpp toYYYYMM.cpp toYYYYMMDD.cpp @@ -424,6 +423,7 @@ SRCS( URL/fragment.cpp URL/path.cpp URL/pathFull.cpp + URL/port.cpp URL/protocol.cpp URL/queryStringAndFragment.cpp URL/queryString.cpp diff --git a/src/IO/ReadHelpers.cpp b/src/IO/ReadHelpers.cpp index dccb413af2c..9d1d27611b5 100644 --- a/src/IO/ReadHelpers.cpp +++ b/src/IO/ReadHelpers.cpp @@ -283,7 +283,9 @@ static void parseComplexEscapeSequence(Vector & s, ReadBuffer & buf) if (buf.eof()) throw Exception("Cannot parse escape sequence", ErrorCodes::CANNOT_PARSE_ESCAPE_SEQUENCE); - if (*buf.position() == 'x') + char char_after_backslash = *buf.position(); + + if (char_after_backslash == 'x') { ++buf.position(); /// escape sequence of the form \xAA @@ -291,7 +293,7 @@ static void parseComplexEscapeSequence(Vector & s, ReadBuffer & buf) readPODBinary(hex_code, buf); s.push_back(unhex2(hex_code)); } - else if (*buf.position() == 'N') + else if (char_after_backslash == 'N') { /// Support for NULLs: \N sequence must be parsed as empty string. ++buf.position(); @@ -299,7 +301,22 @@ static void parseComplexEscapeSequence(Vector & s, ReadBuffer & buf) else { /// The usual escape sequence of a single character. - s.push_back(parseEscapeSequence(*buf.position())); + char decoded_char = parseEscapeSequence(char_after_backslash); + + /// For convenience using LIKE and regular expressions, + /// we leave backslash when user write something like 'Hello 100\%': + /// it is parsed like Hello 100\% instead of Hello 100% + if (decoded_char != '\\' + && decoded_char != '\'' + && decoded_char != '"' + && decoded_char != '`' /// MySQL style identifiers + && decoded_char != '/' /// JavaScript in HTML + && !isControlASCII(decoded_char)) + { + s.push_back('\\'); + } + + s.push_back(decoded_char); ++buf.position(); } } @@ -633,7 +650,6 @@ void readCSVStringInto(Vector & s, ReadBuffer & buf, const FormatSettings::CSV & ++next_pos; }(); - appendToStringOrVector(s, buf, next_pos); buf.position() = next_pos; diff --git a/src/IO/tests/CMakeLists.txt b/src/IO/tests/CMakeLists.txt index 2767ce6e271..dfbbfa77853 100644 --- a/src/IO/tests/CMakeLists.txt +++ b/src/IO/tests/CMakeLists.txt @@ -37,9 +37,6 @@ target_link_libraries (parse_int_perf2 PRIVATE clickhouse_common_io) add_executable (read_write_int read_write_int.cpp) target_link_libraries (read_write_int PRIVATE clickhouse_common_io) -add_executable (mempbrk mempbrk.cpp) -target_link_libraries (mempbrk PRIVATE clickhouse_common_io) - add_executable (o_direct_and_dirty_pages o_direct_and_dirty_pages.cpp) target_link_libraries (o_direct_and_dirty_pages PRIVATE clickhouse_common_io) diff --git a/src/IO/tests/mempbrk.cpp b/src/IO/tests/mempbrk.cpp deleted file mode 100644 index 55097d989af..00000000000 --- a/src/IO/tests/mempbrk.cpp +++ /dev/null @@ -1,90 +0,0 @@ -#include -#include -#include - -#include - -#include -#include -#include -#include -#include - -#include - -namespace DB -{ -namespace ErrorCodes -{ - extern const int CANNOT_PARSE_ESCAPE_SEQUENCE; -} -} - - -namespace test -{ -static void readEscapedString(DB::String & s, DB::ReadBuffer & buf) - { - s = ""; - while (!buf.eof()) - { - const char * next_pos = find_first_symbols<'\b', '\f', '\n', '\r', '\t', '\0', '\\'>(buf.position(), buf.buffer().end()); - - s.append(buf.position(), next_pos - buf.position()); - buf.position() += next_pos - buf.position(); - - if (!buf.hasPendingData()) - continue; - - if (*buf.position() == '\t' || *buf.position() == '\n') - return; - - if (*buf.position() == '\\') - { - ++buf.position(); - if (buf.eof()) - throw DB::Exception("Cannot parse escape sequence", DB::ErrorCodes::CANNOT_PARSE_ESCAPE_SEQUENCE); - s += DB::parseEscapeSequence(*buf.position()); - ++buf.position(); - } - } - } -} - - -int main(int, char **) -{ - try - { - DB::ReadBufferFromFileDescriptor in(STDIN_FILENO); -// DB::WriteBufferFromFileDescriptor out(STDOUT_FILENO); - std::string s; - size_t rows = 0; - - Stopwatch watch; - - while (!in.eof()) - { - test::readEscapedString(s, in); - in.ignore(); - - ++rows; - -/* DB::writeEscapedString(s, out); - DB::writeChar('\n', out);*/ - } - - watch.stop(); - std::cerr << std::fixed << std::setprecision(2) - << "Read " << rows << " rows (" << in.count() / 1000000.0 << " MB) in " << watch.elapsedSeconds() << " sec., " - << rows / watch.elapsedSeconds() << " rows/sec. (" << in.count() / watch.elapsedSeconds() / 1000000 << " MB/s.)" - << std::endl; - } - catch (const DB::Exception & e) - { - std::cerr << e.what() << ", " << e.displayText() << std::endl; - return 1; - } - - return 0; -} diff --git a/src/Interpreters/ActionLocksManager.cpp b/src/Interpreters/ActionLocksManager.cpp index fe5b3def658..e8887f44a45 100644 --- a/src/Interpreters/ActionLocksManager.cpp +++ b/src/Interpreters/ActionLocksManager.cpp @@ -19,23 +19,28 @@ namespace ActionLocks } +ActionLocksManager::ActionLocksManager(const Context & context) + : global_context(context.getGlobalContext()) +{ +} + template -inline void forEachTable(F && f) +inline void forEachTable(F && f, const Context & context) { for (auto & elem : DatabaseCatalog::instance().getDatabases()) - for (auto iterator = elem.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = elem.second->getTablesIterator(context); iterator->isValid(); iterator->next()) f(iterator->table()); } -void ActionLocksManager::add(StorageActionBlockType action_type) +void ActionLocksManager::add(StorageActionBlockType action_type, const Context & context) { - forEachTable([&](const StoragePtr & table) { add(table, action_type); }); + forEachTable([&](const StoragePtr & table) { add(table, action_type); }, context); } void ActionLocksManager::add(const StorageID & table_id, StorageActionBlockType action_type) { - if (auto table = DatabaseCatalog::instance().tryGetTable(table_id)) + if (auto table = DatabaseCatalog::instance().tryGetTable(table_id, global_context)) add(table, action_type); } @@ -60,7 +65,7 @@ void ActionLocksManager::remove(StorageActionBlockType action_type) void ActionLocksManager::remove(const StorageID & table_id, StorageActionBlockType action_type) { - if (auto table = DatabaseCatalog::instance().tryGetTable(table_id)) + if (auto table = DatabaseCatalog::instance().tryGetTable(table_id, global_context)) remove(table, action_type); } diff --git a/src/Interpreters/ActionLocksManager.h b/src/Interpreters/ActionLocksManager.h index 039a95ce218..ea5d96ad8ce 100644 --- a/src/Interpreters/ActionLocksManager.h +++ b/src/Interpreters/ActionLocksManager.h @@ -19,8 +19,10 @@ class Context; class ActionLocksManager { public: + ActionLocksManager(const Context & context); + /// Adds new locks for each table - void add(StorageActionBlockType action_type); + void add(StorageActionBlockType action_type, const Context & context); /// Add new lock for a table if it has not been already added void add(const StorageID & table_id, StorageActionBlockType action_type); void add(const StoragePtr & table, StorageActionBlockType action_type); @@ -41,6 +43,7 @@ private: mutable std::mutex mutex; StorageLocks storage_locks; + const Context & global_context; }; } diff --git a/src/Interpreters/ActionsVisitor.cpp b/src/Interpreters/ActionsVisitor.cpp index 7c2133e629f..b5d9f30573e 100644 --- a/src/Interpreters/ActionsVisitor.cpp +++ b/src/Interpreters/ActionsVisitor.cpp @@ -670,7 +670,7 @@ SetPtr ActionsMatcher::makeSet(const ASTFunction & node, Data & data, bool no_su if (identifier) { auto table_id = data.context.resolveStorageID(right_in_operand); - StoragePtr table = DatabaseCatalog::instance().tryGetTable(table_id); + StoragePtr table = DatabaseCatalog::instance().tryGetTable(table_id, data.context); if (table) { @@ -706,7 +706,7 @@ SetPtr ActionsMatcher::makeSet(const ASTFunction & node, Data & data, bool no_su { auto interpreter = interpretSubquery(right_in_operand, data.context, data.subquery_depth, {}); subquery_for_set.source = std::make_shared( - interpreter->getSampleBlock(), [interpreter]() mutable { return interpreter->execute().in; }); + interpreter->getSampleBlock(), [interpreter]() mutable { return interpreter->execute().getInputStream(); }); /** Why is LazyBlockInputStream used? * diff --git a/src/Interpreters/AsynchronousMetrics.cpp b/src/Interpreters/AsynchronousMetrics.cpp index 59ff01bf972..a4e03d35d42 100644 --- a/src/Interpreters/AsynchronousMetrics.cpp +++ b/src/Interpreters/AsynchronousMetrics.cpp @@ -181,7 +181,7 @@ void AsynchronousMetrics::update() /// Lazy database can not contain MergeTree tables if (db.second->getEngineName() == "Lazy") continue; - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { ++total_number_of_tables; const auto & table = iterator->table(); diff --git a/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp b/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp index 53c61bea60e..5460b4b3286 100644 --- a/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp +++ b/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp @@ -15,6 +15,7 @@ #include #include #include +#include namespace ProfileEvents { @@ -70,35 +71,14 @@ SelectStreamFactory::SelectStreamFactory( namespace { -Pipe createLocalStream( - const ASTPtr & query_ast, const Block & header, const Context & context, QueryProcessingStage::Enum processed_stage, - bool add_totals_port, bool add_extremes_port, bool force_tree_shaped_pipeline) +QueryPipeline createLocalStream( + const ASTPtr & query_ast, const Block & header, const Context & context, QueryProcessingStage::Enum processed_stage) { checkStackSize(); InterpreterSelectQuery interpreter{query_ast, context, SelectQueryOptions(processed_stage)}; - if (force_tree_shaped_pipeline) - { - /// This flag means that pipeline must be tree-shaped, - /// so we can't enable processors for InterpreterSelectQuery here. - auto stream = interpreter.execute().in; - auto source = std::make_shared(std::move(stream)); - - if (add_totals_port) - source->addTotalsPort(); - if (add_extremes_port) - source->addExtremesPort(); - - Pipe pipe(std::move(source)); - - pipe.addSimpleTransform(std::make_shared( - pipe.getHeader(), header, ConvertingTransform::MatchColumnsMode::Name)); - - return pipe; - } - - auto pipeline = interpreter.executeWithProcessors(); + auto pipeline = interpreter.execute().pipeline; pipeline.addSimpleTransform([&](const Block & source_header) { @@ -116,7 +96,8 @@ Pipe createLocalStream( */ /// return std::make_shared(stream); - return std::move(pipeline).getPipe(); + pipeline.setMaxThreads(1); + return pipeline; } String formattedAST(const ASTPtr & ast) @@ -134,7 +115,7 @@ void SelectStreamFactory::createForShard( const Cluster::ShardInfo & shard_info, const String &, const ASTPtr & query_ast, const Context & context, const ThrottlerPtr & throttler, - const SelectQueryInfo & query_info, + const SelectQueryInfo &, Pipes & res) { bool force_add_agg_info = processed_stage == QueryProcessingStage::WithMergeableState; @@ -152,8 +133,7 @@ void SelectStreamFactory::createForShard( auto emplace_local_stream = [&]() { - res.emplace_back(createLocalStream(modified_query_ast, header, context, processed_stage, - add_totals_port, add_extremes_port, query_info.force_tree_shaped_pipeline)); + res.emplace_back(createLocalStream(modified_query_ast, header, context, processed_stage).getPipe()); }; String modified_query = formattedAST(modified_query_ast); @@ -191,7 +171,7 @@ void SelectStreamFactory::createForShard( else { auto resolved_id = context.resolveStorageID(main_table); - main_table_storage = DatabaseCatalog::instance().tryGetTable(resolved_id); + main_table_storage = DatabaseCatalog::instance().tryGetTable(resolved_id, context); } @@ -266,7 +246,7 @@ void SelectStreamFactory::createForShard( auto lazily_create_stream = [ pool = shard_info.pool, shard_num = shard_info.shard_num, modified_query, header = header, modified_query_ast, context, throttler, main_table = main_table, table_func_ptr = table_func_ptr, scalars = scalars, external_tables = external_tables, - stage = processed_stage, local_delay, add_totals_port, add_extremes_port]() + stage = processed_stage, local_delay]() -> BlockInputStreamPtr { auto current_settings = context.getSettingsRef(); @@ -297,8 +277,8 @@ void SelectStreamFactory::createForShard( } if (try_results.empty() || local_delay < max_remote_delay) - return std::make_shared( - createLocalStream(modified_query_ast, header, context, stage, add_totals_port, add_extremes_port, true)); + return std::make_shared( + createLocalStream(modified_query_ast, header, context, stage)); else { std::vector connections; diff --git a/src/Interpreters/Context.cpp b/src/Interpreters/Context.cpp index 4605c606594..9c78fe59da1 100644 --- a/src/Interpreters/Context.cpp +++ b/src/Interpreters/Context.cpp @@ -2017,7 +2017,7 @@ std::shared_ptr Context::getActionLocksManager() auto lock = getLock(); if (!shared->action_locks_manager) - shared->action_locks_manager = std::make_shared(); + shared->action_locks_manager = std::make_shared(*this); return shared->action_locks_manager; } diff --git a/src/Interpreters/DDLWorker.cpp b/src/Interpreters/DDLWorker.cpp index fefeeeed988..ee91d903416 100644 --- a/src/Interpreters/DDLWorker.cpp +++ b/src/Interpreters/DDLWorker.cpp @@ -634,7 +634,7 @@ void DDLWorker::processTask(DDLTask & task, const ZooKeeperPtr & zookeeper) { /// It's not CREATE DATABASE auto table_id = context.tryResolveStorageID(*query_with_table, Context::ResolveOrdinary); - storage = DatabaseCatalog::instance().tryGetTable(table_id); + storage = DatabaseCatalog::instance().tryGetTable(table_id, context); } /// For some reason we check consistency of cluster definition only diff --git a/src/Interpreters/DatabaseCatalog.cpp b/src/Interpreters/DatabaseCatalog.cpp index 7606fdb255a..4871d8d37aa 100644 --- a/src/Interpreters/DatabaseCatalog.cpp +++ b/src/Interpreters/DatabaseCatalog.cpp @@ -58,13 +58,17 @@ TemporaryTableHolder::TemporaryTableHolder(const Context & context_, } -TemporaryTableHolder::TemporaryTableHolder(const Context & context_, const ColumnsDescription & columns, const ASTPtr & query) +TemporaryTableHolder::TemporaryTableHolder( + const Context & context_, + const ColumnsDescription & columns, + const ConstraintsDescription & constraints, + const ASTPtr & query) : TemporaryTableHolder ( context_, [&](const StorageID & table_id) { - return StorageMemory::create(table_id, ColumnsDescription{columns}, ConstraintsDescription{}); + return StorageMemory::create(table_id, ColumnsDescription{columns}, ConstraintsDescription{constraints}); }, query ) @@ -97,7 +101,7 @@ StorageID TemporaryTableHolder::getGlobalTableID() const StoragePtr TemporaryTableHolder::getTable() const { - auto table = temporary_tables->tryGetTable("_tmp_" + toString(id)); + auto table = temporary_tables->tryGetTable("_tmp_" + toString(id), *global_context); if (!table) throw Exception("Temporary table " + getGlobalTableID().getNameForLogs() + " not found", ErrorCodes::LOGICAL_ERROR); return table; @@ -108,7 +112,7 @@ void DatabaseCatalog::loadDatabases() { drop_delay_sec = global_context->getConfigRef().getInt("database_atomic_delay_before_drop_table_sec", default_drop_delay_sec); - auto db_for_temporary_and_external_tables = std::make_shared(TEMPORARY_DATABASE); + auto db_for_temporary_and_external_tables = std::make_shared(TEMPORARY_DATABASE, *global_context); attachDatabase(TEMPORARY_DATABASE, db_for_temporary_and_external_tables); loadMarkedAsDroppedTables(); @@ -159,6 +163,7 @@ DatabaseAndTable DatabaseCatalog::tryGetByUUID(const UUID & uuid) const DatabaseAndTable DatabaseCatalog::getTableImpl( const StorageID & table_id, + const Context & context, std::optional * exception) const { if (!table_id) @@ -206,7 +211,7 @@ DatabaseAndTable DatabaseCatalog::getTableImpl( database = it->second; } - auto table = database->tryGetTable(table_id.table_name); + auto table = database->tryGetTable(table_id.table_name, context); if (!table && exception) exception->emplace("Table " + table_id.getNameForLogs() + " doesn't exist.", ErrorCodes::UNKNOWN_TABLE); @@ -319,7 +324,7 @@ Databases DatabaseCatalog::getDatabases() const return databases; } -bool DatabaseCatalog::isTableExist(const DB::StorageID & table_id) const +bool DatabaseCatalog::isTableExist(const DB::StorageID & table_id, const Context & context) const { if (table_id.hasUUID()) return tryGetByUUID(table_id.uuid).second != nullptr; @@ -331,12 +336,12 @@ bool DatabaseCatalog::isTableExist(const DB::StorageID & table_id) const if (iter != databases.end()) db = iter->second; } - return db && db->isTableExist(table_id.table_name); + return db && db->isTableExist(table_id.table_name, context); } -void DatabaseCatalog::assertTableDoesntExist(const StorageID & table_id) const +void DatabaseCatalog::assertTableDoesntExist(const StorageID & table_id, const Context & context) const { - if (isTableExist(table_id)) + if (isTableExist(table_id, context)) throw Exception("Table " + table_id.getNameForLogs() + " already exists.", ErrorCodes::TABLE_ALREADY_EXISTS); } @@ -468,32 +473,32 @@ bool DatabaseCatalog::isDictionaryExist(const StorageID & table_id) const return db && db->isDictionaryExist(table_id.getTableName()); } -StoragePtr DatabaseCatalog::getTable(const StorageID & table_id) const +StoragePtr DatabaseCatalog::getTable(const StorageID & table_id, const Context & context) const { std::optional exc; - auto res = getTableImpl(table_id, &exc); + auto res = getTableImpl(table_id, context, &exc); if (!res.second) throw Exception(*exc); return res.second; } -StoragePtr DatabaseCatalog::tryGetTable(const StorageID & table_id) const +StoragePtr DatabaseCatalog::tryGetTable(const StorageID & table_id, const Context & context) const { - return getTableImpl(table_id, nullptr).second; + return getTableImpl(table_id, context, nullptr).second; } -DatabaseAndTable DatabaseCatalog::getDatabaseAndTable(const StorageID & table_id) const +DatabaseAndTable DatabaseCatalog::getDatabaseAndTable(const StorageID & table_id, const Context & context) const { std::optional exc; - auto res = getTableImpl(table_id, &exc); + auto res = getTableImpl(table_id, context, &exc); if (!res.second) throw Exception(*exc); return res; } -DatabaseAndTable DatabaseCatalog::tryGetDatabaseAndTable(const StorageID & table_id) const +DatabaseAndTable DatabaseCatalog::tryGetDatabaseAndTable(const StorageID & table_id, const Context & context) const { - return getTableImpl(table_id, nullptr); + return getTableImpl(table_id, context, nullptr); } void DatabaseCatalog::loadMarkedAsDroppedTables() diff --git a/src/Interpreters/DatabaseCatalog.h b/src/Interpreters/DatabaseCatalog.h index a481e3d7e5e..aefed0f372d 100644 --- a/src/Interpreters/DatabaseCatalog.h +++ b/src/Interpreters/DatabaseCatalog.h @@ -21,6 +21,7 @@ class Context; class IDatabase; class Exception; class ColumnsDescription; +struct ConstraintsDescription; using DatabasePtr = std::shared_ptr; using DatabaseAndTable = std::pair; @@ -71,7 +72,11 @@ struct TemporaryTableHolder : boost::noncopyable TemporaryTableHolder(const Context & context, const Creator & creator, const ASTPtr & query = {}); /// Creates temporary table with Engine=Memory - TemporaryTableHolder(const Context & context, const ColumnsDescription & columns, const ASTPtr & query = {}); + TemporaryTableHolder( + const Context & context, + const ColumnsDescription & columns, + const ConstraintsDescription & constraints, + const ASTPtr & query = {}); TemporaryTableHolder(TemporaryTableHolder && rhs); TemporaryTableHolder & operator = (TemporaryTableHolder && rhs); @@ -129,15 +134,17 @@ public: DatabasePtr getDatabase(const String & database_name, const Context & local_context) const; /// For all of the following methods database_name in table_id must be not empty (even for temporary tables). - void assertTableDoesntExist(const StorageID & table_id) const; - bool isTableExist(const StorageID & table_id) const; + void assertTableDoesntExist(const StorageID & table_id, const Context & context) const; + bool isTableExist(const StorageID & table_id, const Context & context) const; bool isDictionaryExist(const StorageID & table_id) const; - StoragePtr getTable(const StorageID & table_id) const; - StoragePtr tryGetTable(const StorageID & table_id) const; - DatabaseAndTable getDatabaseAndTable(const StorageID & table_id) const; - DatabaseAndTable tryGetDatabaseAndTable(const StorageID & table_id) const; - DatabaseAndTable getTableImpl(const StorageID & table_id, std::optional * exception = nullptr) const; + StoragePtr getTable(const StorageID & table_id, const Context & context) const; + StoragePtr tryGetTable(const StorageID & table_id, const Context & context) const; + DatabaseAndTable getDatabaseAndTable(const StorageID & table_id, const Context & context) const; + DatabaseAndTable tryGetDatabaseAndTable(const StorageID & table_id, const Context & context) const; + DatabaseAndTable getTableImpl(const StorageID & table_id, + const Context & context, + std::optional * exception = nullptr) const; void addDependency(const StorageID & from, const StorageID & where); void removeDependency(const StorageID & from, const StorageID & where); diff --git a/src/Interpreters/ExecuteScalarSubqueriesVisitor.cpp b/src/Interpreters/ExecuteScalarSubqueriesVisitor.cpp index 0e9be3c7a96..e2884d99516 100644 --- a/src/Interpreters/ExecuteScalarSubqueriesVisitor.cpp +++ b/src/Interpreters/ExecuteScalarSubqueriesVisitor.cpp @@ -111,11 +111,11 @@ void ExecuteScalarSubqueriesMatcher::visit(const ASTSubquery & subquery, ASTPtr } else { - BlockIO res = interpreter.execute(); + auto stream = interpreter.execute().getInputStream(); try { - block = res.in->read(); + block = stream->read(); if (!block) { @@ -126,7 +126,7 @@ void ExecuteScalarSubqueriesMatcher::visit(const ASTSubquery & subquery, ASTPtr return; } - if (block.rows() != 1 || res.in->read()) + if (block.rows() != 1 || stream->read()) throw Exception("Scalar subquery returned more than one row", ErrorCodes::INCORRECT_RESULT_OF_SCALAR_SUBQUERY); } catch (const Exception & e) diff --git a/src/Interpreters/ExpressionAnalyzer.cpp b/src/Interpreters/ExpressionAnalyzer.cpp index 3341855b8c6..b4988f00699 100644 --- a/src/Interpreters/ExpressionAnalyzer.cpp +++ b/src/Interpreters/ExpressionAnalyzer.cpp @@ -192,61 +192,65 @@ void ExpressionAnalyzer::analyzeAggregation() if (has_aggregation) { - getSelectQuery(); /// assertSelect() /// Find out aggregation keys. - if (select_query->groupBy()) + if (select_query) { - NameSet unique_keys; - ASTs & group_asts = select_query->groupBy()->children; - for (ssize_t i = 0; i < ssize_t(group_asts.size()); ++i) + if (select_query->groupBy()) { - ssize_t size = group_asts.size(); - getRootActionsNoMakeSet(group_asts[i], true, temp_actions, false); - - const auto & column_name = group_asts[i]->getColumnName(); - const auto & block = temp_actions->getSampleBlock(); - - if (!block.has(column_name)) - throw Exception("Unknown identifier (in GROUP BY): " + column_name, ErrorCodes::UNKNOWN_IDENTIFIER); - - const auto & col = block.getByName(column_name); - - /// Constant expressions have non-null column pointer at this stage. - if (col.column && isColumnConst(*col.column)) + NameSet unique_keys; + ASTs & group_asts = select_query->groupBy()->children; + for (ssize_t i = 0; i < ssize_t(group_asts.size()); ++i) { - /// But don't remove last key column if no aggregate functions, otherwise aggregation will not work. - if (!aggregate_descriptions.empty() || size > 1) + ssize_t size = group_asts.size(); + getRootActionsNoMakeSet(group_asts[i], true, temp_actions, false); + + const auto & column_name = group_asts[i]->getColumnName(); + const auto & block = temp_actions->getSampleBlock(); + + if (!block.has(column_name)) + throw Exception("Unknown identifier (in GROUP BY): " + column_name, ErrorCodes::UNKNOWN_IDENTIFIER); + + const auto & col = block.getByName(column_name); + + /// Constant expressions have non-null column pointer at this stage. + if (col.column && isColumnConst(*col.column)) { - if (i + 1 < static_cast(size)) - group_asts[i] = std::move(group_asts.back()); + /// But don't remove last key column if no aggregate functions, otherwise aggregation will not work. + if (!aggregate_descriptions.empty() || size > 1) + { + if (i + 1 < static_cast(size)) + group_asts[i] = std::move(group_asts.back()); - group_asts.pop_back(); + group_asts.pop_back(); - --i; - continue; + --i; + continue; + } + } + + NameAndTypePair key{column_name, col.type}; + + /// Aggregation keys are uniqued. + if (!unique_keys.count(key.name)) + { + unique_keys.insert(key.name); + aggregation_keys.push_back(key); + + /// Key is no longer needed, therefore we can save a little by moving it. + aggregated_columns.push_back(std::move(key)); } } - NameAndTypePair key{column_name, col.type}; - - /// Aggregation keys are uniqued. - if (!unique_keys.count(key.name)) + if (group_asts.empty()) { - unique_keys.insert(key.name); - aggregation_keys.push_back(key); - - /// Key is no longer needed, therefore we can save a little by moving it. - aggregated_columns.push_back(std::move(key)); + select_query->setExpression(ASTSelectQuery::Expression::GROUP_BY, {}); + has_aggregation = select_query->having() || !aggregate_descriptions.empty(); } } - - if (group_asts.empty()) - { - select_query->setExpression(ASTSelectQuery::Expression::GROUP_BY, {}); - has_aggregation = select_query->having() || !aggregate_descriptions.empty(); - } } + else + aggregated_columns = temp_actions->getSampleBlock().getNamesAndTypesList(); for (const auto & desc : aggregate_descriptions) aggregated_columns.emplace_back(desc.column_name, desc.function->getReturnType()); @@ -293,13 +297,13 @@ void SelectQueryExpressionAnalyzer::tryMakeSetForIndexFromSubquery(const ASTPtr } auto interpreter_subquery = interpretSubquery(subquery_or_table_name, context, {}, query_options); - BlockIO res = interpreter_subquery->execute(); + auto stream = interpreter_subquery->execute().getInputStream(); SetPtr set = std::make_shared(settings.size_limits_for_set, true, context.getSettingsRef().transform_null_in); - set->setHeader(res.in->getHeader()); + set->setHeader(stream->getHeader()); - res.in->readPrefix(); - while (Block block = res.in->read()) + stream->readPrefix(); + while (Block block = stream->read()) { /// If the limits have been exceeded, give up and let the default subquery processing actions take place. if (!set->insertFromBlock(block)) @@ -307,7 +311,7 @@ void SelectQueryExpressionAnalyzer::tryMakeSetForIndexFromSubquery(const ASTPtr } set->finishInsert(); - res.in->readSuffix(); + stream->readSuffix(); prepared_sets[set_key] = std::move(set); } @@ -318,7 +322,7 @@ SetPtr SelectQueryExpressionAnalyzer::isPlainStorageSetInSubquery(const ASTPtr & if (!table) return nullptr; auto table_id = context.resolveStorageID(subquery_or_table_name); - const auto storage = DatabaseCatalog::instance().getTable(table_id); + const auto storage = DatabaseCatalog::instance().getTable(table_id, context); if (storage->getName() != "Set") return nullptr; const auto storage_set = std::dynamic_pointer_cast(storage); @@ -926,7 +930,7 @@ void ExpressionAnalyzer::appendExpression(ExpressionActionsChain & chain, const ExpressionActionsPtr ExpressionAnalyzer::getActions(bool add_aliases, bool project_result) { - ExpressionActionsPtr actions = std::make_shared(sourceColumns(), context); + ExpressionActionsPtr actions = std::make_shared(aggregated_columns, context); NamesWithAliases result_columns; Names result_names; diff --git a/src/Interpreters/GlobalSubqueriesVisitor.h b/src/Interpreters/GlobalSubqueriesVisitor.h index 37a358c3d28..041d26a3d58 100644 --- a/src/Interpreters/GlobalSubqueriesVisitor.h +++ b/src/Interpreters/GlobalSubqueriesVisitor.h @@ -103,7 +103,7 @@ public: Block sample = interpreter->getSampleBlock(); NamesAndTypesList columns = sample.getNamesAndTypesList(); - auto external_storage_holder = std::make_shared(context, ColumnsDescription{columns}); + auto external_storage_holder = std::make_shared(context, ColumnsDescription{columns}, ConstraintsDescription{}); StoragePtr external_storage = external_storage_holder->getTable(); /** We replace the subquery with the name of the temporary table. @@ -134,7 +134,7 @@ public: ast = database_and_table_name; external_tables[external_table_name] = external_storage_holder; - subqueries_for_sets[external_table_name].source = interpreter->execute().in; + subqueries_for_sets[external_table_name].source = interpreter->execute().getInputStream(); subqueries_for_sets[external_table_name].table = external_storage; /** NOTE If it was written IN tmp_table - the existing temporary (but not external) table, diff --git a/src/Interpreters/IInterpreter.h b/src/Interpreters/IInterpreter.h index 2425d015e56..41613d30e87 100644 --- a/src/Interpreters/IInterpreter.h +++ b/src/Interpreters/IInterpreter.h @@ -2,14 +2,8 @@ #include -#include - namespace DB { -namespace ErrorCodes -{ - extern const int NOT_IMPLEMENTED; -} /** Interpreters interface for different queries. */ @@ -22,14 +16,10 @@ public: */ virtual BlockIO execute() = 0; - virtual QueryPipeline executeWithProcessors() { throw Exception("executeWithProcessors not implemented", ErrorCodes::NOT_IMPLEMENTED); } - - virtual bool canExecuteWithProcessors() const { return false; } - virtual bool ignoreQuota() const { return false; } virtual bool ignoreLimits() const { return false; } - virtual ~IInterpreter() {} + virtual ~IInterpreter() = default; }; } diff --git a/src/Interpreters/InJoinSubqueriesPreprocessor.cpp b/src/Interpreters/InJoinSubqueriesPreprocessor.cpp index f40e91e7dcd..432a7f40b12 100644 --- a/src/Interpreters/InJoinSubqueriesPreprocessor.cpp +++ b/src/Interpreters/InJoinSubqueriesPreprocessor.cpp @@ -27,7 +27,7 @@ namespace StoragePtr tryGetTable(const ASTPtr & database_and_table, const Context & context) { auto table_id = context.resolveStorageID(database_and_table); - return DatabaseCatalog::instance().tryGetTable(table_id); + return DatabaseCatalog::instance().tryGetTable(table_id, context); } using CheckShardsAndTables = InJoinSubqueriesPreprocessor::CheckShardsAndTables; diff --git a/src/Interpreters/InterpreterAlterQuery.cpp b/src/Interpreters/InterpreterAlterQuery.cpp index c2ab8776c25..bd20d78279d 100644 --- a/src/Interpreters/InterpreterAlterQuery.cpp +++ b/src/Interpreters/InterpreterAlterQuery.cpp @@ -42,7 +42,7 @@ BlockIO InterpreterAlterQuery::execute() context.checkAccess(getRequiredAccess()); auto table_id = context.resolveStorageID(alter, Context::ResolveOrdinary); - StoragePtr table = DatabaseCatalog::instance().getTable(table_id); + StoragePtr table = DatabaseCatalog::instance().getTable(table_id, context); /// Add default database to table identifiers that we can encounter in e.g. default expressions, /// mutation expression, etc. @@ -244,12 +244,12 @@ AccessRightsElements InterpreterAlterQuery::getRequiredAccessForCommand(const AS } case ASTAlterCommand::MOVE_PARTITION: { - if ((command.move_destination_type == PartDestinationType::DISK) - || (command.move_destination_type == PartDestinationType::VOLUME)) + if ((command.move_destination_type == DataDestinationType::DISK) + || (command.move_destination_type == DataDestinationType::VOLUME)) { required_access.emplace_back(AccessType::ALTER_MOVE_PARTITION, database, table); } - else if (command.move_destination_type == PartDestinationType::TABLE) + else if (command.move_destination_type == DataDestinationType::TABLE) { required_access.emplace_back(AccessType::SELECT | AccessType::ALTER_DELETE, database, table); required_access.emplace_back(AccessType::INSERT, command.to_database, command.to_table); diff --git a/src/Interpreters/InterpreterCheckQuery.cpp b/src/Interpreters/InterpreterCheckQuery.cpp index b8f7203e607..b3cd807abe5 100644 --- a/src/Interpreters/InterpreterCheckQuery.cpp +++ b/src/Interpreters/InterpreterCheckQuery.cpp @@ -41,7 +41,7 @@ BlockIO InterpreterCheckQuery::execute() auto table_id = context.resolveStorageID(check, Context::ResolveOrdinary); context.checkAccess(AccessType::SHOW_TABLES, table_id); - StoragePtr table = DatabaseCatalog::instance().getTable(table_id); + StoragePtr table = DatabaseCatalog::instance().getTable(table_id, context); auto check_results = table->checkData(query_ptr, context); Block block; diff --git a/src/Interpreters/InterpreterCreateQuery.cpp b/src/Interpreters/InterpreterCreateQuery.cpp index 147ef7d739b..c9a9a384d8e 100644 --- a/src/Interpreters/InterpreterCreateQuery.cpp +++ b/src/Interpreters/InterpreterCreateQuery.cpp @@ -406,7 +406,7 @@ InterpreterCreateQuery::TableProperties InterpreterCreateQuery::setProperties(AS else if (!create.as_table.empty()) { String as_database_name = context.resolveDatabase(create.as_database); - StoragePtr as_storage = DatabaseCatalog::instance().getTable({as_database_name, create.as_table}); + StoragePtr as_storage = DatabaseCatalog::instance().getTable({as_database_name, create.as_table}, context); /// as_storage->getColumns() and setEngine(...) must be called under structure lock of other_table for CREATE ... AS other_table. as_storage_lock = as_storage->lockStructureForShare( @@ -504,7 +504,7 @@ void InterpreterCreateQuery::setEngine(ASTCreateQuery & create) const String as_database_name = context.resolveDatabase(create.as_database); String as_table_name = create.as_table; - ASTPtr as_create_ptr = DatabaseCatalog::instance().getDatabase(as_database_name)->getCreateTableQuery(as_table_name); + ASTPtr as_create_ptr = DatabaseCatalog::instance().getDatabase(as_database_name)->getCreateTableQuery(as_table_name, context); const auto & as_create = as_create_ptr->as(); const String qualified_name = backQuoteIfNeed(as_database_name) + "." + backQuoteIfNeed(as_table_name); @@ -546,7 +546,7 @@ BlockIO InterpreterCreateQuery::createTable(ASTCreateQuery & create) bool if_not_exists = create.if_not_exists; // Table SQL definition is available even if the table is detached - auto query = database->getCreateTableQuery(create.table); + auto query = database->getCreateTableQuery(create.table, context); create = query->as(); // Copy the saved create query, but use ATTACH instead of CREATE create.attach = true; create.attach_short_syntax = true; @@ -608,7 +608,7 @@ bool InterpreterCreateQuery::doCreateTable(ASTCreateQuery & create, guard = DatabaseCatalog::instance().getDDLGuard(create.database, table_name); /// Table can be created before or it can be created concurrently in another thread, while we were waiting in DDLGuard. - if (database->isTableExist(table_name)) + if (database->isTableExist(table_name, context)) { /// TODO Check structure of table if (create.if_not_exists) @@ -637,7 +637,7 @@ bool InterpreterCreateQuery::doCreateTable(ASTCreateQuery & create, if (create.if_not_exists && context.tryResolveStorageID({"", table_name}, Context::ResolveExternal)) return false; - auto temporary_table = TemporaryTableHolder(context, properties.columns, query_ptr); + auto temporary_table = TemporaryTableHolder(context, properties.columns, properties.constraints, query_ptr); context.getSessionContext().addExternalTable(table_name, std::move(temporary_table)); return true; } diff --git a/src/Interpreters/InterpreterDescribeQuery.cpp b/src/Interpreters/InterpreterDescribeQuery.cpp index 1a6dbbcfc4d..d457fefed6a 100644 --- a/src/Interpreters/InterpreterDescribeQuery.cpp +++ b/src/Interpreters/InterpreterDescribeQuery.cpp @@ -86,7 +86,7 @@ BlockInputStreamPtr InterpreterDescribeQuery::executeImpl() { auto table_id = context.resolveStorageID(table_expression.database_and_table_name); context.checkAccess(AccessType::SHOW_COLUMNS, table_id); - table = DatabaseCatalog::instance().getTable(table_id); + table = DatabaseCatalog::instance().getTable(table_id, context); } auto table_lock = table->lockStructureForShare( diff --git a/src/Interpreters/InterpreterDropQuery.cpp b/src/Interpreters/InterpreterDropQuery.cpp index ecdad0168f0..5ffce2fc3ec 100644 --- a/src/Interpreters/InterpreterDropQuery.cpp +++ b/src/Interpreters/InterpreterDropQuery.cpp @@ -81,8 +81,8 @@ BlockIO InterpreterDropQuery::executeToTable( auto ddl_guard = (!query.no_ddl_lock ? DatabaseCatalog::instance().getDDLGuard(table_id.database_name, table_id.table_name) : nullptr); /// If table was already dropped by anyone, an exception will be thrown - auto [database, table] = query.if_exists ? DatabaseCatalog::instance().tryGetDatabaseAndTable(table_id) - : DatabaseCatalog::instance().getDatabaseAndTable(table_id); + auto [database, table] = query.if_exists ? DatabaseCatalog::instance().tryGetDatabaseAndTable(table_id, context) + : DatabaseCatalog::instance().getDatabaseAndTable(table_id, context); if (database && table) { @@ -182,7 +182,7 @@ BlockIO InterpreterDropQuery::executeToTemporaryTable(const String & table_name, auto resolved_id = context_handle.tryResolveStorageID(StorageID("", table_name), Context::ResolveExternal); if (resolved_id) { - StoragePtr table = DatabaseCatalog::instance().getTable(resolved_id); + StoragePtr table = DatabaseCatalog::instance().getTable(resolved_id, context); if (kind == ASTDropQuery::Kind::Truncate) { auto table_lock = table->lockExclusively(context.getCurrentQueryId(), context.getSettingsRef().lock_acquire_timeout); @@ -234,7 +234,7 @@ BlockIO InterpreterDropQuery::executeToDatabase(const String & database_name, AS ASTDropQuery query; query.kind = kind; query.database = database_name; - for (auto iterator = database->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = database->getTablesIterator(context); iterator->isValid(); iterator->next()) { query.table = iterator->name(); executeToTable({query.database, query.table}, query); diff --git a/src/Interpreters/InterpreterExistsQuery.cpp b/src/Interpreters/InterpreterExistsQuery.cpp index 993b3631e06..8539cb6816e 100644 --- a/src/Interpreters/InterpreterExistsQuery.cpp +++ b/src/Interpreters/InterpreterExistsQuery.cpp @@ -50,7 +50,7 @@ BlockInputStreamPtr InterpreterExistsQuery::executeImpl() { String database = context.resolveDatabase(exists_query->database); context.checkAccess(AccessType::SHOW_TABLES, database, exists_query->table); - result = DatabaseCatalog::instance().isTableExist({database, exists_query->table}); + result = DatabaseCatalog::instance().isTableExist({database, exists_query->table}, context); } } else if ((exists_query = query_ptr->as())) diff --git a/src/Interpreters/InterpreterExplainQuery.cpp b/src/Interpreters/InterpreterExplainQuery.cpp index 1c1e21fc32c..dacd7ca5f20 100644 --- a/src/Interpreters/InterpreterExplainQuery.cpp +++ b/src/Interpreters/InterpreterExplainQuery.cpp @@ -76,7 +76,7 @@ namespace if (const auto * identifier = expression.database_and_table_name->as()) { auto table_id = data.context.resolveStorageID(*identifier); - const auto & storage = DatabaseCatalog::instance().getTable(table_id); + const auto & storage = DatabaseCatalog::instance().getTable(table_id, data.context); if (auto * storage_view = dynamic_cast(storage.get())) storage_view->getRuntimeViewQuery(&select_query, data.context, true); diff --git a/src/Interpreters/InterpreterInsertQuery.cpp b/src/Interpreters/InterpreterInsertQuery.cpp index f3b116e490c..c4a8e3041ac 100644 --- a/src/Interpreters/InterpreterInsertQuery.cpp +++ b/src/Interpreters/InterpreterInsertQuery.cpp @@ -28,6 +28,11 @@ #include #include #include +#include +#include +#include +#include +#include namespace DB @@ -65,7 +70,7 @@ StoragePtr InterpreterInsertQuery::getTable(ASTInsertQuery & query) } query.table_id = context.resolveStorageID(query.table_id); - return DatabaseCatalog::instance().getTable(query.table_id); + return DatabaseCatalog::instance().getTable(query.table_id, context); } Block InterpreterInsertQuery::getSampleBlock(const ASTInsertQuery & query, const StoragePtr & table) const @@ -117,8 +122,6 @@ BlockIO InterpreterInsertQuery::execute() if (!query.table_function) context.checkAccess(AccessType::INSERT, query.table_id, query_sample_block.getNames()); - BlockInputStreams in_streams; - BlockOutputStreams out_streams; bool is_distributed_insert_select = false; if (query.select && table->isRemote() && settings.parallel_distributed_insert_select) @@ -159,6 +162,8 @@ BlockIO InterpreterInsertQuery::execute() const auto & cluster = storage_src->getCluster(); const auto & shards_info = cluster->getShardsInfo(); + std::vector pipelines; + String new_query_str = queryToString(new_query); for (size_t shard_index : ext::range(0, shards_info.size())) { @@ -166,8 +171,7 @@ BlockIO InterpreterInsertQuery::execute() if (shard_info.isLocal()) { InterpreterInsertQuery interpreter(new_query, context); - auto block_io = interpreter.execute(); - in_streams.push_back(block_io.in); + pipelines.emplace_back(interpreter.execute().pipeline); } else { @@ -179,13 +183,20 @@ BlockIO InterpreterInsertQuery::execute() /// INSERT SELECT query returns empty block auto in_stream = std::make_shared(std::move(connections), new_query_str, Block{}, context); - in_streams.push_back(in_stream); + pipelines.emplace_back(); + pipelines.back().init(Pipe(std::make_shared(std::move(in_stream)))); + pipelines.back().setSinks([](const Block & header, QueryPipeline::StreamType) -> ProcessorPtr + { + return std::make_shared(header); + }); } - out_streams.push_back(std::make_shared(Block())); } + + res.pipeline.unitePipelines(std::move(pipelines), {}); } } + BlockOutputStreams out_streams; if (!is_distributed_insert_select || query.watch) { size_t out_streams_size = 1; @@ -193,27 +204,21 @@ BlockIO InterpreterInsertQuery::execute() { /// Passing 1 as subquery_depth will disable limiting size of intermediate result. InterpreterSelectWithUnionQuery interpreter_select{ query.select, context, SelectQueryOptions(QueryProcessingStage::Complete, 1)}; + res = interpreter_select.execute(); if (table->supportsParallelInsert() && settings.max_insert_threads > 1) - { - in_streams = interpreter_select.executeWithMultipleStreams(res.pipeline); - out_streams_size = std::min(size_t(settings.max_insert_threads), in_streams.size()); - } + out_streams_size = std::min(size_t(settings.max_insert_threads), res.pipeline.getNumStreams()); + + if (out_streams_size == 1) + res.pipeline.addPipe({std::make_shared(res.pipeline.getHeader(), res.pipeline.getNumStreams())}); else - { - res = interpreter_select.execute(); - in_streams.emplace_back(res.in); - res.in = nullptr; - res.out = nullptr; - } + res.pipeline.resize(out_streams_size); } else if (query.watch) { InterpreterWatchQuery interpreter_watch{ query.watch, context }; res = interpreter_watch.execute(); - in_streams.emplace_back(res.in); - res.in = nullptr; - res.out = nullptr; + res.pipeline.init(Pipe(std::make_shared(std::move(res.in)))); } for (size_t i = 0; i < out_streams_size; i++) @@ -228,6 +233,21 @@ BlockIO InterpreterInsertQuery::execute() else out = std::make_shared(table, context, query_ptr, no_destination); + /// Note that we wrap transforms one on top of another, so we write them in reverse of data processing order. + + /// Checking constraints. It must be done after calculation of all defaults, so we can check them on calculated columns. + if (const auto & constraints = table->getConstraints(); !constraints.empty()) + out = std::make_shared( + query.table_id, out, out->getHeader(), table->getConstraints(), context); + + /// Actually we don't know structure of input blocks from query/table, + /// because some clients break insertion protocol (columns != header) + out = std::make_shared( + out, query_sample_block, out->getHeader(), table->getColumns().getDefaults(), context); + + /// It's important to squash blocks as early as possible (before other transforms), + /// because other transforms may work inefficient if block size is small. + /// Do not squash blocks if it is a sync INSERT into Distributed, since it lead to double bufferization on client and server side. /// Client-side bufferization might cause excessive timeouts (especially in case of big blocks). if (!(context.getSettingsRef().insert_distributed_sync && table->isRemote()) && !no_squash && !query.watch) @@ -239,15 +259,6 @@ BlockIO InterpreterInsertQuery::execute() context.getSettingsRef().min_insert_block_size_bytes); } - /// Actually we don't know structure of input blocks from query/table, - /// because some clients break insertion protocol (columns != header) - out = std::make_shared( - out, query_sample_block, out->getHeader(), table->getColumns().getDefaults(), context); - - if (const auto & constraints = table->getConstraints(); !constraints.empty()) - out = std::make_shared( - query.table_id, out, query_sample_block, table->getConstraints(), context); - auto out_wrapper = std::make_shared(out); out_wrapper->setProcessListElement(context.getProcessListElement()); out = std::move(out_wrapper); @@ -256,27 +267,35 @@ BlockIO InterpreterInsertQuery::execute() } /// What type of query: INSERT or INSERT SELECT or INSERT WATCH? - if (query.select || query.watch) + if (is_distributed_insert_select) { - for (auto & in_stream : in_streams) - { - in_stream = std::make_shared( - in_stream, out_streams.at(0)->getHeader(), ConvertingBlockInputStream::MatchColumnsMode::Position); - } + /// Pipeline was already built. + } + else if (query.select || query.watch) + { + const auto & header = out_streams.at(0)->getHeader(); - Block in_header = in_streams.at(0)->getHeader(); - if (in_streams.size() > 1) + res.pipeline.addSimpleTransform([&](const Block & in_header) -> ProcessorPtr { - for (size_t i = 1; i < in_streams.size(); ++i) - assertBlocksHaveEqualStructure(in_streams[i]->getHeader(), in_header, query.select ? "INSERT SELECT" : "INSERT WATCH"); - } + return std::make_shared(in_header, header, + ConvertingTransform::MatchColumnsMode::Position); + }); - res.in = std::make_shared(in_streams, out_streams); + res.pipeline.setSinks([&](const Block &, QueryPipeline::StreamType type) -> ProcessorPtr + { + if (type != QueryPipeline::StreamType::Main) + return nullptr; + + auto stream = std::move(out_streams.back()); + out_streams.pop_back(); + + return std::make_shared(std::move(stream)); + }); if (!allow_materialized) { for (const auto & column : table->getColumns()) - if (column.default_desc.kind == ColumnDefaultKind::Materialized && in_header.has(column.name)) + if (column.default_desc.kind == ColumnDefaultKind::Materialized && header.has(column.name)) throw Exception("Cannot insert column " + column.name + ", because it is MATERIALIZED column.", ErrorCodes::ILLEGAL_COLUMN); } } @@ -288,6 +307,7 @@ BlockIO InterpreterInsertQuery::execute() } else res.out = std::move(out_streams.at(0)); + res.pipeline.addStorageHolder(table); return res; diff --git a/src/Interpreters/InterpreterKillQueryQuery.cpp b/src/Interpreters/InterpreterKillQueryQuery.cpp index 42afd0ef477..82c134aeba6 100644 --- a/src/Interpreters/InterpreterKillQueryQuery.cpp +++ b/src/Interpreters/InterpreterKillQueryQuery.cpp @@ -261,7 +261,7 @@ BlockIO InterpreterKillQueryQuery::execute() CancellationCode code = CancellationCode::Unknown; if (!query.test) { - auto storage = DatabaseCatalog::instance().tryGetTable(table_id); + auto storage = DatabaseCatalog::instance().tryGetTable(table_id, context); if (!storage) code = CancellationCode::NotFound; else diff --git a/src/Interpreters/InterpreterOptimizeQuery.cpp b/src/Interpreters/InterpreterOptimizeQuery.cpp index b6c50e59cc3..c47fe1160cf 100644 --- a/src/Interpreters/InterpreterOptimizeQuery.cpp +++ b/src/Interpreters/InterpreterOptimizeQuery.cpp @@ -25,7 +25,7 @@ BlockIO InterpreterOptimizeQuery::execute() context.checkAccess(getRequiredAccess()); auto table_id = context.resolveStorageID(ast, Context::ResolveOrdinary); - StoragePtr table = DatabaseCatalog::instance().getTable(table_id); + StoragePtr table = DatabaseCatalog::instance().getTable(table_id, context); table->optimize(query_ptr, ast.partition, ast.final, ast.deduplicate, context); return {}; } diff --git a/src/Interpreters/InterpreterRenameQuery.cpp b/src/Interpreters/InterpreterRenameQuery.cpp index 78d1c7ee486..de2b6bb0c1c 100644 --- a/src/Interpreters/InterpreterRenameQuery.cpp +++ b/src/Interpreters/InterpreterRenameQuery.cpp @@ -78,7 +78,7 @@ BlockIO InterpreterRenameQuery::execute() for (auto & elem : descriptions) { if (!rename.exchange) - database_catalog.assertTableDoesntExist(StorageID(elem.to_database_name, elem.to_table_name)); + database_catalog.assertTableDoesntExist(StorageID(elem.to_database_name, elem.to_table_name), context); database_catalog.getDatabase(elem.from_database_name)->renameTable( context, diff --git a/src/Interpreters/InterpreterSelectQuery.cpp b/src/Interpreters/InterpreterSelectQuery.cpp index 4f717eda706..56532e532d1 100644 --- a/src/Interpreters/InterpreterSelectQuery.cpp +++ b/src/Interpreters/InterpreterSelectQuery.cpp @@ -1,39 +1,15 @@ #include -#include -#include -#include -#include -#include -#include -#include #include #include -#include -#include -#include -#include -#include -#include -#include #include #include -#include -#include -#include -#include -#include #include -#include -#include -#include - #include #include #include #include #include #include -#include #include #include @@ -59,7 +35,6 @@ #include #include -#include #include #include @@ -68,7 +43,6 @@ #include #include #include -#include #include #include #include @@ -98,7 +72,8 @@ #include #include #include -#include +#include +#include namespace DB @@ -465,38 +440,23 @@ Block InterpreterSelectQuery::getSampleBlock() BlockIO InterpreterSelectQuery::execute() { - Pipeline pipeline; BlockIO res; - executeImpl(pipeline, input, std::move(input_pipe), res.pipeline); - executeUnion(pipeline, getSampleBlock()); - - res.in = pipeline.firstStream(); + executeImpl(res.pipeline, input, std::move(input_pipe)); res.pipeline.addInterpreterContext(context); res.pipeline.addStorageHolder(storage); + + /// We must guarantee that result structure is the same as in getSampleBlock() + if (!blocksHaveEqualStructure(res.pipeline.getHeader(), result_header)) + { + res.pipeline.addSimpleTransform([&](const Block & header) + { + return std::make_shared(header, result_header, ConvertingTransform::MatchColumnsMode::Name); + }); + } + return res; } -BlockInputStreams InterpreterSelectQuery::executeWithMultipleStreams(QueryPipeline & parent_pipeline) -{ - ///FIXME pipeline must be alive until query is finished - Pipeline pipeline; - executeImpl(pipeline, input, std::move(input_pipe), parent_pipeline); - unifyStreams(pipeline, getSampleBlock()); - parent_pipeline.addInterpreterContext(context); - parent_pipeline.addStorageHolder(storage); - return pipeline.streams; -} - -QueryPipeline InterpreterSelectQuery::executeWithProcessors() -{ - QueryPipeline query_pipeline; - executeImpl(query_pipeline, input, std::move(input_pipe), query_pipeline); - query_pipeline.addInterpreterContext(context); - query_pipeline.addStorageHolder(storage); - return query_pipeline; -} - - Block InterpreterSelectQuery::getSampleBlockImpl() { if (storage && !options.only_analyze) @@ -687,9 +647,7 @@ static UInt64 getLimitForSorting(const ASTSelectQuery & query, const Context & c return 0; } - -template -void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputStreamPtr & prepared_input, std::optional prepared_pipe, QueryPipeline & save_context_and_storage) +void InterpreterSelectQuery::executeImpl(QueryPipeline & pipeline, const BlockInputStreamPtr & prepared_input, std::optional prepared_pipe) { /** Streams of data. When the query is executed in parallel, we have several data streams. * If there is no GROUP BY, then perform all operations before ORDER BY and LIMIT in parallel, then @@ -701,8 +659,6 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS * then perform the remaining operations with one resulting stream. */ - constexpr bool pipeline_with_processors = std::is_same::value; - /// Now we will compose block streams that perform the necessary actions. auto & query = getSelectQuery(); const Settings & settings = context->getSettingsRef(); @@ -712,40 +668,27 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS if (options.only_analyze) { - if constexpr (pipeline_with_processors) - pipeline.init(Pipe(std::make_shared(source_header))); - else - pipeline.streams.emplace_back(std::make_shared(source_header)); + pipeline.init(Pipe(std::make_shared(source_header))); if (expressions.prewhere_info) { - if constexpr (pipeline_with_processors) - pipeline.addSimpleTransform([&](const Block & header) - { - return std::make_shared( - header, - expressions.prewhere_info->prewhere_actions, - expressions.prewhere_info->prewhere_column_name, - expressions.prewhere_info->remove_prewhere_column); - }); - else - pipeline.streams.back() = std::make_shared( - pipeline.streams.back(), expressions.prewhere_info->prewhere_actions, - expressions.prewhere_info->prewhere_column_name, expressions.prewhere_info->remove_prewhere_column); + pipeline.addSimpleTransform([&](const Block & header) + { + return std::make_shared( + header, + expressions.prewhere_info->prewhere_actions, + expressions.prewhere_info->prewhere_column_name, + expressions.prewhere_info->remove_prewhere_column); + }); // To remove additional columns in dry run // For example, sample column which can be removed in this stage if (expressions.prewhere_info->remove_columns_actions) { - if constexpr (pipeline_with_processors) + pipeline.addSimpleTransform([&](const Block & header) { - pipeline.addSimpleTransform([&](const Block & header) - { - return std::make_shared(header, expressions.prewhere_info->remove_columns_actions); - }); - } - else - pipeline.streams.back() = std::make_shared(pipeline.streams.back(), expressions.prewhere_info->remove_columns_actions); + return std::make_shared(header, expressions.prewhere_info->remove_columns_actions); + }); } } } @@ -753,17 +696,11 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS { if (prepared_input) { - if constexpr (pipeline_with_processors) - pipeline.init(Pipe(std::make_shared(prepared_input))); - else - pipeline.streams.push_back(prepared_input); + pipeline.init(Pipe(std::make_shared(prepared_input))); } else if (prepared_pipe) { - if constexpr (pipeline_with_processors) - pipeline.init(std::move(*prepared_pipe)); - else - pipeline.streams.push_back(std::make_shared(std::move(*prepared_pipe))); + pipeline.init(std::move(*prepared_pipe)); } if (from_stage == QueryProcessingStage::WithMergeableState && @@ -774,7 +711,7 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS throw Exception("PREWHERE is not supported if the table is filtered by row-level security expression", ErrorCodes::ILLEGAL_PREWHERE); /** Read the data from Storage. from_stage - to what stage the request was completed in Storage. */ - executeFetchColumns(from_stage, pipeline, expressions.prewhere_info, expressions.columns_to_remove_after_prewhere, save_context_and_storage); + executeFetchColumns(from_stage, pipeline, expressions.prewhere_info, expressions.columns_to_remove_after_prewhere); LOG_TRACE(log, "{} -> {}", QueryProcessingStage::toString(from_stage), QueryProcessingStage::toString(options.to_stage)); } @@ -817,12 +754,7 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS } if (query.limitLength()) - { - if constexpr (pipeline_with_processors) - executePreLimit(pipeline, true); - else - executePreLimit(pipeline); - } + executePreLimit(pipeline, true); } }; @@ -840,31 +772,17 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS { if (expressions.hasFilter()) { - if constexpr (pipeline_with_processors) + pipeline.addSimpleTransform([&](const Block & block, QueryPipeline::StreamType stream_type) -> ProcessorPtr { - pipeline.addSimpleTransform([&](const Block & block, QueryPipeline::StreamType stream_type) -> ProcessorPtr - { - bool on_totals = stream_type == QueryPipeline::StreamType::Totals; + bool on_totals = stream_type == QueryPipeline::StreamType::Totals; - return std::make_shared( - block, - expressions.filter_info->actions, - expressions.filter_info->column_name, - expressions.filter_info->do_remove_column, - on_totals); - }); - } - else - { - pipeline.transform([&](auto & stream) - { - stream = std::make_shared( - stream, - expressions.filter_info->actions, - expressions.filter_info->column_name, - expressions.filter_info->do_remove_column); - }); - } + return std::make_shared( + block, + expressions.filter_info->actions, + expressions.filter_info->column_name, + expressions.filter_info->do_remove_column, + on_totals); + }); } if (expressions.hasJoin()) @@ -872,59 +790,43 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS Block join_result_sample; JoinPtr join = expressions.before_join->getTableJoinAlgo(); - if constexpr (pipeline_with_processors) + join_result_sample = ExpressionBlockInputStream( + std::make_shared(pipeline.getHeader()), expressions.before_join).getHeader(); + + /// In case joined subquery has totals, and we don't, add default chunk to totals. + bool default_totals = false; + if (!pipeline.hasTotals()) { - join_result_sample = ExpressionBlockInputStream( - std::make_shared(pipeline.getHeader()), expressions.before_join).getHeader(); - - /// In case joined subquery has totals, and we don't, add default chunk to totals. - bool default_totals = false; - if (!pipeline.hasTotals()) - { - pipeline.addDefaultTotals(); - default_totals = true; - } - - bool inflating_join = false; - if (join) - { - inflating_join = true; - if (auto * hash_join = typeid_cast(join.get())) - inflating_join = isCross(hash_join->getKind()); - } - - pipeline.addSimpleTransform([&](const Block & header, QueryPipeline::StreamType type) - { - bool on_totals = type == QueryPipeline::StreamType::Totals; - std::shared_ptr ret; - if (inflating_join) - ret = std::make_shared(header, expressions.before_join, on_totals, default_totals); - else - ret = std::make_shared(header, expressions.before_join, on_totals, default_totals); - - return ret; - }); + pipeline.addDefaultTotals(); + default_totals = true; } - else + + bool inflating_join = false; + if (join) { - /// Applies to all sources except stream_with_non_joined_data. - for (auto & stream : pipeline.streams) - stream = std::make_shared(stream, expressions.before_join); - - join_result_sample = pipeline.firstStream()->getHeader(); + inflating_join = true; + if (auto * hash_join = typeid_cast(join.get())) + inflating_join = isCross(hash_join->getKind()); } + pipeline.addSimpleTransform([&](const Block & header, QueryPipeline::StreamType type) + { + bool on_totals = type == QueryPipeline::StreamType::Totals; + std::shared_ptr ret; + if (inflating_join) + ret = std::make_shared(header, expressions.before_join, on_totals, default_totals); + else + ret = std::make_shared(header, expressions.before_join, on_totals, default_totals); + + return ret; + }); + if (join) { if (auto stream = join->createStreamWithNonJoinedRows(join_result_sample, settings.max_block_size)) { - if constexpr (pipeline_with_processors) - { - auto source = std::make_shared(std::move(stream)); - pipeline.addDelayedStream(source); - } - else - pipeline.stream_with_non_joined_data = std::move(stream); + auto source = std::make_shared(std::move(stream)); + pipeline.addDelayedStream(source); } } } @@ -1009,28 +911,14 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS if (query.limitLength() && !query.limit_with_ties && pipeline.hasMoreThanOneStream() && !query.distinct && !expressions.hasLimitBy() && !settings.extremes) { - if constexpr (pipeline_with_processors) - executePreLimit(pipeline, false); - else - executePreLimit(pipeline); - + executePreLimit(pipeline, false); has_prelimit = true; } - bool need_merge_streams = need_second_distinct_pass || query.limitBy() - || (!pipeline_with_processors && query.limitLength()); /// Don't merge streams for pre-limit more. - - if constexpr (!pipeline_with_processors) - if (pipeline.hasDelayedStream()) - need_merge_streams = true; + bool need_merge_streams = need_second_distinct_pass || query.limitBy(); if (need_merge_streams) - { - if constexpr (pipeline_with_processors) - pipeline.resize(1); - else - executeUnion(pipeline, {}); - } + pipeline.resize(1); /** If there was more than one stream, * then DISTINCT needs to be performed once again after merging all streams. @@ -1054,7 +942,7 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS */ executeExtremes(pipeline); - if (!(pipeline_with_processors && has_prelimit)) /// Limit is no longer needed if there is prelimit. + if (!has_prelimit) /// Limit is no longer needed if there is prelimit. executeLimit(pipeline); executeOffset(pipeline); @@ -1065,14 +953,10 @@ void InterpreterSelectQuery::executeImpl(TPipeline & pipeline, const BlockInputS executeSubqueriesInSetsAndJoins(pipeline, subqueries_for_sets); } -template void InterpreterSelectQuery::executeFetchColumns( - QueryProcessingStage::Enum processing_stage, TPipeline & pipeline, - const PrewhereInfoPtr & prewhere_info, const Names & columns_to_remove_after_prewhere, - QueryPipeline & save_context_and_storage) + QueryProcessingStage::Enum processing_stage, QueryPipeline & pipeline, + const PrewhereInfoPtr & prewhere_info, const Names & columns_to_remove_after_prewhere) { - constexpr bool pipeline_with_processors = std::is_same::value; - auto & query = getSelectQuery(); const Settings & settings = context->getSettingsRef(); @@ -1126,10 +1010,7 @@ void InterpreterSelectQuery::executeFetchColumns( {std::move(column), std::make_shared(func, argument_types, desc->parameters), desc->column_name}}; auto istream = std::make_shared(block_with_count); - if constexpr (pipeline_with_processors) - pipeline.init(Pipe(std::make_shared(istream))); - else - pipeline.streams.emplace_back(istream); + pipeline.init(Pipe(std::make_shared(istream))); from_stage = QueryProcessingStage::WithMergeableState; analysis_result.first_stage = false; return; @@ -1266,7 +1147,7 @@ void InterpreterSelectQuery::executeFetchColumns( /// Remove columns which will be added by prewhere. required_columns.erase(std::remove_if(required_columns.begin(), required_columns.end(), [&](const String & name) { - return !!required_columns_after_prewhere_set.count(name); + return required_columns_after_prewhere_set.count(name) != 0; }), required_columns.end()); if (prewhere_info) @@ -1377,11 +1258,7 @@ void InterpreterSelectQuery::executeFetchColumns( interpreter_subquery->ignoreWithTotals(); } - if constexpr (pipeline_with_processors) - /// Just use pipeline from subquery. - pipeline = interpreter_subquery->executeWithProcessors(); - else - pipeline.streams = interpreter_subquery->executeWithMultipleStreams(save_context_and_storage); + pipeline = interpreter_subquery->execute().pipeline; } else if (storage) { @@ -1411,48 +1288,9 @@ void InterpreterSelectQuery::executeFetchColumns( query_info.input_sorting_info = query_info.order_by_optimizer->getInputOrder(storage); } + Pipes pipes = storage->read(required_columns, query_info, *context, processing_stage, max_block_size, max_streams); - BlockInputStreams streams; - Pipes pipes; - - if (pipeline_with_processors) - pipes = storage->read(required_columns, query_info, *context, processing_stage, max_block_size, max_streams); - else - streams = storage->readStreams(required_columns, query_info, *context, processing_stage, max_block_size, max_streams); - - if (streams.empty() && !pipeline_with_processors) - { - streams = {std::make_shared(storage->getSampleBlockForColumns(required_columns))}; - - if (query_info.prewhere_info) - { - if (query_info.prewhere_info->alias_actions) - { - streams.back() = std::make_shared( - streams.back(), - query_info.prewhere_info->alias_actions); - } - - streams.back() = std::make_shared( - streams.back(), - prewhere_info->prewhere_actions, - prewhere_info->prewhere_column_name, - prewhere_info->remove_prewhere_column); - - // To remove additional columns - // In some cases, we did not read any marks so that the pipeline.streams is empty - // Thus, some columns in prewhere are not removed as expected - // This leads to mismatched header in distributed table - if (query_info.prewhere_info->remove_columns_actions) - { - streams.back() = std::make_shared(streams.back(), query_info.prewhere_info->remove_columns_actions); - } - } - } - - /// Copy-paste from prev if. - /// Code is temporarily copy-pasted while moving to new pipeline. - if (pipes.empty() && pipeline_with_processors) + if (pipes.empty()) { Pipe pipe(std::make_shared(storage->getSampleBlockForColumns(required_columns))); @@ -1468,6 +1306,10 @@ void InterpreterSelectQuery::executeFetchColumns( prewhere_info->prewhere_column_name, prewhere_info->remove_prewhere_column)); + // To remove additional columns + // In some cases, we did not read any marks so that the pipeline.streams is empty + // Thus, some columns in prewhere are not removed as expected + // This leads to mismatched header in distributed table if (query_info.prewhere_info->remove_columns_actions) pipe.addSimpleTransform(std::make_shared(pipe.getHeader(), query_info.prewhere_info->remove_columns_actions)); } @@ -1475,14 +1317,8 @@ void InterpreterSelectQuery::executeFetchColumns( pipes.emplace_back(std::move(pipe)); } - for (auto & stream : streams) - stream->addTableLock(table_lock); - - if constexpr (pipeline_with_processors) - { - /// Table lock is stored inside pipeline here. - pipeline.addTableLock(table_lock); - } + /// Table lock is stored inside pipeline here. + pipeline.addTableLock(table_lock); /// Set the limits and quota for reading data, the speed and time of the query. { @@ -1510,16 +1346,6 @@ void InterpreterSelectQuery::executeFetchColumns( auto quota = context->getQuota(); - for (auto & stream : streams) - { - if (!options.ignore_limits) - stream->setLimits(limits); - - if (!options.ignore_quota && (options.to_stage == QueryProcessingStage::Complete)) - stream->setQuota(quota); - } - - /// Copy-paste for (auto & pipe : pipes) { if (!options.ignore_limits) @@ -1530,47 +1356,13 @@ void InterpreterSelectQuery::executeFetchColumns( } } - if constexpr (pipeline_with_processors) - { - if (streams.size() == 1 || pipes.size() == 1) - pipeline.setMaxThreads(1); + if (pipes.size() == 1) + pipeline.setMaxThreads(1); - /// Unify streams. They must have same headers. - if (streams.size() > 1) - { - /// Unify streams in case they have different headers. - auto first_header = streams.at(0)->getHeader(); + for (auto & pipe : pipes) + pipe.enableQuota(); - if (first_header.columns() > 1 && first_header.has("_dummy")) - first_header.erase("_dummy"); - - for (auto & stream : streams) - { - auto header = stream->getHeader(); - auto mode = ConvertingBlockInputStream::MatchColumnsMode::Name; - if (!blocksHaveEqualStructure(first_header, header)) - stream = std::make_shared(stream, first_header, mode); - } - } - - for (auto & stream : streams) - { - bool force_add_agg_info = processing_stage == QueryProcessingStage::WithMergeableState; - auto source = std::make_shared(stream, force_add_agg_info); - - if (processing_stage == QueryProcessingStage::Complete) - source->addTotalsPort(); - - pipes.emplace_back(std::move(source)); - } - - for (auto & pipe : pipes) - pipe.enableQuota(); - - pipeline.init(std::move(pipes)); - } - else - pipeline.streams = std::move(streams); + pipeline.init(std::move(pipes)); } else throw Exception("Logical error in InterpreterSelectQuery: nowhere to read", ErrorCodes::LOGICAL_ERROR); @@ -1578,32 +1370,14 @@ void InterpreterSelectQuery::executeFetchColumns( /// Aliases in table declaration. if (processing_stage == QueryProcessingStage::FetchColumns && alias_actions) { - if constexpr (pipeline_with_processors) + pipeline.addSimpleTransform([&](const Block & header) { - pipeline.addSimpleTransform([&](const Block & header) - { - return std::make_shared(header, alias_actions); - }); - } - else - { - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, alias_actions); - }); - } + return std::make_shared(header, alias_actions); + }); } } -void InterpreterSelectQuery::executeWhere(Pipeline & pipeline, const ExpressionActionsPtr & expression, bool remove_filter) -{ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, expression, getSelectQuery().where()->getColumnName(), remove_filter); - }); -} - void InterpreterSelectQuery::executeWhere(QueryPipeline & pipeline, const ExpressionActionsPtr & expression, bool remove_filter) { pipeline.addSimpleTransform([&](const Block & block, QueryPipeline::StreamType stream_type) @@ -1613,69 +1387,6 @@ void InterpreterSelectQuery::executeWhere(QueryPipeline & pipeline, const Expres }); } -void InterpreterSelectQuery::executeAggregation(Pipeline & pipeline, const ExpressionActionsPtr & expression, bool overflow_row, bool final) -{ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, expression); - }); - - Block header = pipeline.firstStream()->getHeader(); - ColumnNumbers keys; - for (const auto & key : query_analyzer->aggregationKeys()) - keys.push_back(header.getPositionByName(key.name)); - - AggregateDescriptions aggregates = query_analyzer->aggregates(); - for (auto & descr : aggregates) - if (descr.arguments.empty()) - for (const auto & name : descr.argument_names) - descr.arguments.push_back(header.getPositionByName(name)); - - const Settings & settings = context->getSettingsRef(); - - /** Two-level aggregation is useful in two cases: - * 1. Parallel aggregation is done, and the results should be merged in parallel. - * 2. An aggregation is done with store of temporary data on the disk, and they need to be merged in a memory efficient way. - */ - bool allow_to_use_two_level_group_by = pipeline.streams.size() > 1 || settings.max_bytes_before_external_group_by != 0; - - Aggregator::Params params(header, keys, aggregates, - overflow_row, settings.max_rows_to_group_by, settings.group_by_overflow_mode, - allow_to_use_two_level_group_by ? settings.group_by_two_level_threshold : SettingUInt64(0), - allow_to_use_two_level_group_by ? settings.group_by_two_level_threshold_bytes : SettingUInt64(0), - settings.max_bytes_before_external_group_by, settings.empty_result_for_aggregation_by_empty_set, - context->getTemporaryVolume(), settings.max_threads, settings.min_free_disk_space_for_temporary_data); - - /// If there are several sources, then we perform parallel aggregation - if (pipeline.streams.size() > 1) - { - pipeline.firstStream() = std::make_shared( - pipeline.streams, pipeline.stream_with_non_joined_data, params, final, - max_streams, - settings.aggregation_memory_efficient_merge_threads - ? static_cast(settings.aggregation_memory_efficient_merge_threads) - : static_cast(settings.max_threads)); - - pipeline.stream_with_non_joined_data = nullptr; - pipeline.streams.resize(1); - } - else - { - BlockInputStreams inputs; - if (!pipeline.streams.empty()) - inputs.push_back(pipeline.firstStream()); - else - pipeline.streams.resize(1); - - if (pipeline.stream_with_non_joined_data) - inputs.push_back(pipeline.stream_with_non_joined_data); - - pipeline.firstStream() = std::make_shared(std::make_shared(inputs), params, final); - - pipeline.stream_with_non_joined_data = nullptr; - } -} - void InterpreterSelectQuery::executeAggregation(QueryPipeline & pipeline, const ExpressionActionsPtr & expression, bool overflow_row, bool final) { @@ -1749,53 +1460,6 @@ void InterpreterSelectQuery::executeAggregation(QueryPipeline & pipeline, const } -void InterpreterSelectQuery::executeMergeAggregated(Pipeline & pipeline, bool overflow_row, bool final) -{ - Block header = pipeline.firstStream()->getHeader(); - - ColumnNumbers keys; - for (const auto & key : query_analyzer->aggregationKeys()) - keys.push_back(header.getPositionByName(key.name)); - - /** There are two modes of distributed aggregation. - * - * 1. In different threads read from the remote servers blocks. - * Save all the blocks in the RAM. Merge blocks. - * If the aggregation is two-level - parallelize to the number of buckets. - * - * 2. In one thread, read blocks from different servers in order. - * RAM stores only one block from each server. - * If the aggregation is a two-level aggregation, we consistently merge the blocks of each next level. - * - * The second option consumes less memory (up to 256 times less) - * in the case of two-level aggregation, which is used for large results after GROUP BY, - * but it can work more slowly. - */ - - const Settings & settings = context->getSettingsRef(); - - Aggregator::Params params(header, keys, query_analyzer->aggregates(), overflow_row, settings.max_threads); - - if (!settings.distributed_aggregation_memory_efficient) - { - /// We union several sources into one, parallelizing the work. - executeUnion(pipeline, {}); - - /// Now merge the aggregated blocks - pipeline.firstStream() = std::make_shared(pipeline.firstStream(), params, final, settings.max_threads); - } - else - { - pipeline.firstStream() = std::make_shared(pipeline.streams, params, final, - max_streams, - settings.aggregation_memory_efficient_merge_threads - ? static_cast(settings.aggregation_memory_efficient_merge_threads) - : static_cast(settings.max_threads)); - - pipeline.streams.resize(1); - } -} - void InterpreterSelectQuery::executeMergeAggregated(QueryPipeline & pipeline, bool overflow_row, bool final) { Block header_before_merge = pipeline.getHeader(); @@ -1856,14 +1520,6 @@ void InterpreterSelectQuery::executeMergeAggregated(QueryPipeline & pipeline, bo } -void InterpreterSelectQuery::executeHaving(Pipeline & pipeline, const ExpressionActionsPtr & expression) -{ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, expression, getSelectQuery().having()->getColumnName()); - }); -} - void InterpreterSelectQuery::executeHaving(QueryPipeline & pipeline, const ExpressionActionsPtr & expression) { pipeline.addSimpleTransform([&](const Block & header, QueryPipeline::StreamType stream_type) -> ProcessorPtr @@ -1876,22 +1532,6 @@ void InterpreterSelectQuery::executeHaving(QueryPipeline & pipeline, const Expre } -void InterpreterSelectQuery::executeTotalsAndHaving(Pipeline & pipeline, bool has_having, const ExpressionActionsPtr & expression, bool overflow_row, bool final) -{ - executeUnion(pipeline, {}); - - const Settings & settings = context->getSettingsRef(); - - pipeline.firstStream() = std::make_shared( - pipeline.firstStream(), - overflow_row, - expression, - has_having ? getSelectQuery().having()->getColumnName() : "", - settings.totals_mode, - settings.totals_auto_threshold, - final); -} - void InterpreterSelectQuery::executeTotalsAndHaving(QueryPipeline & pipeline, bool has_having, const ExpressionActionsPtr & expression, bool overflow_row, bool final) { const Settings & settings = context->getSettingsRef(); @@ -1905,31 +1545,6 @@ void InterpreterSelectQuery::executeTotalsAndHaving(QueryPipeline & pipeline, bo } -void InterpreterSelectQuery::executeRollupOrCube(Pipeline & pipeline, Modificator modificator) -{ - executeUnion(pipeline, {}); - - Block header = pipeline.firstStream()->getHeader(); - - ColumnNumbers keys; - - for (const auto & key : query_analyzer->aggregationKeys()) - keys.push_back(header.getPositionByName(key.name)); - - const Settings & settings = context->getSettingsRef(); - - Aggregator::Params params(header, keys, query_analyzer->aggregates(), - false, settings.max_rows_to_group_by, settings.group_by_overflow_mode, - SettingUInt64(0), SettingUInt64(0), - settings.max_bytes_before_external_group_by, settings.empty_result_for_aggregation_by_empty_set, - context->getTemporaryVolume(), settings.max_threads, settings.min_free_disk_space_for_temporary_data); - - if (modificator == Modificator::ROLLUP) - pipeline.firstStream() = std::make_shared(pipeline.firstStream(), params); - else - pipeline.firstStream() = std::make_shared(pipeline.firstStream(), params); -} - void InterpreterSelectQuery::executeRollupOrCube(QueryPipeline & pipeline, Modificator modificator) { pipeline.resize(1); @@ -1964,14 +1579,6 @@ void InterpreterSelectQuery::executeRollupOrCube(QueryPipeline & pipeline, Modif } -void InterpreterSelectQuery::executeExpression(Pipeline & pipeline, const ExpressionActionsPtr & expression) -{ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, expression); - }); -} - void InterpreterSelectQuery::executeExpression(QueryPipeline & pipeline, const ExpressionActionsPtr & expression) { pipeline.addSimpleTransform([&](const Block & header) -> ProcessorPtr @@ -1980,68 +1587,6 @@ void InterpreterSelectQuery::executeExpression(QueryPipeline & pipeline, const E }); } -void InterpreterSelectQuery::executeOrder(Pipeline & pipeline, InputSortingInfoPtr input_sorting_info) -{ - auto & query = getSelectQuery(); - SortDescription output_order_descr = getSortDescription(query, *context); - const Settings & settings = context->getSettingsRef(); - UInt64 limit = getLimitForSorting(query, *context); - - if (input_sorting_info) - { - /* Case of sorting with optimization using sorting key. - * We have several threads, each of them reads batch of parts in direct - * or reverse order of sorting key using one input stream per part - * and then merge them into one sorted stream. - * At this stage we merge per-thread streams into one. - * If the input is sorted by some prefix of the sorting key required for output, - * we have to finish sorting after the merge. - */ - - bool need_finish_sorting = (input_sorting_info->order_key_prefix_descr.size() < output_order_descr.size()); - - UInt64 limit_for_merging = (need_finish_sorting ? 0 : limit); - executeMergeSorted(pipeline, input_sorting_info->order_key_prefix_descr, limit_for_merging); - - if (need_finish_sorting) - { - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, output_order_descr, limit); - }); - - pipeline.firstStream() = std::make_shared( - pipeline.firstStream(), input_sorting_info->order_key_prefix_descr, - output_order_descr, settings.max_block_size, limit); - } - } - else - { - pipeline.transform([&](auto & stream) - { - auto sorting_stream = std::make_shared(stream, output_order_descr, limit); - - /// Limits on sorting - IBlockInputStream::LocalLimits limits; - limits.mode = IBlockInputStream::LIMITS_TOTAL; - limits.size_limits = SizeLimits(settings.max_rows_to_sort, settings.max_bytes_to_sort, settings.sort_overflow_mode); - sorting_stream->setLimits(limits); - - auto merging_stream = std::make_shared( - sorting_stream, output_order_descr, settings.max_block_size, limit, - settings.max_bytes_before_remerge_sort, - settings.max_bytes_before_external_sort / pipeline.streams.size(), - context->getTemporaryVolume(), - settings.temporary_files_codec, - settings.min_free_disk_space_for_temporary_data); - - stream = merging_stream; - }); - - /// If there are several streams, we merge them into one - executeMergeSorted(pipeline, output_order_descr, limit); - } -} void InterpreterSelectQuery::executeOrder(QueryPipeline & pipeline, InputSortingInfoPtr input_sorting_info) { @@ -2138,41 +1683,6 @@ void InterpreterSelectQuery::executeOrder(QueryPipeline & pipeline, InputSorting } -void InterpreterSelectQuery::executeMergeSorted(Pipeline & pipeline) -{ - auto & query = getSelectQuery(); - SortDescription order_descr = getSortDescription(query, *context); - UInt64 limit = getLimitForSorting(query, *context); - - /// If there are several streams, then we merge them into one - if (pipeline.hasMoreThanOneStream()) - { - unifyStreams(pipeline, pipeline.firstStream()->getHeader()); - executeMergeSorted(pipeline, order_descr, limit); - } -} - - -void InterpreterSelectQuery::executeMergeSorted(Pipeline & pipeline, const SortDescription & sort_description, UInt64 limit) -{ - if (pipeline.hasMoreThanOneStream()) - { - const Settings & settings = context->getSettingsRef(); - - /** MergingSortedBlockInputStream reads the sources sequentially. - * To make the data on the remote servers prepared in parallel, we wrap it in AsynchronousBlockInputStream. - */ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream); - }); - - pipeline.firstStream() = std::make_shared( - pipeline.streams, sort_description, settings.max_block_size, limit); - pipeline.streams.resize(1); - } -} - void InterpreterSelectQuery::executeMergeSorted(QueryPipeline & pipeline) { auto & query = getSelectQuery(); @@ -2202,14 +1712,6 @@ void InterpreterSelectQuery::executeMergeSorted(QueryPipeline & pipeline, const } -void InterpreterSelectQuery::executeProjection(Pipeline & pipeline, const ExpressionActionsPtr & expression) -{ - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, expression); - }); -} - void InterpreterSelectQuery::executeProjection(QueryPipeline & pipeline, const ExpressionActionsPtr & expression) { pipeline.addSimpleTransform([&](const Block & header) -> ProcessorPtr @@ -2219,28 +1721,6 @@ void InterpreterSelectQuery::executeProjection(QueryPipeline & pipeline, const E } -void InterpreterSelectQuery::executeDistinct(Pipeline & pipeline, bool before_order, Names columns) -{ - auto & query = getSelectQuery(); - if (query.distinct) - { - const Settings & settings = context->getSettingsRef(); - - auto [limit_length, limit_offset] = getLimitLengthAndOffset(query, *context); - UInt64 limit_for_distinct = 0; - - /// If after this stage of DISTINCT ORDER BY is not executed, then you can get no more than limit_length + limit_offset of different rows. - if ((!query.orderBy() || !before_order) && !query.limit_with_ties) - limit_for_distinct = limit_length + limit_offset; - - pipeline.transform([&](auto & stream) - { - SizeLimits limits(settings.max_rows_in_distinct, settings.max_bytes_in_distinct, settings.distinct_overflow_mode); - stream = std::make_shared(stream, limits, limit_for_distinct, columns); - }); - } -} - void InterpreterSelectQuery::executeDistinct(QueryPipeline & pipeline, bool before_order, Names columns) { auto & query = getSelectQuery(); @@ -2268,51 +1748,6 @@ void InterpreterSelectQuery::executeDistinct(QueryPipeline & pipeline, bool befo } -void InterpreterSelectQuery::executeUnion(Pipeline & pipeline, Block header) -{ - /// If there are still several streams, then we combine them into one - if (pipeline.hasMoreThanOneStream()) - { - if (!header) - header = pipeline.firstStream()->getHeader(); - - unifyStreams(pipeline, std::move(header)); - - pipeline.firstStream() = std::make_shared(pipeline.streams, pipeline.stream_with_non_joined_data, max_streams); - pipeline.stream_with_non_joined_data = nullptr; - pipeline.streams.resize(1); - pipeline.union_stream = true; - } - else if (pipeline.stream_with_non_joined_data) - { - pipeline.streams.push_back(pipeline.stream_with_non_joined_data); - pipeline.stream_with_non_joined_data = nullptr; - } -} - - -/// Preliminary LIMIT - is used in every source, if there are several sources, before they are combined. -void InterpreterSelectQuery::executePreLimit(Pipeline & pipeline) -{ - auto & query = getSelectQuery(); - /// If there is LIMIT - if (query.limitLength()) - { - auto [limit_length, limit_offset] = getLimitLengthAndOffset(query, *context); - SortDescription sort_descr; - if (query.limit_with_ties) - { - if (!query.orderBy()) - throw Exception("LIMIT WITH TIES without ORDER BY", ErrorCodes::LOGICAL_ERROR); - sort_descr = getSortDescription(query, *context); - } - pipeline.transform([&, limit = limit_length + limit_offset](auto & stream) - { - stream = std::make_shared(stream, limit, 0, false, false, query.limit_with_ties, sort_descr); - }); - } -} - /// Preliminary LIMIT - is used in every source, if there are several sources, before they are combined. void InterpreterSelectQuery::executePreLimit(QueryPipeline & pipeline, bool do_not_skip_offset) { @@ -2334,24 +1769,6 @@ void InterpreterSelectQuery::executePreLimit(QueryPipeline & pipeline, bool do_n } -void InterpreterSelectQuery::executeLimitBy(Pipeline & pipeline) -{ - auto & query = getSelectQuery(); - if (!query.limitByLength() || !query.limitBy()) - return; - - Names columns; - for (const auto & elem : query.limitBy()->children) - columns.emplace_back(elem->getColumnName()); - UInt64 length = getLimitUIntValue(query.limitByLength(), *context, "LIMIT"); - UInt64 offset = (query.limitByOffset() ? getLimitUIntValue(query.limitByOffset(), *context, "OFFSET") : 0); - - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, length, offset, columns); - }); -} - void InterpreterSelectQuery::executeLimitBy(QueryPipeline & pipeline) { auto & query = getSelectQuery(); @@ -2400,73 +1817,6 @@ namespace } } -void InterpreterSelectQuery::executeLimit(Pipeline & pipeline) -{ - auto & query = getSelectQuery(); - /// If there is LIMIT - if (query.limitLength()) - { - /** Rare case: - * if there is no WITH TOTALS and there is a subquery in FROM, and there is WITH TOTALS on one of the levels, - * then when using LIMIT, you should read the data to the end, rather than cancel the query earlier, - * because if you cancel the query, we will not get `totals` data from the remote server. - * - * Another case: - * if there is WITH TOTALS and there is no ORDER BY, then read the data to the end, - * otherwise TOTALS is counted according to incomplete data. - */ - bool always_read_till_end = false; - - if (query.group_by_with_totals && !query.orderBy()) - always_read_till_end = true; - - if (!query.group_by_with_totals && hasWithTotalsInAnySubqueryInFromClause(query)) - always_read_till_end = true; - - SortDescription order_descr; - if (query.limit_with_ties) - { - if (!query.orderBy()) - throw Exception("LIMIT WITH TIES without ORDER BY", ErrorCodes::LOGICAL_ERROR); - order_descr = getSortDescription(query, *context); - } - - UInt64 limit_length; - UInt64 limit_offset; - std::tie(limit_length, limit_offset) = getLimitLengthAndOffset(query, *context); - - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, limit_length, limit_offset, always_read_till_end, false, query.limit_with_ties, order_descr); - }); - } -} - -void InterpreterSelectQuery::executeOffset(Pipeline & /* pipeline */) {} - -void InterpreterSelectQuery::executeWithFill(Pipeline & pipeline) -{ - auto & query = getSelectQuery(); - if (query.orderBy()) - { - SortDescription order_descr = getSortDescription(query, *context); - SortDescription fill_descr; - for (auto & desc : order_descr) - { - if (desc.with_fill) - fill_descr.push_back(desc); - } - - if (fill_descr.empty()) - return; - - pipeline.transform([&](auto & stream) - { - stream = std::make_shared(stream, fill_descr); - }); - } -} - void InterpreterSelectQuery::executeWithFill(QueryPipeline & pipeline) { auto & query = getSelectQuery(); @@ -2557,18 +1907,6 @@ void InterpreterSelectQuery::executeOffset(QueryPipeline & pipeline) } } - -void InterpreterSelectQuery::executeExtremes(Pipeline & pipeline) -{ - if (!context->getSettingsRef().extremes) - return; - - pipeline.transform([&](auto & stream) - { - stream->enableExtremes(); - }); -} - void InterpreterSelectQuery::executeExtremes(QueryPipeline & pipeline) { if (!context->getSettingsRef().extremes) @@ -2577,23 +1915,6 @@ void InterpreterSelectQuery::executeExtremes(QueryPipeline & pipeline) pipeline.addExtremesTransform(); } - -void InterpreterSelectQuery::executeSubqueriesInSetsAndJoins(Pipeline & pipeline, const SubqueriesForSets & subqueries_for_sets) -{ - /// Merge streams to one. Use MergeSorting if data was read in sorted order, Union otherwise. - if (query_info.input_sorting_info) - { - if (pipeline.stream_with_non_joined_data) - throw Exception("Using read in order optimization, but has stream with non-joined data in pipeline", ErrorCodes::LOGICAL_ERROR); - executeMergeSorted(pipeline, query_info.input_sorting_info->order_key_prefix_descr, 0); - } - else - executeUnion(pipeline, {}); - - pipeline.firstStream() = std::make_shared( - pipeline.firstStream(), subqueries_for_sets, *context); -} - void InterpreterSelectQuery::executeSubqueriesInSetsAndJoins(QueryPipeline & pipeline, const SubqueriesForSets & subqueries_for_sets) { if (query_info.input_sorting_info) @@ -2610,25 +1931,6 @@ void InterpreterSelectQuery::executeSubqueriesInSetsAndJoins(QueryPipeline & pip } -void InterpreterSelectQuery::unifyStreams(Pipeline & pipeline, Block header) -{ - /// Unify streams in case they have different headers. - - /// TODO: remove previous addition of _dummy column. - if (header.columns() > 1 && header.has("_dummy")) - header.erase("_dummy"); - - for (auto & stream : pipeline.streams) - { - auto stream_header = stream->getHeader(); - auto mode = ConvertingBlockInputStream::MatchColumnsMode::Name; - - if (!blocksHaveEqualStructure(header, stream_header)) - stream = std::make_shared(stream, header, mode); - } -} - - void InterpreterSelectQuery::ignoreWithTotals() { getSelectQuery().group_by_with_totals = false; diff --git a/src/Interpreters/InterpreterSelectQuery.h b/src/Interpreters/InterpreterSelectQuery.h index b97ff65e988..ca7fb4c72ba 100644 --- a/src/Interpreters/InterpreterSelectQuery.h +++ b/src/Interpreters/InterpreterSelectQuery.h @@ -77,12 +77,6 @@ public: /// Execute a query. Get the stream of blocks to read. BlockIO execute() override; - /// Execute the query and return multuple streams for parallel processing. - BlockInputStreams executeWithMultipleStreams(QueryPipeline & parent_pipeline); - - QueryPipeline executeWithProcessors() override; - bool canExecuteWithProcessors() const override { return true; } - bool ignoreLimits() const override { return options.ignore_limits; } bool ignoreQuota() const override { return options.ignore_quota; } @@ -108,89 +102,15 @@ private: Block getSampleBlockImpl(); - struct Pipeline - { - /** Streams of data. - * The source data streams are produced in the executeFetchColumns function. - * Then they are converted (wrapped in other streams) using the `execute*` functions, - * to get the whole pipeline running the query. - */ - BlockInputStreams streams; - - /** When executing FULL or RIGHT JOIN, there will be a data stream from which you can read "not joined" rows. - * It has a special meaning, since reading from it should be done after reading from the main streams. - * It is appended to the main streams in UnionBlockInputStream or ParallelAggregatingBlockInputStream. - */ - BlockInputStreamPtr stream_with_non_joined_data; - bool union_stream = false; - - /// Cache value of InterpreterSelectQuery::max_streams - size_t max_threads = 1; - - BlockInputStreamPtr & firstStream() { return streams.at(0); } - - template - void transform(Transform && transformation) - { - for (auto & stream : streams) - transformation(stream); - - if (stream_with_non_joined_data) - transformation(stream_with_non_joined_data); - } - - bool hasMoreThanOneStream() const - { - return streams.size() + (stream_with_non_joined_data ? 1 : 0) > 1; - } - - /// Resulting stream is mix of other streams data. Distinct and/or order guaranties are broken. - bool hasMixedStreams() const - { - return hasMoreThanOneStream() || union_stream; - } - - bool hasDelayedStream() const { return stream_with_non_joined_data != nullptr; } - bool initialized() const { return !streams.empty(); } - - /// Compatibility with QueryPipeline (Processors) - void setMaxThreads(size_t max_threads_) { max_threads = max_threads_; } - size_t getNumThreads() const { return max_threads; } - }; - - template - void executeImpl(TPipeline & pipeline, const BlockInputStreamPtr & prepared_input, std::optional prepared_pipe, QueryPipeline & save_context_and_storage); + void executeImpl(QueryPipeline & pipeline, const BlockInputStreamPtr & prepared_input, std::optional prepared_pipe); /// Different stages of query execution. - /// dry_run - don't read from table, use empty header block instead. - void executeWithMultipleStreamsImpl(Pipeline & pipeline, const BlockInputStreamPtr & input, bool dry_run); - - template - void executeFetchColumns(QueryProcessingStage::Enum processing_stage, TPipeline & pipeline, + void executeFetchColumns( + QueryProcessingStage::Enum processing_stage, + QueryPipeline & pipeline, const PrewhereInfoPtr & prewhere_info, - const Names & columns_to_remove_after_prewhere, - QueryPipeline & save_context_and_storage); - - void executeWhere(Pipeline & pipeline, const ExpressionActionsPtr & expression, bool remove_filter); - void executeAggregation(Pipeline & pipeline, const ExpressionActionsPtr & expression, bool overflow_row, bool final); - void executeMergeAggregated(Pipeline & pipeline, bool overflow_row, bool final); - void executeTotalsAndHaving(Pipeline & pipeline, bool has_having, const ExpressionActionsPtr & expression, bool overflow_row, bool final); - void executeHaving(Pipeline & pipeline, const ExpressionActionsPtr & expression); - static void executeExpression(Pipeline & pipeline, const ExpressionActionsPtr & expression); - void executeOrder(Pipeline & pipeline, InputSortingInfoPtr sorting_info); - void executeWithFill(Pipeline & pipeline); - void executeMergeSorted(Pipeline & pipeline); - void executePreLimit(Pipeline & pipeline); - void executeUnion(Pipeline & pipeline, Block header); - void executeLimitBy(Pipeline & pipeline); - void executeLimit(Pipeline & pipeline); - void executeOffset(Pipeline & pipeline); - static void executeProjection(Pipeline & pipeline, const ExpressionActionsPtr & expression); - void executeDistinct(Pipeline & pipeline, bool before_order, Names columns); - void executeExtremes(Pipeline & pipeline); - void executeSubqueriesInSetsAndJoins(Pipeline & pipeline, const std::unordered_map & subqueries_for_sets); - void executeMergeSorted(Pipeline & pipeline, const SortDescription & sort_description, UInt64 limit); + const Names & columns_to_remove_after_prewhere); void executeWhere(QueryPipeline & pipeline, const ExpressionActionsPtr & expression, bool remove_filter); void executeAggregation(QueryPipeline & pipeline, const ExpressionActionsPtr & expression, bool overflow_row, bool final); @@ -213,17 +133,12 @@ private: String generateFilterActions(ExpressionActionsPtr & actions, const ASTPtr & row_policy_filter, const Names & prerequisite_columns = {}) const; - /// Add ConvertingBlockInputStream to specified header. - static void unifyStreams(Pipeline & pipeline, Block header); - enum class Modificator { ROLLUP = 0, CUBE = 1 }; - void executeRollupOrCube(Pipeline & pipeline, Modificator modificator); - void executeRollupOrCube(QueryPipeline & pipeline, Modificator modificator); /** If there is a SETTINGS section in the SELECT query, then apply settings from it. diff --git a/src/Interpreters/InterpreterSelectWithUnionQuery.cpp b/src/Interpreters/InterpreterSelectWithUnionQuery.cpp index 7fe124b31e6..7b86616555a 100644 --- a/src/Interpreters/InterpreterSelectWithUnionQuery.cpp +++ b/src/Interpreters/InterpreterSelectWithUnionQuery.cpp @@ -3,15 +3,9 @@ #include #include #include -#include -#include -#include -#include #include -#include #include #include -#include #include #include @@ -180,69 +174,10 @@ Block InterpreterSelectWithUnionQuery::getSampleBlock( } -BlockInputStreams InterpreterSelectWithUnionQuery::executeWithMultipleStreams(QueryPipeline & parent_pipeline) -{ - BlockInputStreams nested_streams; - - for (auto & interpreter : nested_interpreters) - { - BlockInputStreams streams = interpreter->executeWithMultipleStreams(parent_pipeline); - nested_streams.insert(nested_streams.end(), streams.begin(), streams.end()); - } - - /// Unify data structure. - if (nested_interpreters.size() > 1) - { - for (auto & stream : nested_streams) - stream = std::make_shared(stream, result_header,ConvertingBlockInputStream::MatchColumnsMode::Position); - parent_pipeline.addInterpreterContext(context); - } - - /// Update max_streams due to: - /// - max_distributed_connections for Distributed() engine - /// - max_streams_to_max_threads_ratio - /// - /// XXX: res.pipeline.getMaxThreads() cannot be used since it is capped to - /// number of streams, which is empty for non-Processors case. - max_streams = (*std::min_element(nested_interpreters.begin(), nested_interpreters.end(), [](const auto &a, const auto &b) - { - return a->getMaxStreams() < b->getMaxStreams(); - }))->getMaxStreams(); - - return nested_streams; -} - - BlockIO InterpreterSelectWithUnionQuery::execute() { BlockIO res; - BlockInputStreams nested_streams = executeWithMultipleStreams(res.pipeline); - BlockInputStreamPtr result_stream; - - if (nested_streams.empty()) - { - result_stream = std::make_shared(getSampleBlock()); - } - else if (nested_streams.size() == 1) - { - result_stream = nested_streams.front(); - nested_streams.clear(); - } - else - { - result_stream = std::make_shared(nested_streams, nullptr, max_streams); - nested_streams.clear(); - } - - res.in = result_stream; - res.pipeline.addInterpreterContext(context); - return res; -} - - -QueryPipeline InterpreterSelectWithUnionQuery::executeWithProcessors() -{ - QueryPipeline main_pipeline; + QueryPipeline & main_pipeline = res.pipeline; std::vector pipelines; bool has_main_pipeline = false; @@ -254,12 +189,12 @@ QueryPipeline InterpreterSelectWithUnionQuery::executeWithProcessors() if (!has_main_pipeline) { has_main_pipeline = true; - main_pipeline = interpreter->executeWithProcessors(); + main_pipeline = interpreter->execute().pipeline; headers.emplace_back(main_pipeline.getHeader()); } else { - pipelines.emplace_back(interpreter->executeWithProcessors()); + pipelines.emplace_back(interpreter->execute().pipeline); headers.emplace_back(pipelines.back().getHeader()); } } @@ -280,7 +215,7 @@ QueryPipeline InterpreterSelectWithUnionQuery::executeWithProcessors() main_pipeline.addInterpreterContext(context); - return main_pipeline; + return res; } diff --git a/src/Interpreters/InterpreterSelectWithUnionQuery.h b/src/Interpreters/InterpreterSelectWithUnionQuery.h index c7a8e09578b..3b5fe533a84 100644 --- a/src/Interpreters/InterpreterSelectWithUnionQuery.h +++ b/src/Interpreters/InterpreterSelectWithUnionQuery.h @@ -29,12 +29,6 @@ public: BlockIO execute() override; - /// Execute the query without union of streams. - BlockInputStreams executeWithMultipleStreams(QueryPipeline & parent_pipeline); - - QueryPipeline executeWithProcessors() override; - bool canExecuteWithProcessors() const override { return true; } - bool ignoreLimits() const override { return options.ignore_limits; } bool ignoreQuota() const override { return options.ignore_quota; } diff --git a/src/Interpreters/InterpreterSetRoleQuery.cpp b/src/Interpreters/InterpreterSetRoleQuery.cpp index f8e0167d748..c627061dd51 100644 --- a/src/Interpreters/InterpreterSetRoleQuery.cpp +++ b/src/Interpreters/InterpreterSetRoleQuery.cpp @@ -62,7 +62,7 @@ void InterpreterSetRoleQuery::setRole(const ASTSetRoleQuery & query) void InterpreterSetRoleQuery::setDefaultRole(const ASTSetRoleQuery & query) { - context.checkAccess(AccessType::CREATE_USER | AccessType::DROP_USER); + context.checkAccess(AccessType::ALTER_USER); auto & access_control = context.getAccessControlManager(); std::vector to_users = ExtendedRoleSet{*query.to_users, access_control, context.getUserID()}.getMatchingIDs(access_control); diff --git a/src/Interpreters/InterpreterShowCreateAccessEntityQuery.cpp b/src/Interpreters/InterpreterShowCreateAccessEntityQuery.cpp index 87e1265f793..e37c31aab22 100644 --- a/src/Interpreters/InterpreterShowCreateAccessEntityQuery.cpp +++ b/src/Interpreters/InterpreterShowCreateAccessEntityQuery.cpp @@ -56,10 +56,10 @@ namespace query->default_roles = user.default_roles.toASTWithNames(*manager); } - if (attach_mode && (user.authentication.getType() != Authentication::NO_PASSWORD)) + if (user.authentication.getType() != Authentication::NO_PASSWORD) { - /// We don't show password unless it's an ATTACH statement. query->authentication = user.authentication; + query->show_password = attach_mode; /// We don't show password unless it's an ATTACH statement. } if (!user.settings.empty()) diff --git a/src/Interpreters/InterpreterShowCreateQuery.cpp b/src/Interpreters/InterpreterShowCreateQuery.cpp index 9938910cf1e..30005c7b169 100644 --- a/src/Interpreters/InterpreterShowCreateQuery.cpp +++ b/src/Interpreters/InterpreterShowCreateQuery.cpp @@ -50,7 +50,7 @@ BlockInputStreamPtr InterpreterShowCreateQuery::executeImpl() auto resolve_table_type = show_query->temporary ? Context::ResolveExternal : Context::ResolveOrdinary; auto table_id = context.resolveStorageID(*show_query, resolve_table_type); context.checkAccess(AccessType::SHOW_COLUMNS, table_id); - create_query = DatabaseCatalog::instance().getDatabase(table_id.database_name)->getCreateTableQuery(table_id.table_name); + create_query = DatabaseCatalog::instance().getDatabase(table_id.database_name)->getCreateTableQuery(table_id.table_name, context); } else if ((show_query = query_ptr->as())) { diff --git a/src/Interpreters/InterpreterSystemQuery.cpp b/src/Interpreters/InterpreterSystemQuery.cpp index f3d48651148..fedda7cab50 100644 --- a/src/Interpreters/InterpreterSystemQuery.cpp +++ b/src/Interpreters/InterpreterSystemQuery.cpp @@ -144,7 +144,7 @@ void InterpreterSystemQuery::startStopAction(StorageActionBlockType action_type, auto access = context.getAccess(); for (auto & elem : DatabaseCatalog::instance().getDatabases()) { - for (auto iterator = elem.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = elem.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { if (!access->isGranted(log, getRequiredAccessType(action_type), elem.first, iterator->name())) continue; @@ -321,7 +321,7 @@ StoragePtr InterpreterSystemQuery::tryRestartReplica(const StorageID & replica, context.checkAccess(AccessType::SYSTEM_RESTART_REPLICA, replica); auto table_ddl_guard = need_ddl_guard ? DatabaseCatalog::instance().getDDLGuard(replica.getDatabaseName(), replica.getTableName()) : nullptr; - auto [database, table] = DatabaseCatalog::instance().tryGetDatabaseAndTable(replica); + auto [database, table] = DatabaseCatalog::instance().tryGetDatabaseAndTable(replica, context); ASTPtr create_ast; /// Detach actions @@ -332,7 +332,7 @@ StoragePtr InterpreterSystemQuery::tryRestartReplica(const StorageID & replica, { /// If table was already dropped by anyone, an exception will be thrown auto table_lock = table->lockExclusively(context.getCurrentQueryId(), context.getSettingsRef().lock_acquire_timeout); - create_ast = database->getCreateTableQuery(replica.table_name); + create_ast = database->getCreateTableQuery(replica.table_name, context); database->detachTable(replica.table_name); } @@ -369,7 +369,7 @@ void InterpreterSystemQuery::restartReplicas(Context & system_context) for (auto & elem : catalog.getDatabases()) { DatabasePtr & database = elem.second; - for (auto iterator = database->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = database->getTablesIterator(context); iterator->isValid(); iterator->next()) { if (dynamic_cast(iterator->table().get())) replica_names.emplace_back(StorageID{database->getDatabaseName(), iterator->name()}); @@ -394,7 +394,7 @@ void InterpreterSystemQuery::restartReplicas(Context & system_context) void InterpreterSystemQuery::syncReplica(ASTSystemQuery &) { context.checkAccess(AccessType::SYSTEM_SYNC_REPLICA, table_id); - StoragePtr table = DatabaseCatalog::instance().getTable(table_id); + StoragePtr table = DatabaseCatalog::instance().getTable(table_id, context); if (auto * storage_replicated = dynamic_cast(table.get())) { @@ -416,7 +416,7 @@ void InterpreterSystemQuery::flushDistributed(ASTSystemQuery &) { context.checkAccess(AccessType::SYSTEM_FLUSH_DISTRIBUTED, table_id); - if (auto * storage_distributed = dynamic_cast(DatabaseCatalog::instance().getTable(table_id).get())) + if (auto * storage_distributed = dynamic_cast(DatabaseCatalog::instance().getTable(table_id, context).get())) storage_distributed->flushClusterNodesAllData(); else throw Exception("Table " + table_id.getNameForLogs() + " is not distributed", ErrorCodes::BAD_ARGUMENTS); diff --git a/src/Interpreters/InterpreterWatchQuery.cpp b/src/Interpreters/InterpreterWatchQuery.cpp index dc1ae6a7cad..489be488b4d 100644 --- a/src/Interpreters/InterpreterWatchQuery.cpp +++ b/src/Interpreters/InterpreterWatchQuery.cpp @@ -40,7 +40,7 @@ BlockIO InterpreterWatchQuery::execute() auto table_id = context.resolveStorageID(query, Context::ResolveOrdinary); /// Get storage - storage = DatabaseCatalog::instance().tryGetTable(table_id); + storage = DatabaseCatalog::instance().tryGetTable(table_id, context); if (!storage) throw Exception("Table " + table_id.getNameForLogs() + " doesn't exist.", diff --git a/src/Interpreters/JoinedTables.cpp b/src/Interpreters/JoinedTables.cpp index 3bd883dcce8..7450890952a 100644 --- a/src/Interpreters/JoinedTables.cpp +++ b/src/Interpreters/JoinedTables.cpp @@ -181,7 +181,7 @@ StoragePtr JoinedTables::getLeftTableStorage() } /// Read from table. Even without table expression (implicit SELECT ... FROM system.one). - return DatabaseCatalog::instance().getTable(table_id); + return DatabaseCatalog::instance().getTable(table_id, context); } bool JoinedTables::resolveTables() @@ -261,7 +261,7 @@ std::shared_ptr JoinedTables::makeTableJoin(const ASTSelectQuery & se if (table_to_join.database_and_table_name) { auto joined_table_id = context.resolveStorageID(table_to_join.database_and_table_name); - StoragePtr table = DatabaseCatalog::instance().tryGetTable(joined_table_id); + StoragePtr table = DatabaseCatalog::instance().tryGetTable(joined_table_id, context); if (table) { if (dynamic_cast(table.get()) || diff --git a/src/Interpreters/MutationsInterpreter.cpp b/src/Interpreters/MutationsInterpreter.cpp index 6962885534c..224c3cab02b 100644 --- a/src/Interpreters/MutationsInterpreter.cpp +++ b/src/Interpreters/MutationsInterpreter.cpp @@ -184,7 +184,7 @@ bool isStorageTouchedByMutations( /// For some reason it may copy context and and give it into ExpressionBlockInputStream /// after that we will use context from destroyed stack frame in our stream. InterpreterSelectQuery interpreter(select_query, context_copy, storage, SelectQueryOptions().ignoreLimits()); - BlockInputStreamPtr in = interpreter.execute().in; + BlockInputStreamPtr in = interpreter.execute().getInputStream(); Block block = in->read(); if (!block.rows()) @@ -687,7 +687,7 @@ void MutationsInterpreter::validate(TableStructureReadLockHolder &) } /// Do not use getSampleBlock in order to check the whole pipeline. - Block first_stage_header = select_interpreter->execute().in->getHeader(); + Block first_stage_header = select_interpreter->execute().getInputStream()->getHeader(); BlockInputStreamPtr in = std::make_shared(first_stage_header); addStreamsForLaterStages(stages, in)->getHeader(); } @@ -697,7 +697,7 @@ BlockInputStreamPtr MutationsInterpreter::execute(TableStructureReadLockHolder & if (!can_execute) throw Exception("Cannot execute mutations interpreter because can_execute flag set to false", ErrorCodes::LOGICAL_ERROR); - BlockInputStreamPtr in = select_interpreter->execute().in; + BlockInputStreamPtr in = select_interpreter->execute().getInputStream(); auto result_stream = addStreamsForLaterStages(stages, in); diff --git a/src/Interpreters/SubqueryForSet.cpp b/src/Interpreters/SubqueryForSet.cpp index 72831970de7..ac5c1e3d9eb 100644 --- a/src/Interpreters/SubqueryForSet.cpp +++ b/src/Interpreters/SubqueryForSet.cpp @@ -13,7 +13,7 @@ void SubqueryForSet::makeSource(std::shared_ptr { joined_block_aliases = std::move(joined_block_aliases_); source = std::make_shared(interpreter->getSampleBlock(), - [interpreter]() mutable { return interpreter->execute().in; }); + [interpreter]() mutable { return interpreter->execute().getInputStream(); }); sample_block = source->getHeader(); renameColumns(sample_block); diff --git a/src/Interpreters/SyntaxAnalyzer.cpp b/src/Interpreters/SyntaxAnalyzer.cpp index b3d566dbdc8..b5f86b87fdc 100644 --- a/src/Interpreters/SyntaxAnalyzer.cpp +++ b/src/Interpreters/SyntaxAnalyzer.cpp @@ -839,7 +839,7 @@ SyntaxAnalyzerResultPtr SyntaxAnalyzer::analyzeSelect( return std::make_shared(result); } -SyntaxAnalyzerResultPtr SyntaxAnalyzer::analyze(ASTPtr & query, const NamesAndTypesList & source_columns, ConstStoragePtr storage) const +SyntaxAnalyzerResultPtr SyntaxAnalyzer::analyze(ASTPtr & query, const NamesAndTypesList & source_columns, ConstStoragePtr storage, bool allow_aggregations) const { if (query->as()) throw Exception("Not select analyze for select asts.", ErrorCodes::LOGICAL_ERROR); @@ -855,7 +855,20 @@ SyntaxAnalyzerResultPtr SyntaxAnalyzer::analyze(ASTPtr & query, const NamesAndTy optimizeIf(query, result.aliases, settings.optimize_if_chain_to_miltiif); - assertNoAggregates(query, "in wrong place"); + if (allow_aggregations) + { + GetAggregatesVisitor::Data data; + GetAggregatesVisitor(data).visit(query); + + /// There can not be other aggregate functions within the aggregate functions. + for (const ASTFunction * node : data.aggregates) + for (auto & arg : node->arguments->children) + assertNoAggregates(arg, "inside another aggregate function"); + result.aggregates = data.aggregates; + } + else + assertNoAggregates(query, "in wrong place"); + result.collectUsedColumns(query); return std::make_shared(result); } diff --git a/src/Interpreters/SyntaxAnalyzer.h b/src/Interpreters/SyntaxAnalyzer.h index dda0add38db..abacb25ac4d 100644 --- a/src/Interpreters/SyntaxAnalyzer.h +++ b/src/Interpreters/SyntaxAnalyzer.h @@ -86,7 +86,7 @@ public: {} /// Analyze and rewrite not select query - SyntaxAnalyzerResultPtr analyze(ASTPtr & query, const NamesAndTypesList & source_columns_, ConstStoragePtr storage = {}) const; + SyntaxAnalyzerResultPtr analyze(ASTPtr & query, const NamesAndTypesList & source_columns_, ConstStoragePtr storage = {}, bool allow_aggregations = false) const; /// Analyze and rewrite select query SyntaxAnalyzerResultPtr analyzeSelect( diff --git a/src/Interpreters/SystemLog.h b/src/Interpreters/SystemLog.h index 3c0d2159ef9..649cfa28e6e 100644 --- a/src/Interpreters/SystemLog.h +++ b/src/Interpreters/SystemLog.h @@ -431,7 +431,7 @@ void SystemLog::prepareTable() { String description = table_id.getNameForLogs(); - table = DatabaseCatalog::instance().tryGetTable(table_id); + table = DatabaseCatalog::instance().tryGetTable(table_id, context); if (table) { @@ -442,7 +442,7 @@ void SystemLog::prepareTable() { /// Rename the existing table. int suffix = 0; - while (DatabaseCatalog::instance().isTableExist({table_id.database_name, table_id.table_name + "_" + toString(suffix)})) + while (DatabaseCatalog::instance().isTableExist({table_id.database_name, table_id.table_name + "_" + toString(suffix)}, context)) ++suffix; auto rename = std::make_shared(); @@ -483,7 +483,7 @@ void SystemLog::prepareTable() interpreter.setInternal(true); interpreter.execute(); - table = DatabaseCatalog::instance().getTable(table_id); + table = DatabaseCatalog::instance().getTable(table_id, context); } is_prepared = true; diff --git a/src/Interpreters/executeQuery.cpp b/src/Interpreters/executeQuery.cpp index c69631b2665..8fc799d0b48 100644 --- a/src/Interpreters/executeQuery.cpp +++ b/src/Interpreters/executeQuery.cpp @@ -280,7 +280,6 @@ static std::tuple executeQueryImpl( /// Copy query into string. It will be written to log and presented in processlist. If an INSERT query, string will not include data to insertion. String query(begin, query_end); BlockIO res; - QueryPipeline & pipeline = res.pipeline; String query_for_logging; @@ -338,7 +337,6 @@ static std::tuple executeQueryImpl( context.resetInputCallbacks(); auto interpreter = InterpreterFactory::get(ast, context, stage); - bool use_processors = interpreter->canExecuteWithProcessors(); std::shared_ptr quota; if (!interpreter->ignoreQuota()) @@ -358,10 +356,12 @@ static std::tuple executeQueryImpl( limits.size_limits = SizeLimits(settings.max_result_rows, settings.max_result_bytes, settings.result_overflow_mode); } - if (use_processors) - pipeline = interpreter->executeWithProcessors(); - else - res = interpreter->execute(); + res = interpreter->execute(); + QueryPipeline & pipeline = res.pipeline; + bool use_processors = pipeline.initialized(); + + if (res.pipeline.initialized()) + use_processors = true; if (const auto * insert_interpreter = typeid_cast(&*interpreter)) { @@ -390,7 +390,7 @@ static std::tuple executeQueryImpl( /// Limits apply only to the final result. pipeline.setProgressCallback(context.getProgressCallback()); pipeline.setProcessListElement(context.getProcessListElement()); - if (stage == QueryProcessingStage::Complete) + if (stage == QueryProcessingStage::Complete && !pipeline.isCompleted()) { pipeline.resize(1); pipeline.addSimpleTransform([&](const Block & header) @@ -771,29 +771,36 @@ void executeQuery( if (ast_query_with_output && ast_query_with_output->settings_ast) InterpreterSetQuery(ast_query_with_output->settings_ast, context).executeForCurrentContext(); - pipeline.addSimpleTransform([](const Block & header) + if (!pipeline.isCompleted()) { - return std::make_shared(header); - }); + pipeline.addSimpleTransform([](const Block & header) + { + return std::make_shared(header); + }); - auto out = context.getOutputFormatProcessor(format_name, *out_buf, pipeline.getHeader()); - out->setAutoFlush(); + auto out = context.getOutputFormatProcessor(format_name, *out_buf, pipeline.getHeader()); + out->setAutoFlush(); - /// Save previous progress callback if any. TODO Do it more conveniently. - auto previous_progress_callback = context.getProgressCallback(); + /// Save previous progress callback if any. TODO Do it more conveniently. + auto previous_progress_callback = context.getProgressCallback(); - /// NOTE Progress callback takes shared ownership of 'out'. - pipeline.setProgressCallback([out, previous_progress_callback] (const Progress & progress) + /// NOTE Progress callback takes shared ownership of 'out'. + pipeline.setProgressCallback([out, previous_progress_callback] (const Progress & progress) + { + if (previous_progress_callback) + previous_progress_callback(progress); + out->onProgress(progress); + }); + + if (set_result_details) + set_result_details(context.getClientInfo().current_query_id, out->getContentType(), format_name, DateLUT::instance().getTimeZone()); + + pipeline.setOutputFormat(std::move(out)); + } + else { - if (previous_progress_callback) - previous_progress_callback(progress); - out->onProgress(progress); - }); - - if (set_result_details) - set_result_details(context.getClientInfo().current_query_id, out->getContentType(), format_name, DateLUT::instance().getTimeZone()); - - pipeline.setOutput(std::move(out)); + pipeline.setProgressCallback(context.getProgressCallback()); + } { auto executor = pipeline.execute(); diff --git a/src/Interpreters/getTableExpressions.cpp b/src/Interpreters/getTableExpressions.cpp index b5444f73b35..8467a98685d 100644 --- a/src/Interpreters/getTableExpressions.cpp +++ b/src/Interpreters/getTableExpressions.cpp @@ -96,7 +96,7 @@ static NamesAndTypesList getColumnsFromTableExpression(const ASTTableExpression else if (table_expression.database_and_table_name) { auto table_id = context.resolveStorageID(table_expression.database_and_table_name); - const auto & table = DatabaseCatalog::instance().getTable(table_id); + const auto & table = DatabaseCatalog::instance().getTable(table_id, context); const auto & columns = table->getColumns(); names_and_type_list = columns.getOrdinary(); materialized = columns.getMaterialized(); diff --git a/src/Interpreters/interpretSubquery.cpp b/src/Interpreters/interpretSubquery.cpp index e108db1af30..c94759897f5 100644 --- a/src/Interpreters/interpretSubquery.cpp +++ b/src/Interpreters/interpretSubquery.cpp @@ -96,7 +96,7 @@ std::shared_ptr interpretSubquery( else { auto table_id = context.resolveStorageID(table_expression); - const auto & storage = DatabaseCatalog::instance().getTable(table_id); + const auto & storage = DatabaseCatalog::instance().getTable(table_id, context); columns = storage->getColumns().getOrdinary(); select_query->replaceDatabaseAndTable(table_id); } diff --git a/src/Interpreters/tests/hash_map3.cpp b/src/Interpreters/tests/hash_map3.cpp index 2207edc6cc1..1b4ce8eac77 100644 --- a/src/Interpreters/tests/hash_map3.cpp +++ b/src/Interpreters/tests/hash_map3.cpp @@ -66,7 +66,8 @@ int main(int, char **) UInt64, SimpleHash, Grower, - HashTableAllocatorWithStackMemory<4 * 24>>; + HashTableAllocatorWithStackMemory< + 4 * sizeof(HashMapCell)>>; Map map; diff --git a/src/Parsers/ASTAlterQuery.cpp b/src/Parsers/ASTAlterQuery.cpp index 9ec2fad5768..f323f66be17 100644 --- a/src/Parsers/ASTAlterQuery.cpp +++ b/src/Parsers/ASTAlterQuery.cpp @@ -181,13 +181,13 @@ void ASTAlterCommand::formatImpl( settings.ostr << " TO "; switch (move_destination_type) { - case PartDestinationType::DISK: + case DataDestinationType::DISK: settings.ostr << "DISK "; break; - case PartDestinationType::VOLUME: + case DataDestinationType::VOLUME: settings.ostr << "VOLUME "; break; - case PartDestinationType::TABLE: + case DataDestinationType::TABLE: settings.ostr << "TABLE "; if (!to_database.empty()) { @@ -201,7 +201,7 @@ void ASTAlterCommand::formatImpl( default: break; } - if (move_destination_type != PartDestinationType::TABLE) + if (move_destination_type != DataDestinationType::TABLE) { settings.ostr << quoteString(move_destination_name); } diff --git a/src/Parsers/ASTAlterQuery.h b/src/Parsers/ASTAlterQuery.h index 85e9a4d7552..a9ae06863a9 100644 --- a/src/Parsers/ASTAlterQuery.h +++ b/src/Parsers/ASTAlterQuery.h @@ -136,7 +136,7 @@ public: bool if_exists = false; /// option for DROP_COLUMN, MODIFY_COLUMN, COMMENT_COLUMN - PartDestinationType move_destination_type; /// option for MOVE PART/PARTITION + DataDestinationType move_destination_type; /// option for MOVE PART/PARTITION String move_destination_name; /// option for MOVE PART/PARTITION diff --git a/src/Parsers/ASTCreateUserQuery.cpp b/src/Parsers/ASTCreateUserQuery.cpp index c8e2a76dfa2..e5c1178285b 100644 --- a/src/Parsers/ASTCreateUserQuery.cpp +++ b/src/Parsers/ASTCreateUserQuery.cpp @@ -6,6 +6,12 @@ namespace DB { +namespace ErrorCodes +{ + extern const int LOGICAL_ERROR; +} + + namespace { void formatRenameTo(const String & new_name, const IAST::FormatSettings & settings) @@ -15,27 +21,51 @@ namespace } - void formatAuthentication(const Authentication & authentication, const IAST::FormatSettings & settings) + void formatAuthentication(const Authentication & authentication, bool show_password, const IAST::FormatSettings & settings) { - settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << " IDENTIFIED WITH " << (settings.hilite ? IAST::hilite_none : ""); - switch (authentication.getType()) + auto authentication_type = authentication.getType(); + if (authentication_type == Authentication::NO_PASSWORD) { - case Authentication::Type::NO_PASSWORD: - settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << "no_password" << (settings.hilite ? IAST::hilite_none : ""); - break; - case Authentication::Type::PLAINTEXT_PASSWORD: - settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << "plaintext_password BY " << (settings.hilite ? IAST::hilite_none : "") - << quoteString(authentication.getPassword()); - break; - case Authentication::Type::SHA256_PASSWORD: - settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << "sha256_hash BY " << (settings.hilite ? IAST::hilite_none : "") - << quoteString(authentication.getPasswordHashHex()); - break; - case Authentication::Type::DOUBLE_SHA1_PASSWORD: - settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << "double_sha1_hash BY " << (settings.hilite ? IAST::hilite_none : "") - << quoteString(authentication.getPasswordHashHex()); - break; + settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << " NOT IDENTIFIED" + << (settings.hilite ? IAST::hilite_none : ""); + return; } + + String authentication_type_name = Authentication::TypeInfo::get(authentication_type).name; + std::optional password; + + if (show_password) + { + switch (authentication_type) + { + case Authentication::PLAINTEXT_PASSWORD: + { + password = authentication.getPassword(); + break; + } + case Authentication::SHA256_PASSWORD: + { + authentication_type_name = "sha256_hash"; + password = authentication.getPasswordHashHex(); + break; + } + case Authentication::DOUBLE_SHA1_PASSWORD: + { + authentication_type_name = "double_sha1_hash"; + password = authentication.getPasswordHashHex(); + break; + } + + case Authentication::NO_PASSWORD: [[fallthrough]]; + case Authentication::MAX_TYPE: + throw Exception("AST: Unexpected authentication type " + toString(authentication_type), ErrorCodes::LOGICAL_ERROR); + } + } + + settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << " IDENTIFIED WITH " << authentication_type_name + << (settings.hilite ? IAST::hilite_none : ""); + if (password) + settings.ostr << (settings.hilite ? IAST::hilite_keyword : "") << " BY " << quoteString(*password); } @@ -190,7 +220,7 @@ void ASTCreateUserQuery::formatImpl(const FormatSettings & format, FormatState & formatRenameTo(new_name, format); if (authentication) - formatAuthentication(*authentication, format); + formatAuthentication(*authentication, show_password, format); if (hosts) formatHosts(nullptr, *hosts, format); diff --git a/src/Parsers/ASTCreateUserQuery.h b/src/Parsers/ASTCreateUserQuery.h index 54dc51d783b..28ef6c059da 100644 --- a/src/Parsers/ASTCreateUserQuery.h +++ b/src/Parsers/ASTCreateUserQuery.h @@ -12,14 +12,14 @@ class ASTExtendedRoleSet; class ASTSettingsProfileElements; /** CREATE USER [IF NOT EXISTS | OR REPLACE] name - * [IDENTIFIED [WITH {NO_PASSWORD|PLAINTEXT_PASSWORD|SHA256_PASSWORD|SHA256_HASH|DOUBLE_SHA1_PASSWORD|DOUBLE_SHA1_HASH}] BY {'password'|'hash'}] + * [NOT IDENTIFIED | IDENTIFIED [WITH {no_password|plaintext_password|sha256_password|sha256_hash|double_sha1_password|double_sha1_hash}] BY {'password'|'hash'}] * [HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] * [DEFAULT ROLE role [,...]] * [SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...] * * ALTER USER [IF EXISTS] name * [RENAME TO new_name] - * [IDENTIFIED [WITH {PLAINTEXT_PASSWORD|SHA256_PASSWORD|DOUBLE_SHA1_PASSWORD}] BY {'password'|'hash'}] + * [NOT IDENTIFIED | IDENTIFIED [WITH {no_password|plaintext_password|sha256_password|sha256_hash|double_sha1_password|double_sha1_hash}] BY {'password'|'hash'}] * [[ADD|DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] * [DEFAULT ROLE role [,...] | ALL | ALL EXCEPT role [,...] ] * [SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...] @@ -38,6 +38,7 @@ public: String new_name; std::optional authentication; + bool show_password = true; /// formatImpl() will show the password or hash. std::optional hosts; std::optional add_hosts; diff --git a/src/Parsers/ASTExtendedRoleSet.h b/src/Parsers/ASTExtendedRoleSet.h index 8d619e5d6a0..656f563bd9a 100644 --- a/src/Parsers/ASTExtendedRoleSet.h +++ b/src/Parsers/ASTExtendedRoleSet.h @@ -15,7 +15,10 @@ public: bool all = false; Strings except_names; bool except_current_user = false; - bool id_mode = false; /// If true then `names` and `except_names` keeps UUIDs, not names. + + bool id_mode = false; /// true if `names` and `except_names` keep UUIDs, not names. + bool can_contain_roles = true; /// true if this set can contain names of roles. + bool can_contain_users = true; /// true if this set can contain names of users. bool empty() const { return names.empty() && !current_user && !all; } void replaceCurrentUserTagWithName(const String & current_user_name); diff --git a/src/Parsers/ASTTTLElement.cpp b/src/Parsers/ASTTTLElement.cpp index 7e03a73e36d..1635d376d30 100644 --- a/src/Parsers/ASTTTLElement.cpp +++ b/src/Parsers/ASTTTLElement.cpp @@ -7,21 +7,90 @@ namespace DB { +ASTPtr ASTTTLElement::clone() const +{ + auto clone = std::make_shared(*this); + clone->children.clear(); + clone->ttl_expr_pos = -1; + clone->where_expr_pos = -1; + + clone->setExpression(clone->ttl_expr_pos, getExpression(ttl_expr_pos, true)); + clone->setExpression(clone->where_expr_pos, getExpression(where_expr_pos, true)); + + for (auto & expr : clone->group_by_key) + expr = expr->clone(); + for (auto & [name, expr] : clone->group_by_aggregations) + expr = expr->clone(); + + return clone; +} + void ASTTTLElement::formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const { - children.front()->formatImpl(settings, state, frame); - if (destination_type == PartDestinationType::DISK) + ttl()->formatImpl(settings, state, frame); + if (mode == TTLMode::MOVE && destination_type == DataDestinationType::DISK) { settings.ostr << " TO DISK " << quoteString(destination_name); } - else if (destination_type == PartDestinationType::VOLUME) + else if (mode == TTLMode::MOVE && destination_type == DataDestinationType::VOLUME) { settings.ostr << " TO VOLUME " << quoteString(destination_name); } - else if (destination_type == PartDestinationType::DELETE) + else if (mode == TTLMode::GROUP_BY) + { + settings.ostr << " GROUP BY "; + for (auto it = group_by_key.begin(); it != group_by_key.end(); ++it) + { + if (it != group_by_key.begin()) + settings.ostr << ", "; + (*it)->formatImpl(settings, state, frame); + } + if (!group_by_aggregations.empty()) + { + settings.ostr << " SET "; + for (auto it = group_by_aggregations.begin(); it != group_by_aggregations.end(); ++it) + { + if (it != group_by_aggregations.begin()) + settings.ostr << ", "; + settings.ostr << it->first << " = "; + it->second->formatImpl(settings, state, frame); + } + } + } + else if (mode == TTLMode::DELETE) { /// It would be better to output "DELETE" here but that will break compatibility with earlier versions. } + + if (where()) + { + settings.ostr << " WHERE "; + where()->formatImpl(settings, state, frame); + } +} + +void ASTTTLElement::setExpression(int & pos, ASTPtr && ast) +{ + if (ast) + { + if (pos == -1) + { + pos = children.size(); + children.emplace_back(ast); + } + else + children[pos] = ast; + } + else if (pos != -1) + { + children[pos] = ASTPtr{}; + pos = -1; + } +} + +ASTPtr ASTTTLElement::getExpression(int pos, bool clone) const +{ + return pos != -1 ? (clone ? children[pos]->clone() : children[pos]) : ASTPtr{}; } } diff --git a/src/Parsers/ASTTTLElement.h b/src/Parsers/ASTTTLElement.h index 02f70094e04..7ee1f4795ff 100644 --- a/src/Parsers/ASTTTLElement.h +++ b/src/Parsers/ASTTTLElement.h @@ -1,36 +1,54 @@ #pragma once #include -#include +#include +#include namespace DB { + /** Element of TTL expression. */ class ASTTTLElement : public IAST { public: - PartDestinationType destination_type; + TTLMode mode; + DataDestinationType destination_type; String destination_name; - ASTTTLElement(PartDestinationType destination_type_, const String & destination_name_) - : destination_type(destination_type_) + ASTs group_by_key; + std::vector> group_by_aggregations; + + ASTTTLElement(TTLMode mode_, DataDestinationType destination_type_, const String & destination_name_) + : mode(mode_) + , destination_type(destination_type_) , destination_name(destination_name_) + , ttl_expr_pos(-1) + , where_expr_pos(-1) { } String getID(char) const override { return "TTLElement"; } - ASTPtr clone() const override - { - auto clone = std::make_shared(*this); - clone->cloneChildren(); - return clone; - } + ASTPtr clone() const override; + + const ASTPtr ttl() const { return getExpression(ttl_expr_pos); } + const ASTPtr where() const { return getExpression(where_expr_pos); } + + void setTTL(ASTPtr && ast) { setExpression(ttl_expr_pos, std::forward(ast)); } + void setWhere(ASTPtr && ast) { setExpression(where_expr_pos, std::forward(ast)); } protected: void formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const override; + +private: + int ttl_expr_pos; + int where_expr_pos; + +private: + void setExpression(int & pos, ASTPtr && ast); + ASTPtr getExpression(int pos, bool clone = false) const; }; } diff --git a/src/Parsers/ExpressionElementParsers.cpp b/src/Parsers/ExpressionElementParsers.cpp index 70a8b282a72..785e6b25f98 100644 --- a/src/Parsers/ExpressionElementParsers.cpp +++ b/src/Parsers/ExpressionElementParsers.cpp @@ -1455,23 +1455,50 @@ bool ParserTTLElement::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) ParserKeyword s_to_disk("TO DISK"); ParserKeyword s_to_volume("TO VOLUME"); ParserKeyword s_delete("DELETE"); + ParserKeyword s_where("WHERE"); + ParserKeyword s_group_by("GROUP BY"); + ParserKeyword s_set("SET"); + ParserToken s_comma(TokenType::Comma); + ParserToken s_eq(TokenType::Equals); + + ParserIdentifier parser_identifier; ParserStringLiteral parser_string_literal; ParserExpression parser_exp; + ParserExpressionList parser_expression_list(false); - ASTPtr expr_elem; - if (!parser_exp.parse(pos, expr_elem, expected)) + ASTPtr ttl_expr; + if (!parser_exp.parse(pos, ttl_expr, expected)) return false; - PartDestinationType destination_type = PartDestinationType::DELETE; + TTLMode mode; + DataDestinationType destination_type = DataDestinationType::DELETE; String destination_name; - if (s_to_disk.ignore(pos)) - destination_type = PartDestinationType::DISK; - else if (s_to_volume.ignore(pos)) - destination_type = PartDestinationType::VOLUME; - else - s_delete.ignore(pos); - if (destination_type == PartDestinationType::DISK || destination_type == PartDestinationType::VOLUME) + if (s_to_disk.ignore(pos)) + { + mode = TTLMode::MOVE; + destination_type = DataDestinationType::DISK; + } + else if (s_to_volume.ignore(pos)) + { + mode = TTLMode::MOVE; + destination_type = DataDestinationType::VOLUME; + } + else if (s_group_by.ignore(pos)) + { + mode = TTLMode::GROUP_BY; + } + else + { + s_delete.ignore(pos); + mode = TTLMode::DELETE; + } + + ASTPtr where_expr; + ASTPtr ast_group_by_key; + std::vector> group_by_aggregations; + + if (mode == TTLMode::MOVE) { ASTPtr ast_space_name; if (!parser_string_literal.parse(pos, ast_space_name, expected)) @@ -1479,10 +1506,52 @@ bool ParserTTLElement::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) destination_name = ast_space_name->as().value.get(); } + else if (mode == TTLMode::GROUP_BY) + { + if (!parser_expression_list.parse(pos, ast_group_by_key, expected)) + return false; - node = std::make_shared(destination_type, destination_name); - node->children.push_back(expr_elem); + if (s_set.ignore(pos)) + { + while (true) + { + if (!group_by_aggregations.empty() && !s_comma.ignore(pos)) + break; + ASTPtr name; + ASTPtr value; + if (!parser_identifier.parse(pos, name, expected)) + return false; + if (!s_eq.ignore(pos)) + return false; + if (!parser_exp.parse(pos, value, expected)) + return false; + + String name_str; + if (!tryGetIdentifierNameInto(name, name_str)) + return false; + group_by_aggregations.emplace_back(name_str, std::move(value)); + } + } + } + else if (mode == TTLMode::DELETE && s_where.ignore(pos)) + { + if (!parser_exp.parse(pos, where_expr, expected)) + return false; + } + + auto ttl_element = std::make_shared(mode, destination_type, destination_name); + ttl_element->setTTL(std::move(ttl_expr)); + if (where_expr) + ttl_element->setWhere(std::move(where_expr)); + + if (mode == TTLMode::GROUP_BY) + { + ttl_element->group_by_key = std::move(ast_group_by_key->children); + ttl_element->group_by_aggregations = std::move(group_by_aggregations); + } + + node = ttl_element; return true; } diff --git a/src/Parsers/ParserAlterQuery.cpp b/src/Parsers/ParserAlterQuery.cpp index 623bca440bb..f90d010e9de 100644 --- a/src/Parsers/ParserAlterQuery.cpp +++ b/src/Parsers/ParserAlterQuery.cpp @@ -260,19 +260,19 @@ bool ParserAlterCommand::parseImpl(Pos & pos, ASTPtr & node, Expected & expected command->part = true; if (s_to_disk.ignore(pos)) - command->move_destination_type = PartDestinationType::DISK; + command->move_destination_type = DataDestinationType::DISK; else if (s_to_volume.ignore(pos)) - command->move_destination_type = PartDestinationType::VOLUME; + command->move_destination_type = DataDestinationType::VOLUME; else if (s_to_table.ignore(pos)) { if (!parseDatabaseAndTableName(pos, expected, command->to_database, command->to_table)) return false; - command->move_destination_type = PartDestinationType::TABLE; + command->move_destination_type = DataDestinationType::TABLE; } else return false; - if (command->move_destination_type != PartDestinationType::TABLE) + if (command->move_destination_type != DataDestinationType::TABLE) { ASTPtr ast_space_name; if (!parser_string_literal.parse(pos, ast_space_name, expected)) @@ -289,19 +289,19 @@ bool ParserAlterCommand::parseImpl(Pos & pos, ASTPtr & node, Expected & expected command->type = ASTAlterCommand::MOVE_PARTITION; if (s_to_disk.ignore(pos)) - command->move_destination_type = PartDestinationType::DISK; + command->move_destination_type = DataDestinationType::DISK; else if (s_to_volume.ignore(pos)) - command->move_destination_type = PartDestinationType::VOLUME; + command->move_destination_type = DataDestinationType::VOLUME; else if (s_to_table.ignore(pos)) { if (!parseDatabaseAndTableName(pos, expected, command->to_database, command->to_table)) return false; - command->move_destination_type = PartDestinationType::TABLE; + command->move_destination_type = DataDestinationType::TABLE; } else return false; - if (command->move_destination_type != PartDestinationType::TABLE) + if (command->move_destination_type != DataDestinationType::TABLE) { ASTPtr ast_space_name; if (!parser_string_literal.parse(pos, ast_space_name, expected)) diff --git a/src/Parsers/ParserCreateUserQuery.cpp b/src/Parsers/ParserCreateUserQuery.cpp index 76a06a0282f..3bf7e508220 100644 --- a/src/Parsers/ParserCreateUserQuery.cpp +++ b/src/Parsers/ParserCreateUserQuery.cpp @@ -35,100 +35,74 @@ namespace } - bool parseByPassword(IParserBase::Pos & pos, Expected & expected, String & password) - { - return IParserBase::wrapParseImpl(pos, [&] - { - if (!ParserKeyword{"BY"}.ignore(pos, expected)) - return false; - - ASTPtr ast; - if (!ParserStringLiteral{}.parse(pos, ast, expected)) - return false; - - password = ast->as().value.safeGet(); - return true; - }); - } - - bool parseAuthentication(IParserBase::Pos & pos, Expected & expected, std::optional & authentication) { return IParserBase::wrapParseImpl(pos, [&] { + if (ParserKeyword{"NOT IDENTIFIED"}.ignore(pos, expected)) + { + authentication = Authentication{Authentication::NO_PASSWORD}; + return true; + } + if (!ParserKeyword{"IDENTIFIED"}.ignore(pos, expected)) return false; - if (!ParserKeyword{"WITH"}.ignore(pos, expected)) + std::optional type; + bool expect_password = false; + bool expect_hash = false; + + if (ParserKeyword{"WITH"}.ignore(pos, expected)) { - String password; - if (!parseByPassword(pos, expected, password)) + for (auto check_type : ext::range(Authentication::MAX_TYPE)) + { + if (ParserKeyword{Authentication::TypeInfo::get(check_type).raw_name}.ignore(pos, expected)) + { + type = check_type; + expect_password = (check_type != Authentication::NO_PASSWORD); + break; + } + } + + if (!type) + { + if (ParserKeyword{"SHA256_HASH"}.ignore(pos, expected)) + { + type = Authentication::SHA256_PASSWORD; + expect_hash = true; + } + else if (ParserKeyword{"DOUBLE_SHA1_HASH"}.ignore(pos, expected)) + { + type = Authentication::DOUBLE_SHA1_PASSWORD; + expect_hash = true; + } + else + return false; + } + } + + if (!type) + { + type = Authentication::SHA256_PASSWORD; + expect_password = true; + } + + String password; + if (expect_password || expect_hash) + { + ASTPtr ast; + if (!ParserKeyword{"BY"}.ignore(pos, expected) || !ParserStringLiteral{}.parse(pos, ast, expected)) return false; - authentication = Authentication{Authentication::SHA256_PASSWORD}; + password = ast->as().value.safeGet(); + } + + authentication = Authentication{*type}; + if (expect_password) authentication->setPassword(password); - return true; - } + else if (expect_hash) + authentication->setPasswordHashHex(password); - if (ParserKeyword{"PLAINTEXT_PASSWORD"}.ignore(pos, expected)) - { - String password; - if (!parseByPassword(pos, expected, password)) - return false; - - authentication = Authentication{Authentication::PLAINTEXT_PASSWORD}; - authentication->setPassword(password); - return true; - } - - if (ParserKeyword{"SHA256_PASSWORD"}.ignore(pos, expected)) - { - String password; - if (!parseByPassword(pos, expected, password)) - return false; - - authentication = Authentication{Authentication::SHA256_PASSWORD}; - authentication->setPassword(password); - return true; - } - - if (ParserKeyword{"SHA256_HASH"}.ignore(pos, expected)) - { - String hash; - if (!parseByPassword(pos, expected, hash)) - return false; - - authentication = Authentication{Authentication::SHA256_PASSWORD}; - authentication->setPasswordHashHex(hash); - return true; - } - - if (ParserKeyword{"DOUBLE_SHA1_PASSWORD"}.ignore(pos, expected)) - { - String password; - if (!parseByPassword(pos, expected, password)) - return false; - - authentication = Authentication{Authentication::DOUBLE_SHA1_PASSWORD}; - authentication->setPassword(password); - return true; - } - - if (ParserKeyword{"DOUBLE_SHA1_HASH"}.ignore(pos, expected)) - { - String hash; - if (!parseByPassword(pos, expected, hash)) - return false; - - authentication = Authentication{Authentication::DOUBLE_SHA1_PASSWORD}; - authentication->setPasswordHashHex(hash); - return true; - } - - if (!ParserKeyword{"NO_PASSWORD"}.ignore(pos, expected)) - return false; - - authentication = Authentication{Authentication::NO_PASSWORD}; return true; }); } @@ -227,6 +201,7 @@ namespace return false; default_roles = typeid_cast>(ast); + default_roles->can_contain_users = false; return true; }); } diff --git a/src/Parsers/ParserCreateUserQuery.h b/src/Parsers/ParserCreateUserQuery.h index d609894a7ec..2a890f41060 100644 --- a/src/Parsers/ParserCreateUserQuery.h +++ b/src/Parsers/ParserCreateUserQuery.h @@ -7,13 +7,13 @@ namespace DB { /** Parses queries like * CREATE USER [IF NOT EXISTS | OR REPLACE] name - * [IDENTIFIED [WITH {NO_PASSWORD|PLAINTEXT_PASSWORD|SHA256_PASSWORD|SHA256_HASH|DOUBLE_SHA1_PASSWORD|DOUBLE_SHA1_HASH}] BY {'password'|'hash'}] + * [NOT IDENTIFIED | IDENTIFIED [WITH {no_password|plaintext_password|sha256_password|sha256_hash|double_sha1_password|double_sha1_hash}] BY {'password'|'hash'}] * [HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] * [SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...] * * ALTER USER [IF EXISTS] name * [RENAME TO new_name] - * [IDENTIFIED [WITH {PLAINTEXT_PASSWORD|SHA256_PASSWORD|DOUBLE_SHA1_PASSWORD}] BY {'password'|'hash'}] + * [NOT IDENTIFIED | IDENTIFIED [WITH {no_password|plaintext_password|sha256_password|sha256_hash|double_sha1_password|double_sha1_hash}] BY {'password'|'hash'}] * [[ADD|DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] * [SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...] */ diff --git a/src/Parsers/ParserSetRoleQuery.cpp b/src/Parsers/ParserSetRoleQuery.cpp index e6ff7893891..a69480f89eb 100644 --- a/src/Parsers/ParserSetRoleQuery.cpp +++ b/src/Parsers/ParserSetRoleQuery.cpp @@ -18,6 +18,7 @@ namespace return false; roles = typeid_cast>(ast); + roles->can_contain_users = false; return true; }); } @@ -34,6 +35,7 @@ namespace return false; to_users = typeid_cast>(ast); + to_users->can_contain_roles = false; return true; }); } diff --git a/src/Processors/Executors/PullingAsyncPipelineExecutor.cpp b/src/Processors/Executors/PullingAsyncPipelineExecutor.cpp index 003508ab86f..49e85fcc6d3 100644 --- a/src/Processors/Executors/PullingAsyncPipelineExecutor.cpp +++ b/src/Processors/Executors/PullingAsyncPipelineExecutor.cpp @@ -14,9 +14,10 @@ struct PullingAsyncPipelineExecutor::Data { PipelineExecutorPtr executor; std::exception_ptr exception; - std::atomic_bool is_executed = false; + std::atomic_bool is_finished = false; std::atomic_bool has_exception = false; ThreadFromGlobalPool thread; + Poco::Event finish_event; ~Data() { @@ -36,8 +37,11 @@ struct PullingAsyncPipelineExecutor::Data PullingAsyncPipelineExecutor::PullingAsyncPipelineExecutor(QueryPipeline & pipeline_) : pipeline(pipeline_) { - lazy_format = std::make_shared(pipeline.getHeader()); - pipeline.setOutput(lazy_format); + if (!pipeline.isCompleted()) + { + lazy_format = std::make_shared(pipeline.getHeader()); + pipeline.setOutputFormat(lazy_format); + } } PullingAsyncPipelineExecutor::~PullingAsyncPipelineExecutor() @@ -54,7 +58,8 @@ PullingAsyncPipelineExecutor::~PullingAsyncPipelineExecutor() const Block & PullingAsyncPipelineExecutor::getHeader() const { - return lazy_format->getPort(IOutputFormat::PortKind::Main).getHeader(); + return lazy_format ? lazy_format->getPort(IOutputFormat::PortKind::Main).getHeader() + : pipeline.getHeader(); /// Empty. } static void threadFunction(PullingAsyncPipelineExecutor::Data & data, ThreadGroupStatusPtr thread_group, size_t num_threads) @@ -78,6 +83,9 @@ static void threadFunction(PullingAsyncPipelineExecutor::Data & data, ThreadGrou data.exception = std::current_exception(); data.has_exception = true; } + + data.is_finished = true; + data.finish_event.set(); } @@ -99,20 +107,33 @@ bool PullingAsyncPipelineExecutor::pull(Chunk & chunk, uint64_t milliseconds) if (data->has_exception) { /// Finish lazy format in case of exception. Otherwise thread.join() may hung. - lazy_format->finish(); + if (lazy_format) + lazy_format->finish(); + data->has_exception = false; std::rethrow_exception(std::move(data->exception)); } - if (lazy_format->isFinished()) + bool is_execution_finished = lazy_format ? lazy_format->isFinished() + : data->is_finished.load(); + + if (is_execution_finished) { - data->is_executed = true; + /// If lazy format is finished, we don't cancel pipeline but wait for main thread to be finished. + data->is_finished = true; /// Wait thread ant rethrow exception if any. cancel(); return false; } - chunk = lazy_format->getChunk(milliseconds); + if (lazy_format) + { + chunk = lazy_format->getChunk(milliseconds); + return true; + } + + chunk.clear(); + data->finish_event.tryWait(milliseconds); return true; } @@ -147,11 +168,11 @@ bool PullingAsyncPipelineExecutor::pull(Block & block, uint64_t milliseconds) void PullingAsyncPipelineExecutor::cancel() { /// Cancel execution if it wasn't finished. - if (data && !data->is_executed && data->executor) + if (data && !data->is_finished && data->executor) data->executor->cancel(); /// Finish lazy format. Otherwise thread.join() may hung. - if (!lazy_format->isFinished()) + if (lazy_format && !lazy_format->isFinished()) lazy_format->finish(); /// Join thread here to wait for possible exception. @@ -165,12 +186,14 @@ void PullingAsyncPipelineExecutor::cancel() Chunk PullingAsyncPipelineExecutor::getTotals() { - return lazy_format->getTotals(); + return lazy_format ? lazy_format->getTotals() + : Chunk(); } Chunk PullingAsyncPipelineExecutor::getExtremes() { - return lazy_format->getExtremes(); + return lazy_format ? lazy_format->getExtremes() + : Chunk(); } Block PullingAsyncPipelineExecutor::getTotalsBlock() @@ -197,7 +220,9 @@ Block PullingAsyncPipelineExecutor::getExtremesBlock() BlockStreamProfileInfo & PullingAsyncPipelineExecutor::getProfileInfo() { - return lazy_format->getProfileInfo(); + static BlockStreamProfileInfo profile_info; + return lazy_format ? lazy_format->getProfileInfo() + : profile_info; } } diff --git a/src/Processors/Executors/PullingPipelineExecutor.cpp b/src/Processors/Executors/PullingPipelineExecutor.cpp index 375f6c9ed0e..dc59e0a2f5a 100644 --- a/src/Processors/Executors/PullingPipelineExecutor.cpp +++ b/src/Processors/Executors/PullingPipelineExecutor.cpp @@ -9,7 +9,7 @@ namespace DB PullingPipelineExecutor::PullingPipelineExecutor(QueryPipeline & pipeline_) : pipeline(pipeline_) { pulling_format = std::make_shared(pipeline.getHeader(), has_data_flag); - pipeline.setOutput(pulling_format); + pipeline.setOutputFormat(pulling_format); } PullingPipelineExecutor::~PullingPipelineExecutor() @@ -74,10 +74,6 @@ void PullingPipelineExecutor::cancel() /// Cancel execution if it wasn't finished. if (executor) executor->cancel(); - - /// Read all data and finish execution. - Chunk chunk; - while (pull(chunk)); } Chunk PullingPipelineExecutor::getTotals() diff --git a/src/Processors/Formats/Impl/ArrowBlockInputFormat.cpp b/src/Processors/Formats/Impl/ArrowBlockInputFormat.cpp index df73c93fd55..2873a5417ea 100644 --- a/src/Processors/Formats/Impl/ArrowBlockInputFormat.cpp +++ b/src/Processors/Formats/Impl/ArrowBlockInputFormat.cpp @@ -16,12 +16,12 @@ namespace DB namespace ErrorCodes { - extern const int BAD_ARGUMENTS; + extern const int UNKNOWN_EXCEPTION; extern const int CANNOT_READ_ALL_DATA; } -ArrowBlockInputFormat::ArrowBlockInputFormat(ReadBuffer & in_, const Block & header_) - : IInputFormat(header_, in_) +ArrowBlockInputFormat::ArrowBlockInputFormat(ReadBuffer & in_, const Block & header_, bool stream_) + : IInputFormat(header_, in_), stream{stream_} { prepareReader(); } @@ -30,12 +30,23 @@ Chunk ArrowBlockInputFormat::generate() { Chunk res; const Block & header = getPort().getHeader(); - - if (record_batch_current >= record_batch_total) - return res; - std::vector> single_batch(1); - arrow::Status read_status = file_reader->ReadRecordBatch(record_batch_current, &single_batch[0]); + arrow::Status read_status; + + if (stream) + { + read_status = stream_reader->ReadNext(&single_batch[0]); + if (!single_batch[0]) + return res; + } + else + { + if (record_batch_current >= record_batch_total) + return res; + + read_status = file_reader->ReadRecordBatch(record_batch_current, &single_batch[0]); + } + if (!read_status.ok()) throw Exception{"Error while reading batch of Arrow data: " + read_status.ToString(), ErrorCodes::CANNOT_READ_ALL_DATA}; @@ -57,30 +68,54 @@ void ArrowBlockInputFormat::resetParser() { IInputFormat::resetParser(); - file_reader.reset(); + if (stream) + stream_reader.reset(); + else + file_reader.reset(); prepareReader(); } void ArrowBlockInputFormat::prepareReader() { - arrow::Status open_status = arrow::ipc::RecordBatchFileReader::Open(asArrowFile(in), &file_reader); - if (!open_status.ok()) - throw Exception(open_status.ToString(), ErrorCodes::BAD_ARGUMENTS); - record_batch_total = file_reader->num_record_batches(); + arrow::Status status; + + if (stream) + status = arrow::ipc::RecordBatchStreamReader::Open(asArrowFile(in), &stream_reader); + else + status = arrow::ipc::RecordBatchFileReader::Open(asArrowFile(in), &file_reader); + + if (!status.ok()) + throw Exception{"Error while opening a table: " + status.ToString(), ErrorCodes::UNKNOWN_EXCEPTION}; + + if (stream) + record_batch_total = -1; + else + record_batch_total = file_reader->num_record_batches(); + record_batch_current = 0; } void registerInputFormatProcessorArrow(FormatFactory &factory) { factory.registerInputFormatProcessor( - "Arrow", - [](ReadBuffer & buf, - const Block & sample, - const RowInputFormatParams & /* params */, - const FormatSettings & /* format_settings */) - { - return std::make_shared(buf, sample); - }); + "Arrow", + [](ReadBuffer & buf, + const Block & sample, + const RowInputFormatParams & /* params */, + const FormatSettings & /* format_settings */) + { + return std::make_shared(buf, sample, false); + }); + + factory.registerInputFormatProcessor( + "ArrowStream", + [](ReadBuffer & buf, + const Block & sample, + const RowInputFormatParams & /* params */, + const FormatSettings & /* format_settings */) + { + return std::make_shared(buf, sample, true); + }); } } diff --git a/src/Processors/Formats/Impl/ArrowBlockInputFormat.h b/src/Processors/Formats/Impl/ArrowBlockInputFormat.h index 28ca033dd13..5ad112efde9 100644 --- a/src/Processors/Formats/Impl/ArrowBlockInputFormat.h +++ b/src/Processors/Formats/Impl/ArrowBlockInputFormat.h @@ -4,6 +4,7 @@ #include +namespace arrow { class RecordBatchReader; } namespace arrow::ipc { class RecordBatchFileReader; } namespace DB @@ -14,7 +15,7 @@ class ReadBuffer; class ArrowBlockInputFormat : public IInputFormat { public: - ArrowBlockInputFormat(ReadBuffer & in_, const Block & header_); + ArrowBlockInputFormat(ReadBuffer & in_, const Block & header_, bool stream_); void resetParser() override; @@ -24,12 +25,17 @@ protected: Chunk generate() override; private: - void prepareReader(); - -private: + // Whether to use ArrowStream format + bool stream; + // This field is only used for ArrowStream format + std::shared_ptr stream_reader; + // The following fields are used only for Arrow format std::shared_ptr file_reader; + int record_batch_total = 0; int record_batch_current = 0; + + void prepareReader(); }; } diff --git a/src/Processors/Formats/Impl/ArrowBlockOutputFormat.cpp b/src/Processors/Formats/Impl/ArrowBlockOutputFormat.cpp index ed33eb08728..ef6bd315319 100644 --- a/src/Processors/Formats/Impl/ArrowBlockOutputFormat.cpp +++ b/src/Processors/Formats/Impl/ArrowBlockOutputFormat.cpp @@ -15,8 +15,8 @@ namespace ErrorCodes extern const int UNKNOWN_EXCEPTION; } -ArrowBlockOutputFormat::ArrowBlockOutputFormat(WriteBuffer & out_, const Block & header_, const FormatSettings & format_settings_) - : IOutputFormat(header_, out_), format_settings{format_settings_}, arrow_ostream{std::make_shared(out_)} +ArrowBlockOutputFormat::ArrowBlockOutputFormat(WriteBuffer & out_, const Block & header_, bool stream_, const FormatSettings & format_settings_) + : IOutputFormat(header_, out_), stream{stream_}, format_settings{format_settings_}, arrow_ostream{std::make_shared(out_)} { } @@ -29,12 +29,7 @@ void ArrowBlockOutputFormat::consume(Chunk chunk) CHColumnToArrowColumn::chChunkToArrowTable(arrow_table, header, chunk, columns_num, "Arrow"); if (!writer) - { - // TODO: should we use arrow::ipc::IpcOptions::alignment? - auto status = arrow::ipc::RecordBatchFileWriter::Open(arrow_ostream.get(), arrow_table->schema(), &writer); - if (!status.ok()) - throw Exception{"Error while opening a table: " + status.ToString(), ErrorCodes::UNKNOWN_EXCEPTION}; - } + prepareWriter(arrow_table->schema()); // TODO: calculate row_group_size depending on a number of rows and table size auto status = writer->WriteTable(*arrow_table, format_settings.arrow.row_group_size); @@ -53,6 +48,20 @@ void ArrowBlockOutputFormat::finalize() } } +void ArrowBlockOutputFormat::prepareWriter(const std::shared_ptr & schema) +{ + arrow::Status status; + + // TODO: should we use arrow::ipc::IpcOptions::alignment? + if (stream) + status = arrow::ipc::RecordBatchStreamWriter::Open(arrow_ostream.get(), schema, &writer); + else + status = arrow::ipc::RecordBatchFileWriter::Open(arrow_ostream.get(), schema, &writer); + + if (!status.ok()) + throw Exception{"Error while opening a table writer: " + status.ToString(), ErrorCodes::UNKNOWN_EXCEPTION}; +} + void registerOutputFormatProcessorArrow(FormatFactory & factory) { factory.registerOutputFormatProcessor( @@ -62,7 +71,17 @@ void registerOutputFormatProcessorArrow(FormatFactory & factory) FormatFactory::WriteCallback, const FormatSettings & format_settings) { - return std::make_shared(buf, sample, format_settings); + return std::make_shared(buf, sample, false, format_settings); + }); + + factory.registerOutputFormatProcessor( + "ArrowStream", + [](WriteBuffer & buf, + const Block & sample, + FormatFactory::WriteCallback, + const FormatSettings & format_settings) + { + return std::make_shared(buf, sample, true, format_settings); }); } diff --git a/src/Processors/Formats/Impl/ArrowBlockOutputFormat.h b/src/Processors/Formats/Impl/ArrowBlockOutputFormat.h index 9ea84f83a0d..0cc6804705b 100644 --- a/src/Processors/Formats/Impl/ArrowBlockOutputFormat.h +++ b/src/Processors/Formats/Impl/ArrowBlockOutputFormat.h @@ -6,6 +6,7 @@ #include #include "ArrowBufferedStreams.h" +namespace arrow { class Schema; } namespace arrow::ipc { class RecordBatchWriter; } namespace DB @@ -14,7 +15,7 @@ namespace DB class ArrowBlockOutputFormat : public IOutputFormat { public: - ArrowBlockOutputFormat(WriteBuffer & out_, const Block & header_, const FormatSettings & format_settings_); + ArrowBlockOutputFormat(WriteBuffer & out_, const Block & header_, bool stream_, const FormatSettings & format_settings_); String getName() const override { return "ArrowBlockOutputFormat"; } void consume(Chunk) override; @@ -23,9 +24,12 @@ public: String getContentType() const override { return "application/octet-stream"; } private: + bool stream; const FormatSettings format_settings; std::shared_ptr arrow_ostream; std::shared_ptr writer; + + void prepareWriter(const std::shared_ptr & schema); }; } diff --git a/src/Processors/Pipe.h b/src/Processors/Pipe.h index 984fa7605c6..ec5514915a7 100644 --- a/src/Processors/Pipe.h +++ b/src/Processors/Pipe.h @@ -23,7 +23,7 @@ public: /// Will connect pipes outputs with transform inputs automatically. Pipe(Pipes && pipes, ProcessorPtr transform); /// Create pipe from output port. If pipe was created that way, it possibly will not have tree shape. - Pipe(OutputPort * port); + explicit Pipe(OutputPort * port); Pipe(const Pipe & other) = delete; Pipe(Pipe && other) = default; diff --git a/src/Processors/QueryPipeline.cpp b/src/Processors/QueryPipeline.cpp index 13787a3fd3b..92c91a81b8a 100644 --- a/src/Processors/QueryPipeline.cpp +++ b/src/Processors/QueryPipeline.cpp @@ -34,6 +34,14 @@ void QueryPipeline::checkInitialized() throw Exception("QueryPipeline wasn't initialized.", ErrorCodes::LOGICAL_ERROR); } +void QueryPipeline::checkInitializedAndNotCompleted() +{ + checkInitialized(); + + if (streams.empty()) + throw Exception("QueryPipeline was already completed.", ErrorCodes::LOGICAL_ERROR); +} + void QueryPipeline::checkSource(const ProcessorPtr & source, bool can_have_totals) { if (!source->getInputs().empty()) @@ -194,11 +202,11 @@ static ProcessorPtr callProcessorGetter( template void QueryPipeline::addSimpleTransformImpl(const TProcessorGetter & getter) { - checkInitialized(); + checkInitializedAndNotCompleted(); Block header; - auto add_transform = [&](OutputPort *& stream, StreamType stream_type, size_t stream_num [[maybe_unused]] = IProcessor::NO_STREAM) + auto add_transform = [&](OutputPort *& stream, StreamType stream_type) { if (!stream) return; @@ -231,17 +239,14 @@ void QueryPipeline::addSimpleTransformImpl(const TProcessorGetter & getter) if (transform) { -// if (stream_type == StreamType::Main) -// transform->setStream(stream_num); - connect(*stream, transform->getInputs().front()); stream = &transform->getOutputs().front(); processors.emplace_back(std::move(transform)); } }; - for (size_t stream_num = 0; stream_num < streams.size(); ++stream_num) - add_transform(streams[stream_num], StreamType::Main, stream_num); + for (auto & stream : streams) + add_transform(stream, StreamType::Main); add_transform(totals_having_port, StreamType::Totals); add_transform(extremes_port, StreamType::Extremes); @@ -259,9 +264,50 @@ void QueryPipeline::addSimpleTransform(const ProcessorGetterWithStreamKind & get addSimpleTransformImpl(getter); } +void QueryPipeline::setSinks(const ProcessorGetterWithStreamKind & getter) +{ + checkInitializedAndNotCompleted(); + + auto add_transform = [&](OutputPort *& stream, StreamType stream_type) + { + if (!stream) + return; + + auto transform = getter(stream->getHeader(), stream_type); + + if (transform) + { + if (transform->getInputs().size() != 1) + throw Exception("Sink for query pipeline transform should have single input, " + "but " + transform->getName() + " has " + + toString(transform->getInputs().size()) + " inputs.", ErrorCodes::LOGICAL_ERROR); + + if (!transform->getOutputs().empty()) + throw Exception("Sink for query pipeline transform should have no outputs, " + "but " + transform->getName() + " has " + + toString(transform->getOutputs().size()) + " outputs.", ErrorCodes::LOGICAL_ERROR); + } + + if (!transform) + transform = std::make_shared(stream->getHeader()); + + connect(*stream, transform->getInputs().front()); + processors.emplace_back(std::move(transform)); + }; + + for (auto & stream : streams) + add_transform(stream, StreamType::Main); + + add_transform(totals_having_port, StreamType::Totals); + add_transform(extremes_port, StreamType::Extremes); + + streams.clear(); + current_header.clear(); +} + void QueryPipeline::addPipe(Processors pipe) { - checkInitialized(); + checkInitializedAndNotCompleted(); if (pipe.empty()) throw Exception("Can't add empty processors list to QueryPipeline.", ErrorCodes::LOGICAL_ERROR); @@ -298,7 +344,7 @@ void QueryPipeline::addPipe(Processors pipe) void QueryPipeline::addDelayedStream(ProcessorPtr source) { - checkInitialized(); + checkInitializedAndNotCompleted(); checkSource(source, false); assertBlocksHaveEqualStructure(current_header, source->getOutputs().front().getHeader(), "QueryPipeline"); @@ -313,7 +359,7 @@ void QueryPipeline::addDelayedStream(ProcessorPtr source) void QueryPipeline::resize(size_t num_streams, bool force, bool strict) { - checkInitialized(); + checkInitializedAndNotCompleted(); if (!force && num_streams == getNumStreams()) return; @@ -347,7 +393,7 @@ void QueryPipeline::enableQuotaForCurrentStreams() void QueryPipeline::addTotalsHavingTransform(ProcessorPtr transform) { - checkInitialized(); + checkInitializedAndNotCompleted(); if (!typeid_cast(transform.get())) throw Exception("TotalsHavingTransform expected for QueryPipeline::addTotalsHavingTransform.", @@ -370,7 +416,7 @@ void QueryPipeline::addTotalsHavingTransform(ProcessorPtr transform) void QueryPipeline::addDefaultTotals() { - checkInitialized(); + checkInitializedAndNotCompleted(); if (totals_having_port) throw Exception("Totals having transform was already added to pipeline.", ErrorCodes::LOGICAL_ERROR); @@ -392,7 +438,7 @@ void QueryPipeline::addDefaultTotals() void QueryPipeline::addTotals(ProcessorPtr source) { - checkInitialized(); + checkInitializedAndNotCompleted(); if (totals_having_port) throw Exception("Totals having transform was already added to pipeline.", ErrorCodes::LOGICAL_ERROR); @@ -423,7 +469,7 @@ void QueryPipeline::dropTotalsAndExtremes() void QueryPipeline::addExtremesTransform() { - checkInitialized(); + checkInitializedAndNotCompleted(); if (extremes_port) throw Exception("Extremes transform was already added to pipeline.", ErrorCodes::LOGICAL_ERROR); @@ -450,7 +496,7 @@ void QueryPipeline::addExtremesTransform() void QueryPipeline::addCreatingSetsTransform(ProcessorPtr transform) { - checkInitialized(); + checkInitializedAndNotCompleted(); if (!typeid_cast(transform.get())) throw Exception("CreatingSetsTransform expected for QueryPipeline::addExtremesTransform.", @@ -467,14 +513,14 @@ void QueryPipeline::addCreatingSetsTransform(ProcessorPtr transform) processors.emplace_back(std::move(concat)); } -void QueryPipeline::setOutput(ProcessorPtr output) +void QueryPipeline::setOutputFormat(ProcessorPtr output) { - checkInitialized(); + checkInitializedAndNotCompleted(); auto * format = dynamic_cast(output.get()); if (!format) - throw Exception("IOutputFormat processor expected for QueryPipeline::setOutput.", ErrorCodes::LOGICAL_ERROR); + throw Exception("IOutputFormat processor expected for QueryPipeline::setOutputFormat.", ErrorCodes::LOGICAL_ERROR); if (output_format) throw Exception("QueryPipeline already has output.", ErrorCodes::LOGICAL_ERROR); @@ -507,19 +553,25 @@ void QueryPipeline::setOutput(ProcessorPtr output) connect(*totals_having_port, totals); connect(*extremes_port, extremes); + streams.clear(); + current_header.clear(); + extremes_port = nullptr; + totals_having_port = nullptr; + initRowsBeforeLimit(); } void QueryPipeline::unitePipelines( std::vector && pipelines, const Block & common_header) { - checkInitialized(); - - addSimpleTransform([&](const Block & header) + if (initialized()) { - return std::make_shared( - header, common_header, ConvertingTransform::MatchColumnsMode::Position); - }); + addSimpleTransform([&](const Block & header) + { + return std::make_shared( + header, common_header, ConvertingTransform::MatchColumnsMode::Position); + }); + } std::vector extremes; std::vector totals; @@ -534,11 +586,14 @@ void QueryPipeline::unitePipelines( { pipeline.checkInitialized(); - pipeline.addSimpleTransform([&](const Block & header) + if (!pipeline.isCompleted()) { - return std::make_shared( - header, common_header, ConvertingTransform::MatchColumnsMode::Position); - }); + pipeline.addSimpleTransform([&](const Block & header) + { + return std::make_shared( + header, common_header, ConvertingTransform::MatchColumnsMode::Position); + }); + } if (pipeline.extremes_port) { @@ -703,6 +758,11 @@ void QueryPipeline::initRowsBeforeLimit() Pipe QueryPipeline::getPipe() && { resize(1); + return std::move(std::move(*this).getPipes()[0]); +} + +Pipes QueryPipeline::getPipes() && +{ Pipe pipe(std::move(processors), streams.at(0), totals_having_port, extremes_port); pipe.max_parallel_streams = streams.maxParallelStreams(); @@ -721,15 +781,19 @@ Pipe QueryPipeline::getPipe() && if (extremes_port) pipe.setExtremesPort(extremes_port); - return pipe; + Pipes pipes; + pipes.emplace_back(std::move(pipe)); + + for (size_t i = 1; i < streams.size(); ++i) + pipes.emplace_back(Pipe(streams[i])); + + return pipes; } PipelineExecutorPtr QueryPipeline::execute() { - checkInitialized(); - - if (!output_format) - throw Exception("Cannot execute pipeline because it doesn't have output.", ErrorCodes::LOGICAL_ERROR); + if (!isCompleted()) + throw Exception("Cannot execute pipeline because it is not completed.", ErrorCodes::LOGICAL_ERROR); return std::make_shared(processors, process_list_element); } diff --git a/src/Processors/QueryPipeline.h b/src/Processors/QueryPipeline.h index 45e38ffa715..129b7f5ae3c 100644 --- a/src/Processors/QueryPipeline.h +++ b/src/Processors/QueryPipeline.h @@ -28,6 +28,7 @@ private: { public: auto size() const { return data.size(); } + bool empty() const { return size() == 0; } auto begin() { return data.begin(); } auto end() { return data.end(); } auto & front() { return data.front(); } @@ -81,6 +82,7 @@ public: void init(Pipes pipes); void init(Pipe pipe); /// Simple init for single pipe bool initialized() { return !processors.empty(); } + bool isCompleted() { return initialized() && streams.empty(); } /// Type of logical data stream for simple transform. /// Sometimes it's important to know which part of pipeline we are working for. @@ -95,13 +97,23 @@ public: using ProcessorGetter = std::function; using ProcessorGetterWithStreamKind = std::function; + /// Add transform with simple input and simple output for each port. void addSimpleTransform(const ProcessorGetter & getter); void addSimpleTransform(const ProcessorGetterWithStreamKind & getter); + /// Add several processors. They must have same header for inputs and same for outputs. + /// Total number of inputs must be the same as the number of streams. Output ports will become new streams. void addPipe(Processors pipe); + /// Add TotalsHavingTransform. Resize pipeline to single input. Adds totals port. void addTotalsHavingTransform(ProcessorPtr transform); + /// Add transform which calculates extremes. This transform adds extremes port and doesn't change inputs number. void addExtremesTransform(); + /// Adds transform which creates sets. It will be executed before reading any data from input ports. void addCreatingSetsTransform(ProcessorPtr transform); - void setOutput(ProcessorPtr output); + /// Resize pipeline to single output and add IOutputFormat. Pipeline will be completed after this transformation. + void setOutputFormat(ProcessorPtr output); + /// Sink is a processor with single input port and no output ports. Creates sink for each output port. + /// Pipeline will be completed after this transformation. + void setSinks(const ProcessorGetterWithStreamKind & getter); /// Add totals which returns one chunk with single row with defaults. void addDefaultTotals(); @@ -118,6 +130,7 @@ public: /// Check if resize transform was used. (In that case another distinct transform will be added). bool hasMixedStreams() const { return has_resize || hasMoreThanOneStream(); } + /// Changes the number of input ports if needed. Adds ResizeTransform. void resize(size_t num_streams, bool force = false, bool strict = false); void enableQuotaForCurrentStreams(); @@ -155,8 +168,9 @@ public: /// Set upper limit for the recommend number of threads void setMaxThreads(size_t max_threads_) { max_threads = max_threads_; } - /// Convert query pipeline to single pipe. + /// Convert query pipeline to single or several pipes. Pipe getPipe() &&; + Pipes getPipes() &&; private: /// Destruction order: processors, header, locks, temporary storages, local contexts @@ -193,6 +207,7 @@ private: QueryStatus * process_list_element = nullptr; void checkInitialized(); + void checkInitializedAndNotCompleted(); static void checkSource(const ProcessorPtr & source, bool can_have_totals); template diff --git a/src/Processors/ResizeProcessor.cpp b/src/Processors/ResizeProcessor.cpp index 3fcf4281105..d652a342150 100644 --- a/src/Processors/ResizeProcessor.cpp +++ b/src/Processors/ResizeProcessor.cpp @@ -347,11 +347,16 @@ IProcessor::Status StrictResizeProcessor::prepare(const PortNumbers & updated_in auto & waiting_output = output_ports[input_with_data.waiting_output]; - if (waiting_output.status != OutputStatus::NeedData) - throw Exception("Invalid status for associated output.", ErrorCodes::LOGICAL_ERROR); + if (waiting_output.status == OutputStatus::NotActive) + throw Exception("Invalid status NotActive for associated output.", ErrorCodes::LOGICAL_ERROR); - waiting_output.port->pushData(input_with_data.port->pullData(/* set_not_needed = */ true)); - waiting_output.status = OutputStatus::NotActive; + if (waiting_output.status != OutputStatus::Finished) + { + waiting_output.port->pushData(input_with_data.port->pullData(/* set_not_needed = */ true)); + waiting_output.status = OutputStatus::NotActive; + } + else + abandoned_chunks.emplace_back(input_with_data.port->pullData(/* set_not_needed = */ true)); if (input_with_data.port->isFinished()) { @@ -370,6 +375,18 @@ IProcessor::Status StrictResizeProcessor::prepare(const PortNumbers & updated_in return Status::Finished; } + /// Process abandoned chunks if any. + while (!abandoned_chunks.empty() && !waiting_outputs.empty()) + { + auto & waiting_output = output_ports[waiting_outputs.front()]; + waiting_outputs.pop(); + + waiting_output.port->pushData(std::move(abandoned_chunks.back())); + abandoned_chunks.pop_back(); + + waiting_output.status = OutputStatus::NotActive; + } + /// Enable more inputs if needed. while (!disabled_input_ports.empty() && !waiting_outputs.empty()) { @@ -383,6 +400,7 @@ IProcessor::Status StrictResizeProcessor::prepare(const PortNumbers & updated_in waiting_outputs.pop(); } + /// Close all other waiting for data outputs (there is no corresponding input for them). while (!waiting_outputs.empty()) { auto & output = output_ports[waiting_outputs.front()]; diff --git a/src/Processors/ResizeProcessor.h b/src/Processors/ResizeProcessor.h index 1f364ffcf15..5c9660af113 100644 --- a/src/Processors/ResizeProcessor.h +++ b/src/Processors/ResizeProcessor.h @@ -128,6 +128,9 @@ private: std::vector input_ports; std::vector output_ports; + /// This field contained chunks which were read for output which had became finished while reading was happening. + /// They will be pushed to any next waiting output. + std::vector abandoned_chunks; }; } diff --git a/src/Processors/Transforms/ConvertingTransform.cpp b/src/Processors/Transforms/ConvertingTransform.cpp index c5bf5ad4d70..a0e9626b302 100644 --- a/src/Processors/Transforms/ConvertingTransform.cpp +++ b/src/Processors/Transforms/ConvertingTransform.cpp @@ -59,7 +59,11 @@ ConvertingTransform::ConvertingTransform( break; case MatchColumnsMode::Name: - if (source.has(res_elem.name)) + /// It may seem strange, but sometimes block may have columns with the same name. + /// For this specific case, try to get column from the same position if it has correct name first. + if (result_col_num < source.columns() && source.getByPosition(result_col_num).name == res_elem.name) + conversion[result_col_num] = result_col_num; + else if (source.has(res_elem.name)) conversion[result_col_num] = source.getPositionByName(res_elem.name); else throw Exception("Cannot find column " + backQuoteIfNeed(res_elem.name) + " in source stream", diff --git a/src/Processors/Transforms/PartialSortingTransform.cpp b/src/Processors/Transforms/PartialSortingTransform.cpp index 018614f0165..f68a415117b 100644 --- a/src/Processors/Transforms/PartialSortingTransform.cpp +++ b/src/Processors/Transforms/PartialSortingTransform.cpp @@ -1,5 +1,6 @@ #include #include +#include namespace DB { @@ -11,6 +12,38 @@ PartialSortingTransform::PartialSortingTransform( { } +static ColumnRawPtrs extractColumns(const Block & block, const SortDescription & description) +{ + size_t size = description.size(); + ColumnRawPtrs res; + res.reserve(size); + + for (size_t i = 0; i < size; ++i) + { + const IColumn * column = !description[i].column_name.empty() + ? block.getByName(description[i].column_name).column.get() + : block.safeGetByPosition(description[i].column_number).column.get(); + res.emplace_back(column); + } + + return res; +} + +bool less(const ColumnRawPtrs & lhs, UInt64 lhs_row_num, + const ColumnRawPtrs & rhs, UInt64 rhs_row_num, const SortDescription & description) +{ + size_t size = description.size(); + for (size_t i = 0; i < size; ++i) + { + int res = description[i].direction * lhs[i]->compareAt(lhs_row_num, rhs_row_num, *rhs[i], 1); + if (res < 0) + return true; + else if (res > 0) + return false; + } + return false; +} + void PartialSortingTransform::transform(Chunk & chunk) { if (read_rows) @@ -19,7 +52,42 @@ void PartialSortingTransform::transform(Chunk & chunk) auto block = getInputPort().getHeader().cloneWithColumns(chunk.detachColumns()); chunk.clear(); + ColumnRawPtrs block_columns; + UInt64 rows_num = block.rows(); + + if (!threshold_block_columns.empty()) + { + IColumn::Filter filter(rows_num, 0); + block_columns = extractColumns(block, description); + size_t filtered_count = 0; + + for (UInt64 i = 0; i < rows_num; ++i) + { + if (less(threshold_block_columns, limit - 1, block_columns, i, description)) + { + ++filtered_count; + filter[i] = 1; + } + } + + if (filtered_count) + { + for (auto & column : block.getColumns()) + { + column = column->filter(filter, filtered_count); + } + } + } + sortBlock(block, description, limit); + + if (limit && limit < block.rows() && + (threshold_block_columns.empty() || less(block_columns, limit - 1, threshold_block_columns, limit - 1, description))) + { + threshold_block = block.cloneWithColumns(block.getColumns()); + threshold_block_columns = extractColumns(threshold_block, description); + } + chunk.setColumns(block.getColumns(), block.rows()); } diff --git a/src/Processors/Transforms/PartialSortingTransform.h b/src/Processors/Transforms/PartialSortingTransform.h index 47ac90c6904..d6749e4dfad 100644 --- a/src/Processors/Transforms/PartialSortingTransform.h +++ b/src/Processors/Transforms/PartialSortingTransform.h @@ -29,6 +29,8 @@ private: SortDescription description; UInt64 limit; RowsBeforeLimitCounterPtr read_rows; + Block threshold_block; + ColumnRawPtrs threshold_block_columns; }; } diff --git a/src/Server/CMakeLists.txt b/src/Server/CMakeLists.txt new file mode 100644 index 00000000000..e69de29bb2d diff --git a/programs/server/HTTPHandler.cpp b/src/Server/HTTPHandler.cpp similarity index 99% rename from programs/server/HTTPHandler.cpp rename to src/Server/HTTPHandler.cpp index e5c784fd409..82068496159 100644 --- a/programs/server/HTTPHandler.cpp +++ b/src/Server/HTTPHandler.cpp @@ -404,8 +404,6 @@ void HTTPHandler::processQuery( used_output.out_maybe_delayed_and_compressed = used_output.out_maybe_compressed; } - std::unique_ptr in_post_raw = std::make_unique(istr); - /// Request body can be compressed using algorithm specified in the Content-Encoding header. String http_request_compression_method_str = request.get("Content-Encoding", ""); std::unique_ptr in_post = wrapReadBufferWithCompressionMethod( diff --git a/programs/server/HTTPHandler.h b/src/Server/HTTPHandler.h similarity index 97% rename from programs/server/HTTPHandler.h rename to src/Server/HTTPHandler.h index 6228523d343..b1a6355d281 100644 --- a/programs/server/HTTPHandler.h +++ b/src/Server/HTTPHandler.h @@ -6,6 +6,7 @@ #include #include +#include #include @@ -21,7 +22,7 @@ namespace DB class WriteBufferFromHTTPServerResponse; -typedef std::shared_ptr CompiledRegexPtr; +using CompiledRegexPtr = std::shared_ptr; class HTTPHandler : public Poco::Net::HTTPRequestHandler { diff --git a/programs/server/HTTPHandlerFactory.cpp b/src/Server/HTTPHandlerFactory.cpp similarity index 99% rename from programs/server/HTTPHandlerFactory.cpp rename to src/Server/HTTPHandlerFactory.cpp index f302216e22b..e916070be22 100644 --- a/programs/server/HTTPHandlerFactory.cpp +++ b/src/Server/HTTPHandlerFactory.cpp @@ -4,6 +4,7 @@ #include #include #include +#include #include "HTTPHandler.h" #include "NotFoundHandler.h" diff --git a/programs/server/HTTPHandlerFactory.h b/src/Server/HTTPHandlerFactory.h similarity index 100% rename from programs/server/HTTPHandlerFactory.h rename to src/Server/HTTPHandlerFactory.h diff --git a/programs/server/HTTPHandlerRequestFilter.h b/src/Server/HTTPHandlerRequestFilter.h similarity index 99% rename from programs/server/HTTPHandlerRequestFilter.h rename to src/Server/HTTPHandlerRequestFilter.h index b0b748506e5..f952efd7653 100644 --- a/programs/server/HTTPHandlerRequestFilter.h +++ b/src/Server/HTTPHandlerRequestFilter.h @@ -6,6 +6,7 @@ #include #include #include +#include #include diff --git a/programs/server/IServer.h b/src/Server/IServer.h similarity index 82% rename from programs/server/IServer.h rename to src/Server/IServer.h index 29e9bc16a75..131e7443646 100644 --- a/programs/server/IServer.h +++ b/src/Server/IServer.h @@ -1,14 +1,22 @@ #pragma once -#include -#include +namespace Poco +{ -#include +namespace Util +{ +class LayeredConfiguration; +} +class Logger; + +} namespace DB { +class Context; + class IServer { public: diff --git a/programs/server/InterserverIOHTTPHandler.cpp b/src/Server/InterserverIOHTTPHandler.cpp similarity index 99% rename from programs/server/InterserverIOHTTPHandler.cpp rename to src/Server/InterserverIOHTTPHandler.cpp index 4b733c7f1fd..062721a01aa 100644 --- a/programs/server/InterserverIOHTTPHandler.cpp +++ b/src/Server/InterserverIOHTTPHandler.cpp @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include diff --git a/programs/server/InterserverIOHTTPHandler.h b/src/Server/InterserverIOHTTPHandler.h similarity index 100% rename from programs/server/InterserverIOHTTPHandler.h rename to src/Server/InterserverIOHTTPHandler.h diff --git a/programs/server/MySQLHandler.cpp b/src/Server/MySQLHandler.cpp similarity index 99% rename from programs/server/MySQLHandler.cpp rename to src/Server/MySQLHandler.cpp index dabb0c12208..51b3d7eaef5 100644 --- a/programs/server/MySQLHandler.cpp +++ b/src/Server/MySQLHandler.cpp @@ -253,7 +253,7 @@ void MySQLHandler::comFieldList(ReadBuffer & payload) ComFieldList packet; packet.readPayload(payload); String database = connection_context.getCurrentDatabase(); - StoragePtr table_ptr = DatabaseCatalog::instance().getTable({database, packet.table}); + StoragePtr table_ptr = DatabaseCatalog::instance().getTable({database, packet.table}, connection_context); for (const NameAndTypePair & column: table_ptr->getColumns().getAll()) { ColumnDefinition column_definition( diff --git a/programs/server/MySQLHandler.h b/src/Server/MySQLHandler.h similarity index 100% rename from programs/server/MySQLHandler.h rename to src/Server/MySQLHandler.h diff --git a/programs/server/MySQLHandlerFactory.cpp b/src/Server/MySQLHandlerFactory.cpp similarity index 99% rename from programs/server/MySQLHandlerFactory.cpp rename to src/Server/MySQLHandlerFactory.cpp index 022167fe766..5d78ed81068 100644 --- a/programs/server/MySQLHandlerFactory.cpp +++ b/src/Server/MySQLHandlerFactory.cpp @@ -4,8 +4,7 @@ #include #include #include -#include "IServer.h" -#include "MySQLHandler.h" +#include #if USE_SSL # include diff --git a/programs/server/MySQLHandlerFactory.h b/src/Server/MySQLHandlerFactory.h similarity index 95% rename from programs/server/MySQLHandlerFactory.h rename to src/Server/MySQLHandlerFactory.h index 74f0bb35a40..df7bd794b16 100644 --- a/programs/server/MySQLHandlerFactory.h +++ b/src/Server/MySQLHandlerFactory.h @@ -2,7 +2,8 @@ #include #include -#include "IServer.h" +#include +#include #if !defined(ARCADIA_BUILD) # include diff --git a/programs/server/NotFoundHandler.cpp b/src/Server/NotFoundHandler.cpp similarity index 100% rename from programs/server/NotFoundHandler.cpp rename to src/Server/NotFoundHandler.cpp diff --git a/programs/server/NotFoundHandler.h b/src/Server/NotFoundHandler.h similarity index 100% rename from programs/server/NotFoundHandler.h rename to src/Server/NotFoundHandler.h diff --git a/programs/server/PrometheusMetricsWriter.cpp b/src/Server/PrometheusMetricsWriter.cpp similarity index 100% rename from programs/server/PrometheusMetricsWriter.cpp rename to src/Server/PrometheusMetricsWriter.cpp diff --git a/programs/server/PrometheusMetricsWriter.h b/src/Server/PrometheusMetricsWriter.h similarity index 100% rename from programs/server/PrometheusMetricsWriter.h rename to src/Server/PrometheusMetricsWriter.h diff --git a/programs/server/PrometheusRequestHandler.cpp b/src/Server/PrometheusRequestHandler.cpp similarity index 95% rename from programs/server/PrometheusRequestHandler.cpp rename to src/Server/PrometheusRequestHandler.cpp index b5a48d13b64..43f39e36de8 100644 --- a/programs/server/PrometheusRequestHandler.cpp +++ b/src/Server/PrometheusRequestHandler.cpp @@ -6,6 +6,7 @@ #include #include +#include #include #include diff --git a/programs/server/PrometheusRequestHandler.h b/src/Server/PrometheusRequestHandler.h similarity index 100% rename from programs/server/PrometheusRequestHandler.h rename to src/Server/PrometheusRequestHandler.h diff --git a/programs/server/ReplicasStatusHandler.cpp b/src/Server/ReplicasStatusHandler.cpp similarity index 96% rename from programs/server/ReplicasStatusHandler.cpp rename to src/Server/ReplicasStatusHandler.cpp index f2d1ffe2ee5..986af59d3a4 100644 --- a/programs/server/ReplicasStatusHandler.cpp +++ b/src/Server/ReplicasStatusHandler.cpp @@ -44,7 +44,7 @@ void ReplicasStatusHandler::handleRequest(Poco::Net::HTTPServerRequest & request if (db.second->getEngineName() == "Lazy") continue; - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { const auto & table = iterator->table(); StorageReplicatedMergeTree * table_replicated = dynamic_cast(table.get()); diff --git a/programs/server/ReplicasStatusHandler.h b/src/Server/ReplicasStatusHandler.h similarity index 100% rename from programs/server/ReplicasStatusHandler.h rename to src/Server/ReplicasStatusHandler.h diff --git a/programs/server/StaticRequestHandler.cpp b/src/Server/StaticRequestHandler.cpp similarity index 100% rename from programs/server/StaticRequestHandler.cpp rename to src/Server/StaticRequestHandler.cpp diff --git a/programs/server/StaticRequestHandler.h b/src/Server/StaticRequestHandler.h similarity index 93% rename from programs/server/StaticRequestHandler.h rename to src/Server/StaticRequestHandler.h index bdbc17f5e00..707087df24d 100644 --- a/programs/server/StaticRequestHandler.h +++ b/src/Server/StaticRequestHandler.h @@ -4,6 +4,8 @@ #include #include +#include +#include namespace DB diff --git a/programs/server/TCPHandler.cpp b/src/Server/TCPHandler.cpp similarity index 99% rename from programs/server/TCPHandler.cpp rename to src/Server/TCPHandler.cpp index 190c549361f..6e9275540e5 100644 --- a/programs/server/TCPHandler.cpp +++ b/src/Server/TCPHandler.cpp @@ -262,8 +262,8 @@ void TCPHandler::runImpl() else if (state.need_receive_data_for_input) { /// It is special case for input(), all works for reading data from client will be done in callbacks. - /// state.io.in is NullAndDoCopyBlockInputStream so read it once. - state.io.in->read(); + auto executor = state.io.pipeline.execute(); + executor->execute(state.io.pipeline.getNumThreads()); state.io.onFinish(); } else if (state.io.pipeline.initialized()) @@ -474,7 +474,7 @@ void TCPHandler::processInsertQuery(const Settings & connection_settings) if (query_context->getSettingsRef().input_format_defaults_for_omitted_fields) { if (!table_id.empty()) - sendTableColumns(DatabaseCatalog::instance().getTable(table_id)->getColumns()); + sendTableColumns(DatabaseCatalog::instance().getTable(table_id, *query_context)->getColumns()); } } @@ -627,7 +627,7 @@ void TCPHandler::processTablesStatusRequest() for (const QualifiedTableName & table_name: request.tables) { auto resolved_id = connection_context.tryResolveStorageID({table_name.database, table_name.table}); - StoragePtr table = DatabaseCatalog::instance().tryGetTable(resolved_id); + StoragePtr table = DatabaseCatalog::instance().tryGetTable(resolved_id, connection_context); if (!table) continue; @@ -944,11 +944,11 @@ bool TCPHandler::receiveData(bool scalar) StoragePtr storage; /// If such a table does not exist, create it. if (resolved) - storage = DatabaseCatalog::instance().getTable(resolved); + storage = DatabaseCatalog::instance().getTable(resolved, *query_context); else { NamesAndTypesList columns = block.getNamesAndTypesList(); - auto temporary_table = TemporaryTableHolder(*query_context, ColumnsDescription{columns}); + auto temporary_table = TemporaryTableHolder(*query_context, ColumnsDescription{columns}, {}); storage = temporary_table.getTable(); query_context->addExternalTable(temporary_id.table_name, std::move(temporary_table)); } diff --git a/programs/server/TCPHandler.h b/src/Server/TCPHandler.h similarity index 100% rename from programs/server/TCPHandler.h rename to src/Server/TCPHandler.h diff --git a/programs/server/TCPHandlerFactory.h b/src/Server/TCPHandlerFactory.h similarity index 95% rename from programs/server/TCPHandlerFactory.h rename to src/Server/TCPHandlerFactory.h index 68652540192..a5532a8dc02 100644 --- a/programs/server/TCPHandlerFactory.h +++ b/src/Server/TCPHandlerFactory.h @@ -3,8 +3,8 @@ #include #include #include -#include "IServer.h" -#include "TCPHandler.h" +#include +#include namespace Poco { class Logger; } diff --git a/src/Server/ya.make b/src/Server/ya.make new file mode 100644 index 00000000000..1d689ee73b8 --- /dev/null +++ b/src/Server/ya.make @@ -0,0 +1,22 @@ +LIBRARY() + +PEERDIR( + clickhouse/src/Common + contrib/libs/poco/Util +) + +SRCS( + HTTPHandler.cpp + HTTPHandlerFactory.cpp + InterserverIOHTTPHandler.cpp + MySQLHandler.cpp + MySQLHandlerFactory.cpp + NotFoundHandler.cpp + PrometheusMetricsWriter.cpp + PrometheusRequestHandler.cpp + ReplicasStatusHandler.cpp + StaticRequestHandler.cpp + TCPHandler.cpp +) + +END() diff --git a/src/Storages/MergeTree/PartDestinationType.h b/src/Storages/DataDestinationType.h similarity index 73% rename from src/Storages/MergeTree/PartDestinationType.h rename to src/Storages/DataDestinationType.h index 8f3e44537a6..05d1d89c2b5 100644 --- a/src/Storages/MergeTree/PartDestinationType.h +++ b/src/Storages/DataDestinationType.h @@ -4,7 +4,7 @@ namespace DB { -enum class PartDestinationType +enum class DataDestinationType { DISK, VOLUME, diff --git a/src/Storages/Distributed/DirectoryMonitor.cpp b/src/Storages/Distributed/DirectoryMonitor.cpp index fdcbe8e69f9..4dd62db0965 100644 --- a/src/Storages/Distributed/DirectoryMonitor.cpp +++ b/src/Storages/Distributed/DirectoryMonitor.cpp @@ -110,8 +110,9 @@ void StorageDistributedDirectoryMonitor::flushAllData() { if (!quit) { + CurrentMetrics::Increment metric_pending_files{CurrentMetrics::DistributedFilesToInsert, 0}; std::unique_lock lock{mutex}; - processFiles(); + processFiles(metric_pending_files); } } @@ -131,6 +132,9 @@ void StorageDistributedDirectoryMonitor::run() { std::unique_lock lock{mutex}; + /// This metric will be updated with the number of pending files later. + CurrentMetrics::Increment metric_pending_files{CurrentMetrics::DistributedFilesToInsert, 0}; + bool do_sleep = false; while (!quit) { @@ -139,7 +143,7 @@ void StorageDistributedDirectoryMonitor::run() { try { - do_sleep = !processFiles(); + do_sleep = !processFiles(metric_pending_files); } catch (...) { @@ -222,7 +226,7 @@ ConnectionPoolPtr StorageDistributedDirectoryMonitor::createPool(const std::stri } -bool StorageDistributedDirectoryMonitor::processFiles() +bool StorageDistributedDirectoryMonitor::processFiles(CurrentMetrics::Increment & metric_pending_files) { std::map files; @@ -236,14 +240,16 @@ bool StorageDistributedDirectoryMonitor::processFiles() files[parse(file_path.getBaseName())] = file_path_str; } + /// Note: the value of this metric will be kept if this function will throw an exception. + /// This is needed, because in case of exception, files still pending. + metric_pending_files.changeTo(files.size()); + if (files.empty()) return false; - CurrentMetrics::Increment metric_increment{CurrentMetrics::DistributedFilesToInsert, CurrentMetrics::Value(files.size())}; - if (should_batch_inserts) { - processFilesWithBatching(files); + processFilesWithBatching(files, metric_pending_files); } else { @@ -252,14 +258,14 @@ bool StorageDistributedDirectoryMonitor::processFiles() if (quit) return true; - processFile(file.second); + processFile(file.second, metric_pending_files); } } return true; } -void StorageDistributedDirectoryMonitor::processFile(const std::string & file_path) +void StorageDistributedDirectoryMonitor::processFile(const std::string & file_path, CurrentMetrics::Increment & metric_pending_files) { LOG_TRACE(log, "Started processing `{}`", file_path); auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(storage.global_context->getSettingsRef()); @@ -289,6 +295,7 @@ void StorageDistributedDirectoryMonitor::processFile(const std::string & file_pa } Poco::File{file_path}.remove(); + metric_pending_files.sub(); LOG_TRACE(log, "Finished processing `{}`", file_path); } @@ -584,7 +591,9 @@ bool StorageDistributedDirectoryMonitor::scheduleAfter(size_t ms) return task_handle->scheduleAfter(ms, false); } -void StorageDistributedDirectoryMonitor::processFilesWithBatching(const std::map & files) +void StorageDistributedDirectoryMonitor::processFilesWithBatching( + const std::map & files, + CurrentMetrics::Increment & metric_pending_files) { std::unordered_set file_indices_to_skip; @@ -596,6 +605,7 @@ void StorageDistributedDirectoryMonitor::processFilesWithBatching(const std::map batch.readText(in); file_indices_to_skip.insert(batch.file_indices.begin(), batch.file_indices.end()); batch.send(); + metric_pending_files.sub(batch.file_indices.size()); } std::unordered_map header_to_batch; @@ -656,13 +666,17 @@ void StorageDistributedDirectoryMonitor::processFilesWithBatching(const std::map batch.total_bytes += total_bytes; if (batch.isEnoughSize()) + { batch.send(); + metric_pending_files.sub(batch.file_indices.size()); + } } for (auto & kv : header_to_batch) { Batch & batch = kv.second; batch.send(); + metric_pending_files.sub(batch.file_indices.size()); } /// current_batch.txt will not exist if there was no send diff --git a/src/Storages/Distributed/DirectoryMonitor.h b/src/Storages/Distributed/DirectoryMonitor.h index 77abf35630c..e2a913ee1ef 100644 --- a/src/Storages/Distributed/DirectoryMonitor.h +++ b/src/Storages/Distributed/DirectoryMonitor.h @@ -9,6 +9,8 @@ #include +namespace CurrentMetrics { class Increment; } + namespace DB { @@ -37,9 +39,9 @@ public: bool scheduleAfter(size_t ms); private: void run(); - bool processFiles(); - void processFile(const std::string & file_path); - void processFilesWithBatching(const std::map & files); + bool processFiles(CurrentMetrics::Increment & metric_pending_files); + void processFile(const std::string & file_path, CurrentMetrics::Increment & metric_pending_files); + void processFilesWithBatching(const std::map & files, CurrentMetrics::Increment & metric_pending_files); static bool isFileBrokenErrorCode(int code); void markAsBroken(const std::string & file_path) const; diff --git a/src/Storages/IStorage.cpp b/src/Storages/IStorage.cpp index 64e06a2534e..501b905817d 100644 --- a/src/Storages/IStorage.cpp +++ b/src/Storages/IStorage.cpp @@ -397,25 +397,6 @@ void IStorage::checkAlterIsPossible(const AlterCommands & commands, const Settin } } -BlockInputStreams IStorage::readStreams( - const Names & column_names, - const SelectQueryInfo & query_info, - const Context & context, - QueryProcessingStage::Enum processed_stage, - size_t max_block_size, - unsigned num_streams) -{ - ForceTreeShapedPipeline enable_tree_shape(query_info); - auto pipes = read(column_names, query_info, context, processed_stage, max_block_size, num_streams); - - BlockInputStreams res; - res.reserve(pipes.size()); - - for (auto & pipe : pipes) - res.emplace_back(std::make_shared(std::move(pipe))); - - return res; -} StorageID IStorage::getStorageID() const { @@ -444,9 +425,14 @@ void IStorage::setPartitionKey(const StorageMetadataKeyField & partition_key_) partition_key = partition_key_; } +bool IStorage::isPartitionKeyDefined() const +{ + return partition_key.definition_ast != nullptr; +} + bool IStorage::hasPartitionKey() const { - return partition_key.expression != nullptr; + return !partition_key.column_names.empty(); } Names IStorage::getColumnsRequiredForPartitionKey() const @@ -466,9 +452,14 @@ void IStorage::setSortingKey(const StorageMetadataKeyField & sorting_key_) sorting_key = sorting_key_; } +bool IStorage::isSortingKeyDefined() const +{ + return sorting_key.definition_ast != nullptr; +} + bool IStorage::hasSortingKey() const { - return sorting_key.expression != nullptr; + return !sorting_key.column_names.empty(); } Names IStorage::getColumnsRequiredForSortingKey() const @@ -502,7 +493,7 @@ bool IStorage::isPrimaryKeyDefined() const bool IStorage::hasPrimaryKey() const { - return primary_key.expression != nullptr; + return !primary_key.column_names.empty(); } Names IStorage::getColumnsRequiredForPrimaryKey() const @@ -529,9 +520,15 @@ void IStorage::setSamplingKey(const StorageMetadataKeyField & sampling_key_) sampling_key = sampling_key_; } + +bool IStorage::isSamplingKeyDefined() const +{ + return sampling_key.definition_ast != nullptr; +} + bool IStorage::hasSamplingKey() const { - return sampling_key.expression != nullptr; + return !sampling_key.column_names.empty(); } Names IStorage::getColumnsRequiredForSampling() const @@ -541,4 +538,54 @@ Names IStorage::getColumnsRequiredForSampling() const return {}; } +const TTLTableDescription & IStorage::getTableTTLs() const +{ + return table_ttl; +} + +void IStorage::setTableTTLs(const TTLTableDescription & table_ttl_) +{ + table_ttl = table_ttl_; +} + +bool IStorage::hasAnyTableTTL() const +{ + return hasAnyMoveTTL() || hasRowsTTL(); +} + +const TTLColumnsDescription & IStorage::getColumnTTLs() const +{ + return column_ttls_by_name; +} + +void IStorage::setColumnTTLs(const TTLColumnsDescription & column_ttls_by_name_) +{ + column_ttls_by_name = column_ttls_by_name_; +} + +bool IStorage::hasAnyColumnTTL() const +{ + return !column_ttls_by_name.empty(); +} + +const TTLDescription & IStorage::getRowsTTL() const +{ + return table_ttl.rows_ttl; +} + +bool IStorage::hasRowsTTL() const +{ + return table_ttl.rows_ttl.expression != nullptr; +} + +const TTLDescriptions & IStorage::getMoveTTLs() const +{ + return table_ttl.move_ttl; +} + +bool IStorage::hasAnyMoveTTL() const +{ + return !table_ttl.move_ttl.empty(); +} + } diff --git a/src/Storages/IStorage.h b/src/Storages/IStorage.h index f707b3a4b5c..41d658aac98 100644 --- a/src/Storages/IStorage.h +++ b/src/Storages/IStorage.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -82,7 +83,9 @@ class IStorage : public std::enable_shared_from_this, public TypePromo { public: IStorage() = delete; - explicit IStorage(StorageID storage_id_) : storage_id(std::move(storage_id_)) {} + /// Storage fields should be initialized in separate methods like setColumns + /// or setTableTTLs. + explicit IStorage(StorageID storage_id_) : storage_id(std::move(storage_id_)) {} //-V730 virtual ~IStorage() = default; IStorage(const IStorage &) = delete; @@ -130,10 +133,7 @@ public: virtual bool hasEvenlyDistributedRead() const { return false; } /// Returns true if there is set table TTL, any column TTL or any move TTL. - virtual bool hasAnyTTL() const { return false; } - - /// Returns true if there is set TTL for rows. - virtual bool hasRowsTTL() const { return false; } + virtual bool hasAnyTTL() const { return hasAnyColumnTTL() || hasAnyTableTTL(); } /// Optional size information of each physical column. /// Currently it's only used by the MergeTree family for query optimizations. @@ -205,6 +205,9 @@ private: StorageMetadataKeyField sorting_key; StorageMetadataKeyField sampling_key; + TTLColumnsDescription column_ttls_by_name; + TTLTableDescription table_ttl; + private: RWLockImpl::LockHolder tryLockTimed( const RWLock & rwlock, RWLockImpl::Type type, const String & query_id, const SettingSeconds & acquire_timeout) const; @@ -303,16 +306,6 @@ public: throw Exception("Method read is not supported by storage " + getName(), ErrorCodes::NOT_IMPLEMENTED); } - /** The same as read, but returns BlockInputStreams. - */ - BlockInputStreams readStreams( - const Names & /*column_names*/, - const SelectQueryInfo & /*query_info*/, - const Context & /*context*/, - QueryProcessingStage::Enum /*processed_stage*/, - size_t /*max_block_size*/, - unsigned /*num_streams*/); - /** Writes the data to a table. * Receives a description of the query, which can contain information about the data write method. * Returns an object by which you can write data sequentially. @@ -453,6 +446,8 @@ public: void setPartitionKey(const StorageMetadataKeyField & partition_key_); /// Returns ASTExpressionList of partition key expression for storage or nullptr if there is none. ASTPtr getPartitionKeyAST() const { return partition_key.definition_ast; } + /// Storage has user-defined (in CREATE query) partition key. + bool isPartitionKeyDefined() const; /// Storage has partition key. bool hasPartitionKey() const; /// Returns column names that need to be read to calculate partition key. @@ -466,7 +461,9 @@ public: void setSortingKey(const StorageMetadataKeyField & sorting_key_); /// Returns ASTExpressionList of sorting key expression for storage or nullptr if there is none. ASTPtr getSortingKeyAST() const { return sorting_key.definition_ast; } - /// Storage has sorting key. + /// Storage has user-defined (in CREATE query) sorting key. + bool isSortingKeyDefined() const; + /// Storage has sorting key. It means, that it contains at least one column. bool hasSortingKey() const; /// Returns column names that need to be read to calculate sorting key. Names getColumnsRequiredForSortingKey() const; @@ -483,7 +480,8 @@ public: ASTPtr getPrimaryKeyAST() const { return primary_key.definition_ast; } /// Storage has user-defined (in CREATE query) sorting key. bool isPrimaryKeyDefined() const; - /// Storage has primary key (maybe part of some other key). + /// Storage has primary key (maybe part of some other key). It means, that + /// it contains at least one column. bool hasPrimaryKey() const; /// Returns column names that need to be read to calculate primary key. Names getColumnsRequiredForPrimaryKey() const; @@ -498,6 +496,8 @@ public: void setSamplingKey(const StorageMetadataKeyField & sampling_key_); /// Returns sampling expression AST for storage or nullptr if there is none. ASTPtr getSamplingKeyAST() const { return sampling_key.definition_ast; } + /// Storage has user-defined (in CREATE query) sampling key. + bool isSamplingKeyDefined() const; /// Storage has sampling key. bool hasSamplingKey() const; /// Returns column names that need to be read to calculate sampling key. @@ -507,13 +507,32 @@ public: Names getColumnsRequiredForFinal() const { return getColumnsRequiredForSortingKey(); } - /// Returns columns, which will be needed to calculate dependencies - /// (skip indices, TTL expressions) if we update @updated_columns set of columns. + /// Returns columns, which will be needed to calculate dependencies (skip + /// indices, TTL expressions) if we update @updated_columns set of columns. virtual ColumnDependencies getColumnDependencies(const NameSet & /* updated_columns */) const { return {}; } - /// Returns storage policy if storage supports it + /// Returns storage policy if storage supports it. virtual StoragePolicyPtr getStoragePolicy() const { return {}; } + /// Common tables TTLs (for rows and moves). + const TTLTableDescription & getTableTTLs() const; + void setTableTTLs(const TTLTableDescription & table_ttl_); + bool hasAnyTableTTL() const; + + /// Separate TTLs for columns. + const TTLColumnsDescription & getColumnTTLs() const; + void setColumnTTLs(const TTLColumnsDescription & column_ttls_by_name_); + bool hasAnyColumnTTL() const; + + /// Just wrapper for table TTLs, return rows part of table TTLs. + const TTLDescription & getRowsTTL() const; + bool hasRowsTTL() const; + + /// Just wrapper for table TTLs, return moves (to disks or volumes) parts of + /// table TTL. + const TTLDescriptions & getMoveTTLs() const; + bool hasAnyMoveTTL() const; + /// If it is possible to quickly determine exact number of rows in the table at this moment of time, then return it. /// Used for: /// - Simple count() opimization diff --git a/src/Storages/Kafka/KafkaBlockInputStream.h b/src/Storages/Kafka/KafkaBlockInputStream.h index 1f94ee332d3..e3052122894 100644 --- a/src/Storages/Kafka/KafkaBlockInputStream.h +++ b/src/Storages/Kafka/KafkaBlockInputStream.h @@ -25,6 +25,7 @@ public: void readSuffixImpl() override; void commit(); + bool isStalled() const { return buffer->isStalled(); } private: StorageKafka & storage; diff --git a/src/Storages/Kafka/ReadBufferFromKafkaConsumer.h b/src/Storages/Kafka/ReadBufferFromKafkaConsumer.h index 12da701a55d..e90e3b48881 100644 --- a/src/Storages/Kafka/ReadBufferFromKafkaConsumer.h +++ b/src/Storages/Kafka/ReadBufferFromKafkaConsumer.h @@ -38,6 +38,7 @@ public: bool hasMorePolledMessages() const; bool polledDataUnusable() const { return (was_stopped || rebalance_happened); } + bool isStalled() const { return stalled; } void storeLastReadMessageOffset(); void resetToLastCommitted(const char * msg); diff --git a/src/Storages/Kafka/StorageKafka.cpp b/src/Storages/Kafka/StorageKafka.cpp index d1dfbe9d875..930d6ff55b5 100644 --- a/src/Storages/Kafka/StorageKafka.cpp +++ b/src/Storages/Kafka/StorageKafka.cpp @@ -51,6 +51,7 @@ namespace { const auto RESCHEDULE_MS = 500; const auto CLEANUP_TIMEOUT_MS = 3000; + const auto MAX_THREAD_WORK_DURATION_MS = 60000; // once per minute leave do reschedule (we can't lock threads in pool forever) /// Configuration prefix const String CONFIG_PREFIX = "kafka"; @@ -323,10 +324,10 @@ void StorageKafka::updateConfiguration(cppkafka::Configuration & conf) } // No need to add any prefix, messages can be distinguished - conf.set_log_callback([this](cppkafka::KafkaHandleBase &, int level, const std::string & /* facility */, const std::string & message) + conf.set_log_callback([this](cppkafka::KafkaHandleBase &, int level, const std::string & facility, const std::string & message) { auto [poco_level, client_logs_level] = parseSyslogLevel(level); - LOG_IMPL(log, client_logs_level, poco_level, message); + LOG_IMPL(log, client_logs_level, poco_level, "[rdk:{}] {}", facility, message); }); // Configure interceptor to change thread name @@ -360,7 +361,7 @@ bool StorageKafka::checkDependencies(const StorageID & table_id) // Check the dependencies are ready? for (const auto & db_tab : dependencies) { - auto table = DatabaseCatalog::instance().tryGetTable(db_tab); + auto table = DatabaseCatalog::instance().tryGetTable(db_tab, global_context); if (!table) return false; @@ -386,6 +387,8 @@ void StorageKafka::threadFunc() size_t dependencies_count = DatabaseCatalog::instance().getDependencies(table_id).size(); if (dependencies_count) { + auto start_time = std::chrono::steady_clock::now(); + // Keep streaming as long as there are attached views and streaming is not cancelled while (!stream_cancelled && num_created_consumers > 0) { @@ -394,9 +397,21 @@ void StorageKafka::threadFunc() LOG_DEBUG(log, "Started streaming to {} attached views", dependencies_count); - // Reschedule if not limited - if (!streamToViews()) + // Exit the loop & reschedule if some stream stalled + auto some_stream_is_stalled = streamToViews(); + if (some_stream_is_stalled) + { + LOG_TRACE(log, "Stream(s) stalled. Reschedule."); break; + } + + auto ts = std::chrono::steady_clock::now(); + auto duration = std::chrono::duration_cast(ts-start_time); + if (duration.count() > MAX_THREAD_WORK_DURATION_MS) + { + LOG_TRACE(log, "Thread work duration limit exceeded. Reschedule."); + break; + } } } } @@ -414,7 +429,7 @@ void StorageKafka::threadFunc() bool StorageKafka::streamToViews() { auto table_id = getStorageID(); - auto table = DatabaseCatalog::instance().getTable(table_id); + auto table = DatabaseCatalog::instance().getTable(table_id, global_context); if (!table) throw Exception("Engine table " + table_id.getNameForLogs() + " doesn't exist.", ErrorCodes::LOGICAL_ERROR); @@ -459,15 +474,15 @@ bool StorageKafka::streamToViews() // It will be cancelled on underlying layer (kafka buffer) std::atomic stub = {false}; copyData(*in, *block_io.out, &stub); + + bool some_stream_is_stalled = false; for (auto & stream : streams) + { + some_stream_is_stalled = some_stream_is_stalled || stream->as()->isStalled(); stream->as()->commit(); + } - // Check whether the limits were applied during query execution - bool limits_applied = false; - const BlockStreamProfileInfo & info = in->getProfileInfo(); - limits_applied = info.hasAppliedLimit(); - - return limits_applied; + return some_stream_is_stalled; } void registerStorageKafka(StorageFactory & factory) diff --git a/src/Storages/LiveView/StorageLiveView.cpp b/src/Storages/LiveView/StorageLiveView.cpp index cd660407c89..3ee8c8409b8 100644 --- a/src/Storages/LiveView/StorageLiveView.cpp +++ b/src/Storages/LiveView/StorageLiveView.cpp @@ -111,7 +111,7 @@ MergeableBlocksPtr StorageLiveView::collectMergeableBlocks(const Context & conte InterpreterSelectQuery interpreter(mergeable_query->clone(), context, SelectQueryOptions(QueryProcessingStage::WithMergeableState), Names()); - auto view_mergeable_stream = std::make_shared(interpreter.execute().in); + auto view_mergeable_stream = std::make_shared(interpreter.execute().getInputStream()); while (Block this_block = view_mergeable_stream->read()) base_blocks->push_back(this_block); @@ -148,7 +148,7 @@ BlockInputStreamPtr StorageLiveView::completeQuery(Pipes pipes) block_context->addExternalTable(getBlocksTableName(), TemporaryTableHolder(global_context, creator)); InterpreterSelectQuery select(getInnerBlocksQuery(), *block_context, StoragePtr(), SelectQueryOptions(QueryProcessingStage::Complete)); - BlockInputStreamPtr data = std::make_shared(select.execute().in); + BlockInputStreamPtr data = std::make_shared(select.execute().getInputStream()); /// Squashing is needed here because the view query can generate a lot of blocks /// even when only one block is inserted into the parent table (e.g. if the query is a GROUP BY @@ -218,7 +218,7 @@ void StorageLiveView::writeIntoLiveView( QueryProcessingStage::WithMergeableState); auto data_mergeable_stream = std::make_shared( - select_block.execute().in); + select_block.execute().getInputStream()); while (Block this_block = data_mergeable_stream->read()) new_mergeable_blocks->push_back(this_block); @@ -401,7 +401,7 @@ void StorageLiveView::noUsersThread(std::shared_ptr storage, co if (drop_table) { - if (DatabaseCatalog::instance().tryGetTable(table_id)) + if (DatabaseCatalog::instance().tryGetTable(table_id, storage->global_context)) { try { diff --git a/src/Storages/LiveView/StorageLiveView.h b/src/Storages/LiveView/StorageLiveView.h index 801b0b42ec4..fe62de224da 100644 --- a/src/Storages/LiveView/StorageLiveView.h +++ b/src/Storages/LiveView/StorageLiveView.h @@ -53,7 +53,7 @@ public: { return getStorageID().table_name + "_blocks"; } - StoragePtr getParentStorage() const { return DatabaseCatalog::instance().getTable(select_table_id); } + StoragePtr getParentStorage() const { return DatabaseCatalog::instance().getTable(select_table_id, global_context); } ASTPtr getInnerQuery() const { return inner_query->clone(); } ASTPtr getInnerSubQuery() const diff --git a/src/Storages/MergeTree/IMergeTreeDataPart.cpp b/src/Storages/MergeTree/IMergeTreeDataPart.cpp index 6e048a956da..287bf916c19 100644 --- a/src/Storages/MergeTree/IMergeTreeDataPart.cpp +++ b/src/Storages/MergeTree/IMergeTreeDataPart.cpp @@ -775,6 +775,7 @@ void IMergeTreeDataPart::remove() const } } + String IMergeTreeDataPart::getRelativePathForDetachedPart(const String & prefix) const { /// Do not allow underscores in the prefix because they are used as separators. @@ -839,9 +840,10 @@ void IMergeTreeDataPart::checkConsistencyBase() const { String path = getFullRelativePath(); + const auto & pk = storage.getPrimaryKey(); if (!checksums.empty()) { - if (storage.hasPrimaryKey() && !checksums.files.count("primary.idx")) + if (!pk.column_names.empty() && !checksums.files.count("primary.idx")) throw Exception("No checksum for primary.idx", ErrorCodes::NO_FILE_IN_DATA_PART); if (storage.format_version >= MERGE_TREE_DATA_MIN_FORMAT_VERSION_WITH_CUSTOM_PARTITIONING) @@ -875,7 +877,7 @@ void IMergeTreeDataPart::checkConsistencyBase() const }; /// Check that the primary key index is not empty. - if (storage.hasPrimaryKey()) + if (!pk.column_names.empty()) check_file_not_empty(volume->getDisk(), path + "primary.idx"); if (storage.format_version >= MERGE_TREE_DATA_MIN_FORMAT_VERSION_WITH_CUSTOM_PARTITIONING) diff --git a/src/Storages/MergeTree/KeyCondition.cpp b/src/Storages/MergeTree/KeyCondition.cpp index 6ae22885dfd..ee381709dd4 100644 --- a/src/Storages/MergeTree/KeyCondition.cpp +++ b/src/Storages/MergeTree/KeyCondition.cpp @@ -181,8 +181,11 @@ const KeyCondition::AtomMap KeyCondition::atom_map }, { "empty", - [] (RPNElement & out, const Field &) + [] (RPNElement & out, const Field & value) { + if (value.getType() != Field::Types::String) + return false; + out.function = RPNElement::FUNCTION_IN_RANGE; out.range = Range(""); return true; @@ -190,8 +193,11 @@ const KeyCondition::AtomMap KeyCondition::atom_map }, { "notEmpty", - [] (RPNElement & out, const Field &) + [] (RPNElement & out, const Field & value) { + if (value.getType() != Field::Types::String) + return false; + out.function = RPNElement::FUNCTION_NOT_IN_RANGE; out.range = Range(""); return true; diff --git a/src/Storages/MergeTree/MergeTreeData.cpp b/src/Storages/MergeTree/MergeTreeData.cpp index d80dce167b4..175cf53ca93 100644 --- a/src/Storages/MergeTree/MergeTreeData.cpp +++ b/src/Storages/MergeTree/MergeTreeData.cpp @@ -250,19 +250,19 @@ StorageInMemoryMetadata MergeTreeData::getInMemoryMetadata() const { StorageInMemoryMetadata metadata(getColumns(), getIndices(), getConstraints()); - if (hasPartitionKey()) + if (isPartitionKeyDefined()) metadata.partition_by_ast = getPartitionKeyAST()->clone(); - if (hasSortingKey()) + if (isSortingKeyDefined()) metadata.order_by_ast = getSortingKeyAST()->clone(); if (isPrimaryKeyDefined()) metadata.primary_key_ast = getPrimaryKeyAST()->clone(); - if (ttl_table_ast) - metadata.ttl_for_table_ast = ttl_table_ast->clone(); + if (hasAnyTableTTL()) + metadata.ttl_for_table_ast = getTableTTLs().definition_ast->clone(); - if (hasSamplingKey()) + if (isSamplingKeyDefined()) metadata.sample_by_ast = getSamplingKeyAST()->clone(); if (settings_ast) @@ -580,55 +580,16 @@ void MergeTreeData::initPartitionKey(ASTPtr partition_by_ast) setPartitionKey(new_partition_key); } -namespace -{ - -void checkTTLExpression(const ExpressionActionsPtr & ttl_expression, const String & result_column_name) -{ - for (const auto & action : ttl_expression->getActions()) - { - if (action.type == ExpressionAction::APPLY_FUNCTION) - { - IFunctionBase & func = *action.function_base; - if (!func.isDeterministic()) - throw Exception("TTL expression cannot contain non-deterministic functions, " - "but contains function " + func.getName(), ErrorCodes::BAD_ARGUMENTS); - } - } - - const auto & result_column = ttl_expression->getSampleBlock().getByName(result_column_name); - - if (!typeid_cast(result_column.type.get()) - && !typeid_cast(result_column.type.get())) - { - throw Exception("TTL expression result column should have DateTime or Date type, but has " - + result_column.type->getName(), ErrorCodes::BAD_TTL_EXPRESSION); - } -} - -} - void MergeTreeData::setTTLExpressions(const ColumnsDescription & new_columns, const ASTPtr & new_ttl_table_ast, bool only_check) { - auto new_column_ttls = new_columns.getColumnTTLs(); + auto new_column_ttls_asts = new_columns.getColumnTTLs(); - auto create_ttl_entry = [this, &new_columns](ASTPtr ttl_ast) - { - TTLEntry result; + TTLColumnsDescription new_column_ttl_by_name = getColumnTTLs(); - auto syntax_result = SyntaxAnalyzer(global_context).analyze(ttl_ast, new_columns.getAllPhysical()); - result.expression = ExpressionAnalyzer(ttl_ast, syntax_result, global_context).getActions(false); - result.destination_type = PartDestinationType::DELETE; - result.result_column = ttl_ast->getColumnName(); - - checkTTLExpression(result.expression, result.result_column); - return result; - }; - - if (!new_column_ttls.empty()) + if (!new_column_ttls_asts.empty()) { NameSet columns_ttl_forbidden; @@ -640,23 +601,24 @@ void MergeTreeData::setTTLExpressions(const ColumnsDescription & new_columns, for (const auto & col : getColumnsRequiredForSortingKey()) columns_ttl_forbidden.insert(col); - for (const auto & [name, ast] : new_column_ttls) + for (const auto & [name, ast] : new_column_ttls_asts) { if (columns_ttl_forbidden.count(name)) throw Exception("Trying to set TTL for key column " + name, ErrorCodes::ILLEGAL_COLUMN); else { - auto new_ttl_entry = create_ttl_entry(ast); - if (!only_check) - column_ttl_entries_by_name[name] = new_ttl_entry; + auto new_ttl_entry = TTLDescription::getTTLFromAST(ast, new_columns, global_context, getPrimaryKey()); + new_column_ttl_by_name[name] = new_ttl_entry; } } + if (!only_check) + setColumnTTLs(new_column_ttl_by_name); } if (new_ttl_table_ast) { - std::vector update_move_ttl_entries; - TTLEntry update_rows_ttl_entry; + TTLDescriptions update_move_ttl_entries; + TTLDescription update_rows_ttl_entry; bool seen_delete_ttl = false; for (const auto & ttl_element_ptr : new_ttl_table_ast->children) @@ -665,48 +627,46 @@ void MergeTreeData::setTTLExpressions(const ColumnsDescription & new_columns, if (!ttl_element) throw Exception("Unexpected AST element in TTL expression", ErrorCodes::UNEXPECTED_AST_STRUCTURE); - if (ttl_element->destination_type == PartDestinationType::DELETE) + if (ttl_element->destination_type == DataDestinationType::DELETE) { if (seen_delete_ttl) { throw Exception("More than one DELETE TTL expression is not allowed", ErrorCodes::BAD_TTL_EXPRESSION); } - auto new_rows_ttl_entry = create_ttl_entry(ttl_element->children[0]); - if (!only_check) - update_rows_ttl_entry = new_rows_ttl_entry; + update_rows_ttl_entry = TTLDescription::getTTLFromAST(ttl_element_ptr, new_columns, global_context, getPrimaryKey()); seen_delete_ttl = true; } else { - auto new_ttl_entry = create_ttl_entry(ttl_element->children[0]); + auto new_ttl_entry = TTLDescription::getTTLFromAST(ttl_element_ptr, new_columns, global_context, getPrimaryKey()); - new_ttl_entry.entry_ast = ttl_element_ptr; - new_ttl_entry.destination_type = ttl_element->destination_type; - new_ttl_entry.destination_name = ttl_element->destination_name; - if (!new_ttl_entry.getDestination(getStoragePolicy())) + if (!getDestinationForTTL(new_ttl_entry)) { String message; - if (new_ttl_entry.destination_type == PartDestinationType::DISK) + if (new_ttl_entry.destination_type == DataDestinationType::DISK) message = "No such disk " + backQuote(new_ttl_entry.destination_name) + " for given storage policy."; else message = "No such volume " + backQuote(new_ttl_entry.destination_name) + " for given storage policy."; throw Exception(message, ErrorCodes::BAD_TTL_EXPRESSION); } - if (!only_check) - update_move_ttl_entries.emplace_back(std::move(new_ttl_entry)); + update_move_ttl_entries.emplace_back(std::move(new_ttl_entry)); } } if (!only_check) { - rows_ttl_entry = update_rows_ttl_entry; - ttl_table_ast = new_ttl_table_ast; + TTLTableDescription new_table_ttl + { + .definition_ast = new_ttl_table_ast, + .rows_ttl = update_rows_ttl_entry, + .move_ttl = update_move_ttl_entries, + }; auto move_ttl_entries_lock = std::lock_guard(move_ttl_entries_mutex); - move_ttl_entries = update_move_ttl_entries; + setTableTTLs(new_table_ttl); } } } @@ -2520,9 +2480,6 @@ void MergeTreeData::movePartitionToDisk(const ASTPtr & partition, const String & return part_ptr->volume->getDisk()->getName() == disk->getName(); }), parts.end()); - if (parts.empty()) - throw Exception("Nothing to move", ErrorCodes::NO_SUCH_DATA_PART); - if (parts.empty()) { String no_parts_to_move_message; @@ -2913,12 +2870,12 @@ ReservationPtr MergeTreeData::tryReserveSpacePreferringTTLRules(UInt64 expected_ auto ttl_entry = selectTTLEntryForTTLInfos(ttl_infos, time_of_move); if (ttl_entry) { - SpacePtr destination_ptr = ttl_entry->getDestination(getStoragePolicy()); + SpacePtr destination_ptr = getDestinationForTTL(*ttl_entry); if (!destination_ptr) { - if (ttl_entry->destination_type == PartDestinationType::VOLUME) + if (ttl_entry->destination_type == DataDestinationType::VOLUME) LOG_WARNING(log, "Would like to reserve space on volume '{}' by TTL rule of table '{}' but volume was not found", ttl_entry->destination_name, log_name); - else if (ttl_entry->destination_type == PartDestinationType::DISK) + else if (ttl_entry->destination_type == DataDestinationType::DISK) LOG_WARNING(log, "Would like to reserve space on disk '{}' by TTL rule of table '{}' but disk was not found", ttl_entry->destination_name, log_name); } else @@ -2927,9 +2884,9 @@ ReservationPtr MergeTreeData::tryReserveSpacePreferringTTLRules(UInt64 expected_ if (reservation) return reservation; else - if (ttl_entry->destination_type == PartDestinationType::VOLUME) + if (ttl_entry->destination_type == DataDestinationType::VOLUME) LOG_WARNING(log, "Would like to reserve space on volume '{}' by TTL rule of table '{}' but there is not enough space", ttl_entry->destination_name, log_name); - else if (ttl_entry->destination_type == PartDestinationType::DISK) + else if (ttl_entry->destination_type == DataDestinationType::DISK) LOG_WARNING(log, "Would like to reserve space on disk '{}' by TTL rule of table '{}' but there is not enough space", ttl_entry->destination_name, log_name); } } @@ -2939,37 +2896,39 @@ ReservationPtr MergeTreeData::tryReserveSpacePreferringTTLRules(UInt64 expected_ return reservation; } -SpacePtr MergeTreeData::TTLEntry::getDestination(StoragePolicyPtr policy) const +SpacePtr MergeTreeData::getDestinationForTTL(const TTLDescription & ttl) const { - if (destination_type == PartDestinationType::VOLUME) - return policy->getVolumeByName(destination_name); - else if (destination_type == PartDestinationType::DISK) - return policy->getDiskByName(destination_name); + auto policy = getStoragePolicy(); + if (ttl.destination_type == DataDestinationType::VOLUME) + return policy->getVolumeByName(ttl.destination_name); + else if (ttl.destination_type == DataDestinationType::DISK) + return policy->getDiskByName(ttl.destination_name); else return {}; } -bool MergeTreeData::TTLEntry::isPartInDestination(StoragePolicyPtr policy, const IMergeTreeDataPart & part) const +bool MergeTreeData::isPartInTTLDestination(const TTLDescription & ttl, const IMergeTreeDataPart & part) const { - if (destination_type == PartDestinationType::VOLUME) + auto policy = getStoragePolicy(); + if (ttl.destination_type == DataDestinationType::VOLUME) { - for (const auto & disk : policy->getVolumeByName(destination_name)->getDisks()) + for (const auto & disk : policy->getVolumeByName(ttl.destination_name)->getDisks()) if (disk->getName() == part.volume->getDisk()->getName()) return true; } - else if (destination_type == PartDestinationType::DISK) - return policy->getDiskByName(destination_name)->getName() == part.volume->getDisk()->getName(); + else if (ttl.destination_type == DataDestinationType::DISK) + return policy->getDiskByName(ttl.destination_name)->getName() == part.volume->getDisk()->getName(); return false; } -std::optional MergeTreeData::selectTTLEntryForTTLInfos( - const IMergeTreeDataPart::TTLInfos & ttl_infos, - time_t time_of_move) const +std::optional +MergeTreeData::selectTTLEntryForTTLInfos(const IMergeTreeDataPart::TTLInfos & ttl_infos, time_t time_of_move) const { time_t max_max_ttl = 0; - std::vector::const_iterator best_entry_it; + TTLDescriptions::const_iterator best_entry_it; auto lock = std::lock_guard(move_ttl_entries_mutex); + const auto & move_ttl_entries = getMoveTTLs(); for (auto ttl_entry_it = move_ttl_entries.begin(); ttl_entry_it != move_ttl_entries.end(); ++ttl_entry_it) { auto ttl_info_it = ttl_infos.moves_ttl.find(ttl_entry_it->result_column); @@ -2983,7 +2942,7 @@ std::optional MergeTreeData::selectTTLEntryForTTLInfos( } } - return max_max_ttl ? *best_entry_it : std::optional(); + return max_max_ttl ? *best_entry_it : std::optional(); } MergeTreeData::DataParts MergeTreeData::getDataParts(const DataPartStates & affordable_states) const @@ -3402,7 +3361,7 @@ bool MergeTreeData::areBackgroundMovesNeeded() const if (policy->getVolumes().size() > 1) return true; - return policy->getVolumes().size() == 1 && policy->getVolumes()[0]->getDisks().size() > 1 && !move_ttl_entries.empty(); + return policy->getVolumes().size() == 1 && policy->getVolumes()[0]->getDisks().size() > 1 && hasAnyMoveTTL(); } bool MergeTreeData::movePartsToSpace(const DataPartsVector & parts, SpacePtr space) @@ -3541,7 +3500,7 @@ ColumnDependencies MergeTreeData::getColumnDependencies(const NameSet & updated_ if (hasRowsTTL()) { - if (add_dependent_columns(rows_ttl_entry.expression, required_ttl_columns)) + if (add_dependent_columns(getRowsTTL().expression, required_ttl_columns)) { /// Filter all columns, if rows TTL expression have to be recalculated. for (const auto & column : getColumns().getAllPhysical()) @@ -3549,13 +3508,13 @@ ColumnDependencies MergeTreeData::getColumnDependencies(const NameSet & updated_ } } - for (const auto & [name, entry] : column_ttl_entries_by_name) + for (const auto & [name, entry] : getColumnTTLs()) { if (add_dependent_columns(entry.expression, required_ttl_columns)) updated_ttl_columns.insert(name); } - for (const auto & entry : move_ttl_entries) + for (const auto & entry : getMoveTTLs()) add_dependent_columns(entry.expression, required_ttl_columns); for (const auto & column : indices_columns) diff --git a/src/Storages/MergeTree/MergeTreeData.h b/src/Storages/MergeTree/MergeTreeData.h index cd1d4912a29..bf9bfea88b3 100644 --- a/src/Storages/MergeTree/MergeTreeData.h +++ b/src/Storages/MergeTree/MergeTreeData.h @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -519,11 +520,6 @@ public: bool hasSkipIndices() const { return !skip_indices.empty(); } - bool hasAnyColumnTTL() const { return !column_ttl_entries_by_name.empty(); } - bool hasAnyMoveTTL() const { return !move_ttl_entries.empty(); } - bool hasRowsTTL() const override { return !rows_ttl_entry.isEmpty(); } - bool hasAnyTTL() const override { return hasRowsTTL() || hasAnyMoveTTL() || hasAnyColumnTTL(); } - /// Check that the part is not broken and calculate the checksums for it if they are not present. MutableDataPartPtr loadPartAndFixMetadata(const VolumePtr & volume, const String & relative_path) const; @@ -625,6 +621,13 @@ public: /// Return alter conversions for part which must be applied on fly. AlterConversions getAlterConversionsForPart(const MergeTreeDataPartPtr part) const; + /// Returns destination disk or volume for the TTL rule according to current + /// storage policy + SpacePtr getDestinationForTTL(const TTLDescription & ttl) const; + + /// Checks if given part already belongs destination disk or volume for the + /// TTL rule. + bool isPartInTTLDestination(const TTLDescription & ttl, const IMergeTreeDataPart & part) const; MergeTreeDataFormatVersion format_version; @@ -647,39 +650,13 @@ public: ExpressionActionsPtr primary_key_and_skip_indices_expr; ExpressionActionsPtr sorting_key_and_skip_indices_expr; - struct TTLEntry - { - ExpressionActionsPtr expression; - String result_column; + std::optional selectTTLEntryForTTLInfos(const IMergeTreeDataPart::TTLInfos & ttl_infos, time_t time_of_move) const; - /// Name and type of a destination are only valid in table-level context. - PartDestinationType destination_type; - String destination_name; - - ASTPtr entry_ast; - - /// Returns destination disk or volume for this rule. - SpacePtr getDestination(StoragePolicyPtr policy) const; - - /// Checks if given part already belongs destination disk or volume for this rule. - bool isPartInDestination(StoragePolicyPtr policy, const IMergeTreeDataPart & part) const; - - bool isEmpty() const { return expression == nullptr; } - }; - - std::optional selectTTLEntryForTTLInfos(const IMergeTreeDataPart::TTLInfos & ttl_infos, time_t time_of_move) const; - - using TTLEntriesByName = std::unordered_map; - TTLEntriesByName column_ttl_entries_by_name; - - TTLEntry rows_ttl_entry; - - /// This mutex is required for background move operations which do not obtain global locks. + /// This mutex is required for background move operations which do not + /// obtain global locks. + /// TODO (alesap) It will be removed after metadata became atomic mutable std::mutex move_ttl_entries_mutex; - /// Vector rw operations have to be done under "move_ttl_entries_mutex". - std::vector move_ttl_entries; - /// Limiting parallel sends per one table, used in DataPartsExchange std::atomic_uint current_table_sends {0}; @@ -706,7 +683,6 @@ protected: friend struct ReplicatedMergeTreeTableMetadata; friend class StorageReplicatedMergeTree; - ASTPtr ttl_table_ast; ASTPtr settings_ast; bool require_part_metadata; diff --git a/src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp b/src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp index f90add64732..24e3e3ac69d 100644 --- a/src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp +++ b/src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp @@ -1151,7 +1151,7 @@ Pipes MergeTreeDataSelectExecutor::spreadMarkRangesAmongStreamsFinal( if (num_streams > settings.max_final_threads) num_streams = settings.max_final_threads; - if (num_streams <= 1 || sort_description.empty() || query_info.force_tree_shaped_pipeline) + if (num_streams <= 1 || sort_description.empty()) { Pipe pipe(std::move(pipes), get_merging_processor()); diff --git a/src/Storages/MergeTree/MergeTreeDataWriter.cpp b/src/Storages/MergeTree/MergeTreeDataWriter.cpp index 3aa15d22e88..4eedf99c837 100644 --- a/src/Storages/MergeTree/MergeTreeDataWriter.cpp +++ b/src/Storages/MergeTree/MergeTreeDataWriter.cpp @@ -78,10 +78,12 @@ void buildScatterSelector( } /// Computes ttls and updates ttl infos -void updateTTL(const MergeTreeData::TTLEntry & ttl_entry, +void updateTTL( + const TTLDescription & ttl_entry, IMergeTreeDataPart::TTLInfos & ttl_infos, DB::MergeTreeDataPartTTLInfo & ttl_info, - Block & block, bool update_part_min_max_ttls) + Block & block, + bool update_part_min_max_ttls) { bool remove_column = false; if (!block.has(ttl_entry.result_column)) @@ -229,7 +231,8 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataWriter::writeTempPart(BlockWithPa size_t expected_size = block.bytes(); DB::IMergeTreeDataPart::TTLInfos move_ttl_infos; - for (const auto & ttl_entry : data.move_ttl_entries) + const auto & move_ttl_entries = data.getMoveTTLs(); + for (const auto & ttl_entry : move_ttl_entries) updateTTL(ttl_entry, move_ttl_infos, move_ttl_infos.moves_ttl[ttl_entry.result_column], block, false); NamesAndTypesList columns = data.getColumns().getAllPhysical().filter(block.getNames()); @@ -288,9 +291,9 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataWriter::writeTempPart(BlockWithPa } if (data.hasRowsTTL()) - updateTTL(data.rows_ttl_entry, new_data_part->ttl_infos, new_data_part->ttl_infos.table_ttl, block, true); + updateTTL(data.getRowsTTL(), new_data_part->ttl_infos, new_data_part->ttl_infos.table_ttl, block, true); - for (const auto & [name, ttl_entry] : data.column_ttl_entries_by_name) + for (const auto & [name, ttl_entry] : data.getColumnTTLs()) updateTTL(ttl_entry, new_data_part->ttl_infos, new_data_part->ttl_infos.columns_ttl[name], block, true); new_data_part->ttl_infos.update(move_ttl_infos); diff --git a/src/Storages/MergeTree/MergeTreePartsMover.cpp b/src/Storages/MergeTree/MergeTreePartsMover.cpp index ae66e40e042..4e564b512d6 100644 --- a/src/Storages/MergeTree/MergeTreePartsMover.cpp +++ b/src/Storages/MergeTree/MergeTreePartsMover.cpp @@ -128,14 +128,14 @@ bool MergeTreePartsMover::selectPartsForMove( if (!can_move(part, &reason)) continue; - auto ttl_entry = part->storage.selectTTLEntryForTTLInfos(part->ttl_infos, time_of_move); + auto ttl_entry = data->selectTTLEntryForTTLInfos(part->ttl_infos, time_of_move); auto to_insert = need_to_move.find(part->volume->getDisk()); ReservationPtr reservation; if (ttl_entry) { - auto destination = ttl_entry->getDestination(policy); - if (destination && !ttl_entry->isPartInDestination(policy, *part)) - reservation = part->storage.tryReserveSpace(part->getBytesOnDisk(), ttl_entry->getDestination(policy)); + auto destination = data->getDestinationForTTL(*ttl_entry); + if (destination && !data->isPartInTTLDestination(*ttl_entry, *part)) + reservation = data->tryReserveSpace(part->getBytesOnDisk(), data->getDestinationForTTL(*ttl_entry)); } if (reservation) /// Found reservation by TTL rule. diff --git a/src/Storages/MergeTree/ReplicatedMergeTreeTableMetadata.cpp b/src/Storages/MergeTree/ReplicatedMergeTreeTableMetadata.cpp index 00116775213..3f9d039ffa1 100644 --- a/src/Storages/MergeTree/ReplicatedMergeTreeTableMetadata.cpp +++ b/src/Storages/MergeTree/ReplicatedMergeTreeTableMetadata.cpp @@ -53,7 +53,7 @@ ReplicatedMergeTreeTableMetadata::ReplicatedMergeTreeTableMetadata(const MergeTr if (data.format_version >= MERGE_TREE_DATA_MIN_FORMAT_VERSION_WITH_CUSTOM_PARTITIONING) partition_key = formattedAST(data.getPartitionKey().expression_list_ast); - ttl_table = formattedAST(data.ttl_table_ast); + ttl_table = formattedAST(data.getTableTTLs().definition_ast); skip_indices = data.getIndices().toString(); if (data.canUseAdaptiveGranularity()) diff --git a/src/Storages/MergeTree/StorageFromMergeTreeDataPart.h b/src/Storages/MergeTree/StorageFromMergeTreeDataPart.h index a25a3a25337..37acf0f0160 100644 --- a/src/Storages/MergeTree/StorageFromMergeTreeDataPart.h +++ b/src/Storages/MergeTree/StorageFromMergeTreeDataPart.h @@ -39,9 +39,6 @@ public: return part->storage.mayBenefitFromIndexForIn(left_in_operand, query_context); } - bool hasAnyTTL() const override { return part->storage.hasAnyTTL(); } - bool hasRowsTTL() const override { return part->storage.hasRowsTTL(); } - ColumnDependencies getColumnDependencies(const NameSet & updated_columns) const override { return part->storage.getColumnDependencies(updated_columns); @@ -65,6 +62,8 @@ protected: setColumns(part_->storage.getColumns()); setIndices(part_->storage.getIndices()); setSortingKey(part_->storage.getSortingKey()); + setColumnTTLs(part->storage.getColumnTTLs()); + setTableTTLs(part->storage.getTableTTLs()); } private: diff --git a/src/Storages/PartitionCommands.cpp b/src/Storages/PartitionCommands.cpp index 9c8fc2cb598..c3bf00187af 100644 --- a/src/Storages/PartitionCommands.cpp +++ b/src/Storages/PartitionCommands.cpp @@ -1,6 +1,6 @@ #include #include -#include +#include #include #include @@ -42,13 +42,13 @@ std::optional PartitionCommand::parse(const ASTAlterCommand * res.part = command_ast->part; switch (command_ast->move_destination_type) { - case PartDestinationType::DISK: + case DataDestinationType::DISK: res.move_destination_type = PartitionCommand::MoveDestinationType::DISK; break; - case PartDestinationType::VOLUME: + case DataDestinationType::VOLUME: res.move_destination_type = PartitionCommand::MoveDestinationType::VOLUME; break; - case PartDestinationType::TABLE: + case DataDestinationType::TABLE: res.move_destination_type = PartitionCommand::MoveDestinationType::TABLE; res.to_database = command_ast->to_database; res.to_table = command_ast->to_table; diff --git a/src/Storages/RabbitMQ/StorageRabbitMQ.cpp b/src/Storages/RabbitMQ/StorageRabbitMQ.cpp index b1060a59e00..fb705e4d1bc 100644 --- a/src/Storages/RabbitMQ/StorageRabbitMQ.cpp +++ b/src/Storages/RabbitMQ/StorageRabbitMQ.cpp @@ -215,7 +215,7 @@ bool StorageRabbitMQ::checkDependencies(const StorageID & table_id) // Check the dependencies are ready? for (const auto & db_tab : dependencies) { - auto table = DatabaseCatalog::instance().tryGetTable(db_tab); + auto table = DatabaseCatalog::instance().tryGetTable(db_tab, global_context); if (!table) return false; @@ -270,7 +270,7 @@ void StorageRabbitMQ::threadFunc() bool StorageRabbitMQ::streamToViews() { auto table_id = getStorageID(); - auto table = DatabaseCatalog::instance().getTable(table_id); + auto table = DatabaseCatalog::instance().getTable(table_id, global_context); if (!table) throw Exception("Engine table " + table_id.getNameForLogs() + " doesn't exist.", ErrorCodes::LOGICAL_ERROR); diff --git a/src/Storages/SelectQueryInfo.h b/src/Storages/SelectQueryInfo.h index 3d7e26d3817..84cf3a32aa1 100644 --- a/src/Storages/SelectQueryInfo.h +++ b/src/Storages/SelectQueryInfo.h @@ -80,28 +80,6 @@ struct SelectQueryInfo /// Prepared sets are used for indices by storage engine. /// Example: x IN (1, 2, 3) PreparedSets sets; - - /// Temporary flag is needed to support old pipeline with input streams. - /// If enabled, then pipeline returned by storage must be a tree. - /// Processors from the tree can't return ExpandPipeline status. - mutable bool force_tree_shaped_pipeline = false; -}; - -/// RAII class to enable force_tree_shaped_pipeline for SelectQueryInfo. -/// Looks awful, but I hope it's temporary. -struct ForceTreeShapedPipeline -{ - explicit ForceTreeShapedPipeline(const SelectQueryInfo & info_) : info(info_) - { - force_tree_shaped_pipeline = info.force_tree_shaped_pipeline; - info.force_tree_shaped_pipeline = true; - } - - ~ForceTreeShapedPipeline() { info.force_tree_shaped_pipeline = force_tree_shaped_pipeline; } - -private: - bool force_tree_shaped_pipeline; - const SelectQueryInfo & info; }; } diff --git a/src/Storages/StorageBuffer.cpp b/src/Storages/StorageBuffer.cpp index 95be1275d3d..1072f0f3537 100644 --- a/src/Storages/StorageBuffer.cpp +++ b/src/Storages/StorageBuffer.cpp @@ -129,7 +129,7 @@ QueryProcessingStage::Enum StorageBuffer::getQueryProcessingStage(const Context { if (destination_id) { - auto destination = DatabaseCatalog::instance().getTable(destination_id); + auto destination = DatabaseCatalog::instance().getTable(destination_id, context); if (destination.get() == this) throw Exception("Destination table is myself. Read will cause infinite loop.", ErrorCodes::INFINITE_LOOP); @@ -153,7 +153,7 @@ Pipes StorageBuffer::read( if (destination_id) { - auto destination = DatabaseCatalog::instance().getTable(destination_id); + auto destination = DatabaseCatalog::instance().getTable(destination_id, context); if (destination.get() == this) throw Exception("Destination table is myself. Read will cause infinite loop.", ErrorCodes::INFINITE_LOOP); @@ -234,7 +234,7 @@ Pipes StorageBuffer::read( */ if (processed_stage > QueryProcessingStage::FetchColumns) for (auto & pipe : pipes_from_buffers) - pipe = InterpreterSelectQuery(query_info.query, context, std::move(pipe), SelectQueryOptions(processed_stage)).executeWithProcessors().getPipe(); + pipe = InterpreterSelectQuery(query_info.query, context, std::move(pipe), SelectQueryOptions(processed_stage)).execute().pipeline.getPipe(); if (query_info.prewhere_info) { @@ -334,7 +334,7 @@ public: StoragePtr destination; if (storage.destination_id) { - destination = DatabaseCatalog::instance().tryGetTable(storage.destination_id); + destination = DatabaseCatalog::instance().tryGetTable(storage.destination_id, storage.global_context); if (destination.get() == &storage) throw Exception("Destination table is myself. Write will cause infinite loop.", ErrorCodes::INFINITE_LOOP); } @@ -434,7 +434,7 @@ bool StorageBuffer::mayBenefitFromIndexForIn(const ASTPtr & left_in_operand, con if (!destination_id) return false; - auto destination = DatabaseCatalog::instance().getTable(destination_id); + auto destination = DatabaseCatalog::instance().getTable(destination_id, query_context); if (destination.get() == this) throw Exception("Destination table is myself. Read will cause infinite loop.", ErrorCodes::INFINITE_LOOP); @@ -602,7 +602,7 @@ void StorageBuffer::flushBuffer(Buffer & buffer, bool check_thresholds, bool loc */ try { - writeBlockToDestination(block_to_write, DatabaseCatalog::instance().tryGetTable(destination_id)); + writeBlockToDestination(block_to_write, DatabaseCatalog::instance().tryGetTable(destination_id, global_context)); } catch (...) { @@ -739,7 +739,7 @@ void StorageBuffer::checkAlterIsPossible(const AlterCommands & commands, const S std::optional StorageBuffer::totalRows() const { std::optional underlying_rows; - auto underlying = DatabaseCatalog::instance().tryGetTable(destination_id); + auto underlying = DatabaseCatalog::instance().tryGetTable(destination_id, global_context); if (underlying) underlying_rows = underlying->totalRows(); diff --git a/src/Storages/StorageBuffer.h b/src/Storages/StorageBuffer.h index 6d6c1f66569..10a4482c801 100644 --- a/src/Storages/StorageBuffer.h +++ b/src/Storages/StorageBuffer.h @@ -75,7 +75,7 @@ public: { if (!destination_id) return false; - auto dest = DatabaseCatalog::instance().tryGetTable(destination_id); + auto dest = DatabaseCatalog::instance().tryGetTable(destination_id, global_context); if (dest && dest.get() != this) return dest->supportsPrewhere(); return false; diff --git a/src/Storages/StorageInMemoryMetadata.cpp b/src/Storages/StorageInMemoryMetadata.cpp index 6c13033da1e..6713519151f 100644 --- a/src/Storages/StorageInMemoryMetadata.cpp +++ b/src/Storages/StorageInMemoryMetadata.cpp @@ -5,11 +5,11 @@ #include #include #include -#include namespace DB { + StorageInMemoryMetadata::StorageInMemoryMetadata( const ColumnsDescription & columns_, const IndicesDescription & indices_, @@ -138,4 +138,5 @@ StorageMetadataKeyField StorageMetadataKeyField::getKeyFromAST(const ASTPtr & de return result; } + } diff --git a/src/Storages/StorageInMemoryMetadata.h b/src/Storages/StorageInMemoryMetadata.h index 37dce5a78b9..1733cb4a308 100644 --- a/src/Storages/StorageInMemoryMetadata.h +++ b/src/Storages/StorageInMemoryMetadata.h @@ -72,5 +72,4 @@ struct StorageMetadataKeyField static StorageMetadataKeyField getKeyFromAST(const ASTPtr & definition_ast, const ColumnsDescription & columns, const Context & context); }; - } diff --git a/src/Storages/StorageMaterializedView.cpp b/src/Storages/StorageMaterializedView.cpp index a565c8c6260..2afa7f7d713 100644 --- a/src/Storages/StorageMaterializedView.cpp +++ b/src/Storages/StorageMaterializedView.cpp @@ -149,7 +149,7 @@ StorageMaterializedView::StorageMaterializedView( create_interpreter.setInternal(true); create_interpreter.execute(); - target_table_id = DatabaseCatalog::instance().getTable({manual_create_query->database, manual_create_query->table})->getStorageID(); + target_table_id = DatabaseCatalog::instance().getTable({manual_create_query->database, manual_create_query->table}, global_context)->getStorageID(); } if (!select_table_id.empty()) @@ -204,7 +204,7 @@ BlockOutputStreamPtr StorageMaterializedView::write(const ASTPtr & query, const static void executeDropQuery(ASTDropQuery::Kind kind, Context & global_context, const StorageID & target_table_id) { - if (DatabaseCatalog::instance().tryGetTable(target_table_id)) + if (DatabaseCatalog::instance().tryGetTable(target_table_id, global_context)) { /// We create and execute `drop` query for internal table. auto drop_query = std::make_shared(); @@ -362,12 +362,12 @@ void StorageMaterializedView::shutdown() StoragePtr StorageMaterializedView::getTargetTable() const { - return DatabaseCatalog::instance().getTable(target_table_id); + return DatabaseCatalog::instance().getTable(target_table_id, global_context); } StoragePtr StorageMaterializedView::tryGetTargetTable() const { - return DatabaseCatalog::instance().tryGetTable(target_table_id); + return DatabaseCatalog::instance().tryGetTable(target_table_id, global_context); } Strings StorageMaterializedView::getDataPaths() const diff --git a/src/Storages/StorageMerge.cpp b/src/Storages/StorageMerge.cpp index fb6d88c8d33..5bf3f8a3ce2 100644 --- a/src/Storages/StorageMerge.cpp +++ b/src/Storages/StorageMerge.cpp @@ -62,7 +62,7 @@ StorageMerge::StorageMerge( template StoragePtr StorageMerge::getFirstTable(F && predicate) const { - auto iterator = getDatabaseIterator(); + auto iterator = getDatabaseIterator(global_context); while (iterator->isValid()) { @@ -110,7 +110,7 @@ QueryProcessingStage::Enum StorageMerge::getQueryProcessingStage(const Context & { auto stage_in_source_tables = QueryProcessingStage::FetchColumns; - DatabaseTablesIteratorPtr iterator = getDatabaseIterator(); + DatabaseTablesIteratorPtr iterator = getDatabaseIterator(context); size_t selected_table_size = 0; @@ -238,20 +238,9 @@ Pipes StorageMerge::createSources(const SelectQueryInfo & query_info, const Quer if (!storage) { - if (query_info.force_tree_shaped_pipeline) - { - /// This flag means that pipeline must be tree-shaped, - /// so we can't enable processors for InterpreterSelectQuery here. - auto stream = InterpreterSelectQuery(modified_query_info.query, *modified_context, std::make_shared(header), - SelectQueryOptions(processed_stage).analyze()).execute().in; - - pipes.emplace_back(std::make_shared(std::move(stream))); - return pipes; - } - auto pipe = InterpreterSelectQuery(modified_query_info.query, *modified_context, std::make_shared(header), - SelectQueryOptions(processed_stage).analyze()).executeWithProcessors().getPipe(); + SelectQueryOptions(processed_stage).analyze()).execute().pipeline.getPipe(); pipe.addInterpreterContext(modified_context); pipes.emplace_back(std::move(pipe)); return pipes; @@ -276,15 +265,8 @@ Pipes StorageMerge::createSources(const SelectQueryInfo & query_info, const Quer InterpreterSelectQuery interpreter{modified_query_info.query, *modified_context, SelectQueryOptions(processed_stage)}; - if (query_info.force_tree_shaped_pipeline) { - BlockInputStreamPtr stream = interpreter.execute().in; - Pipe pipe(std::make_shared(std::move(stream))); - pipes.emplace_back(std::move(pipe)); - } - else - { - Pipe pipe = interpreter.executeWithProcessors().getPipe(); + Pipe pipe = interpreter.execute().pipeline.getPipe(); pipes.emplace_back(std::move(pipe)); } @@ -329,7 +311,7 @@ Pipes StorageMerge::createSources(const SelectQueryInfo & query_info, const Quer StorageMerge::StorageListWithLocks StorageMerge::getSelectedTables(const String & query_id, const Settings & settings) const { StorageListWithLocks selected_tables; - auto iterator = getDatabaseIterator(); + auto iterator = getDatabaseIterator(global_context); while (iterator->isValid()) { @@ -349,7 +331,7 @@ StorageMerge::StorageListWithLocks StorageMerge::getSelectedTables( const ASTPtr & query, bool has_virtual_column, const String & query_id, const Settings & settings) const { StorageListWithLocks selected_tables; - DatabaseTablesIteratorPtr iterator = getDatabaseIterator(); + DatabaseTablesIteratorPtr iterator = getDatabaseIterator(global_context); auto virtual_column = ColumnString::create(); @@ -384,12 +366,12 @@ StorageMerge::StorageListWithLocks StorageMerge::getSelectedTables( } -DatabaseTablesIteratorPtr StorageMerge::getDatabaseIterator() const +DatabaseTablesIteratorPtr StorageMerge::getDatabaseIterator(const Context & context) const { checkStackSize(); auto database = DatabaseCatalog::instance().getDatabase(source_database); auto table_name_match = [this](const String & table_name_) { return table_name_regexp.match(table_name_); }; - return database->getTablesIterator(table_name_match); + return database->getTablesIterator(context, table_name_match); } diff --git a/src/Storages/StorageMerge.h b/src/Storages/StorageMerge.h index ebe40109d84..401c5facf0c 100644 --- a/src/Storages/StorageMerge.h +++ b/src/Storages/StorageMerge.h @@ -61,7 +61,7 @@ private: template StoragePtr getFirstTable(F && predicate) const; - DatabaseTablesIteratorPtr getDatabaseIterator() const; + DatabaseTablesIteratorPtr getDatabaseIterator(const Context & context) const; NamesAndTypesList getVirtuals() const override; diff --git a/src/Storages/StorageMergeTree.cpp b/src/Storages/StorageMergeTree.cpp index f6114d709b6..c6af41cc163 100644 --- a/src/Storages/StorageMergeTree.cpp +++ b/src/Storages/StorageMergeTree.cpp @@ -990,7 +990,7 @@ void StorageMergeTree::alterPartition(const ASTPtr & query, const PartitionComma case PartitionCommand::MoveDestinationType::TABLE: checkPartitionCanBeDropped(command.partition); String dest_database = context.resolveDatabase(command.to_database); - auto dest_storage = DatabaseCatalog::instance().getTable({dest_database, command.to_table}); + auto dest_storage = DatabaseCatalog::instance().getTable({dest_database, command.to_table}, context); movePartitionToTable(dest_storage, command.partition, context); break; } @@ -1002,7 +1002,7 @@ void StorageMergeTree::alterPartition(const ASTPtr & query, const PartitionComma { checkPartitionCanBeDropped(command.partition); String from_database = context.resolveDatabase(command.from_database); - auto from_storage = DatabaseCatalog::instance().getTable({from_database, command.from_table}); + auto from_storage = DatabaseCatalog::instance().getTable({from_database, command.from_table}, context); replacePartitionFrom(from_storage, command.partition, command.replace, context); } break; diff --git a/src/Storages/StorageReplicatedMergeTree.cpp b/src/Storages/StorageReplicatedMergeTree.cpp index b4ca97602c4..00565e777ae 100644 --- a/src/Storages/StorageReplicatedMergeTree.cpp +++ b/src/Storages/StorageReplicatedMergeTree.cpp @@ -1570,7 +1570,7 @@ bool StorageReplicatedMergeTree::executeReplaceRange(const LogEntry & entry) auto clone_data_parts_from_source_table = [&] () -> size_t { - source_table = DatabaseCatalog::instance().tryGetTable(source_table_id); + source_table = DatabaseCatalog::instance().tryGetTable(source_table_id, global_context); if (!source_table) { LOG_DEBUG(log, "Can't use {} as source table for REPLACE PARTITION command. It does not exist.", source_table_id.getNameForLogs()); @@ -3485,7 +3485,7 @@ void StorageReplicatedMergeTree::alterPartition(const ASTPtr & query, const Part case PartitionCommand::MoveDestinationType::TABLE: checkPartitionCanBeDropped(command.partition); String dest_database = query_context.resolveDatabase(command.to_database); - auto dest_storage = DatabaseCatalog::instance().getTable({dest_database, command.to_table}); + auto dest_storage = DatabaseCatalog::instance().getTable({dest_database, command.to_table}, query_context); movePartitionToTable(dest_storage, command.partition, query_context); break; } @@ -3496,7 +3496,7 @@ void StorageReplicatedMergeTree::alterPartition(const ASTPtr & query, const Part { checkPartitionCanBeDropped(command.partition); String from_database = query_context.resolveDatabase(command.from_database); - auto from_storage = DatabaseCatalog::instance().getTable({from_database, command.from_table}); + auto from_storage = DatabaseCatalog::instance().getTable({from_database, command.from_table}, query_context); replacePartitionFrom(from_storage, command.partition, command.replace, query_context); } break; diff --git a/src/Storages/StorageView.cpp b/src/Storages/StorageView.cpp index 636c7f9d64d..c6b37a50aa9 100644 --- a/src/Storages/StorageView.cpp +++ b/src/Storages/StorageView.cpp @@ -19,6 +19,8 @@ #include #include #include +#include +#include namespace DB @@ -62,30 +64,25 @@ Pipes StorageView::read( if (context.getSettings().enable_optimize_predicate_expression) current_inner_query = getRuntimeViewQuery(*query_info.query->as(), context); - QueryPipeline pipeline; InterpreterSelectWithUnionQuery interpreter(current_inner_query, context, {}, column_names); - /// FIXME res may implicitly use some objects owned be pipeline, but them will be destructed after return - if (query_info.force_tree_shaped_pipeline) - { - BlockInputStreams streams = interpreter.executeWithMultipleStreams(pipeline); - for (auto & stream : streams) - pipes.emplace_back(std::make_shared(std::move(stream))); - } - else - /// TODO: support multiple streams here. Need more general interface than pipes. - pipes.emplace_back(interpreter.executeWithProcessors().getPipe()); + + auto pipeline = interpreter.execute().pipeline; /// It's expected that the columns read from storage are not constant. /// Because method 'getSampleBlockForColumns' is used to obtain a structure of result in InterpreterSelectQuery. - for (auto & pipe : pipes) + pipeline.addSimpleTransform([](const Block & header) { - pipe.addSimpleTransform(std::make_shared(pipe.getHeader())); + return std::make_shared(header); + }); - /// And also convert to expected structure. - pipe.addSimpleTransform(std::make_shared( - pipe.getHeader(), getSampleBlockForColumns(column_names), - ConvertingTransform::MatchColumnsMode::Name)); - } + /// And also convert to expected structure. + pipeline.addSimpleTransform([&](const Block & header) + { + return std::make_shared(header, getSampleBlockForColumns(column_names), + ConvertingTransform::MatchColumnsMode::Name); + }); + + pipes = std::move(pipeline).getPipes(); return pipes; } diff --git a/src/Storages/System/StorageSystemColumns.cpp b/src/Storages/System/StorageSystemColumns.cpp index ab824fc8bdc..8eb8856512e 100644 --- a/src/Storages/System/StorageSystemColumns.cpp +++ b/src/Storages/System/StorageSystemColumns.cpp @@ -301,7 +301,7 @@ Pipes StorageSystemColumns::read( const DatabasePtr database = databases.at(database_name); offsets[i] = i ? offsets[i - 1] : 0; - for (auto iterator = database->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = database->getTablesIterator(context); iterator->isValid(); iterator->next()) { const String & table_name = iterator->name(); storages.emplace(std::piecewise_construct, diff --git a/src/Storages/System/StorageSystemGraphite.cpp b/src/Storages/System/StorageSystemGraphite.cpp index cde75aa5550..bfa25a99838 100644 --- a/src/Storages/System/StorageSystemGraphite.cpp +++ b/src/Storages/System/StorageSystemGraphite.cpp @@ -25,7 +25,7 @@ NamesAndTypesList StorageSystemGraphite::getNamesAndTypes() /* * Looking for (Replicated)*GraphiteMergeTree and get all configuration parameters for them */ -static StorageSystemGraphite::Configs getConfigs() +static StorageSystemGraphite::Configs getConfigs(const Context & context) { const Databases databases = DatabaseCatalog::instance().getDatabases(); StorageSystemGraphite::Configs graphite_configs; @@ -36,7 +36,7 @@ static StorageSystemGraphite::Configs getConfigs() if (db.second->getEngineName() == "Lazy") continue; - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { const auto & table = iterator->table(); @@ -71,9 +71,9 @@ static StorageSystemGraphite::Configs getConfigs() return graphite_configs; } -void StorageSystemGraphite::fillData(MutableColumns & res_columns, const Context &, const SelectQueryInfo &) const +void StorageSystemGraphite::fillData(MutableColumns & res_columns, const Context & context, const SelectQueryInfo &) const { - Configs graphite_configs = getConfigs(); + Configs graphite_configs = getConfigs(context); for (const auto & config : graphite_configs) { diff --git a/src/Storages/System/StorageSystemMutations.cpp b/src/Storages/System/StorageSystemMutations.cpp index d4a262860dc..685565d82e1 100644 --- a/src/Storages/System/StorageSystemMutations.cpp +++ b/src/Storages/System/StorageSystemMutations.cpp @@ -51,7 +51,7 @@ void StorageSystemMutations::fillData(MutableColumns & res_columns, const Contex const bool check_access_for_tables = check_access_for_databases && !access->isGranted(AccessType::SHOW_TABLES, db.first); - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { if (!dynamic_cast(iterator->table().get())) continue; diff --git a/src/Storages/System/StorageSystemPartsBase.cpp b/src/Storages/System/StorageSystemPartsBase.cpp index 6356e6d699e..3b97cbb2d9b 100644 --- a/src/Storages/System/StorageSystemPartsBase.cpp +++ b/src/Storages/System/StorageSystemPartsBase.cpp @@ -111,7 +111,7 @@ StoragesInfoStream::StoragesInfoStream(const SelectQueryInfo & query_info, const const DatabasePtr database = databases.at(database_name); offsets[i] = i ? offsets[i - 1] : 0; - for (auto iterator = database->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = database->getTablesIterator(context); iterator->isValid(); iterator->next()) { String table_name = iterator->name(); StoragePtr storage = iterator->table(); diff --git a/src/Storages/System/StorageSystemReplicas.cpp b/src/Storages/System/StorageSystemReplicas.cpp index 734d0098d8d..251b45e44b6 100644 --- a/src/Storages/System/StorageSystemReplicas.cpp +++ b/src/Storages/System/StorageSystemReplicas.cpp @@ -76,7 +76,7 @@ Pipes StorageSystemReplicas::read( if (db.second->getEngineName() == "Lazy") continue; const bool check_access_for_tables = check_access_for_databases && !access->isGranted(AccessType::SHOW_TABLES, db.first); - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { if (!dynamic_cast(iterator->table().get())) continue; diff --git a/src/Storages/System/StorageSystemReplicationQueue.cpp b/src/Storages/System/StorageSystemReplicationQueue.cpp index a6f0af8cc6c..2c188cf3734 100644 --- a/src/Storages/System/StorageSystemReplicationQueue.cpp +++ b/src/Storages/System/StorageSystemReplicationQueue.cpp @@ -60,7 +60,7 @@ void StorageSystemReplicationQueue::fillData(MutableColumns & res_columns, const const bool check_access_for_tables = check_access_for_databases && !access->isGranted(AccessType::SHOW_TABLES, db.first); - for (auto iterator = db.second->getTablesIterator(); iterator->isValid(); iterator->next()) + for (auto iterator = db.second->getTablesIterator(context); iterator->isValid(); iterator->next()) { if (!dynamic_cast(iterator->table().get())) continue; diff --git a/src/Storages/System/StorageSystemTables.cpp b/src/Storages/System/StorageSystemTables.cpp index 2caf599fe51..2bf6595bf53 100644 --- a/src/Storages/System/StorageSystemTables.cpp +++ b/src/Storages/System/StorageSystemTables.cpp @@ -232,7 +232,7 @@ protected: const bool check_access_for_tables = check_access_for_databases && !access->isGranted(AccessType::SHOW_TABLES, database_name); if (!tables_it || !tables_it->isValid()) - tables_it = database->getTablesIterator(); + tables_it = database->getTablesIterator(context); const bool need_lock_structure = needLockStructure(database, getPort().getHeader()); @@ -331,7 +331,7 @@ protected: if (columns_mask[src_index] || columns_mask[src_index + 1]) { - ASTPtr ast = database->tryGetCreateTableQuery(table_name); + ASTPtr ast = database->tryGetCreateTableQuery(table_name, context); if (columns_mask[src_index++]) res_columns[res_index++]->insert(ast ? queryToString(ast) : ""); diff --git a/src/Storages/System/StorageSystemUsers.cpp b/src/Storages/System/StorageSystemUsers.cpp index d0e042d054f..e0755fe59ab 100644 --- a/src/Storages/System/StorageSystemUsers.cpp +++ b/src/Storages/System/StorageSystemUsers.cpp @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -15,12 +16,26 @@ namespace DB { +namespace +{ + DataTypeEnum8::Values getAuthenticationTypeEnumValues() + { + DataTypeEnum8::Values enum_values; + for (auto type : ext::range(Authentication::MAX_TYPE)) + enum_values.emplace_back(Authentication::TypeInfo::get(type).name, static_cast(type)); + return enum_values; + } +} + + NamesAndTypesList StorageSystemUsers::getNamesAndTypes() { NamesAndTypesList names_and_types{ {"name", std::make_shared()}, {"id", std::make_shared()}, {"storage", std::make_shared()}, + {"auth_type", std::make_shared(getAuthenticationTypeEnumValues())}, + {"auth_params", std::make_shared(std::make_shared())}, {"host_ip", std::make_shared(std::make_shared())}, {"host_names", std::make_shared(std::make_shared())}, {"host_names_regexp", std::make_shared(std::make_shared())}, @@ -43,6 +58,9 @@ void StorageSystemUsers::fillData(MutableColumns & res_columns, const Context & auto & column_name = assert_cast(*res_columns[column_index++]); auto & column_id = assert_cast(*res_columns[column_index++]).getData(); auto & column_storage = assert_cast(*res_columns[column_index++]); + auto & column_auth_type = assert_cast(*res_columns[column_index++]).getData(); + auto & column_auth_params = assert_cast(assert_cast(*res_columns[column_index]).getData()); + auto & column_auth_params_offsets = assert_cast(*res_columns[column_index++]).getOffsets(); auto & column_host_ip = assert_cast(assert_cast(*res_columns[column_index]).getData()); auto & column_host_ip_offsets = assert_cast(*res_columns[column_index++]).getOffsets(); auto & column_host_names = assert_cast(assert_cast(*res_columns[column_index]).getData()); @@ -60,12 +78,15 @@ void StorageSystemUsers::fillData(MutableColumns & res_columns, const Context & auto add_row = [&](const String & name, const UUID & id, const String & storage_name, + const Authentication & authentication, const AllowedClientHosts & allowed_hosts, const ExtendedRoleSet & default_roles) { column_name.insertData(name.data(), name.length()); column_id.push_back(id); column_storage.insertData(storage_name.data(), storage_name.length()); + column_auth_type.push_back(static_cast(authentication.getType())); + column_auth_params_offsets.push_back(column_auth_params.size()); if (allowed_hosts.containsAnyHost()) { @@ -128,7 +149,7 @@ void StorageSystemUsers::fillData(MutableColumns & res_columns, const Context & if (!storage) continue; - add_row(user->getName(), id, storage->getStorageName(), user->allowed_client_hosts, user->default_roles); + add_row(user->getName(), id, storage->getStorageName(), user->authentication, user->allowed_client_hosts, user->default_roles); } } diff --git a/src/Storages/TTLDescription.cpp b/src/Storages/TTLDescription.cpp new file mode 100644 index 00000000000..da9691aab4a --- /dev/null +++ b/src/Storages/TTLDescription.cpp @@ -0,0 +1,198 @@ +#include + +#include +#include +#include +#include +#include +#include +#include +#include + + +#include +#include + + +namespace DB +{ + +namespace ErrorCodes +{ +extern const int BAD_ARGUMENTS; +extern const int BAD_TTL_EXPRESSION; +} + +namespace +{ + +void checkTTLExpression(const ExpressionActionsPtr & ttl_expression, const String & result_column_name) +{ + for (const auto & action : ttl_expression->getActions()) + { + if (action.type == ExpressionAction::APPLY_FUNCTION) + { + IFunctionBase & func = *action.function_base; + if (!func.isDeterministic()) + throw Exception( + "TTL expression cannot contain non-deterministic functions, " + "but contains function " + + func.getName(), + ErrorCodes::BAD_ARGUMENTS); + } + } + + const auto & result_column = ttl_expression->getSampleBlock().getByName(result_column_name); + + if (!typeid_cast(result_column.type.get()) + && !typeid_cast(result_column.type.get())) + { + throw Exception( + "TTL expression result column should have DateTime or Date type, but has " + result_column.type->getName(), + ErrorCodes::BAD_TTL_EXPRESSION); + } +} + +} + +TTLDescription TTLDescription::getTTLFromAST( + const ASTPtr & definition_ast, + const ColumnsDescription & columns, + const Context & context, + const StorageMetadataKeyField & primary_key) +{ + TTLDescription result; + const auto * ttl_element = definition_ast->as(); + + /// First child is expression: `TTL expr TO DISK` + if (ttl_element != nullptr) + result.expression_ast = ttl_element->children.front()->clone(); + else /// It's columns TTL without any additions, just copy it + result.expression_ast = definition_ast->clone(); + + auto ttl_ast = result.expression_ast->clone(); + auto syntax_analyzer_result = SyntaxAnalyzer(context).analyze(ttl_ast, columns.getAllPhysical()); + result.expression = ExpressionAnalyzer(ttl_ast, syntax_analyzer_result, context).getActions(false); + result.result_column = ttl_ast->getColumnName(); + + if (ttl_element == nullptr) /// columns TTL + { + result.destination_type = DataDestinationType::DELETE; + result.mode = TTLMode::DELETE; + } + else /// rows TTL + { + result.destination_type = ttl_element->destination_type; + result.destination_name = ttl_element->destination_name; + result.mode = ttl_element->mode; + + if (ttl_element->mode == TTLMode::DELETE) + { + if (ASTPtr where_expr_ast = ttl_element->where()) + { + auto where_syntax_result = SyntaxAnalyzer(context).analyze(where_expr_ast, columns.getAllPhysical()); + result.where_expression = ExpressionAnalyzer(where_expr_ast, where_syntax_result, context).getActions(false); + result.where_result_column = where_expr_ast->getColumnName(); + } + } + else if (ttl_element->mode == TTLMode::GROUP_BY) + { + const auto & pk_columns = primary_key.column_names; + + if (ttl_element->group_by_key.size() > pk_columns.size()) + throw Exception("TTL Expression GROUP BY key should be a prefix of primary key", ErrorCodes::BAD_TTL_EXPRESSION); + + NameSet primary_key_columns_set(pk_columns.begin(), pk_columns.end()); + NameSet aggregation_columns_set; + + for (const auto & column : primary_key.expression->getRequiredColumns()) + primary_key_columns_set.insert(column); + + for (size_t i = 0; i < ttl_element->group_by_key.size(); ++i) + { + if (ttl_element->group_by_key[i]->getColumnName() != pk_columns[i]) + throw Exception( + "TTL Expression GROUP BY key should be a prefix of primary key", + ErrorCodes::BAD_TTL_EXPRESSION); + } + + for (const auto & [name, value] : ttl_element->group_by_aggregations) + { + if (primary_key_columns_set.count(name)) + throw Exception( + "Can not set custom aggregation for column in primary key in TTL Expression", + ErrorCodes::BAD_TTL_EXPRESSION); + + aggregation_columns_set.insert(name); + } + + if (aggregation_columns_set.size() != ttl_element->group_by_aggregations.size()) + throw Exception( + "Multiple aggregations set for one column in TTL Expression", + ErrorCodes::BAD_TTL_EXPRESSION); + + + result.group_by_keys = Names(pk_columns.begin(), pk_columns.begin() + ttl_element->group_by_key.size()); + + auto aggregations = ttl_element->group_by_aggregations; + + for (size_t i = 0; i < pk_columns.size(); ++i) + { + ASTPtr value = primary_key.expression_list_ast->children[i]->clone(); + + if (i >= ttl_element->group_by_key.size()) + { + ASTPtr value_max = makeASTFunction("max", value->clone()); + aggregations.emplace_back(value->getColumnName(), std::move(value_max)); + } + + if (value->as()) + { + auto syntax_result = SyntaxAnalyzer(context).analyze(value, columns.getAllPhysical(), {}, true); + auto expr_actions = ExpressionAnalyzer(value, syntax_result, context).getActions(false); + for (const auto & column : expr_actions->getRequiredColumns()) + { + if (i < ttl_element->group_by_key.size()) + { + ASTPtr expr = makeASTFunction("any", std::make_shared(column)); + aggregations.emplace_back(column, std::move(expr)); + } + else + { + ASTPtr expr = makeASTFunction("argMax", std::make_shared(column), value->clone()); + aggregations.emplace_back(column, std::move(expr)); + } + } + } + } + + for (const auto & column : columns.getAllPhysical()) + { + if (!primary_key_columns_set.count(column.name) && !aggregation_columns_set.count(column.name)) + { + ASTPtr expr = makeASTFunction("any", std::make_shared(column.name)); + aggregations.emplace_back(column.name, std::move(expr)); + } + } + + for (auto [name, value] : aggregations) + { + auto syntax_result = SyntaxAnalyzer(context).analyze(value, columns.getAllPhysical(), {}, true); + auto expr_analyzer = ExpressionAnalyzer(value, syntax_result, context); + + result.set_parts.emplace_back(TTLAggregateDescription{ + name, value->getColumnName(), expr_analyzer.getActions(false)}); + + for (const auto & descr : expr_analyzer.getAnalyzedData().aggregate_descriptions) + result.aggregate_descriptions.push_back(descr); + } + } + } + + checkTTLExpression(result.expression, result.result_column); + + + return result; +} + +} diff --git a/src/Storages/TTLDescription.h b/src/Storages/TTLDescription.h new file mode 100644 index 00000000000..99a145b8acc --- /dev/null +++ b/src/Storages/TTLDescription.h @@ -0,0 +1,98 @@ +#pragma once +#include +#include +#include +#include +#include +#include +#include + +namespace DB +{ + +/// Assignment expression in TTL with GROUP BY +struct TTLAggregateDescription +{ + /// Name of column in assignment + /// x = sum(y) + /// ^ + String column_name; + + /// Name of column on the right hand of the assignment + /// x = sum(y) + /// ^~~~~~^ + String expression_result_column_name; + + /// Expressions to calculate the value of assignment expression + ExpressionActionsPtr expression; +}; + +using TTLAggregateDescriptions = std::vector; + +/// Common struct for TTL record in storage +struct TTLDescription +{ + TTLMode mode; + + /// Expression part of TTL AST: + /// TTL d + INTERVAL 1 DAY + /// ^~~~~~~~~~~~~~~~~~~^ + ASTPtr expression_ast; + + /// Expresion actions evaluated from AST + ExpressionActionsPtr expression; + + /// Result column of this TTL expression + String result_column; + + /// WHERE part in TTL expression + /// TTL ... WHERE x % 10 == 0 and y > 5 + /// ^~~~~~~~~~~~~~~~~~~~~~^ + ExpressionActionsPtr where_expression; + + /// Name of result column from WHERE expression + String where_result_column; + + /// Names of key columns in GROUP BY expression + /// TTL ... GROUP BY toDate(d), x SET ... + /// ^~~~~~~~~~~~^ + Names group_by_keys; + + /// SET parts of TTL expression + TTLAggregateDescriptions set_parts; + + /// Aggregate descriptions for GROUP BY in TTL + AggregateDescriptions aggregate_descriptions; + + /// Destination type, only valid for table TTLs. + /// For example DISK or VOLUME + DataDestinationType destination_type; + + /// Name of destination disk or volume + String destination_name; + + /// Parse TTL structure from definition. Able to parse both column and table + /// TTLs. + static TTLDescription getTTLFromAST(const ASTPtr & definition_ast, const ColumnsDescription & columns, const Context & context, const StorageMetadataKeyField & primary_key); +}; + +/// Mapping from column name to column TTL +using TTLColumnsDescription = std::unordered_map; +using TTLDescriptions = std::vector; + +/// Common TTL for all table. Specified after defining the table columns. +struct TTLTableDescription +{ + /// Definition. Include all parts of TTL: + /// TTL d + INTERVAL 1 day TO VOLUME 'disk1' + /// ^~~~~~~~~~~~~~~definition~~~~~~~~~~~~~~~^ + ASTPtr definition_ast; + + /// Rows removing TTL + TTLDescription rows_ttl; + + /// Moving data TTL (to other disks or volumes) + TTLDescriptions move_ttl; +}; + +} diff --git a/src/Storages/TTLMode.h b/src/Storages/TTLMode.h new file mode 100644 index 00000000000..0681f10fc17 --- /dev/null +++ b/src/Storages/TTLMode.h @@ -0,0 +1,14 @@ +#pragma once + + +namespace DB +{ + +enum class TTLMode +{ + DELETE, + MOVE, + GROUP_BY +}; + +} diff --git a/src/Storages/getStructureOfRemoteTable.cpp b/src/Storages/getStructureOfRemoteTable.cpp index 711612cf9e5..19d1172f1ff 100644 --- a/src/Storages/getStructureOfRemoteTable.cpp +++ b/src/Storages/getStructureOfRemoteTable.cpp @@ -84,7 +84,7 @@ ColumnsDescription getStructureOfRemoteTableInShard( else { if (shard_info.isLocal()) - return DatabaseCatalog::instance().getTable(table_id)->getColumns(); + return DatabaseCatalog::instance().getTable(table_id, context)->getColumns(); /// Request for a table description query = "DESC TABLE " + table_id.getFullTableName(); diff --git a/src/Storages/tests/gtest_storage_log.cpp b/src/Storages/tests/gtest_storage_log.cpp index 203104801aa..fff352210e7 100644 --- a/src/Storages/tests/gtest_storage_log.cpp +++ b/src/Storages/tests/gtest_storage_log.cpp @@ -68,7 +68,7 @@ using DiskImplementations = testing::Types; TYPED_TEST_SUITE(StorageLogTest, DiskImplementations); // Returns data written to table in Values format. -std::string writeData(int rows, DB::StoragePtr & table, DB::Context & context) +std::string writeData(int rows, DB::StoragePtr & table, const DB::Context & context) { using namespace DB; @@ -104,7 +104,7 @@ std::string writeData(int rows, DB::StoragePtr & table, DB::Context & context) } // Returns all table data in Values format. -std::string readData(DB::StoragePtr & table, DB::Context & context) +std::string readData(DB::StoragePtr & table, const DB::Context & context) { using namespace DB; @@ -136,7 +136,7 @@ std::string readData(DB::StoragePtr & table, DB::Context & context) TYPED_TEST(StorageLogTest, testReadWrite) { using namespace DB; - auto context_holder = getContext(); + const auto & context_holder = getContext(); std::string data; diff --git a/src/Storages/tests/gtest_transform_query_for_external_database.cpp b/src/Storages/tests/gtest_transform_query_for_external_database.cpp index df6ee2bd0a5..bf86322a676 100644 --- a/src/Storages/tests/gtest_transform_query_for_external_database.cpp +++ b/src/Storages/tests/gtest_transform_query_for_external_database.cpp @@ -18,7 +18,7 @@ using namespace DB; /// NOTE How to do better? struct State { - Context & context; + Context context; NamesAndTypesList columns{ {"column", std::make_shared()}, {"apply_id", std::make_shared()}, @@ -27,10 +27,11 @@ struct State {"create_time", std::make_shared()}, }; - explicit State(Context & context_) : context(context_) + explicit State() + : context(getContext().context) { registerFunctions(); - DatabasePtr database = std::make_shared("test"); + DatabasePtr database = std::make_shared("test", context); database->attachTable("table", StorageMemory::create(StorageID("test", "table"), ColumnsDescription{columns}, ConstraintsDescription{})); context.makeGlobalContext(); DatabaseCatalog::instance().attachDatabase("test", database); @@ -38,6 +39,11 @@ struct State } }; +State getState() +{ + static State state; + return state; +} static void check(const std::string & query, const std::string & expected, const Context & context, const NamesAndTypesList & columns) { @@ -54,8 +60,7 @@ static void check(const std::string & query, const std::string & expected, const TEST(TransformQueryForExternalDatabase, InWithSingleElement) { - auto context_holder = getContext(); - State state(context_holder.context); + const State & state = getState(); check("SELECT column FROM test.table WHERE 1 IN (1)", R"(SELECT "column" FROM "test"."table" WHERE 1)", @@ -70,8 +75,7 @@ TEST(TransformQueryForExternalDatabase, InWithSingleElement) TEST(TransformQueryForExternalDatabase, Like) { - auto context_holder = getContext(); - State state(context_holder.context); + const State & state = getState(); check("SELECT column FROM test.table WHERE column LIKE '%hello%'", R"(SELECT "column" FROM "test"."table" WHERE "column" LIKE '%hello%')", @@ -83,8 +87,7 @@ TEST(TransformQueryForExternalDatabase, Like) TEST(TransformQueryForExternalDatabase, Substring) { - auto context_holder = getContext(); - State state(context_holder.context); + const State & state = getState(); check("SELECT column FROM test.table WHERE left(column, 10) = RIGHT(column, 10) AND SUBSTRING(column FROM 1 FOR 2) = 'Hello'", R"(SELECT "column" FROM "test"."table")", @@ -93,8 +96,7 @@ TEST(TransformQueryForExternalDatabase, Substring) TEST(TransformQueryForExternalDatabase, MultipleAndSubqueries) { - auto context_holder = getContext(); - State state(context_holder.context); + const State & state = getState(); check("SELECT column FROM test.table WHERE 1 = 1 AND toString(column) = '42' AND column = 42 AND left(column, 10) = RIGHT(column, 10) AND column IN (1, 42) AND SUBSTRING(column FROM 1 FOR 2) = 'Hello' AND column != 4", R"(SELECT "column" FROM "test"."table" WHERE 1 AND ("column" = 42) AND ("column" IN (1, 42)) AND ("column" != 4))", @@ -106,8 +108,7 @@ TEST(TransformQueryForExternalDatabase, MultipleAndSubqueries) TEST(TransformQueryForExternalDatabase, Issue7245) { - auto context_holder = getContext(); - State state(context_holder.context); + const State & state = getState(); check("select apply_id from test.table where apply_type = 2 and create_time > addDays(toDateTime('2019-01-01 01:02:03'),-7) and apply_status in (3,4)", R"(SELECT "apply_id", "apply_type", "apply_status", "create_time" FROM "test"."table" WHERE ("apply_type" = 2) AND ("create_time" > '2018-12-25 01:02:03') AND ("apply_status" IN (3, 4)))", diff --git a/src/Storages/ya.make b/src/Storages/ya.make index ffa3924d11a..8a36fad696f 100644 --- a/src/Storages/ya.make +++ b/src/Storages/ya.make @@ -173,6 +173,7 @@ SRCS( StorageXDBC.cpp transformQueryForExternalDatabase.cpp VirtualColumnUtils.cpp + TTLDescription.cpp ) END() diff --git a/src/TableFunctions/TableFunctionMerge.cpp b/src/TableFunctions/TableFunctionMerge.cpp index 7a161c13bdc..cd924270f7c 100644 --- a/src/TableFunctions/TableFunctionMerge.cpp +++ b/src/TableFunctions/TableFunctionMerge.cpp @@ -22,7 +22,7 @@ namespace ErrorCodes } -static NamesAndTypesList chooseColumns(const String & source_database, const String & table_name_regexp_) +static NamesAndTypesList chooseColumns(const String & source_database, const String & table_name_regexp_, const Context & context) { OptimizedRegularExpression table_name_regexp(table_name_regexp_); auto table_name_match = [&](const String & table_name) { return table_name_regexp.match(table_name); }; @@ -31,7 +31,7 @@ static NamesAndTypesList chooseColumns(const String & source_database, const Str { auto database = DatabaseCatalog::instance().getDatabase(source_database); - auto iterator = database->getTablesIterator(table_name_match); + auto iterator = database->getTablesIterator(context, table_name_match); if (iterator->isValid()) any_table = iterator->table(); @@ -69,7 +69,7 @@ StoragePtr TableFunctionMerge::executeImpl(const ASTPtr & ast_function, const Co auto res = StorageMerge::create( StorageID(getDatabaseName(), table_name), - ColumnsDescription{chooseColumns(source_database, table_name_regexp)}, + ColumnsDescription{chooseColumns(source_database, table_name_regexp, context)}, source_database, table_name_regexp, context); diff --git a/src/ya.make b/src/ya.make index 95e5914bbe7..eedd98cb178 100644 --- a/src/ya.make +++ b/src/ya.make @@ -19,6 +19,7 @@ PEERDIR( clickhouse/src/IO clickhouse/src/Parsers clickhouse/src/Processors + clickhouse/src/Server clickhouse/src/Storages clickhouse/src/TableFunctions ) diff --git a/tests/clickhouse-test b/tests/clickhouse-test index 1a2735296e8..60390c999ab 100755 --- a/tests/clickhouse-test +++ b/tests/clickhouse-test @@ -30,6 +30,8 @@ from contextlib import closing MESSAGES_TO_RETRY = [ "DB::Exception: ZooKeeper session has been expired", "Coordination::Exception: Connection loss", + "Operation timed out", + "ConnectionPoolWithFailover: Connection failed at try", ] @@ -331,6 +333,19 @@ def run_tests_array(all_tests_with_params): server_logs_level = "warning" +def check_server_started(client, retry_count): + while retry_count > 0: + clickhouse_proc = Popen(shlex.split(client), stdin=PIPE, stdout=PIPE, stderr=PIPE) + (stdout, stderr) = clickhouse_proc.communicate("SELECT 1") + if clickhouse_proc.returncode != 0 or not stdout.startswith("1"): + retry_count -= 1 + sleep(0.5) + else: + return True + + return False + + def main(args): global SERVER_DIED global exit_code @@ -344,6 +359,9 @@ def main(args): return stdout.startswith('1') + if not check_server_started(args.client, args.server_check_retries): + raise Exception("clickhouse-server is not responding. Cannot execute 'SELECT 1' query.") + base_dir = os.path.abspath(args.queries) tmp_dir = os.path.abspath(args.tmp) @@ -360,7 +378,7 @@ def main(args): os.environ.setdefault("CLICKHOUSE_CLIENT_SERVER_LOGS_LEVEL", server_logs_level) if args.zookeeper is None: - code, out = commands.getstatusoutput(args.extract_from_config +" --try --config " + args.configserver + ' --key zookeeper | grep . | wc -l') + code, out = commands.getstatusoutput(args.extract_from_config + " --try --config " + args.configserver + ' --key zookeeper | grep . | wc -l') try: if int(out) > 0: args.zookeeper = True @@ -570,6 +588,7 @@ if __name__ == '__main__': parser.add_argument('--parallel', default='1/1', help='One parallel test run number/total') parser.add_argument('-j', '--jobs', default=1, nargs='?', type=int, help='Run all tests in parallel') parser.add_argument('-U', '--unified', default=3, type=int, help='output NUM lines of unified context') + parser.add_argument('-r', '--server-check-retries', default=30, type=int, help='Num of tries to execute SELECT 1 before tests started') parser.add_argument('--no-stateless', action='store_true', help='Disable all stateless tests') parser.add_argument('--no-stateful', action='store_true', help='Disable all stateful tests') diff --git a/tests/integration/test_default_role/__init__.py b/tests/integration/test_default_role/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/integration/test_default_role/test.py b/tests/integration/test_default_role/test.py new file mode 100644 index 00000000000..2b6b4698b20 --- /dev/null +++ b/tests/integration/test_default_role/test.py @@ -0,0 +1,77 @@ +import pytest +from helpers.cluster import ClickHouseCluster +from helpers.test_tools import TSV +import re + +cluster = ClickHouseCluster(__file__) +instance = cluster.add_instance('instance') + + +@pytest.fixture(scope="module", autouse=True) +def started_cluster(): + try: + cluster.start() + + instance.query("CREATE USER john") + instance.query("CREATE ROLE rx") + instance.query("CREATE ROLE ry") + + yield cluster + + finally: + cluster.shutdown() + + +@pytest.fixture(autouse=True) +def reset_users_and_roles(): + instance.query("CREATE USER OR REPLACE john") + yield + + +def test_set_default_roles(): + assert instance.query("SHOW CURRENT ROLES", user="john") == "" + + instance.query("GRANT rx, ry TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1], ['ry', 0, 1]] ) + + instance.query("SET DEFAULT ROLE NONE TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == "" + + instance.query("SET DEFAULT ROLE rx TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1]] ) + + instance.query("SET DEFAULT ROLE ry TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['ry', 0, 1]] ) + + instance.query("SET DEFAULT ROLE ALL TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1], ['ry', 0, 1]] ) + + instance.query("SET DEFAULT ROLE ALL EXCEPT rx TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['ry', 0, 1]] ) + + +def test_alter_user(): + assert instance.query("SHOW CURRENT ROLES", user="john") == "" + + instance.query("GRANT rx, ry TO john") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1], ['ry', 0, 1]] ) + + instance.query("ALTER USER john DEFAULT ROLE NONE") + assert instance.query("SHOW CURRENT ROLES", user="john") == "" + + instance.query("ALTER USER john DEFAULT ROLE rx") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1]] ) + + instance.query("ALTER USER john DEFAULT ROLE ALL") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['rx', 0, 1], ['ry', 0, 1]] ) + + instance.query("ALTER USER john DEFAULT ROLE ALL EXCEPT rx") + assert instance.query("SHOW CURRENT ROLES", user="john") == TSV( [['ry', 0, 1]] ) + + +def test_wrong_set_default_role(): + assert "There is no user `rx`" in instance.query_and_get_error("SET DEFAULT ROLE NONE TO rx") + assert "There is no user `ry`" in instance.query_and_get_error("SET DEFAULT ROLE rx TO ry") + assert "There is no role `john`" in instance.query_and_get_error("SET DEFAULT ROLE john TO john") + assert "There is no role `john`" in instance.query_and_get_error("ALTER USER john DEFAULT ROLE john") + assert "There is no role `john`" in instance.query_and_get_error("ALTER USER john DEFAULT ROLE ALL EXCEPT john") diff --git a/tests/integration/test_dictionary_allow_read_expired_keys/configs/dictionaries/cache_strings_default_settings.xml b/tests/integration/test_dictionary_allow_read_expired_keys/configs/dictionaries/cache_strings_default_settings.xml new file mode 100644 index 00000000000..11807bc1ad6 --- /dev/null +++ b/tests/integration/test_dictionary_allow_read_expired_keys/configs/dictionaries/cache_strings_default_settings.xml @@ -0,0 +1,35 @@ + + + default_string + + + dictionary_node + 9000 + default + + test + strings
+ + + + 2 + 1 + + + + 1000 + 10000 + + + + + key + + + value + String + > + + + + \ No newline at end of file diff --git a/tests/integration/test_dictionary_allow_read_expired_keys/test_default_string.py b/tests/integration/test_dictionary_allow_read_expired_keys/test_default_string.py new file mode 100644 index 00000000000..7d762db2a6d --- /dev/null +++ b/tests/integration/test_dictionary_allow_read_expired_keys/test_default_string.py @@ -0,0 +1,61 @@ +from __future__ import print_function +import pytest +import os +import random +import string +import time + +from helpers.cluster import ClickHouseCluster +from helpers.test_tools import TSV + +SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__)) +cluster = ClickHouseCluster(__file__, base_configs_dir=os.path.join(SCRIPT_DIR, 'configs')) + +dictionary_node = cluster.add_instance('dictionary_node', stay_alive=True) +main_node = cluster.add_instance('main_node', main_configs=['configs/dictionaries/cache_strings_default_settings.xml']) + + +def get_random_string(string_length=8): + alphabet = string.ascii_letters + string.digits + return ''.join((random.choice(alphabet) for _ in range(string_length))) + +@pytest.fixture(scope="module") +def started_cluster(): + try: + cluster.start() + dictionary_node.query("CREATE DATABASE IF NOT EXISTS test;") + dictionary_node.query("DROP TABLE IF EXISTS test.strings;") + dictionary_node.query(""" + CREATE TABLE test.strings + (key UInt64, value String) + ENGINE = Memory; + """) + + values_to_insert = ", ".join(["({}, '{}')".format(1000000 + number, get_random_string()) for number in range(100)]) + dictionary_node.query("INSERT INTO test.strings VALUES {}".format(values_to_insert)) + + yield cluster + finally: + cluster.shutdown() + +# @pytest.mark.skip(reason="debugging") +def test_return_real_values(started_cluster): + assert None != dictionary_node.get_process_pid("clickhouse"), "ClickHouse must be alive" + + first_batch = """ + SELECT count(*) + FROM + ( + SELECT + arrayJoin(arrayMap(x -> (x + 1000000), range(100))) AS id, + dictGetString('default_string', 'value', toUInt64(id)) AS value + ) + WHERE value = ''; + """ + + assert TSV("0") == TSV(main_node.query(first_batch)) + + # Waiting for cache to become expired + time.sleep(5) + + assert TSV("0") == TSV(main_node.query(first_batch)) diff --git a/tests/integration/test_disk_access_storage/test.py b/tests/integration/test_disk_access_storage/test.py index 315440b4358..a47af5ad5b8 100644 --- a/tests/integration/test_disk_access_storage/test.py +++ b/tests/integration/test_disk_access_storage/test.py @@ -39,7 +39,7 @@ def test_create(): def check(): assert instance.query("SHOW CREATE USER u1") == "CREATE USER u1 SETTINGS PROFILE s1\n" - assert instance.query("SHOW CREATE USER u2") == "CREATE USER u2 HOST LOCAL DEFAULT ROLE rx\n" + assert instance.query("SHOW CREATE USER u2") == "CREATE USER u2 IDENTIFIED WITH sha256_password HOST LOCAL DEFAULT ROLE rx\n" assert instance.query("SHOW CREATE ROW POLICY p ON mydb.mytable") == "CREATE ROW POLICY p ON mydb.mytable FOR SELECT USING a < 1000 TO u1, u2\n" assert instance.query("SHOW CREATE QUOTA q") == "CREATE QUOTA q KEYED BY \\'none\\' FOR INTERVAL 1 HOUR MAX QUERIES 100 TO ALL EXCEPT rx\n" assert instance.query("SHOW GRANTS FOR u1") == "" @@ -69,7 +69,7 @@ def test_alter(): def check(): assert instance.query("SHOW CREATE USER u1") == "CREATE USER u1 SETTINGS PROFILE s1\n" - assert instance.query("SHOW CREATE USER u2") == "CREATE USER u2 HOST LOCAL DEFAULT ROLE ry\n" + assert instance.query("SHOW CREATE USER u2") == "CREATE USER u2 IDENTIFIED WITH sha256_password HOST LOCAL DEFAULT ROLE ry\n" assert instance.query("SHOW GRANTS FOR u1") == "GRANT SELECT ON mydb.mytable TO u1\n" assert instance.query("SHOW GRANTS FOR u2") == "GRANT rx, ry TO u2\n" assert instance.query("SHOW CREATE ROLE rx") == "CREATE ROLE rx SETTINGS PROFILE s2\n" diff --git a/tests/integration/test_grant_and_revoke/test.py b/tests/integration/test_grant_and_revoke/test.py index 8df68547f38..7054ce28e59 100644 --- a/tests/integration/test_grant_and_revoke/test.py +++ b/tests/integration/test_grant_and_revoke/test.py @@ -155,9 +155,9 @@ def test_introspection(): assert instance.query("SHOW ENABLED ROLES", user='A') == TSV([[ "R1", 0, 1, 1 ]]) assert instance.query("SHOW ENABLED ROLES", user='B') == TSV([[ "R2", 1, 1, 1 ]]) - assert instance.query("SELECT name, storage, host_ip, host_names, host_names_regexp, host_names_like, default_roles_all, default_roles_list, default_roles_except from system.users WHERE name IN ('A', 'B') ORDER BY name") ==\ - TSV([[ "A", "disk", "['::/0']", "[]", "[]", "[]", 1, "[]", "[]" ], - [ "B", "disk", "['::/0']", "[]", "[]", "[]", 1, "[]", "[]" ]]) + assert instance.query("SELECT name, storage, auth_type, auth_params, host_ip, host_names, host_names_regexp, host_names_like, default_roles_all, default_roles_list, default_roles_except from system.users WHERE name IN ('A', 'B') ORDER BY name") ==\ + TSV([[ "A", "disk", "no_password", "[]", "['::/0']", "[]", "[]", "[]", 1, "[]", "[]" ], + [ "B", "disk", "no_password", "[]", "['::/0']", "[]", "[]", "[]", 1, "[]", "[]" ]]) assert instance.query("SELECT name, storage from system.roles WHERE name IN ('R1', 'R2') ORDER BY name") ==\ TSV([[ "R1", "disk" ], diff --git a/tests/integration/test_row_policy/test.py b/tests/integration/test_row_policy/test.py index a1884d059c7..71496c6dbf2 100644 --- a/tests/integration/test_row_policy/test.py +++ b/tests/integration/test_row_policy/test.py @@ -42,8 +42,13 @@ def started_cluster(): CREATE TABLE mydb.`.filtered_table4` (a UInt8, b UInt8, c UInt16 ALIAS a + b) ENGINE MergeTree ORDER BY a; INSERT INTO mydb.`.filtered_table4` values (0, 0), (0, 1), (1, 0), (1, 1); + + CREATE TABLE mydb.local (a UInt8, b UInt8) ENGINE MergeTree ORDER BY a; ''') + node.query("INSERT INTO mydb.local values (2, 0), (2, 1), (1, 0), (1, 1)") + node2.query("INSERT INTO mydb.local values (3, 0), (3, 1), (1, 0), (1, 1)") + yield cluster finally: @@ -122,6 +127,17 @@ def test_single_table_name(): assert node.query("SELECT a + b = 1 FROM mydb.filtered_table3") == TSV([[1], [1]]) +def test_policy_from_users_xml_affects_only_user_assigned(): + assert node.query("SELECT * FROM mydb.filtered_table1") == TSV([[1,0], [1, 1]]) + assert node.query("SELECT * FROM mydb.filtered_table1", user="another") == TSV([[0, 0], [0, 1], [1, 0], [1, 1]]) + + assert node.query("SELECT * FROM mydb.filtered_table2") == TSV([[0, 0, 0, 0], [0, 0, 6, 0]]) + assert node.query("SELECT * FROM mydb.filtered_table2", user="another") == TSV([[0, 0, 0, 0], [0, 0, 6, 0], [1, 2, 3, 4], [4, 3, 2, 1]]) + + assert node.query("SELECT * FROM mydb.local") == TSV([[1,0], [1, 1], [2, 0], [2, 1]]) + assert node.query("SELECT * FROM mydb.local", user="another") == TSV([[1, 0], [1, 1]]) + + def test_custom_table_name(): copy_policy_xml('multiple_tags_with_table_names.xml') assert node.query("SELECT * FROM mydb.table") == TSV([[1, 0], [1, 1]]) @@ -286,9 +302,5 @@ def test_miscellaneous_engines(): # DistributedMergeTree node.query("DROP TABLE IF EXISTS mydb.not_filtered_table") node.query("CREATE TABLE mydb.not_filtered_table (a UInt8, b UInt8) ENGINE Distributed('test_local_cluster', mydb, local)") - node.query("CREATE TABLE mydb.local (a UInt8, b UInt8) ENGINE MergeTree ORDER BY a") - node2.query("CREATE TABLE mydb.local (a UInt8, b UInt8) ENGINE MergeTree ORDER BY a") - node.query("INSERT INTO mydb.local values (2, 0), (2, 1), (1, 0), (1, 1)") - node2.query("INSERT INTO mydb.local values (3, 0), (3, 1), (1, 0), (1, 1)") assert node.query("SELECT * FROM mydb.not_filtered_table", user="another") == TSV([[1, 0], [1, 1], [1, 0], [1, 1]]) assert node.query("SELECT sum(a), b FROM mydb.not_filtered_table GROUP BY b ORDER BY b", user="another") == TSV([[2, 0], [2, 1]]) diff --git a/tests/integration/test_storage_kafka/test.py b/tests/integration/test_storage_kafka/test.py index 8e329a1cb60..13577864870 100644 --- a/tests/integration/test_storage_kafka/test.py +++ b/tests/integration/test_storage_kafka/test.py @@ -1017,7 +1017,10 @@ def test_kafka_flush_by_block_size(kafka_cluster): time.sleep(1) - result = instance.query('SELECT count() FROM test.view') + # TODO: due to https://github.com/ClickHouse/ClickHouse/issues/11216 + # second flush happens earlier than expected, so we have 2 parts here instead of one + # flush by block size works correctly, so the feature checked by the test is working correctly + result = instance.query("SELECT count() FROM test.view WHERE _part='all_1_1_0'") # print(result) # kafka_cluster.open_bash_shell('instance') @@ -1390,6 +1393,41 @@ def test_commits_of_unprocessed_messages_on_drop(kafka_cluster): assert TSV(result) == TSV('{0}\t{0}\t{0}'.format(i[0]-1)), 'Missing data!' + +@pytest.mark.timeout(120) +def test_bad_reschedule(kafka_cluster): + messages = [json.dumps({'key': j+1, 'value': j+1}) for j in range(20000)] + kafka_produce('test_bad_reschedule', messages) + + instance.query(''' + CREATE TABLE test.kafka (key UInt64, value UInt64) + ENGINE = Kafka + SETTINGS kafka_broker_list = 'kafka1:19092', + kafka_topic_list = 'test_bad_reschedule', + kafka_group_name = 'test_bad_reschedule', + kafka_format = 'JSONEachRow', + kafka_max_block_size = 1000; + + CREATE MATERIALIZED VIEW test.destination Engine=Log AS + SELECT + key, + now() as consume_ts, + value, + _topic, + _key, + _offset, + _partition, + _timestamp + FROM test.kafka; + ''') + + while int(instance.query("SELECT count() FROM test.destination")) < 20000: + print("Waiting for consume") + time.sleep(1) + + assert int(instance.query("SELECT max(consume_ts) - min(consume_ts) FROM test.destination")) < 8 + + @pytest.mark.timeout(1200) def test_kafka_duplicates_when_commit_failed(kafka_cluster): messages = [json.dumps({'key': j+1, 'value': 'x' * 300}) for j in range(22)] diff --git a/tests/integration/test_system_queries/test.py b/tests/integration/test_system_queries/test.py index 1761017362a..6f36a13b184 100644 --- a/tests/integration/test_system_queries/test.py +++ b/tests/integration/test_system_queries/test.py @@ -95,17 +95,25 @@ def test_RELOAD_CONFIG_AND_MACROS(started_cluster): def test_SYSTEM_FLUSH_LOGS(started_cluster): instance = cluster.instances['ch1'] + instance.query(''' + SET log_queries = 0; + SYSTEM FLUSH LOGS; + TRUNCATE TABLE system.query_log; + ''') for i in range(4): # Sleep to execute flushing from background thread at first query # by expiration of flush_interval_millisecond and test probable race condition. time.sleep(0.5) result = instance.query(''' - SET log_queries = 1; SELECT 1 FORMAT Null; SET log_queries = 0; SYSTEM FLUSH LOGS; SELECT count() FROM system.query_log;''') - instance.query('TRUNCATE TABLE system.query_log') + instance.query(''' + SET log_queries = 0; + SYSTEM FLUSH LOGS; + TRUNCATE TABLE system.query_log; + ''') assert TSV(result) == TSV('4') diff --git a/tests/integration/test_ttl_move/test.py b/tests/integration/test_ttl_move/test.py index c6453beea6a..fc5c6725148 100644 --- a/tests/integration/test_ttl_move/test.py +++ b/tests/integration/test_ttl_move/test.py @@ -864,6 +864,8 @@ def test_double_move_while_select(started_cluster, name, positive): thread = threading.Thread(target=long_select) thread.start() + time.sleep(1) + node1.query("ALTER TABLE {name} MOVE PART '{part}' TO DISK 'jbod1'".format(name=name, part=parts[0])) # Fill jbod1 to force ClickHouse to make move of partition 1 to external. diff --git a/tests/integration/test_version_update_after_mutation/test.py b/tests/integration/test_version_update_after_mutation/test.py index 3f2063bdddb..9e3471175fa 100644 --- a/tests/integration/test_version_update_after_mutation/test.py +++ b/tests/integration/test_version_update_after_mutation/test.py @@ -6,9 +6,9 @@ from helpers.test_tools import assert_eq_with_retry cluster = ClickHouseCluster(__file__) -node1 = cluster.add_instance('node1', with_zookeeper=True, image='yandex/clickhouse-server:20.1.6.3', with_installed_binary=True, stay_alive=True) -node2 = cluster.add_instance('node2', with_zookeeper=True, image='yandex/clickhouse-server:20.1.6.3', with_installed_binary=True, stay_alive=True) -node3 = cluster.add_instance('node3', with_zookeeper=True, image='yandex/clickhouse-server:20.1.6.3', with_installed_binary=True, stay_alive=True) +node1 = cluster.add_instance('node1', with_zookeeper=True, image='yandex/clickhouse-server:20.1.10.70', with_installed_binary=True, stay_alive=True) +node2 = cluster.add_instance('node2', with_zookeeper=True, image='yandex/clickhouse-server:20.1.10.70', with_installed_binary=True, stay_alive=True) +node3 = cluster.add_instance('node3', with_zookeeper=True, image='yandex/clickhouse-server:20.1.10.70', with_installed_binary=True, stay_alive=True) @pytest.fixture(scope="module") def start_cluster(): diff --git a/tests/performance/agg_functions_min_max_any.xml b/tests/performance/agg_functions_min_max_any.xml index 4591182cdfc..9c16cb88970 100644 --- a/tests/performance/agg_functions_min_max_any.xml +++ b/tests/performance/agg_functions_min_max_any.xml @@ -35,10 +35,6 @@ select max(PageCharset) from test.hits where PageCharset != '' group by intHash32(UserID) % 1000000 FORMAT Null select any(PageCharset) from test.hits where PageCharset != '' group by intHash32(UserID) % 1000000 FORMAT Null select anyHeavy(PageCharset) from test.hits where PageCharset != '' group by intHash32(UserID) % 1000000 FORMAT Null -select min(OriginalURL) from test.hits where OriginalURL != '' group by intHash32(UserID) % 1000000 FORMAT Null -select max(OriginalURL) from test.hits where OriginalURL != '' group by intHash32(UserID) % 1000000 FORMAT Null -select any(OriginalURL) from test.hits where OriginalURL != '' group by intHash32(UserID) % 1000000 FORMAT Null -select anyHeavy(OriginalURL) from test.hits where OriginalURL != '' group by intHash32(UserID) % 1000000 FORMAT Null select min(SocialNetwork) from test.hits where SocialNetwork != '' group by intHash32(UserID) % 1000000 FORMAT Null select max(SocialNetwork) from test.hits where SocialNetwork != '' group by intHash32(UserID) % 1000000 FORMAT Null select any(SocialNetwork) from test.hits where SocialNetwork != '' group by intHash32(UserID) % 1000000 FORMAT Null diff --git a/tests/performance/functions_with_hash_tables.xml b/tests/performance/functions_with_hash_tables.xml new file mode 100644 index 00000000000..2e9a88107bd --- /dev/null +++ b/tests/performance/functions_with_hash_tables.xml @@ -0,0 +1,8 @@ + + select arrayUniq(range(1 + (number % 100) * 10)) from numbers(100000) format Null + select arrayDistinct(range(1 + (number % 100) * 10)) from numbers(100000) format Null + select arrayEnumerateUniq(range(1 + (number % 100) * 10)) from numbers(100000) format Null + select arrayIntersect(range((1 + number % 100)), range(1, (1 + number % 100) + 1)) from numbers(100000) format Null + select groupUniqArray(rand() % 100) from numbers(1000 * 1000) group by number / 1000 format Null + select entropy(number / 10) from numbers(1000 * 1000) group by number / 1000 format Null + diff --git a/tests/performance/insert_select_default_small_block.xml b/tests/performance/insert_select_default_small_block.xml new file mode 100644 index 00000000000..12e67b09d2f --- /dev/null +++ b/tests/performance/insert_select_default_small_block.xml @@ -0,0 +1,38 @@ + + 1 + + +CREATE TABLE insert_small_block_performance +( + `x` String, + `a` DEFAULT SHA256(x), + `b` DEFAULT SHA256(toString(a)), + `c` DEFAULT SHA256(toString(b)), + `d` DEFAULT SHA256(toString(c)), + `e` DEFAULT SHA256(toString(d)), + `f` DEFAULT SHA256(toString(e)), + `g` DEFAULT SHA256(toString(f)), + `h` DEFAULT SHA256(toString(g)), + `i` DEFAULT SHA256(toString(h)), + `j` DEFAULT SHA256(toString(i)), + `k` DEFAULT SHA256(toString(j)), + `l` DEFAULT SHA256(toString(k)), + `m` DEFAULT SHA256(toString(l)), + `n` DEFAULT SHA256(toString(m)), + `o` DEFAULT SHA256(toString(n)), + `p` DEFAULT SHA256(toString(o)), + `q` DEFAULT SHA256(toString(p)), + `r` DEFAULT SHA256(toString(q)), + `s` DEFAULT SHA256(toString(r)), + `t` DEFAULT SHA256(toString(s)), + `u` DEFAULT SHA256(toString(t)), + `v` DEFAULT SHA256(toString(u)), + `w` DEFAULT SHA256(toString(v)) +) +ENGINE = Null; + + + INSERT INTO insert_small_block_performance (x) SELECT toString(number) FROM numbers(10000); + + DROP TABLE IF EXISTS insert_small_block_performance + diff --git a/tests/performance/leftpad.xml b/tests/performance/leftpad.xml index 4349c6ac0e5..199f9224b89 100644 --- a/tests/performance/leftpad.xml +++ b/tests/performance/leftpad.xml @@ -6,7 +6,6 @@ - diff --git a/tests/performance/sort_radix_trivial.xml b/tests/performance/sort_radix_trivial.xml index fb3dc838a9c..096c3dd0854 100644 --- a/tests/performance/sort_radix_trivial.xml +++ b/tests/performance/sort_radix_trivial.xml @@ -1,5 +1,5 @@ - SELECT rand32() AS x FROM numbers(1000000) ORDER BY x - SELECT rand64() AS x FROM numbers(1000000) ORDER BY x - SELECT 1 / rand64() AS x FROM numbers(1000000) ORDER BY x + SELECT rand32() AS x FROM numbers(1000000) ORDER BY x FORMAT Null + SELECT rand64() AS x FROM numbers(1000000) ORDER BY x FORMAT Null + SELECT 1 / rand64() AS x FROM numbers(1000000) ORDER BY x FORMAT Null diff --git a/tests/queries/0_stateless/001283_strict_resize_bug.reference b/tests/queries/0_stateless/001283_strict_resize_bug.reference new file mode 100644 index 00000000000..e1fe7af425d --- /dev/null +++ b/tests/queries/0_stateless/001283_strict_resize_bug.reference @@ -0,0 +1 @@ +49999995000000 diff --git a/tests/queries/0_stateless/001283_strict_resize_bug.sql b/tests/queries/0_stateless/001283_strict_resize_bug.sql new file mode 100644 index 00000000000..f462f50c61f --- /dev/null +++ b/tests/queries/0_stateless/001283_strict_resize_bug.sql @@ -0,0 +1,7 @@ +drop table if exists num_10m; +create table num_10m (number UInt64) engine = MergeTree order by tuple(); +insert into num_10m select * from numbers(10000000); + +select * from (select sum(number) from num_10m union all select sum(number) from num_10m) limit 1 settings max_block_size = 1024; + +drop table if exists num_1m; diff --git a/tests/queries/0_stateless/00342_escape_sequences.reference b/tests/queries/0_stateless/00342_escape_sequences.reference index b7ecd06be78..50e0756d16f 100644 --- a/tests/queries/0_stateless/00342_escape_sequences.reference +++ b/tests/queries/0_stateless/00342_escape_sequences.reference @@ -1 +1 @@ -07080C0A0D090B5C27223FAA +07080C0A0D090B5C27225C3FAA diff --git a/tests/queries/0_stateless/00365_statistics_in_formats.sh b/tests/queries/0_stateless/00365_statistics_in_formats.sh index f0e23337806..fb79b23f78e 100755 --- a/tests/queries/0_stateless/00365_statistics_in_formats.sh +++ b/tests/queries/0_stateless/00365_statistics_in_formats.sh @@ -3,16 +3,16 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.numbers"; -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.numbers (number UInt64) engine = MergeTree order by number"; -$CLICKHOUSE_CLIENT --query="INSERT INTO test.numbers select * from system.numbers limit 10"; +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS numbers"; +$CLICKHOUSE_CLIENT --query="CREATE TABLE numbers (number UInt64) engine = MergeTree order by number"; +$CLICKHOUSE_CLIENT --query="INSERT INTO numbers select * from system.numbers limit 10"; -$CLICKHOUSE_CLIENT --query="SELECT number FROM test.numbers LIMIT 10 FORMAT JSON" | grep 'rows_read'; -$CLICKHOUSE_CLIENT --query="SELECT number FROM test.numbers LIMIT 10 FORMAT JSONCompact" | grep 'rows_read'; -$CLICKHOUSE_CLIENT --query="SELECT number FROM test.numbers LIMIT 10 FORMAT XML" | grep 'rows_read'; +$CLICKHOUSE_CLIENT --query="SELECT number FROM numbers LIMIT 10 FORMAT JSON" | grep 'rows_read'; +$CLICKHOUSE_CLIENT --query="SELECT number FROM numbers LIMIT 10 FORMAT JSONCompact" | grep 'rows_read'; +$CLICKHOUSE_CLIENT --query="SELECT number FROM numbers LIMIT 10 FORMAT XML" | grep 'rows_read'; -${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM test.numbers LIMIT 10 FORMAT JSON" | grep 'rows_read'; -${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM test.numbers LIMIT 10 FORMAT JSONCompact" | grep 'rows_read'; -${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM test.numbers LIMIT 10 FORMAT XML" | grep 'rows_read'; +${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM numbers LIMIT 10 FORMAT JSON" | grep 'rows_read'; +${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM numbers LIMIT 10 FORMAT JSONCompact" | grep 'rows_read'; +${CLICKHOUSE_CURL} -sS "${CLICKHOUSE_URL}" -d "SELECT number FROM numbers LIMIT 10 FORMAT XML" | grep 'rows_read'; -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.numbers"; \ No newline at end of file +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS numbers"; diff --git a/tests/queries/0_stateless/00563_insert_into_remote_and_zookeeper.sql b/tests/queries/0_stateless/00563_insert_into_remote_and_zookeeper.sql index d26e947b54f..b4579e6aac3 100644 --- a/tests/queries/0_stateless/00563_insert_into_remote_and_zookeeper.sql +++ b/tests/queries/0_stateless/00563_insert_into_remote_and_zookeeper.sql @@ -1,14 +1,14 @@ -- Check that settings are correctly passed through Distributed table -DROP TABLE IF EXISTS test.simple; -CREATE TABLE test.simple (d Int8) ENGINE = ReplicatedMergeTree('/clickhouse/test/tables/test/simple', '1') ORDER BY d; +DROP TABLE IF EXISTS simple; +CREATE TABLE simple (d Int8) ENGINE = ReplicatedMergeTree('/clickhouse/test/tables/test/simple', '1') ORDER BY d; -- TODO: replace '127.0.0.2' -> '127.0.0.1' after a fix -INSERT INTO TABLE FUNCTION remote('127.0.0.2', 'test', 'simple') VALUES (1); -INSERT INTO TABLE FUNCTION remote('127.0.0.2', 'test', 'simple') VALUES (1); +INSERT INTO TABLE FUNCTION remote('127.0.0.2', currentDatabase(), 'simple') VALUES (1); +INSERT INTO TABLE FUNCTION remote('127.0.0.2', currentDatabase(), 'simple') VALUES (1); SET insert_deduplicate=0; -INSERT INTO TABLE FUNCTION remote('127.0.0.2', 'test', 'simple') VALUES (2); -INSERT INTO TABLE FUNCTION remote('127.0.0.2', 'test', 'simple') VALUES (2); +INSERT INTO TABLE FUNCTION remote('127.0.0.2', currentDatabase(), 'simple') VALUES (2); +INSERT INTO TABLE FUNCTION remote('127.0.0.2', currentDatabase(), 'simple') VALUES (2); -SELECT * FROM remote('127.0.0.2', 'test', 'simple') ORDER BY d; -DROP TABLE test.simple; \ No newline at end of file +SELECT * FROM remote('127.0.0.2', currentDatabase(), 'simple') ORDER BY d; +DROP TABLE simple; diff --git a/tests/queries/0_stateless/00626_replace_partition_from_table_zookeeper.sh b/tests/queries/0_stateless/00626_replace_partition_from_table_zookeeper.sh index 44ab712bcf8..2f3514ae2f5 100755 --- a/tests/queries/0_stateless/00626_replace_partition_from_table_zookeeper.sh +++ b/tests/queries/0_stateless/00626_replace_partition_from_table_zookeeper.sh @@ -26,144 +26,143 @@ function query_with_retry echo "Query '$1' failed with '$result'" } -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.src;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.dst_r1;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.dst_r2;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS src;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS dst_r1;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS dst_r2;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.dst_r1 (p UInt64, k String, d UInt64) ENGINE = ReplicatedMergeTree('/clickhouse/test/dst_1', '1') PARTITION BY p ORDER BY k SETTINGS old_parts_lifetime=1, cleanup_delay_period=1, cleanup_delay_period_random_add=0;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.dst_r2 (p UInt64, k String, d UInt64) ENGINE = ReplicatedMergeTree('/clickhouse/test/dst_1', '2') PARTITION BY p ORDER BY k SETTINGS old_parts_lifetime=1, cleanup_delay_period=1, cleanup_delay_period_random_add=0;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE dst_r1 (p UInt64, k String, d UInt64) ENGINE = ReplicatedMergeTree('/clickhouse/test/dst_1', '1') PARTITION BY p ORDER BY k SETTINGS old_parts_lifetime=1, cleanup_delay_period=1, cleanup_delay_period_random_add=0;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE dst_r2 (p UInt64, k String, d UInt64) ENGINE = ReplicatedMergeTree('/clickhouse/test/dst_1', '2') PARTITION BY p ORDER BY k SETTINGS old_parts_lifetime=1, cleanup_delay_period=1, cleanup_delay_period_random_add=0;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (0, '0', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '0', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '1', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (2, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (0, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '1', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (2, '0', 1);" $CLICKHOUSE_CLIENT --query="SELECT 'Initial';" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (0, '1', 2);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (1, '1', 2), (1, '2', 2);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (2, '1', 2);" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (0, '1', 2);" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (1, '1', 2), (1, '2', 2);" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (2, '1', 2);" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.src;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM src;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'REPLACE simple';" -query_with_retry "ALTER TABLE test.dst_r1 REPLACE PARTITION 1 FROM test.src;" -query_with_retry "ALTER TABLE test.src DROP PARTITION 1;" +query_with_retry "ALTER TABLE dst_r1 REPLACE PARTITION 1 FROM src;" +query_with_retry "ALTER TABLE src DROP PARTITION 1;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.src;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM src;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'REPLACE empty';" -query_with_retry "ALTER TABLE test.src DROP PARTITION 1;" -query_with_retry "ALTER TABLE test.dst_r1 REPLACE PARTITION 1 FROM test.src;" +query_with_retry "ALTER TABLE src DROP PARTITION 1;" +query_with_retry "ALTER TABLE dst_r1 REPLACE PARTITION 1 FROM src;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'REPLACE recursive';" -query_with_retry "ALTER TABLE test.dst_r1 DROP PARTITION 1;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (1, '1', 2), (1, '2', 2);" +query_with_retry "ALTER TABLE dst_r1 DROP PARTITION 1;" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (1, '1', 2), (1, '2', 2);" $CLICKHOUSE_CLIENT --query="CREATE table test_block_numbers (m UInt64) ENGINE MergeTree() ORDER BY tuple();" -$CLICKHOUSE_CLIENT --query="INSERT INTO test_block_numbers SELECT max(max_block_number) AS m FROM system.parts WHERE database='test' AND table='dst_r1' AND active AND name LIKE '1_%';" +$CLICKHOUSE_CLIENT --query="INSERT INTO test_block_numbers SELECT max(max_block_number) AS m FROM system.parts WHERE database=currentDatabase() AND table='dst_r1' AND active AND name LIKE '1_%';" -query_with_retry "ALTER TABLE test.dst_r1 REPLACE PARTITION 1 FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +query_with_retry "ALTER TABLE dst_r1 REPLACE PARTITION 1 FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test_block_numbers SELECT max(max_block_number) AS m FROM system.parts WHERE database='test' AND table='dst_r1' AND active AND name LIKE '1_%';" +$CLICKHOUSE_CLIENT --query="INSERT INTO test_block_numbers SELECT max(max_block_number) AS m FROM system.parts WHERE database=currentDatabase() AND table='dst_r1' AND active AND name LIKE '1_%';" $CLICKHOUSE_CLIENT --query="SELECT (max(m) - min(m) > 1) AS new_block_is_generated FROM test_block_numbers;" $CLICKHOUSE_CLIENT --query="DROP TABLE test_block_numbers;" $CLICKHOUSE_CLIENT --query="SELECT 'ATTACH FROM';" -query_with_retry "ALTER TABLE test.dst_r1 DROP PARTITION 1;" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.src;" +query_with_retry "ALTER TABLE dst_r1 DROP PARTITION 1;" +$CLICKHOUSE_CLIENT --query="DROP TABLE src;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '0', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '1', 1);" +$CLICKHOUSE_CLIENT --query="CREATE TABLE src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '1', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r2 VALUES (1, '1', 2);" -query_with_retry "ALTER TABLE test.dst_r2 ATTACH PARTITION 1 FROM test.src;" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r2 VALUES (1, '1', 2);" +query_with_retry "ALTER TABLE dst_r2 ATTACH PARTITION 1 FROM src;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'REPLACE with fetch';" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.src;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '0', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '1', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (1, '1', 2); -- trash part to be deleted" +$CLICKHOUSE_CLIENT --query="DROP TABLE src;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '1', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (1, '1', 2); -- trash part to be deleted" # Stop replication at the second replica and remove source table to use fetch instead of copying -$CLICKHOUSE_CLIENT --query="SYSTEM STOP REPLICATION QUEUES test.dst_r2;" -query_with_retry "ALTER TABLE test.dst_r1 REPLACE PARTITION 1 FROM test.src;" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.src;" -$CLICKHOUSE_CLIENT --query="SYSTEM START REPLICATION QUEUES test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM STOP REPLICATION QUEUES dst_r2;" +query_with_retry "ALTER TABLE dst_r1 REPLACE PARTITION 1 FROM src;" +$CLICKHOUSE_CLIENT --query="DROP TABLE src;" +$CLICKHOUSE_CLIENT --query="SYSTEM START REPLICATION QUEUES dst_r2;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'REPLACE with fetch of merged';" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.src;" -query_with_retry "ALTER TABLE test.dst_r1 DROP PARTITION 1;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS src;" +query_with_retry "ALTER TABLE dst_r1 DROP PARTITION 1;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '0', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.src VALUES (1, '1', 1);" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.dst_r1 VALUES (1, '1', 2); -- trash part to be deleted" +$CLICKHOUSE_CLIENT --query="CREATE TABLE src (p UInt64, k String, d UInt64) ENGINE = MergeTree PARTITION BY p ORDER BY k;" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '0', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO src VALUES (1, '1', 1);" +$CLICKHOUSE_CLIENT --query="INSERT INTO dst_r1 VALUES (1, '1', 2); -- trash part to be deleted" -$CLICKHOUSE_CLIENT --query="SYSTEM STOP MERGES test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SYSTEM STOP REPLICATION QUEUES test.dst_r2;" -query_with_retry "ALTER TABLE test.dst_r1 REPLACE PARTITION 1 FROM test.src;" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.src;" +$CLICKHOUSE_CLIENT --query="SYSTEM STOP MERGES dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM STOP REPLICATION QUEUES dst_r2;" +query_with_retry "ALTER TABLE dst_r1 REPLACE PARTITION 1 FROM src;" +$CLICKHOUSE_CLIENT --query="DROP TABLE src;" # do not wait other replicas to execute OPTIMIZE -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r1;" -query_with_retry "OPTIMIZE TABLE test.dst_r1 PARTITION 1;" "--replication_alter_partitions_sync=0 --optimize_throw_if_noop=1" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r1;" +query_with_retry "OPTIMIZE TABLE dst_r1 PARTITION 1;" "--replication_alter_partitions_sync=0 --optimize_throw_if_noop=1" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM test.dst_r1;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM dst_r1;" -$CLICKHOUSE_CLIENT --query="SYSTEM START REPLICATION QUEUES test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SYSTEM START MERGES test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM START REPLICATION QUEUES dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM START MERGES dst_r2;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d), uniqExact(_part) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'After restart';" -$CLICKHOUSE_CLIENT --query="USE test;" -$CLICKHOUSE_CLIENT --query="SYSTEM RESTART REPLICA test.dst_r1;" +$CLICKHOUSE_CLIENT --query="SYSTEM RESTART REPLICA dst_r1;" $CLICKHOUSE_CLIENT --query="SYSTEM RESTART REPLICAS;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" $CLICKHOUSE_CLIENT --query="SELECT 'DETACH+ATTACH PARTITION';" -query_with_retry "ALTER TABLE test.dst_r1 DETACH PARTITION 0;" -query_with_retry "ALTER TABLE test.dst_r1 DETACH PARTITION 1;" -query_with_retry "ALTER TABLE test.dst_r1 DETACH PARTITION 2;" -query_with_retry "ALTER TABLE test.dst_r1 ATTACH PARTITION 1;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r1;" -$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA test.dst_r2;" -$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM test.dst_r2;" +query_with_retry "ALTER TABLE dst_r1 DETACH PARTITION 0;" +query_with_retry "ALTER TABLE dst_r1 DETACH PARTITION 1;" +query_with_retry "ALTER TABLE dst_r1 DETACH PARTITION 2;" +query_with_retry "ALTER TABLE dst_r1 ATTACH PARTITION 1;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r1;" +$CLICKHOUSE_CLIENT --query="SYSTEM SYNC REPLICA dst_r2;" +$CLICKHOUSE_CLIENT --query="SELECT count(), sum(d) FROM dst_r2;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.src;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.dst_r1;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.dst_r2;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS src;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS dst_r1;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS dst_r2;" diff --git a/tests/queries/0_stateless/00731_long_merge_tree_select_opened_files.sh b/tests/queries/0_stateless/00731_long_merge_tree_select_opened_files.sh index 5177cb6087c..5ae9dcf67ec 100755 --- a/tests/queries/0_stateless/00731_long_merge_tree_select_opened_files.sh +++ b/tests/queries/0_stateless/00731_long_merge_tree_select_opened_files.sh @@ -14,9 +14,11 @@ $CLICKHOUSE_CLIENT $settings -n -q " DROP TABLE IF EXISTS merge_tree_table; CREATE TABLE merge_tree_table (id UInt64, date Date, uid UInt32) ENGINE = MergeTree(date, id, 8192);" + $CLICKHOUSE_CLIENT $settings -q "INSERT INTO merge_tree_table SELECT (intHash64(number)) % 10000, toDate('2018-08-01'), rand() FROM system.numbers LIMIT 10000000;" -$CLICKHOUSE_CLIENT $settings -q "OPTIMIZE TABLE merge_tree_table FINAL;" +# If merge is already happening, OPTIMIZE will be noop. But we have to ensure that the data is merged. +for i in {1..100}; do $CLICKHOUSE_CLIENT $settings --optimize_throw_if_noop=1 -q "OPTIMIZE TABLE merge_tree_table FINAL;" && break; sleep 1; done # The query may open more files if query log will be flushed during the query. # To lower this chance, we also flush logs before the query. diff --git a/tests/queries/0_stateless/00763_lock_buffer.sh b/tests/queries/0_stateless/00763_lock_buffer.sh index 3146ce96132..d320ae51a37 100755 --- a/tests/queries/0_stateless/00763_lock_buffer.sh +++ b/tests/queries/0_stateless/00763_lock_buffer.sh @@ -4,20 +4,20 @@ set -e CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS test.mt_00763_2" -${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS test.buffer_00763_2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS mt_00763_2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS buffer_00763_2" -${CLICKHOUSE_CLIENT} --query="CREATE TABLE test.buffer_00763_2 (s String) ENGINE = Buffer(test, mt_00763_2, 1, 1, 1, 1, 1, 1, 1)" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE buffer_00763_2 (s String) ENGINE = Buffer('$CLICKHOUSE_DATABASE', mt_00763_2, 1, 1, 1, 1, 1, 1, 1)" function thread1() { - seq 1 500 | sed -r -e 's/.+/DROP TABLE IF EXISTS test.mt_00763_2; CREATE TABLE test.mt_00763_2 (s String) ENGINE = MergeTree ORDER BY s; INSERT INTO test.mt_00763_2 SELECT toString(number) FROM numbers(10);/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error ||: + seq 1 500 | sed -r -e 's/.+/DROP TABLE IF EXISTS mt_00763_2; CREATE TABLE mt_00763_2 (s String) ENGINE = MergeTree ORDER BY s; INSERT INTO mt_00763_2 SELECT toString(number) FROM numbers(10);/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error ||: } function thread2() { - seq 1 1000 | sed -r -e 's/.+/SELECT count() FROM test.buffer_00763_2;/' | ${CLICKHOUSE_CLIENT} --multiquery --server_logs_file='/dev/null' --ignore-error 2>&1 | grep -vP '^0$|^10$|^Received exception|^Code: 60|^Code: 218|^Code: 473' + seq 1 1000 | sed -r -e 's/.+/SELECT count() FROM buffer_00763_2;/' | ${CLICKHOUSE_CLIENT} --multiquery --server_logs_file='/dev/null' --ignore-error 2>&1 | grep -vP '^0$|^10$|^Received exception|^Code: 60|^Code: 218|^Code: 473' } thread1 & @@ -25,5 +25,5 @@ thread2 & wait -${CLICKHOUSE_CLIENT} --query="DROP TABLE test.mt_00763_2" -${CLICKHOUSE_CLIENT} --query="DROP TABLE test.buffer_00763_2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE mt_00763_2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE buffer_00763_2" diff --git a/tests/queries/0_stateless/00763_long_lock_buffer_alter_destination_table.sh b/tests/queries/0_stateless/00763_long_lock_buffer_alter_destination_table.sh index 059d70253b2..26bdb712ec5 100755 --- a/tests/queries/0_stateless/00763_long_lock_buffer_alter_destination_table.sh +++ b/tests/queries/0_stateless/00763_long_lock_buffer_alter_destination_table.sh @@ -6,21 +6,21 @@ CLICKHOUSE_CLIENT_SERVER_LOGS_LEVEL=none CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS test.mt_00763_1" -${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS test.buffer_00763_1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS mt_00763_1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS buffer_00763_1" -${CLICKHOUSE_CLIENT} --query="CREATE TABLE test.buffer_00763_1 (s String) ENGINE = Buffer(test, mt_00763_1, 1, 1, 1, 1, 1, 1, 1)" -${CLICKHOUSE_CLIENT} --query="CREATE TABLE test.mt_00763_1 (x UInt32, s String) ENGINE = MergeTree ORDER BY x" -${CLICKHOUSE_CLIENT} --query="INSERT INTO test.mt_00763_1 VALUES (1, '1'), (2, '2'), (3, '3')" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE buffer_00763_1 (s String) ENGINE = Buffer($CLICKHOUSE_DATABASE, mt_00763_1, 1, 1, 1, 1, 1, 1, 1)" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE mt_00763_1 (x UInt32, s String) ENGINE = MergeTree ORDER BY x" +${CLICKHOUSE_CLIENT} --query="INSERT INTO mt_00763_1 VALUES (1, '1'), (2, '2'), (3, '3')" function thread1() { - seq 1 300 | sed -r -e 's/.+/ALTER TABLE test.mt_00763_1 MODIFY column s UInt32; ALTER TABLE test.mt_00763_1 MODIFY column s String;/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error ||: + seq 1 300 | sed -r -e 's/.+/ALTER TABLE mt_00763_1 MODIFY column s UInt32; ALTER TABLE mt_00763_1 MODIFY column s String;/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error ||: } function thread2() { - seq 1 2000 | sed -r -e 's/.+/SELECT sum(length(s)) FROM test.buffer_00763_1;/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error 2>&1 | grep -vP '(^3$|^Received exception from server|^Code: 473)' + seq 1 2000 | sed -r -e 's/.+/SELECT sum(length(s)) FROM buffer_00763_1;/' | ${CLICKHOUSE_CLIENT} --multiquery --ignore-error 2>&1 | grep -vP '(^3$|^Received exception from server|^Code: 473)' } thread1 & @@ -28,5 +28,5 @@ thread2 & wait -${CLICKHOUSE_CLIENT} --query="DROP TABLE test.mt_00763_1" -${CLICKHOUSE_CLIENT} --query="DROP TABLE test.buffer_00763_1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE mt_00763_1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE buffer_00763_1" diff --git a/tests/queries/0_stateless/00814_replicated_minimalistic_part_header_zookeeper.sql b/tests/queries/0_stateless/00814_replicated_minimalistic_part_header_zookeeper.sql index 2e1df541f14..9f0850ff7e5 100644 --- a/tests/queries/0_stateless/00814_replicated_minimalistic_part_header_zookeeper.sql +++ b/tests/queries/0_stateless/00814_replicated_minimalistic_part_header_zookeeper.sql @@ -1,15 +1,15 @@ -DROP TABLE IF EXISTS test.part_header_r1; -DROP TABLE IF EXISTS test.part_header_r2; +DROP TABLE IF EXISTS part_header_r1; +DROP TABLE IF EXISTS part_header_r2; SET replication_alter_partitions_sync = 2; -CREATE TABLE test.part_header_r1(x UInt32, y UInt32) +CREATE TABLE part_header_r1(x UInt32, y UInt32) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/part_header', '1') ORDER BY x SETTINGS use_minimalistic_part_header_in_zookeeper = 0, old_parts_lifetime = 1, cleanup_delay_period = 0, cleanup_delay_period_random_add = 0; -CREATE TABLE test.part_header_r2(x UInt32, y UInt32) +CREATE TABLE part_header_r2(x UInt32, y UInt32) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/part_header', '2') ORDER BY x SETTINGS use_minimalistic_part_header_in_zookeeper = 1, old_parts_lifetime = 1, @@ -17,47 +17,47 @@ CREATE TABLE test.part_header_r2(x UInt32, y UInt32) cleanup_delay_period_random_add = 0; SELECT '*** Test fetches ***'; -INSERT INTO test.part_header_r1 VALUES (1, 1); -INSERT INTO test.part_header_r2 VALUES (2, 2); -SYSTEM SYNC REPLICA test.part_header_r1; -SYSTEM SYNC REPLICA test.part_header_r2; +INSERT INTO part_header_r1 VALUES (1, 1); +INSERT INTO part_header_r2 VALUES (2, 2); +SYSTEM SYNC REPLICA part_header_r1; +SYSTEM SYNC REPLICA part_header_r2; SELECT '*** replica 1 ***'; -SELECT x, y FROM test.part_header_r1 ORDER BY x; +SELECT x, y FROM part_header_r1 ORDER BY x; SELECT '*** replica 2 ***'; -SELECT x, y FROM test.part_header_r2 ORDER BY x; +SELECT x, y FROM part_header_r2 ORDER BY x; SELECT '*** Test merges ***'; -OPTIMIZE TABLE test.part_header_r1; -SYSTEM SYNC REPLICA test.part_header_r2; +OPTIMIZE TABLE part_header_r1; +SYSTEM SYNC REPLICA part_header_r2; SELECT '*** replica 1 ***'; -SELECT _part, x FROM test.part_header_r1 ORDER BY x; +SELECT _part, x FROM part_header_r1 ORDER BY x; SELECT '*** replica 2 ***'; -SELECT _part, x FROM test.part_header_r2 ORDER BY x; +SELECT _part, x FROM part_header_r2 ORDER BY x; SELECT sleep(3) FORMAT Null; SELECT '*** Test part removal ***'; SELECT '*** replica 1 ***'; -SELECT name FROM system.parts WHERE active AND database = 'test' AND table = 'part_header_r1'; +SELECT name FROM system.parts WHERE active AND database = currentDatabase() AND table = 'part_header_r1'; SELECT name FROM system.zookeeper WHERE path = '/clickhouse/tables/test/part_header/replicas/1/parts'; SELECT '*** replica 2 ***'; -SELECT name FROM system.parts WHERE active AND database = 'test' AND table = 'part_header_r2'; +SELECT name FROM system.parts WHERE active AND database = currentDatabase() AND table = 'part_header_r2'; SELECT name FROM system.zookeeper WHERE path = '/clickhouse/tables/test/part_header/replicas/1/parts'; SELECT '*** Test ALTER ***'; -ALTER TABLE test.part_header_r1 MODIFY COLUMN y String; +ALTER TABLE part_header_r1 MODIFY COLUMN y String; SELECT '*** replica 1 ***'; -SELECT x, length(y) FROM test.part_header_r1 ORDER BY x; +SELECT x, length(y) FROM part_header_r1 ORDER BY x; SELECT '*** replica 2 ***'; -SELECT x, length(y) FROM test.part_header_r2 ORDER BY x; +SELECT x, length(y) FROM part_header_r2 ORDER BY x; SELECT '*** Test CLEAR COLUMN ***'; SET replication_alter_partitions_sync = 2; -ALTER TABLE test.part_header_r1 CLEAR COLUMN y IN PARTITION tuple(); +ALTER TABLE part_header_r1 CLEAR COLUMN y IN PARTITION tuple(); SELECT '*** replica 1 ***'; -SELECT x, length(y) FROM test.part_header_r1 ORDER BY x; +SELECT x, length(y) FROM part_header_r1 ORDER BY x; SELECT '*** replica 2 ***'; -SELECT x, length(y) FROM test.part_header_r2 ORDER BY x; +SELECT x, length(y) FROM part_header_r2 ORDER BY x; -DROP TABLE test.part_header_r1; -DROP TABLE test.part_header_r2; +DROP TABLE part_header_r1; +DROP TABLE part_header_r2; diff --git a/tests/queries/0_stateless/00825_protobuf_format_input.reference b/tests/queries/0_stateless/00825_protobuf_format_input.reference index 884cc74c4e5..0c56bc4ebf0 100644 --- a/tests/queries/0_stateless/00825_protobuf_format_input.reference +++ b/tests/queries/0_stateless/00825_protobuf_format_input.reference @@ -8,3 +8,4 @@ a7522158-3d41-4b77-ad69-6c598ee55c49 Ivan Petrov male 1980-12-29 png +7495123456 0 0 2 4 3 9 +ok diff --git a/tests/queries/0_stateless/00825_protobuf_format_input.sh b/tests/queries/0_stateless/00825_protobuf_format_input.sh index d28b70bb002..1c915bc3f24 100755 --- a/tests/queries/0_stateless/00825_protobuf_format_input.sh +++ b/tests/queries/0_stateless/00825_protobuf_format_input.sh @@ -3,7 +3,7 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -set -e -o pipefail +set -eo pipefail # Run the client. $CLICKHOUSE_CLIENT --multiquery <<'EOF' @@ -48,5 +48,12 @@ source $CURDIR/00825_protobuf_format_input.insh $CLICKHOUSE_CLIENT --query "SELECT * FROM in_persons_00825 ORDER BY uuid;" $CLICKHOUSE_CLIENT --query "SELECT * FROM in_squares_00825 ORDER BY number;" +# Try to input malformed data. +set +eo pipefail +echo -ne '\xe0\x80\x3f\x0b' \ + | $CLICKHOUSE_CLIENT --query="INSERT INTO in_persons_00825 FORMAT Protobuf SETTINGS format_schema = '$CURDIR/00825_protobuf_format:Person'" 2>&1 \ + | grep -qF "Protobuf messages are corrupted" && echo "ok" || echo "fail" +set -eo pipefail + $CLICKHOUSE_CLIENT --query "DROP TABLE IF EXISTS in_persons_00825;" $CLICKHOUSE_CLIENT --query "DROP TABLE IF EXISTS in_squares_00825;" diff --git a/tests/queries/0_stateless/00926_multimatch.sql b/tests/queries/0_stateless/00926_multimatch.sql index d54e4fd2280..bf67533bb6c 100644 --- a/tests/queries/0_stateless/00926_multimatch.sql +++ b/tests/queries/0_stateless/00926_multimatch.sql @@ -89,4 +89,4 @@ SELECT [1, 2, 3, 11] = arraySort(multiMatchAllIndices('фабрикант', ['', SELECT [1] = multiMatchAllIndices(materialize('/odezhda-dlya-bega/'), ['/odezhda-dlya-bega/', 'kurtki-i-vetrovki-dlya-bega', 'futbolki-i-mayki-dlya-bega']); SELECT [] = multiMatchAllIndices(materialize('aaaa'), ['.*aa.*aaa.*', 'aaaaaa{2}', '\(aa\){3}']); SELECT 'All tests above must return 1, all tests below return something.'; -SELECT arraySort(multiMatchAllIndices(arrayJoin(['aaaa', 'aaaaaa', 'bbbb', 'aaaaaaaaaaaaaa']), ['.*aa.*aaa.*', 'aaaaaa{2}', '\(aa\){3}'])); +SELECT arraySort(multiMatchAllIndices(arrayJoin(['aaaa', 'aaaaaa', 'bbbb', 'aaaaaaaaaaaaaa']), ['.*aa.*aaa.*', 'aaaaaa{2}', '(aa){3}'])); diff --git a/tests/queries/0_stateless/00926_zookeeper_adaptive_index_granularity_replicated_merge_tree.sql b/tests/queries/0_stateless/00926_zookeeper_adaptive_index_granularity_replicated_merge_tree.sql index 5b785d31497..a7ae0402b5a 100644 --- a/tests/queries/0_stateless/00926_zookeeper_adaptive_index_granularity_replicated_merge_tree.sql +++ b/tests/queries/0_stateless/00926_zookeeper_adaptive_index_granularity_replicated_merge_tree.sql @@ -1,214 +1,214 @@ ----- Group of very similar simple tests ------ select '----HORIZONTAL MERGE TESTS----'; -DROP TABLE IF EXISTS test.zero_rows_per_granule1; -DROP TABLE IF EXISTS test.zero_rows_per_granule2; +DROP TABLE IF EXISTS zero_rows_per_granule1; +DROP TABLE IF EXISTS zero_rows_per_granule2; -CREATE TABLE test.zero_rows_per_granule1 ( +CREATE TABLE zero_rows_per_granule1 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/zero_rows_in_granule', '1') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 20, write_final_mark = 0; -CREATE TABLE test.zero_rows_per_granule2 ( +CREATE TABLE zero_rows_per_granule2 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/zero_rows_in_granule', '2') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 20, write_final_mark = 0; -INSERT INTO test.zero_rows_per_granule1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); +INSERT INTO zero_rows_per_granule1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); -SYSTEM SYNC REPLICA test.zero_rows_per_granule2; +SYSTEM SYNC REPLICA zero_rows_per_granule2; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.zero_rows_per_granule1; +SELECT COUNT(*) FROM zero_rows_per_granule1; -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database=currentDatabase() and active=1; -SELECT COUNT(*) FROM test.zero_rows_per_granule2; +SELECT COUNT(*) FROM zero_rows_per_granule2; -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database=currentDatabase() and active=1; -INSERT INTO test.zero_rows_per_granule2 (p, k, v1, v2) VALUES ('2018-05-15', 5, 1000, 2000), ('2018-05-16', 6, 3000, 4000), ('2018-05-17', 7, 5000, 6000), ('2018-05-19', 8, 7000, 8000); +INSERT INTO zero_rows_per_granule2 (p, k, v1, v2) VALUES ('2018-05-15', 5, 1000, 2000), ('2018-05-16', 6, 3000, 4000), ('2018-05-17', 7, 5000, 6000), ('2018-05-19', 8, 7000, 8000); -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database=currentDatabase() and active=1; -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database=currentDatabase() and active=1; SELECT sleep(0.7) Format Null; -OPTIMIZE TABLE test.zero_rows_per_granule2 FINAL; +OPTIMIZE TABLE zero_rows_per_granule2 FINAL; SELECT 'Parts optimized'; -SYSTEM SYNC REPLICA test.zero_rows_per_granule1; +SYSTEM SYNC REPLICA zero_rows_per_granule1; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.zero_rows_per_granule2; +SELECT COUNT(*) FROM zero_rows_per_granule2; -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule2' and database=currentDatabase() and active=1; -SELECT COUNT(*) FROM test.zero_rows_per_granule1; +SELECT COUNT(*) FROM zero_rows_per_granule1; -SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'zero_rows_per_granule1' and database=currentDatabase() and active=1; -DROP TABLE IF EXISTS test.zero_rows_per_granule1; -DROP TABLE IF EXISTS test.zero_rows_per_granule2; +DROP TABLE IF EXISTS zero_rows_per_granule1; +DROP TABLE IF EXISTS zero_rows_per_granule2; SELECT '-----'; -DROP TABLE IF EXISTS test.four_rows_per_granule1; -DROP TABLE IF EXISTS test.four_rows_per_granule2; +DROP TABLE IF EXISTS four_rows_per_granule1; +DROP TABLE IF EXISTS four_rows_per_granule2; -CREATE TABLE test.four_rows_per_granule1 ( +CREATE TABLE four_rows_per_granule1 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/four_rows_in_granule', '1') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 110, write_final_mark = 0; -CREATE TABLE test.four_rows_per_granule2 ( +CREATE TABLE four_rows_per_granule2 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/four_rows_in_granule', '2') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 110, write_final_mark = 0; -INSERT INTO test.four_rows_per_granule1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); +INSERT INTO four_rows_per_granule1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); -SELECT COUNT(*) FROM test.four_rows_per_granule1; +SELECT COUNT(*) FROM four_rows_per_granule1; -SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.four_rows_per_granule2; +SYSTEM SYNC REPLICA four_rows_per_granule2; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.four_rows_per_granule2; +SELECT COUNT(*) FROM four_rows_per_granule2; -SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database=currentDatabase() and active=1; -DETACH TABLE test.four_rows_per_granule2; -ATTACH TABLE test.four_rows_per_granule2; +DETACH TABLE four_rows_per_granule2; +ATTACH TABLE four_rows_per_granule2; SELECT 'Table attached'; -INSERT INTO test.four_rows_per_granule2 (p, k, v1, v2) VALUES ('2018-05-15', 5, 1000, 2000), ('2018-05-16', 6, 3000, 4000), ('2018-05-17', 7, 5000, 6000), ('2018-05-19', 8, 7000, 8000); +INSERT INTO four_rows_per_granule2 (p, k, v1, v2) VALUES ('2018-05-15', 5, 1000, 2000), ('2018-05-16', 6, 3000, 4000), ('2018-05-17', 7, 5000, 6000), ('2018-05-19', 8, 7000, 8000); -SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database=currentDatabase() and active=1; -SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database=currentDatabase() and active=1; SELECT sleep(0.7) Format Null; -OPTIMIZE TABLE test.four_rows_per_granule2 FINAL; +OPTIMIZE TABLE four_rows_per_granule2 FINAL; SELECT 'Parts optimized'; -DETACH TABLE test.four_rows_per_granule2; +DETACH TABLE four_rows_per_granule2; -ATTACH TABLE test.four_rows_per_granule2; +ATTACH TABLE four_rows_per_granule2; -SELECT COUNT(*) FROM test.four_rows_per_granule2; +SELECT COUNT(*) FROM four_rows_per_granule2; ---SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database='test' and active=1; +--SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule2' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.four_rows_per_granule1; +SYSTEM SYNC REPLICA four_rows_per_granule1; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.four_rows_per_granule1; +SELECT COUNT(*) FROM four_rows_per_granule1; ---SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database='test' and active=1; +--SELECT distinct(marks) from system.parts WHERE table = 'four_rows_per_granule1' and database=currentDatabase() and active=1; -DROP TABLE IF EXISTS test.four_rows_per_granule1; -DROP TABLE IF EXISTS test.four_rows_per_granule2; +DROP TABLE IF EXISTS four_rows_per_granule1; +DROP TABLE IF EXISTS four_rows_per_granule2; SELECT '-----'; -DROP TABLE IF EXISTS test.adaptive_granularity_alter1; -DROP TABLE IF EXISTS test.adaptive_granularity_alter2; +DROP TABLE IF EXISTS adaptive_granularity_alter1; +DROP TABLE IF EXISTS adaptive_granularity_alter2; -CREATE TABLE test.adaptive_granularity_alter1 ( +CREATE TABLE adaptive_granularity_alter1 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/adaptive_granularity_alter', '1') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 110, write_final_mark = 0; -CREATE TABLE test.adaptive_granularity_alter2 ( +CREATE TABLE adaptive_granularity_alter2 ( p Date, k UInt64, v1 UInt64, v2 Int64 ) ENGINE ReplicatedMergeTree('/clickhouse/tables/test/adaptive_granularity_alter', '2') PARTITION BY toYYYYMM(p) ORDER BY k SETTINGS index_granularity_bytes = 110, write_final_mark = 0; -INSERT INTO test.adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); +INSERT INTO adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 2, 3000, 4000), ('2018-05-17', 3, 5000, 6000), ('2018-05-18', 4, 7000, 8000); -SELECT COUNT(*) FROM test.adaptive_granularity_alter1; +SELECT COUNT(*) FROM adaptive_granularity_alter1; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.adaptive_granularity_alter2; +SYSTEM SYNC REPLICA adaptive_granularity_alter2; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.adaptive_granularity_alter2; +SELECT COUNT(*) FROM adaptive_granularity_alter2; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database=currentDatabase() and active=1; -ALTER TABLE test.adaptive_granularity_alter2 MODIFY COLUMN v1 Int16; +ALTER TABLE adaptive_granularity_alter2 MODIFY COLUMN v1 Int16; -DETACH TABLE test.adaptive_granularity_alter2; +DETACH TABLE adaptive_granularity_alter2; -ATTACH TABLE test.adaptive_granularity_alter2; +ATTACH TABLE adaptive_granularity_alter2; -SELECT COUNT(*) FROM test.adaptive_granularity_alter2; +SELECT COUNT(*) FROM adaptive_granularity_alter2; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.adaptive_granularity_alter1; +SYSTEM SYNC REPLICA adaptive_granularity_alter1; SELECT 'Replica synced'; -SELECT COUNT(*) FROM test.adaptive_granularity_alter1; +SELECT COUNT(*) FROM adaptive_granularity_alter1; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database=currentDatabase() and active=1; -INSERT INTO test.adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 5, 3000, 4000), ('2018-05-17', 6, 5000, 6000), ('2018-05-19', 42, 42, 42); +INSERT INTO adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 1, 1000, 2000), ('2018-05-16', 5, 3000, 4000), ('2018-05-17', 6, 5000, 6000), ('2018-05-19', 42, 42, 42); -SELECT COUNT(*) FROM test.adaptive_granularity_alter1; +SELECT COUNT(*) FROM adaptive_granularity_alter1; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.adaptive_granularity_alter2; +SYSTEM SYNC REPLICA adaptive_granularity_alter2; -SELECT COUNT(*) FROM test.adaptive_granularity_alter2; +SELECT COUNT(*) FROM adaptive_granularity_alter2; -SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database='test' and active=1; +SELECT distinct(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database=currentDatabase() and active=1; -ALTER TABLE test.adaptive_granularity_alter1 MODIFY COLUMN v2 String; +ALTER TABLE adaptive_granularity_alter1 MODIFY COLUMN v2 String; -DETACH TABLE test.adaptive_granularity_alter1; +DETACH TABLE adaptive_granularity_alter1; -ATTACH TABLE test.adaptive_granularity_alter1; +ATTACH TABLE adaptive_granularity_alter1; -INSERT INTO test.adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 100, 1000, 'aaaa'), ('2018-05-16', 101, 3000, 'bbbb'), ('2018-05-17', 102, 5000, 'cccc'), ('2018-05-19', 103, 7000, 'dddd'); +INSERT INTO adaptive_granularity_alter1 (p, k, v1, v2) VALUES ('2018-05-15', 100, 1000, 'aaaa'), ('2018-05-16', 101, 3000, 'bbbb'), ('2018-05-17', 102, 5000, 'cccc'), ('2018-05-19', 103, 7000, 'dddd'); SELECT sleep(0.7) Format Null; -OPTIMIZE TABLE test.adaptive_granularity_alter1 FINAL; +OPTIMIZE TABLE adaptive_granularity_alter1 FINAL; SELECT 'Parts optimized'; -SELECT k, v2 FROM test.adaptive_granularity_alter1 WHERE k >= 100 OR k = 42 ORDER BY k; +SELECT k, v2 FROM adaptive_granularity_alter1 WHERE k >= 100 OR k = 42 ORDER BY k; -SELECT sum(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database='test' and active=1; +SELECT sum(marks) from system.parts WHERE table = 'adaptive_granularity_alter1' and database=currentDatabase() and active=1; -SYSTEM SYNC REPLICA test.adaptive_granularity_alter2; +SYSTEM SYNC REPLICA adaptive_granularity_alter2; SELECT 'Replica synced'; -SELECT k, v2 FROM test.adaptive_granularity_alter2 WHERE k >= 100 OR k = 42 ORDER BY k; +SELECT k, v2 FROM adaptive_granularity_alter2 WHERE k >= 100 OR k = 42 ORDER BY k; -SELECT sum(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database='test' and active=1; +SELECT sum(marks) from system.parts WHERE table = 'adaptive_granularity_alter2' and database=currentDatabase() and active=1; -DROP TABLE IF EXISTS test.adaptive_granularity_alter1; -DROP TABLE IF EXISTS test.adaptive_granularity_alter2; +DROP TABLE IF EXISTS adaptive_granularity_alter1; +DROP TABLE IF EXISTS adaptive_granularity_alter2; diff --git a/tests/queries/0_stateless/00937_test_use_header_csv.sh b/tests/queries/0_stateless/00937_test_use_header_csv.sh index bd9204ffdcc..c0d4f2be522 100755 --- a/tests/queries/0_stateless/00937_test_use_header_csv.sh +++ b/tests/queries/0_stateless/00937_test_use_header_csv.sh @@ -3,10 +3,10 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.csv" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.csv (d Date, u UInt8, str String) ENGINE = TinyLog" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS csv" +$CLICKHOUSE_CLIENT --query="CREATE TABLE csv (d Date, u UInt8, str String) ENGINE = TinyLog" -INSERT_QUERY='$CLICKHOUSE_CLIENT --query="INSERT INTO test.csv FORMAT CSVWithNames"' +INSERT_QUERY='$CLICKHOUSE_CLIENT --query="INSERT INTO csv FORMAT CSVWithNames"' USE_HEADER='--input_format_with_names_use_header=1' SKIP_UNKNOWN='--input_format_skip_unknown_fields=1' @@ -32,5 +32,5 @@ echo -ne 'str,u\nLine16,1\nLine17,2\n' | eval $INSERT_QUERY $US echo -ne 'd,str\n2019-04-18,Line18\n2019-04-18,Line19\n'| eval $INSERT_QUERY $USE_HEADER echo -ne 'unknown\n\n\n' | eval $INSERT_QUERY $USE_HEADER $SKIP_UNKNOWN -$CLICKHOUSE_CLIENT --query="SELECT * FROM test.csv" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.csv" +$CLICKHOUSE_CLIENT --query="SELECT * FROM csv" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS csv" diff --git a/tests/queries/0_stateless/00942_mutate_index.sh b/tests/queries/0_stateless/00942_mutate_index.sh index 30ac7e8821b..d14c5659fc9 100755 --- a/tests/queries/0_stateless/00942_mutate_index.sh +++ b/tests/queries/0_stateless/00942_mutate_index.sh @@ -4,11 +4,11 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh . $CURDIR/mergetree_mutations.lib -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.minmax_idx;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS minmax_idx;" $CLICKHOUSE_CLIENT -n --query=" -CREATE TABLE test.minmax_idx +CREATE TABLE minmax_idx ( u64 UInt64, i64 Int64, @@ -19,7 +19,7 @@ ORDER BY u64 SETTINGS index_granularity = 2;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES +$CLICKHOUSE_CLIENT --query="INSERT INTO minmax_idx VALUES (0, 1, 1), (1, 1, 2), (2, 1, 3), @@ -31,13 +31,13 @@ $CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES (8, 1, 9), (9, 1, 10)" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 1;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 5;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 1;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 5;" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx UPDATE i64 = 5 WHERE i64 = 1;" -wait_for_mutation "minmax_idx" "mutation_2.txt" "test" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx UPDATE i64 = 5 WHERE i64 = 1;" +wait_for_mutation "minmax_idx" "mutation_2.txt" "$CLICKHOUSE_DATABASE" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 1;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 5;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 1;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 5;" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.minmax_idx" +$CLICKHOUSE_CLIENT --query="DROP TABLE minmax_idx" diff --git a/tests/queries/0_stateless/00943_materialize_index.sh b/tests/queries/0_stateless/00943_materialize_index.sh index b406f3894eb..c3d5a6bb219 100755 --- a/tests/queries/0_stateless/00943_materialize_index.sh +++ b/tests/queries/0_stateless/00943_materialize_index.sh @@ -4,11 +4,11 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh . $CURDIR/mergetree_mutations.lib -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.minmax_idx;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS minmax_idx;" $CLICKHOUSE_CLIENT -n --query=" -CREATE TABLE test.minmax_idx +CREATE TABLE minmax_idx ( u64 UInt64, i64 Int64, @@ -19,7 +19,7 @@ ORDER BY u64 SETTINGS index_granularity = 2;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES +$CLICKHOUSE_CLIENT --query="INSERT INTO minmax_idx VALUES (0, 2, 1), (1, 1, 1), (2, 1, 1), @@ -31,35 +31,35 @@ $CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES (8, 1, 2), (9, 1, 2)" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" $CLICKHOUSE_CLIENT -n --query=" -ALTER TABLE test.minmax_idx ADD INDEX idx (i64, u64 * i64) TYPE minmax GRANULARITY 1;" +ALTER TABLE minmax_idx ADD INDEX idx (i64, u64 * i64) TYPE minmax GRANULARITY 1;" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx MATERIALIZE INDEX idx IN PARTITION 1;" -wait_for_mutation "minmax_idx" "mutation_3.txt" "test" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx MATERIALIZE INDEX idx IN PARTITION 1;" +wait_for_mutation "minmax_idx" "mutation_3.txt" "$CLICKHOUSE_DATABASE" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx MATERIALIZE INDEX idx IN PARTITION 2;" -wait_for_mutation "minmax_idx" "mutation_4.txt" "test" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx MATERIALIZE INDEX idx IN PARTITION 2;" +wait_for_mutation "minmax_idx" "mutation_4.txt" "$CLICKHOUSE_DATABASE" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx CLEAR INDEX idx IN PARTITION 1;" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx CLEAR INDEX idx IN PARTITION 2;" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx CLEAR INDEX idx IN PARTITION 1;" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx CLEAR INDEX idx IN PARTITION 2;" sleep 0.5 -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx MATERIALIZE INDEX idx;" -wait_for_mutation "minmax_idx" "mutation_5.txt" "test" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx MATERIALIZE INDEX idx;" +wait_for_mutation "minmax_idx" "mutation_5.txt" "$CLICKHOUSE_DATABASE" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.minmax_idx" +$CLICKHOUSE_CLIENT --query="DROP TABLE minmax_idx" diff --git a/tests/queries/0_stateless/00944_clear_index_in_partition.sh b/tests/queries/0_stateless/00944_clear_index_in_partition.sh index 9f53ec16c35..d6ca4106a0e 100755 --- a/tests/queries/0_stateless/00944_clear_index_in_partition.sh +++ b/tests/queries/0_stateless/00944_clear_index_in_partition.sh @@ -4,11 +4,11 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh . $CURDIR/mergetree_mutations.lib -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.minmax_idx;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS minmax_idx;" $CLICKHOUSE_CLIENT -n --query=" -CREATE TABLE test.minmax_idx +CREATE TABLE minmax_idx ( u64 UInt64, i64 Int64, @@ -20,7 +20,7 @@ ORDER BY u64 SETTINGS index_granularity = 2;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES +$CLICKHOUSE_CLIENT --query="INSERT INTO minmax_idx VALUES (0, 2, 1), (1, 1, 1), (2, 1, 1), @@ -32,19 +32,19 @@ $CLICKHOUSE_CLIENT --query="INSERT INTO test.minmax_idx VALUES (8, 1, 2), (9, 1, 2)" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx CLEAR INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx CLEAR INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.minmax_idx MATERIALIZE INDEX idx IN PARTITION 1;" -wait_for_mutation "minmax_idx" "mutation_3.txt" "test" +$CLICKHOUSE_CLIENT --query="ALTER TABLE minmax_idx MATERIALIZE INDEX idx IN PARTITION 1;" +wait_for_mutation "minmax_idx" "mutation_3.txt" "$CLICKHOUSE_DATABASE" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM minmax_idx WHERE i64 = 2 FORMAT JSON" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.minmax_idx" +$CLICKHOUSE_CLIENT --query="DROP TABLE minmax_idx" diff --git a/tests/queries/0_stateless/00975_indices_mutation_replicated_zookeeper.sh b/tests/queries/0_stateless/00975_indices_mutation_replicated_zookeeper.sh index 28e7bd0b94e..b8b133cde3d 100755 --- a/tests/queries/0_stateless/00975_indices_mutation_replicated_zookeeper.sh +++ b/tests/queries/0_stateless/00975_indices_mutation_replicated_zookeeper.sh @@ -4,12 +4,12 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh . $CURDIR/mergetree_mutations.lib -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.indices_mutaions1;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.indices_mutaions2;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS indices_mutaions1;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS indices_mutaions2;" $CLICKHOUSE_CLIENT -n --query=" -CREATE TABLE test.indices_mutaions1 +CREATE TABLE indices_mutaions1 ( u64 UInt64, i64 Int64, @@ -19,7 +19,7 @@ CREATE TABLE test.indices_mutaions1 PARTITION BY i32 ORDER BY u64 SETTINGS index_granularity = 2; -CREATE TABLE test.indices_mutaions2 +CREATE TABLE indices_mutaions2 ( u64 UInt64, i64 Int64, @@ -31,7 +31,7 @@ ORDER BY u64 SETTINGS index_granularity = 2;" -$CLICKHOUSE_CLIENT --query="INSERT INTO test.indices_mutaions1 VALUES +$CLICKHOUSE_CLIENT --query="INSERT INTO indices_mutaions1 VALUES (0, 2, 1), (1, 1, 1), (2, 1, 1), @@ -43,18 +43,18 @@ $CLICKHOUSE_CLIENT --query="INSERT INTO test.indices_mutaions1 VALUES (8, 1, 2), (9, 1, 2)" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.indices_mutaions1 CLEAR INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 --mutations_sync=2 +$CLICKHOUSE_CLIENT --query="ALTER TABLE indices_mutaions1 CLEAR INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 --mutations_sync=2 -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="ALTER TABLE test.indices_mutaions1 MATERIALIZE INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 --mutations_sync=2 +$CLICKHOUSE_CLIENT --query="ALTER TABLE indices_mutaions1 MATERIALIZE INDEX idx IN PARTITION 1;" --replication_alter_partitions_sync=2 --mutations_sync=2 -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2;" -$CLICKHOUSE_CLIENT --query="SELECT count() FROM test.indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2;" +$CLICKHOUSE_CLIENT --query="SELECT count() FROM indices_mutaions2 WHERE i64 = 2 FORMAT JSON;" | grep "rows_read" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.indices_mutaions1" -$CLICKHOUSE_CLIENT --query="DROP TABLE test.indices_mutaions2" +$CLICKHOUSE_CLIENT --query="DROP TABLE indices_mutaions1" +$CLICKHOUSE_CLIENT --query="DROP TABLE indices_mutaions2" diff --git a/tests/queries/0_stateless/01019_parallel_parsing_cancel.sh b/tests/queries/0_stateless/01019_parallel_parsing_cancel.sh index 19d2b487955..067c19658ab 100755 --- a/tests/queries/0_stateless/01019_parallel_parsing_cancel.sh +++ b/tests/queries/0_stateless/01019_parallel_parsing_cancel.sh @@ -3,17 +3,17 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) . $CURDIR/../shell_config.sh -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.a;" -$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS test.b;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS a;" +$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS b;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.a (x UInt64) ENGINE = Memory;" -$CLICKHOUSE_CLIENT --query="CREATE TABLE test.b (x UInt64) ENGINE = Memory;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE a (x UInt64) ENGINE = Memory;" +$CLICKHOUSE_CLIENT --query="CREATE TABLE b (x UInt64) ENGINE = Memory;" function thread1() { for attempt_thread1 in {1..10} do - seq 1 500000 | $CLICKHOUSE_CLIENT --query_id=11 --query="INSERT INTO test.a FORMAT TSV" & + seq 1 500000 | $CLICKHOUSE_CLIENT --query_id=11 --query="INSERT INTO a FORMAT TSV" & while true; do $CLICKHOUSE_CLIENT --query="KILL QUERY WHERE query_id='11' SYNC" | grep -q "cant_cancel" && sleep .1 || break ||: done @@ -27,7 +27,7 @@ function thread2() { for attempt_thread2 in {1..10} do - seq 1 500000 | $CLICKHOUSE_CLIENT --query_id=22 --query="INSERT INTO test.b FORMAT TSV" & + seq 1 500000 | $CLICKHOUSE_CLIENT --query_id=22 --query="INSERT INTO b FORMAT TSV" & while true; do $CLICKHOUSE_CLIENT --query="KILL QUERY WHERE query_id='22' SYNC" | grep -q "cant_cancel" && sleep .1 || break ||: done @@ -46,5 +46,5 @@ bash -c thread2 > /dev/null 2>&1 & wait echo OK -$CLICKHOUSE_CLIENT --query "DROP TABLE test.a" -$CLICKHOUSE_CLIENT --query "DROP TABLE test.b" +$CLICKHOUSE_CLIENT --query "DROP TABLE a" +$CLICKHOUSE_CLIENT --query "DROP TABLE b" diff --git a/tests/queries/0_stateless/01075_allowed_client_hosts.reference b/tests/queries/0_stateless/01075_allowed_client_hosts.reference index 73f54c6027a..3fdea9d1cda 100644 --- a/tests/queries/0_stateless/01075_allowed_client_hosts.reference +++ b/tests/queries/0_stateless/01075_allowed_client_hosts.reference @@ -8,10 +8,10 @@ CREATE USER test_user_01075 HOST LOCAL, IP \'2001:db8:11a3:9d7:1f34:8a2e:7a0:765 CREATE USER test_user_01075 HOST LOCAL CREATE USER test_user_01075 HOST NONE CREATE USER test_user_01075 HOST LIKE \'@.somesite.com\' -CREATE USER test_user_01075 HOST REGEXP \'.*.anothersite.com\' -CREATE USER test_user_01075 HOST REGEXP \'.*.anothersite.com\', \'.*.anothersite.org\' -CREATE USER test_user_01075 HOST REGEXP \'.*.anothersite2.com\', \'.*.anothersite2.org\' -CREATE USER test_user_01075 HOST REGEXP \'.*.anothersite3.com\', \'.*.anothersite3.org\' +CREATE USER test_user_01075 HOST REGEXP \'.*\\\\.anothersite\\\\.com\' +CREATE USER test_user_01075 HOST REGEXP \'.*\\\\.anothersite\\\\.com\', \'.*\\\\.anothersite\\\\.org\' +CREATE USER test_user_01075 HOST REGEXP \'.*\\\\.anothersite2\\\\.com\', \'.*\\\\.anothersite2\\\\.org\' +CREATE USER test_user_01075 HOST REGEXP \'.*\\\\.anothersite3\\\\.com\', \'.*\\\\.anothersite3\\\\.org\' CREATE USER `test_user_01075_x@localhost` HOST LOCAL CREATE USER test_user_01075_x CREATE USER `test_user_01075_x@192.168.23.15` HOST LIKE \'192.168.23.15\' diff --git a/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.reference b/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.reference index 59c88f013dd..03ed07cf1a4 100644 --- a/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.reference +++ b/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.reference @@ -1,4 +1,5 @@ Instruction check fail. The CPU does not support SSSE3 instruction set. Instruction check fail. The CPU does not support SSE4.1 instruction set. Instruction check fail. The CPU does not support SSE4.2 instruction set. +Instruction check fail. The CPU does not support POPCNT instruction set. 1 diff --git a/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.sh b/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.sh index 15466e1889a..5ae4f8b3dd2 100755 --- a/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.sh +++ b/tests/queries/0_stateless/01103_check_cpu_instructions_at_startup.sh @@ -9,8 +9,13 @@ ${CLICKHOUSE_LOCAL} --query "SELECT max(value LIKE '%sanitize%') FROM system.bui command=$(command -v ${CLICKHOUSE_LOCAL}) -qemu-x86_64-static -cpu qemu64 $command --query "SELECT 1" 2>&1 | grep -v -F "warning: TCG doesn't support requested feature" ||: -qemu-x86_64-static -cpu qemu64,+ssse3 $command --query "SELECT 1" 2>&1 | grep -v -F "warning: TCG doesn't support requested feature" ||: -qemu-x86_64-static -cpu qemu64,+ssse3,+sse4.1 $command --query "SELECT 1" 2>&1 | grep -v -F "warning: TCG doesn't support requested feature" ||: -qemu-x86_64-static -cpu qemu64,+ssse3,+sse4.1,+sse4.2 $command --query "SELECT 1" 2>&1 | grep -v -F "warning: TCG doesn't support requested feature" ||: +function run_with_cpu() +{ + qemu-x86_64-static -cpu "$@" $command --query "SELECT 1" 2>&1 | grep -v -F "warning: TCG doesn't support requested feature" ||: +} +run_with_cpu qemu64 +run_with_cpu qemu64,+ssse3 +run_with_cpu qemu64,+ssse3,+sse4.1 +run_with_cpu qemu64,+ssse3,+sse4.1,+sse4.2 +run_with_cpu qemu64,+ssse3,+sse4.1,+sse4.2,+popcnt diff --git a/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.reference b/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.reference index 337ab7fe2e3..89a55127234 100644 --- a/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.reference +++ b/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.reference @@ -1 +1,5 @@ +replica_01108_1 +replica_01108_2 +replica_01108_3 +replica_01108_4 1180 40 diff --git a/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.sh b/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.sh index 01c9ef0a277..65b738aed8e 100755 --- a/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.sh +++ b/tests/queries/0_stateless/01108_restart_replicas_rename_deadlock.sh @@ -53,7 +53,7 @@ export -f rename_thread_2; export -f restart_thread_1; export -f restart_thread_2; -TIMEOUT=30 +TIMEOUT=10 timeout $TIMEOUT bash -c rename_thread_1 2> /dev/null & timeout $TIMEOUT bash -c rename_thread_2 2> /dev/null & @@ -63,6 +63,12 @@ timeout $TIMEOUT bash -c restart_thread_2 2> /dev/null & wait sleep 3 +for i in `seq 4`; do + $CLICKHOUSE_CLIENT -q "SYSTEM SYNC REPLICA replica_01108_$i" >/dev/null 2>&1 + $CLICKHOUSE_CLIENT -q "SYSTEM SYNC REPLICA replica_01108_${i}_tmp" >/dev/null 2>&1 +done + +$CLICKHOUSE_CLIENT -q "SELECT replaceOne(name, '_tmp', '') FROM system.tables WHERE database = currentDatabase() AND match(name, '^replica_01108_')" $CLICKHOUSE_CLIENT -q "SELECT sum(n), count(n) FROM merge(currentDatabase(), '^replica_01108_') GROUP BY position(_table, 'tmp')" diff --git a/tests/queries/0_stateless/01122_totals_rollup_having_block_header.sql b/tests/queries/0_stateless/01122_totals_rollup_having_block_header.sql index 4f4f3355912..6fb877c350a 100644 --- a/tests/queries/0_stateless/01122_totals_rollup_having_block_header.sql +++ b/tests/queries/0_stateless/01122_totals_rollup_having_block_header.sql @@ -1,14 +1,14 @@ -DROP TABLE IF EXISTS test.rollup_having; -CREATE TABLE test.rollup_having ( +DROP TABLE IF EXISTS rollup_having; +CREATE TABLE rollup_having ( a Nullable(String), b Nullable(String) ) ENGINE = Memory; -INSERT INTO test.rollup_having VALUES (NULL, NULL); -INSERT INTO test.rollup_having VALUES ('a', NULL); -INSERT INTO test.rollup_having VALUES ('a', 'b'); +INSERT INTO rollup_having VALUES (NULL, NULL); +INSERT INTO rollup_having VALUES ('a', NULL); +INSERT INTO rollup_having VALUES ('a', 'b'); -SELECT a, b, count(*) FROM test.rollup_having GROUP BY a, b WITH ROLLUP WITH TOTALS HAVING a IS NOT NULL; -- { serverError 48 } -SELECT a, b, count(*) FROM test.rollup_having GROUP BY a, b WITH ROLLUP WITH TOTALS HAVING a IS NOT NULL and b IS NOT NULL; -- { serverError 48 } +SELECT a, b, count(*) FROM rollup_having GROUP BY a, b WITH ROLLUP WITH TOTALS HAVING a IS NOT NULL; -- { serverError 48 } +SELECT a, b, count(*) FROM rollup_having GROUP BY a, b WITH ROLLUP WITH TOTALS HAVING a IS NOT NULL and b IS NOT NULL; -- { serverError 48 } -DROP TABLE test.rollup_having; +DROP TABLE rollup_having; diff --git a/tests/queries/0_stateless/01124_view_bad_types.sql b/tests/queries/0_stateless/01124_view_bad_types.sql index 81fc53930c1..715f7b375f1 100644 --- a/tests/queries/0_stateless/01124_view_bad_types.sql +++ b/tests/queries/0_stateless/01124_view_bad_types.sql @@ -1,11 +1,11 @@ -DROP TABLE IF EXISTS test.table; -CREATE TABLE test.table (x UInt16) ENGINE = TinyLog; -INSERT INTO test.table SELECT * FROM system.numbers LIMIT 10; +DROP TABLE IF EXISTS source_table; +CREATE TABLE source_table (x UInt16) ENGINE = TinyLog; +INSERT INTO source_table SELECT * FROM system.numbers LIMIT 10; -DROP TABLE IF EXISTS test.view; -CREATE VIEW test.view (x UInt64) AS SELECT * FROM test.table; +DROP TABLE IF EXISTS dest_view; +CREATE VIEW dest_view (x UInt64) AS SELECT * FROM source_table; -SELECT x, any(x) FROM test.view GROUP BY x ORDER BY x; +SELECT x, any(x) FROM dest_view GROUP BY x ORDER BY x; -DROP TABLE test.view; -DROP TABLE test.table; +DROP TABLE dest_view; +DROP TABLE source_table; diff --git a/tests/queries/0_stateless/01138_join_on_distributed_and_tmp.reference b/tests/queries/0_stateless/01138_join_on_distributed_and_tmp.reference new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/queries/0_stateless/01138_join_on_distributed_and_tmp.sql b/tests/queries/0_stateless/01138_join_on_distributed_and_tmp.sql new file mode 100644 index 00000000000..67492e7c683 --- /dev/null +++ b/tests/queries/0_stateless/01138_join_on_distributed_and_tmp.sql @@ -0,0 +1,16 @@ +DROP TABLE IF EXISTS foo_local; +DROP TABLE IF EXISTS foo_distributed; + +CREATE TABLE foo_local (bar UInt64) +ENGINE = MergeTree() +ORDER BY tuple(); + +CREATE TABLE foo_distributed AS foo_local +ENGINE = Distributed('test_cluster_two_shards_localhost', currentDatabase(), foo_local); + +CREATE TEMPORARY TABLE _tmp_baz (qux UInt64); + +SELECT * FROM foo_distributed JOIN _tmp_baz ON foo_distributed.bar = _tmp_baz.qux; + +DROP TABLE foo_local; +DROP TABLE foo_distributed; diff --git a/tests/queries/0_stateless/01247_dist_on_dist_group_by_sharding_key_optimization.sql b/tests/queries/0_stateless/01247_dist_on_dist_group_by_sharding_key_optimization.sql index 7cf171c8c73..29e45ffdb80 100644 --- a/tests/queries/0_stateless/01247_dist_on_dist_group_by_sharding_key_optimization.sql +++ b/tests/queries/0_stateless/01247_dist_on_dist_group_by_sharding_key_optimization.sql @@ -1,5 +1,9 @@ -- TODO: correct testing with real unique shards +-- Avoid "Connection failed at try №1" messages. +SET send_logs_level = 'none'; +SET connect_timeout_with_failover_ms = 5000; + set optimize_distributed_group_by_sharding_key=1; drop table if exists dist_01247; diff --git a/tests/queries/0_stateless/01273_arrow.reference b/tests/queries/0_stateless/01273_arrow.reference index 0f4be2c74a0..0dc503f65e4 100644 --- a/tests/queries/0_stateless/01273_arrow.reference +++ b/tests/queries/0_stateless/01273_arrow.reference @@ -31,8 +31,6 @@ 992 991 990 -ContextLock Number of times the lock of Context was acquired or tried to acquire. This is global lock. -Query Number of queries to be interpreted and potentially executed. Does not include queries that failed to parse or were rejected due to AST size limits, quota limits or limits on the number of simultaneously running queries. May include internal queries initiated by ClickHouse itself. Does not count subqueries. original: -128 0 -32768 0 -2147483648 0 -9223372036854775808 0 -1.032 -1.064 string-1 fixedstring-1\0\0 2003-04-05 2003-02-03 04:05:06 -108 108 -1016 1116 -1032 1132 -1064 1164 -1.032 -1.064 string-0 fixedstring\0\0\0\0 2001-02-03 2002-02-03 04:05:06 diff --git a/tests/queries/0_stateless/01273_arrow.sh b/tests/queries/0_stateless/01273_arrow.sh index f659a81f118..deb0aa20ccc 100755 --- a/tests/queries/0_stateless/01273_arrow.sh +++ b/tests/queries/0_stateless/01273_arrow.sh @@ -34,14 +34,6 @@ ${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_numbers ORDER BY number DESC L ${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_numbers" -${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_events" -${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_events (event String, value UInt64, description String) ENGINE = Memory" -${CLICKHOUSE_CLIENT} --query="SELECT * FROM system.events FORMAT Arrow" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_events FORMAT Arrow" -${CLICKHOUSE_CLIENT} --query="SELECT event, description FROM arrow_events WHERE event IN ('ContextLock', 'Query') ORDER BY event" -${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_events" - - - ${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types1" ${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types2" ${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types3" @@ -61,8 +53,6 @@ ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types1 values ( -128, # max ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types1 values ( 127, 255, 32767, 65535, 2147483647, 4294967295, 9223372036854775807, 9223372036854775807, -1.032, -1.064, 'string-2', 'fixedstring-2', '2004-06-07', '2004-02-03 04:05:06')" -# 'SELECT -127,-128,-129,126,127,128,255,256,257,-32767,-32768,-32769,32766,32767,32768,65535,65536,65537, -2147483647,-2147483648,-2147483649,2147483646,2147483647,2147483648,4294967295,4294967296,4294967297, -9223372036854775807,-9223372036854775808,9223372036854775806,9223372036854775807,9223372036854775808,18446744073709551615'; - ${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 FORMAT Arrow" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types2 FORMAT Arrow" echo original: @@ -98,7 +88,6 @@ ${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types5 (int8 Nullable(Int ${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types6 (int8 Nullable(Int8), uint8 Nullable(UInt8), int16 Nullable(Int16), uint16 Nullable(UInt16), int32 Nullable(Int32), uint32 Nullable(UInt32), int64 Nullable(Int64), uint64 Nullable(UInt64), float32 Nullable(Float32), float64 Nullable(Float64), string Nullable(String), fixedstring Nullable(FixedString(15)), date Nullable(Date), datetime Nullable(DateTime)) ENGINE = Memory" ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types5 values ( NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)" ${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types5 ORDER BY int8 FORMAT Arrow" > ${CLICKHOUSE_TMP}/arrow_all_types_5.arrow -#${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types5 FORMAT Arrow" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types6 FORMAT Arrow" ${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types5 ORDER BY int8 FORMAT Arrow" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types6 FORMAT Arrow" ${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8 FORMAT Arrow" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types6 FORMAT Arrow" echo dest from null: diff --git a/tests/queries/0_stateless/01273_arrow_stream.reference b/tests/queries/0_stateless/01273_arrow_stream.reference new file mode 100644 index 00000000000..0dc503f65e4 --- /dev/null +++ b/tests/queries/0_stateless/01273_arrow_stream.reference @@ -0,0 +1,60 @@ +9999 +9998 +9997 +9996 +9995 +9994 +9993 +9992 +9991 +9990 +99999 +99998 +99997 +99996 +99995 +99994 +99993 +99992 +99991 +99990 +2 +1 +0 +999 +998 +997 +996 +995 +994 +993 +992 +991 +990 +original: +-128 0 -32768 0 -2147483648 0 -9223372036854775808 0 -1.032 -1.064 string-1 fixedstring-1\0\0 2003-04-05 2003-02-03 04:05:06 +-108 108 -1016 1116 -1032 1132 -1064 1164 -1.032 -1.064 string-0 fixedstring\0\0\0\0 2001-02-03 2002-02-03 04:05:06 +127 255 32767 65535 2147483647 4294967295 9223372036854775807 9223372036854775807 -1.032 -1.064 string-2 fixedstring-2\0\0 2004-06-07 2004-02-03 04:05:06 +converted: +-128 0 -32768 0 -2147483648 0 -9223372036854775808 0 -1.032 -1.064 string-1 fixedstring-1\0\0 2003-04-05 2003-02-03 04:05:06 +-108 108 -1016 1116 -1032 1132 -1064 1164 -1.032 -1.064 string-0 fixedstring\0\0\0\0 2001-02-03 2002-02-03 04:05:06 +127 255 32767 65535 2147483647 4294967295 9223372036854775807 9223372036854775807 -1.032 -1.064 string-2 fixedstring-2\0\0 2004-06-07 2004-02-03 04:05:06 +diff: +dest: +79 81 82 83 84 85 86 87 88 89 str01\0\0\0\0\0\0\0\0\0\0 fstr1\0\0\0\0\0\0\0\0\0\0 2003-03-04 1970-01-01 06:29:04 +80 81 82 83 84 85 86 87 88 89 str02 fstr2\0\0\0\0\0\0\0\0\0\0 2005-03-04 2006-08-09 10:11:12 +min: +-128 0 0 0 0 0 0 0 -1 -1 string-1\0\0\0\0\0\0\0 fixedstring-1\0\0 2003-04-05 2003-02-03 +-108 108 8 92 -8 108 -40 -116 -1 -1 string-0\0\0\0\0\0\0\0 fixedstring\0\0\0\0 2001-02-03 2002-02-03 +79 81 82 83 84 85 86 87 88 89 str01\0\0\0\0\0\0\0\0\0\0 fstr1\0\0\0\0\0\0\0\0\0\0 2003-03-04 2004-05-06 +127 -1 -1 -1 -1 -1 -1 -1 -1 -1 string-2\0\0\0\0\0\0\0 fixedstring-2\0\0 2004-06-07 2004-02-03 +max: +-128 0 -32768 0 -2147483648 0 -9223372036854775808 0 -1 -1 string-1 fixedstring-1\0\0 1970-01-01 06:22:27 2003-02-03 04:05:06 +-108 108 -1016 1116 -1032 1132 -1064 1164 -1 -1 string-0 fixedstring\0\0\0\0 1970-01-01 06:09:16 2002-02-03 04:05:06 +80 81 82 83 84 85 86 87 88 89 str02 fstr2 2005-03-04 05:06:07 2006-08-09 10:11:12 +127 255 32767 65535 2147483647 4294967295 9223372036854775807 9223372036854775807 -1 -1 string-2 fixedstring-2\0\0 1970-01-01 06:29:36 2004-02-03 04:05:06 +dest from null: +-128 0 -32768 0 -2147483648 0 -9223372036854775808 0 -1.032 -1.064 string-1 fixedstring-1\0\0 2003-04-05 2003-02-03 04:05:06 +-108 108 -1016 1116 -1032 1132 -1064 1164 -1.032 -1.064 string-0 fixedstring\0\0\0\0 2001-02-03 2002-02-03 04:05:06 +127 255 32767 65535 2147483647 4294967295 9223372036854775807 9223372036854775807 -1.032 -1.064 string-2 fixedstring-2\0\0 2004-06-07 2004-02-03 04:05:06 +\N \N \N \N \N \N \N \N \N \N \N \N \N \N diff --git a/tests/queries/0_stateless/01273_arrow_stream.sh b/tests/queries/0_stateless/01273_arrow_stream.sh new file mode 100755 index 00000000000..a4bb403cb5a --- /dev/null +++ b/tests/queries/0_stateless/01273_arrow_stream.sh @@ -0,0 +1,104 @@ +#!/usr/bin/env bash + +set -e + +CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) +. $CUR_DIR/../shell_config.sh + + +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS contributors" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE contributors (name String) ENGINE = Memory" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM system.contributors ORDER BY name DESC FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO contributors FORMAT ArrowStream" +# random results +${CLICKHOUSE_CLIENT} --query="SELECT * FROM contributors LIMIT 10" > /dev/null +${CLICKHOUSE_CLIENT} --query="DROP TABLE contributors" + +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_numbers" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_numbers (number UInt64) ENGINE = Memory" +# less than default block size (65k) +${CLICKHOUSE_CLIENT} --query="SELECT * FROM system.numbers LIMIT 10000 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_numbers FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_numbers ORDER BY number DESC LIMIT 10" +${CLICKHOUSE_CLIENT} --query="TRUNCATE TABLE arrow_numbers" + +# More than default block size +${CLICKHOUSE_CLIENT} --query="SELECT * FROM system.numbers LIMIT 100000 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_numbers FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_numbers ORDER BY number DESC LIMIT 10" +${CLICKHOUSE_CLIENT} --query="TRUNCATE TABLE arrow_numbers" + +${CLICKHOUSE_CLIENT} --max_block_size=2 --query="SELECT * FROM system.numbers LIMIT 3 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_numbers FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_numbers ORDER BY number DESC LIMIT 10" + +${CLICKHOUSE_CLIENT} --query="TRUNCATE TABLE arrow_numbers" +${CLICKHOUSE_CLIENT} --max_block_size=1 --query="SELECT * FROM system.numbers LIMIT 1000 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_numbers FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_numbers ORDER BY number DESC LIMIT 10" + +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_numbers" + +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types3" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types4" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types1 (int8 Int8, uint8 UInt8, int16 Int16, uint16 UInt16, int32 Int32, uint32 UInt32, int64 Int64, uint64 UInt64, float32 Float32, float64 Float64, string String, fixedstring FixedString(15), date Date, datetime DateTime) ENGINE = Memory" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types2 (int8 Int8, uint8 UInt8, int16 Int16, uint16 UInt16, int32 Int32, uint32 UInt32, int64 Int64, uint64 UInt64, float32 Float32, float64 Float64, string String, fixedstring FixedString(15), date Date, datetime DateTime) ENGINE = Memory" +# convert min type +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types3 (int8 Int8, uint8 Int8, int16 Int8, uint16 Int8, int32 Int8, uint32 Int8, int64 Int8, uint64 Int8, float32 Int8, float64 Int8, string FixedString(15), fixedstring FixedString(15), date Date, datetime Date) ENGINE = Memory" +# convert max type +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types4 (int8 Int64, uint8 Int64, int16 Int64, uint16 Int64, int32 Int64, uint32 Int64, int64 Int64, uint64 Int64, float32 Int64, float64 Int64, string String, fixedstring String, date DateTime, datetime DateTime) ENGINE = Memory" + +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types1 values ( -108, 108, -1016, 1116, -1032, 1132, -1064, 1164, -1.032, -1.064, 'string-0', 'fixedstring', '2001-02-03', '2002-02-03 04:05:06')" + +# min +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types1 values ( -128, 0, -32768, 0, -2147483648, 0, -9223372036854775808, 0, -1.032, -1.064, 'string-1', 'fixedstring-1', '2003-04-05', '2003-02-03 04:05:06')" + +# max +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types1 values ( 127, 255, 32767, 65535, 2147483647, 4294967295, 9223372036854775807, 9223372036854775807, -1.032, -1.064, 'string-2', 'fixedstring-2', '2004-06-07', '2004-02-03 04:05:06')" + +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types2 FORMAT ArrowStream" + +echo original: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8" | tee ${CLICKHOUSE_TMP}/arrow_all_types_1.dump +echo converted: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types2 ORDER BY int8" | tee ${CLICKHOUSE_TMP}/arrow_all_types_2.dump +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8 FORMAT ArrowStream" > ${CLICKHOUSE_TMP}/arrow_all_types_1.arrow +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types2 ORDER BY int8 FORMAT ArrowStream" > ${CLICKHOUSE_TMP}/arrow_all_types_2.arrow +echo diff: +diff ${CLICKHOUSE_TMP}/arrow_all_types_1.dump ${CLICKHOUSE_TMP}/arrow_all_types_2.dump + +${CLICKHOUSE_CLIENT} --query="TRUNCATE TABLE arrow_types2" +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types3 values ( 79, 81, 82, 83, 84, 85, 86, 87, 88, 89, 'str01', 'fstr1', '2003-03-04', '2004-05-06')" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types3 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types2 FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types3 FORMAT ArrowStream" + +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types4 values ( 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 'str02', 'fstr2', '2005-03-04 05:06:07', '2006-08-09 10:11:12')" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types4 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types2 FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types4 FORMAT ArrowStream" + +echo dest: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types2 ORDER BY int8" +echo min: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types3 ORDER BY int8" +echo max: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types4 ORDER BY int8" + + +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types5" +${CLICKHOUSE_CLIENT} --query="DROP TABLE IF EXISTS arrow_types6" +${CLICKHOUSE_CLIENT} --query="TRUNCATE TABLE arrow_types2" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types5 (int8 Nullable(Int8), uint8 Nullable(UInt8), int16 Nullable(Int16), uint16 Nullable(UInt16), int32 Nullable(Int32), uint32 Nullable(UInt32), int64 Nullable(Int64), uint64 Nullable(UInt64), float32 Nullable(Float32), float64 Nullable(Float64), string Nullable(String), fixedstring Nullable(FixedString(15)), date Nullable(Date), datetime Nullable(DateTime)) ENGINE = Memory" +${CLICKHOUSE_CLIENT} --query="CREATE TABLE arrow_types6 (int8 Nullable(Int8), uint8 Nullable(UInt8), int16 Nullable(Int16), uint16 Nullable(UInt16), int32 Nullable(Int32), uint32 Nullable(UInt32), int64 Nullable(Int64), uint64 Nullable(UInt64), float32 Nullable(Float32), float64 Nullable(Float64), string Nullable(String), fixedstring Nullable(FixedString(15)), date Nullable(Date), datetime Nullable(DateTime)) ENGINE = Memory" +${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types5 values ( NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types5 ORDER BY int8 FORMAT ArrowStream" > ${CLICKHOUSE_TMP}/arrow_all_types_5.arrow +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types5 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types6 FORMAT ArrowStream" +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types1 ORDER BY int8 FORMAT ArrowStream" | ${CLICKHOUSE_CLIENT} --query="INSERT INTO arrow_types6 FORMAT ArrowStream" +echo dest from null: +${CLICKHOUSE_CLIENT} --query="SELECT * FROM arrow_types6 ORDER BY int8" + +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types5" +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types6" + + +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types1" +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types2" +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types3" +${CLICKHOUSE_CLIENT} --query="DROP TABLE arrow_types4" + diff --git a/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.reference b/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.reference index ed22b7e1e35..e4872ddeddd 100644 --- a/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.reference +++ b/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.reference @@ -1,4 +1,4 @@ 0 0 -100000 -200000 +800000 +1600000 diff --git a/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.sh b/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.sh index 7e08c930f67..c9a4de647b9 100755 --- a/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.sh +++ b/tests/queries/0_stateless/01278_min_insert_block_size_rows_for_materialized_views.sh @@ -54,7 +54,7 @@ EOL echo "create table null_01278 as data_01278 Engine=Null();" | execute for i in $(seq 1 $TEST_01278_PARTS); do echo "create table part_01278_$i as data_01278 Engine=Buffer(currentDatabase(), null_01278, 1, 86400, 86400, 1e5, 1e6, 10e6, 100e6);" - echo "create materialized view mv_01278_$i to part_01278_$i as select * from data_01278 where key%$TEST_01278_PARTS+1 == $i;" + echo "create materialized view mv_01278_$i to part_01278_$i as select * from data_01278 where key%$TEST_01278_PARTS+1 != $i;" done | execute echo "create table out_01278 as data_01278 Engine=Merge(currentDatabase(), 'part_01278_');" | execute diff --git a/tests/queries/0_stateless/01280_ttl_where_group_by.reference b/tests/queries/0_stateless/01280_ttl_where_group_by.reference new file mode 100644 index 00000000000..dead0a5aac3 --- /dev/null +++ b/tests/queries/0_stateless/01280_ttl_where_group_by.reference @@ -0,0 +1,20 @@ +1 1 0 4 +1 2 3 7 +1 3 0 5 +2 1 20 1 +2 1 0 1 +1 1 [0,2,3] 4 +1 1 [5,4,1] 13 +1 3 [1,0,1,0] 17 +2 1 [3,1,0,3] 8 +3 1 [2,4,5] 8 +1 1 0 4 +1 3 10 6 +2 1 0 3 +3 5 8 2 +1 1 0 4 +3 3 13 9 +1 2 7 5 +2 3 6 5 +1 2 3 5 +2 3 3 5 diff --git a/tests/queries/0_stateless/01280_ttl_where_group_by.sql b/tests/queries/0_stateless/01280_ttl_where_group_by.sql new file mode 100644 index 00000000000..e61716cfe81 --- /dev/null +++ b/tests/queries/0_stateless/01280_ttl_where_group_by.sql @@ -0,0 +1,87 @@ +drop table if exists ttl_01280_1; + +create table ttl_01280_1 (a Int, b Int, x Int, y Int, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second delete where x % 10 == 0 and y > 5; +insert into ttl_01280_1 values (1, 1, 0, 4, now() + 10); +insert into ttl_01280_1 values (1, 1, 10, 6, now()); +insert into ttl_01280_1 values (1, 2, 3, 7, now()); +insert into ttl_01280_1 values (1, 3, 0, 5, now()); +insert into ttl_01280_1 values (2, 1, 20, 1, now()); +insert into ttl_01280_1 values (2, 1, 0, 1, now()); +insert into ttl_01280_1 values (3, 1, 0, 8, now()); +select sleep(1.1) format Null; +optimize table ttl_01280_1 final; +select a, b, x, y from ttl_01280_1; + +drop table if exists ttl_01280_2; + +create table ttl_01280_2 (a Int, b Int, x Array(Int32), y Double, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by a, b set x = minForEach(x), y = sum(y), d = max(d); +insert into ttl_01280_2 values (1, 1, array(0, 2, 3), 4, now() + 10); +insert into ttl_01280_2 values (1, 1, array(5, 4, 3), 6, now()); +insert into ttl_01280_2 values (1, 1, array(5, 5, 1), 7, now()); +insert into ttl_01280_2 values (1, 3, array(3, 0, 4), 5, now()); +insert into ttl_01280_2 values (1, 3, array(1, 1, 2, 1), 9, now()); +insert into ttl_01280_2 values (1, 3, array(3, 2, 1, 0), 3, now()); +insert into ttl_01280_2 values (2, 1, array(3, 3, 3), 7, now()); +insert into ttl_01280_2 values (2, 1, array(11, 1, 0, 3), 1, now()); +insert into ttl_01280_2 values (3, 1, array(2, 4, 5), 8, now()); +select sleep(1.1) format Null; +optimize table ttl_01280_2 final; +select a, b, x, y from ttl_01280_2; + +drop table if exists ttl_01280_3; + +create table ttl_01280_3 (a Int, b Int, x Int64, y Int, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by a set x = argMax(x, d), y = argMax(y, d), d = max(d); +insert into ttl_01280_3 values (1, 1, 0, 4, now() + 10); +insert into ttl_01280_3 values (1, 1, 10, 6, now() + 1); +insert into ttl_01280_3 values (1, 2, 3, 7, now()); +insert into ttl_01280_3 values (1, 3, 0, 5, now()); +insert into ttl_01280_3 values (2, 1, 20, 1, now()); +insert into ttl_01280_3 values (2, 1, 0, 3, now() + 1); +insert into ttl_01280_3 values (3, 1, 0, 3, now()); +insert into ttl_01280_3 values (3, 2, 8, 2, now() + 1); +insert into ttl_01280_3 values (3, 5, 5, 8, now()); +select sleep(2.1) format Null; +optimize table ttl_01280_3 final; +select a, b, x, y from ttl_01280_3; + +drop table if exists ttl_01280_4; + +create table ttl_01280_4 (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (toDate(d), -(a + b)) ttl d + interval 1 second group by toDate(d) set x = sum(x), y = max(y); +insert into ttl_01280_4 values (1, 1, 0, 4, now() + 10); +insert into ttl_01280_4 values (10, 2, 3, 3, now()); +insert into ttl_01280_4 values (2, 10, 1, 7, now()); +insert into ttl_01280_4 values (3, 3, 5, 2, now()); +insert into ttl_01280_4 values (1, 5, 4, 9, now()); +select sleep(1.1) format Null; +optimize table ttl_01280_4 final; +select a, b, x, y from ttl_01280_4; + +drop table if exists ttl_01280_5; + +create table ttl_01280_5 (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (toDate(d), a, -b) ttl d + interval 1 second group by toDate(d), a set x = sum(x); +insert into ttl_01280_5 values (1, 2, 3, 5, now()); +insert into ttl_01280_5 values (2, 10, 1, 5, now()); +insert into ttl_01280_5 values (2, 3, 5, 5, now()); +insert into ttl_01280_5 values (1, 5, 4, 5, now()); +select sleep(1.1) format Null; +optimize table ttl_01280_5 final; +select a, b, x, y from ttl_01280_5; + +drop table if exists ttl_01280_6; + +create table ttl_01280_6 (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (toDate(d), a, -b) ttl d + interval 1 second group by toDate(d), a; +insert into ttl_01280_6 values (1, 2, 3, 5, now()); +insert into ttl_01280_6 values (2, 10, 3, 5, now()); +insert into ttl_01280_6 values (2, 3, 3, 5, now()); +insert into ttl_01280_6 values (1, 5, 3, 5, now()); +select sleep(1.1) format Null; +optimize table ttl_01280_6 final; +select a, b, x, y from ttl_01280_6; + +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by x set y = max(y); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by b set y = max(y); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by a, b, x set y = max(y); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by a set b = min(b), y = max(y); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (a, b) ttl d + interval 1 second group by a, b set y = max(y), y = max(y); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (toDate(d), a) ttl d + interval 1 second group by toDate(d), a set d = min(d), b = max(b); -- { serverError 450} +create table ttl_01280_error (a Int, b Int, x Int64, y Int64, d DateTime) engine = MergeTree order by (d, -(a + b)) ttl d + interval 1 second group by d, -(a + b) set a = sum(a), b = min(b); -- { serverError 450} diff --git a/tests/queries/0_stateless/01281_group_by_limit_memory_tracking.reference b/tests/queries/0_stateless/01281_group_by_limit_memory_tracking.reference new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/queries/0_stateless/01281_group_by_limit_memory_tracking.sh b/tests/queries/0_stateless/01281_group_by_limit_memory_tracking.sh new file mode 100755 index 00000000000..5922b8d74d2 --- /dev/null +++ b/tests/queries/0_stateless/01281_group_by_limit_memory_tracking.sh @@ -0,0 +1,35 @@ +#!/usr/bin/env bash + +# Regression for MemoryTracker that had been incorrectly accounted +# (it was reseted before deallocation) +# +# For this will be used: +# - two-level group by +# - max_memory_usage_for_user +# - one users' query in background (to avoid reseting max_memory_usage_for_user) + +CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) +. $CURDIR/../shell_config.sh + +set -o pipefail + +function execute_null() +{ + ${CLICKHOUSE_CLIENT} --format Null -n "$@" +} + +function execute_group_by() +{ + local opts=( + --max_memory_usage_for_user=$((150<<20)) + --max_threads=2 + ) + execute_null "${opts[@]}" <<<'SELECT uniq(number) FROM numbers_mt(toUInt64(1e6)) GROUP BY number % 5e5' +} + +# This is needed to keep at least one running query for user for the time of test. +execute_null <<<'SELECT sleep(3)' & +execute_group_by +# if memory accounting will be incorrect, the second query will be failed with MEMORY_LIMIT_EXCEEDED +execute_group_by +wait diff --git a/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.reference b/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.reference new file mode 100644 index 00000000000..19a5fc680ff --- /dev/null +++ b/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.reference @@ -0,0 +1,3 @@ +a\\_\\c\\l\\i\\c\\k\\h\\o\\u\\s a\\_\\c\\l\\i\\c\\k\\h\\o\\u\\s\\e +1 0 1 1 +1 1 0 0 0 diff --git a/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.sql b/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.sql new file mode 100644 index 00000000000..36ad7b4506c --- /dev/null +++ b/tests/queries/0_stateless/01284_escape_sequences_php_mysql_style.sql @@ -0,0 +1,6 @@ +SELECT 'a\_\c\l\i\c\k\h\o\u\s\e', 'a\\_\\c\\l\\i\\c\\k\\h\\o\\u\\s\\e'; +select 'aXb' like 'a_b', 'aXb' like 'a\_b', 'a_b' like 'a\_b', 'a_b' like 'a\\_b'; +SELECT match('Hello', '\w+'), match('Hello', '\\w+'), match('Hello', '\\\w+'), match('Hello', '\w\+'), match('Hello', 'w+'); + +SELECT match('Hello', '\He\l\l\o'); -- { serverError 427 } +SELECT match('Hello', '\H\e\l\l\o'); -- { serverError 427 } diff --git a/tests/queries/0_stateless/01284_port.reference b/tests/queries/0_stateless/01284_port.reference new file mode 100644 index 00000000000..7e776595065 --- /dev/null +++ b/tests/queries/0_stateless/01284_port.reference @@ -0,0 +1,24 @@ +ipv4 +0 +80 +80 +80 +80 +hostname +0 +80 +80 +80 +80 +default-port +80 +80 +ipv6 +0 +0 +0 +0 +0 +0 +host-no-dot +0 diff --git a/tests/queries/0_stateless/01284_port.sql b/tests/queries/0_stateless/01284_port.sql new file mode 100644 index 00000000000..9c31a5d42ad --- /dev/null +++ b/tests/queries/0_stateless/01284_port.sql @@ -0,0 +1,34 @@ +select 'ipv4'; +select port('http://127.0.0.1/'); +select port('http://127.0.0.1:80'); +select port('http://127.0.0.1:80/'); +select port('//127.0.0.1:80/'); +select port('127.0.0.1:80'); +select 'hostname'; +select port('http://foobar.com/'); +select port('http://foobar.com:80'); +select port('http://foobar.com:80/'); +select port('//foobar.com:80/'); +select port('foobar.com:80'); + +select 'default-port'; +select port('http://127.0.0.1/', toUInt16(80)); +select port('http://foobar.com/', toUInt16(80)); + +-- unsupported +/* ILLEGAL_TYPE_OF_ARGUMENT */ select port(toFixedString('', 1)); -- { serverError 43; } +/* ILLEGAL_TYPE_OF_ARGUMENT */ select port('', 1); -- { serverError 43; } +/* NUMBER_OF_ARGUMENTS_DOESNT_MATCH */ select port('', 1, 1); -- { serverError 42; } + +-- +-- Known limitations of domain() (getURLHost()) +-- +select 'ipv6'; +select port('http://[2001:db8::8a2e:370:7334]/'); +select port('http://[2001:db8::8a2e:370:7334]:80'); +select port('http://[2001:db8::8a2e:370:7334]:80/'); +select port('//[2001:db8::8a2e:370:7334]:80/'); +select port('[2001:db8::8a2e:370:7334]:80'); +select port('2001:db8::8a2e:370:7334:80'); +select 'host-no-dot'; +select port('//foobar:80/'); diff --git a/tests/queries/0_stateless/01284_view_and_extremes_bug.reference b/tests/queries/0_stateless/01284_view_and_extremes_bug.reference new file mode 100644 index 00000000000..216e97ce082 --- /dev/null +++ b/tests/queries/0_stateless/01284_view_and_extremes_bug.reference @@ -0,0 +1 @@ +World diff --git a/tests/queries/0_stateless/01284_view_and_extremes_bug.sql b/tests/queries/0_stateless/01284_view_and_extremes_bug.sql new file mode 100644 index 00000000000..c444441a258 --- /dev/null +++ b/tests/queries/0_stateless/01284_view_and_extremes_bug.sql @@ -0,0 +1,4 @@ +drop table if exists view_bug_const; +CREATE VIEW view_bug_const AS SELECT 'World' AS hello FROM (SELECT number FROM system.numbers LIMIT 1) AS n1 JOIN (SELECT number FROM system.numbers LIMIT 1) AS n2 USING (number); +select * from view_bug_const; +drop table if exists view_bug_const; diff --git a/tests/queries/1_stateful/00155_date_datetime_key_condition.reference b/tests/queries/0_stateless/01285_date_datetime_key_condition.reference similarity index 100% rename from tests/queries/1_stateful/00155_date_datetime_key_condition.reference rename to tests/queries/0_stateless/01285_date_datetime_key_condition.reference diff --git a/tests/queries/0_stateless/01285_date_datetime_key_condition.sql b/tests/queries/0_stateless/01285_date_datetime_key_condition.sql new file mode 100644 index 00000000000..fe1454cd7c4 --- /dev/null +++ b/tests/queries/0_stateless/01285_date_datetime_key_condition.sql @@ -0,0 +1,22 @@ +DROP TABLE IF EXISTS date_datetime_key_condition; + +CREATE TABLE date_datetime_key_condition (dt DateTime) ENGINE = MergeTree() ORDER BY dt; +INSERT INTO date_datetime_key_condition VALUES ('2020-01-01 00:00:00'), ('2020-01-01 10:00:00'), ('2020-01-02 00:00:00'); + +-- partial +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt > toDate('2020-01-01') AND dt < toDate('2020-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt >= toDate('2020-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt < toDate('2020-01-02'); + +-- inside +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt > toDate('2019-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt < toDate('2021-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt >= toDate('2019-01-02') AND dt < toDate('2021-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt > toDate('2019-01-02') OR dt <= toDate('2021-01-02'); + +-- outside +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt < toDate('2019-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt > toDate('2021-01-02'); +SELECT groupArray(dt) from date_datetime_key_condition WHERE dt < toDate('2019-01-02') OR dt > toDate('2021-01-02'); + +DROP TABLE date_datetime_key_condition; diff --git a/tests/queries/0_stateless/01285_engine_join_donmikel.reference b/tests/queries/0_stateless/01285_engine_join_donmikel.reference new file mode 100644 index 00000000000..573541ac970 --- /dev/null +++ b/tests/queries/0_stateless/01285_engine_join_donmikel.reference @@ -0,0 +1 @@ +0 diff --git a/tests/queries/0_stateless/01285_engine_join_donmikel.sh b/tests/queries/0_stateless/01285_engine_join_donmikel.sh new file mode 100755 index 00000000000..8a867921dbe --- /dev/null +++ b/tests/queries/0_stateless/01285_engine_join_donmikel.sh @@ -0,0 +1,65 @@ +#!/usr/bin/env bash + +CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) +. $CURDIR/../shell_config.sh + +$CLICKHOUSE_CLIENT --multiquery --query " +DROP TABLE IF EXISTS NmSubj; +DROP TABLE IF EXISTS events; + +create table NmSubj +( + NmId UInt32, + SubjectId UInt32 +) + engine = Join(All, inner, NmId); + +create table events +( + EventDate Date, + EventDateTime DateTime, + EventId String, + SessionId FixedString(36), + PageViewId FixedString(36), + UserId UInt64, + UniqUserId FixedString(36), + UrlReferrer String, + Param1 String, + Param2 String, + Param3 String, + Param4 String, + Param5 String, + Param6 String, + Param7 String, + Param8 String, + Param9 String, + Param10 String, + ApplicationType UInt8, + Locale String, + Lang String, + Version String, + Path String, + QueryString String, + UserHostAddress UInt32 +) + engine = MergeTree() + PARTITION BY (toYYYYMM(EventDate), EventId) + ORDER BY (EventId, EventDate, Locale, ApplicationType, intHash64(UserId)) + SAMPLE BY intHash64(UserId) + SETTINGS index_granularity = 8192; + +insert into NmSubj values (1, 1), (2, 2), (3, 3); +" + +$CLICKHOUSE_CLIENT --query "INSERT INTO events FORMAT TSV" < ${CURDIR}/01285_engine_join_donmikel.tsv + +$CLICKHOUSE_CLIENT --query " +SELECT toInt32(count() / 24) as Count +FROM events as e INNER JOIN NmSubj as ns +ON ns.NmId = toUInt32(e.Param1) +WHERE e.EventDate = today() - 7 AND e.EventId = 'GCO' AND ns.SubjectId = 2073" + +$CLICKHOUSE_CLIENT --multiquery --query " +DROP TABLE NmSubj; +DROP TABLE events; +" diff --git a/tests/queries/0_stateless/01285_engine_join_donmikel.tsv b/tests/queries/0_stateless/01285_engine_join_donmikel.tsv new file mode 100644 index 00000000000..a6f47144ff2 --- /dev/null +++ b/tests/queries/0_stateless/01285_engine_join_donmikel.tsv @@ -0,0 +1,100 @@ +2020-02-17 2020-02-17 19:40:09 EMC wFxiX8iZ3Vns8pO6bx0WvYftGEOM9WMff Ku5ofnKwBaQ0CtcdZa6sAnSQbyufu0zfd 0 X16qWFb_h8JONLGxs7oiXFZTdBFfTniRMG mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=33&userId=274574634&email=Z21haWwucnU%3D&source=mn 657583482 +2020-02-17 2020-02-17 20:23:53 EMC foco1fj5Li6ey>MSfn?jKHBBdiwKXiBmy7Ni ICZBjN7en5snnszHKbTVUU*xyOhuZEgI1EK 0 I7XAKnCMsD9tdFHmmcCrI~KqiKQdo7Gxd5 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=E17727463464LnJ1&source=mn 2992671877 +2020-02-17 2020-02-17 19:49:04 EMC q3AxEdMQhsr1NewVSKjHzYvh63XdxtGcBZX GVGMPZhenJd83JarI7Qicq5BKRfijT0ls 18536997 D_myvD3U4bmy5anwdNRFaxm KNoDfcCDL9U6 http&o=mail.ru/redir?u=http&o=mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=AD0581918974621haWwuY29t&source=mn 1656424571 +2020-02-17 2020-02-17 21:55:32 EMC ef7tm7k7Yvpb4XIfvf7ON-s4Xv3ztD7SkB KIDkUzEgcAMu%ObAQAkI3jmm3638bSnX0 22341123 6NcB26yJrLhWgldC_HvV2fUOHNLRFvkLbA mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=E943634627468871D581940274695&userId=2746887723D&source=mn 1429586160 +2020-02-17 2020-02-17 21:37:47 EMC 3Y_KZLEJgn4bw?omv4EizIs1lUMz0Li0Ws0 I3QaVG9UvXWvWReLSHuDCs3DdgTbX8av6 28213800 KnoofunrqFKdIta8pMuR!FNX2yu1I6gNo https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail&v=2&s=3745772 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5YWxpbC5jb20%3D&source=mn 872136829 +2020-02-17 2020-02-17 19:15:34 EMC JcHEtSzMb70K}04FW#ShpZw1ot_fb7wxj8 KG9bmRo6yweN2EX48CUBQcsOqzbHn6g3u 30047107 UKb5rJ5D\bFncBHxCioYswtJKAlv6Ua5MVSrj mn 48 Ru ru 7.0.32 /confirm/vipstatus ?key=75ydQ%3D%3D&source=mn 626057004 +2020-02-17 2020-02-17 18:15:04 EMC _sjptcVU5CF4sTnXh0C6DCYcOo0rNowf 0a0AcabOllf7\rN9X9aa7rVmJ0J1oZGJY2 30648090 Z2K_4kffe21iW1hl2jby1RXAAh5XtPLP3 mn 48 Ru ru 7.0.32 /confirm/vipstatus ?key=5&ts=15819420%3D&source=mn 3682305993 +2020-02-17 2020-02-17 16:10:20 EMC WM44OUvEZse_9hQ0NJsn0k47pX6_UnaS7 LgCWwTMZ+GwiQEbNT95zUnkMCXYqPs1Xt1 0 QUuSVpqq#SgMdveJDW0bQ6s8jn8MLXzL1w mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=CCD&source=mn 726391852 +2020-02-17 2020-02-17 17:30:44 EMC PGfQVZHuAY0A_kUA\04ceYRjWqgPJtfhCn 4TR9oRKCNrouy:zJBLBi8J4=u7Mkt9jgzgmB 0 xbCoBX9pTDaWiRxW@F3fOgKD9lX58oWsc mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=DB3D&source=pcap 2498835913 +2020-02-17 2020-02-17 19:10:51 EMC gnd66xWlKf2H2tiZdbivjoz4ILmJ4lp_ ysgw6WLdbNWSHQrybWjhH9uJqnlZMWAv 0 nDQDqsnm/dlpbFMPJE93b6EETHzFxUSzVv pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=4&userId=274634688&userId=274688&userId=27465D85CD4F634627468877266792YXJ1&source=mn 816668334 +2020-02-17 2020-02-17 20:52:00 EMC pBzkcTpn50WpO]BZH7^js6TpPGp7Uid7mFg jQVdKDl4+Sp_j5CZc PtVoMGTIGOfYO6Q2 0 aQGyrF9s3qUMPq_dUnOiM6QVMX5PNQ_eiV pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=50&email=YWlsLmNvbQ%3D%3D&source=pcap 1770779506 +2020-02-17 2020-02-17 21:31:14 EMC cyTu3wNRCI1TzkxCybFNz\rCkrdDZQxYtlW gmtJF_hWE8M79bWSaKkn8UT5Xdwfb0uK8T 0 RSJUU0SBDIXjpYORna59cWouc20W5VIP mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=4CD%3D&source=mn 3448881839 +2020-02-17 2020-02-17 17:15:46 EMC I3bvr8ce2SU_&UuDX4J6KRJl5uipnL2Or myxD8nQXFYnKqBoPGGo4Hy6hBTXRL04K 0 ntHjLMvhnb7b09Tu7jRkM8KgS5ni0w4oH mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=36274695&userId=2560&userId=27463465&userId=27468872EDB908&ts=158193819382 2447621965 +2020-02-17 2020-02-17 18:21:21 EMC _468tOVLPpIkgKvPGX8ypjfTZV09k8w5 0KakGIWk9uaL0Rv3]1T5wPeHPklVWzhytg 0 QAJxAuQADoEQqY0HUT56P0O4K5y55K_L https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://mail&v=2&s=92Ymail&v=2&s=3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D66email&v=2&s=93D158192YWlsLnJ1%26source%3Dmn&c=swm&r=https%3A%2F%2Fwww.wildberries.ru mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5819392158193634&userId=274688&ts=15819408BD1haWwucnU%3D&source=mn 1547300784 +2020-02-17 2020-02-17 19:07:33 EMC Y8yBoZ7Cp2GUTQ8srLMZJFIZ85WgiBeau wmIgwW88aSGvvjKwV,8EooQonI_90taLrh 0 KXVqerLQyaMaMtuT1FzUjrLev8Fw11mkfO pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=72846239707&userId=274688&ts=1581921haWwucnU%3D&source=pcap 2777789095 +2020-02-17 2020-02-17 11:27:36 EMC n66D1ZN9C6y7LASQucHNdkw_QseVRnt32 yeqFeZFa,7cQ_JyTO3yJJKS QaCKEWERPx4Z 24388614 6h91HeiPyIKw8yV0p\tcaK99w_zmnmXU77RI https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail.ru/redir?u=https://click.mail&v=2&s=3D158192YWlsLnJ1%26source%3Dmn&c=swm&r=http&o=mail.ru/redir?u=https://click.mail.ru/redir?u=https://mail%3DYWlsLnJ1%26source mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=6167462E4CD570A0312D6BF1BtYWlsLnJ1&source=mn 662531688 +2020-02-17 2020-02-17 14:11:06 EMC jamANU2zei_lBkfEk_Im5ow0gWB5G0gL1S So7Jc6gheYgclfoq8l0hqsPExrMNSXPLV 20685668 nwRXATVEY2PaYr34qwtZX0Q6ah_sceXjbL https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail&v=2&s=9444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69103Dmn&c=swm&r=http&o=mail&v=2&s=92YWlsLnJ1%26source%3Dpc&c=swm&r=https mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=420%3D&source=mn 3233174651 +2020-02-17 2020-02-17 14:32:04 EMC lsruHZ0Ywg1yDdrio.j5piNMTnqNxeaOQJ G6K62xDbm9aJ_kNlLqEo4AhVf46wDtWi 32046518 wgpf1yqVtVhLL7yT9sp1RbqaXGF81GmSiQ6 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=1581943D&source=pcap 3183159832 +2020-02-17 2020-02-17 15:11:37 EMC 5EW8o4vD850H>TQam3NA2@egQm32jpASIF KJKN5QAHdoqw_RGol5hLvSq6753cKLswM 32971244 8Vh3DVlCjfXs[5hqVMGDDP2iBjoiqhoACB https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://mail&v=2&s=3D27457AD3D274576userId%3D27461haWwucnU%253D%26source%3Dmn&c=swm&r=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6ts%3D158193Fkey%3D669%26email&v=2&s=3Fkey%3D69D01 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5634&userId=274695&ts=15819440446274695&userId=27465&email=Z21haWwucnU%3D&source=pcap 574798405 +2020-02-17 2020-02-17 13:59:25 EMC i6LAlVL3U0GUFFtjiRgfPyjyattjzds6y2 IYv_jZ2k+bNO33nbLKRRGcJvTHVIueEDI 21779069 eUgOCUGbEZM15\'Of0Vz6zQmAT0T0zX3XSO http&o=mail.ru/redir?u=http&o=mail.ru/redir?u=https%3A%2F%2Fwww.wildberries mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=D1F9sail=YWxpbC5ydQ%3D%3D&source=mn 3475274476 +2020-02-17 2020-02-17 06:40:47 EMC A_3372QT5xhTmjNrokk3yZCtuOm52FfZT oOD7es9hGUs7jB3_)jVKh3Oo10IQvAu01 27168564 UYEHX0itbLKZjChWxLsP4a7LUXQLX4iB mn 48 Ru ru 7.0.32 /confirm/vipstatus ?key=467468874634&email=dG92&userId=274695&email=email=a2B7AD60&email=bWFpbC5ydQ%3D%3D&source=mn 3084609784 +2020-02-17 2020-02-17 14:10:13 EMC WSlfONgzmGj8kylbItxLW8MX4u60oapxy U8TMovlAcJTcA~u3KoOFG7pchP3CBPbcB4 28904171 nBfRyelBAkOfR70tIzBusuS0M8_KbRsOGI pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=4462F5B37274695&email=Ymail=Z21haWwucnU%3D&source=mn 2020344465 +2020-02-17 2020-02-17 01:43:57 EMC khjsNWq7 Iq564D1u\'vWuKZHN4kfq0Kyfv hcAK5RGOjZHYbFJwufN7\tZeXCRWAEKoT2 0 G0Zi9TAk`t0aUcHRiOcb1|RgoT8xMOH4KV mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=1581940095&ts=158193819382&userId=27465D8B8F1936256C35B4B466&userId=2746887C1A97&userId=274695&userId=274634&userId 902363005 +2020-02-17 2020-02-17 02:17:35 EMC H56Q4qwa\'eYiFCmGR40Pp7,m6fDiE2nJSmB Efk7W3ZrgNsEi.anvkrteuN>lF2UlX0RZFzr 0 QhyRjVGEsD_4YaQiaLorQ6y0fbCxkEVzQ5 pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=44695&email=YW5hcnU%3D&source=mn 2161496531 +2020-02-17 2020-02-17 03:20:48 EMC 1wBv9Q7rDQuImuif>0v1t8OXWSIXymKrI sNujW7iatZLPxEOpI1fZdT4p0QRaotsXPZ 0 LSKNxAcrTMsADK9VI7AMqm05blzLWXCJ05 pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=AE1FAC2BFA1E75hce=mn 985607445 +2020-02-17 2020-02-17 06:18:16 EMC 6dqrbyyKHWPBEyPZGbJRKjxtmt0Aq8IsON k57VHYX59Ws9u[L3nNEruOGCVgGH_l27J1 0 _lwuZQycqGeyMxkRSM7pR1lHNU6_V0nVWG pcap 187 Ru ru 7.0.32 /confirm/vipstatus ?key=B27465D88&userId=274572BE3274577273AF0&email=a274578&userId=274692&userId=274688&userId=27465D8192 130983489 +2020-02-17 2020-02-17 09:20:13 EMC UCLTP56_YcQ9rWVJa8rif2Aq5NNqVThlwH 7Rx9OsBs7BemVxuArwZ7N5BqcFwK7CSI 0 JOIbkOPdPPbPCtqRV6wQHsdWYNnmarCxm mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=A6E819420%3D&source=pcap 2567294448 +2020-02-17 2020-02-17 13:05:00 EMC 28AZ4n0zpsVuwzenZ6*gd0VNMjnT8Kmfncv PFiGZRLTjK1CxfLJajtGVFOATfWnTE00 0 QYPUzvwV=w8ev0E77B|RK6Z<66ZX5y1YIK1J mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=C19213C0060312E9E28A82&email=bmFA2095&userId=2746346&userId=27457455266&ts=15819213D&source=pcap 2881908356 +2020-02-17 2020-02-17 13:40:53 EMC uDOkWKoTLCbB2SFYoepda0 itJJ9zJgyZVY d50Y87RQCO70ci0u{QDZcA8dU31qm0IS1 0 0MuqyXoTtKYpmheID1AiXWz9sZ0zroDj mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=A3274695&userId=2746346470&userId=274634&userId=256AEA56926&ts=158194407&userId=27463467720%3D&source=pcap 700256219 +2020-02-17 2020-02-17 13:56:10 EMC rOXnSk45QcoEkw03yMYbGUhD_YZ_yCx9OU DyGXuVg8;P6Tq8CDp2_0XI`zPz4wuG8iJJh 0 3IM74UyhDyv2Jamik02pDQJu_L10vfPCKTm mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=459&email=bmFA81942095&userId=27468872095&userId=27457F1944672Y29t&source=pcap 607085190 +2020-02-17 2020-02-17 13:57:55 EMC xo09ZqxjuPBo_2aYOgnG\\sH3HDRtPH7xW 1I3ceRxYeGTFgNy30ojqJ]qrOgqu1Ag8yO 0 PwQkOkG2N1_p*ZFjOwmM6FviVATMGY5_rbK mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=158193979967F628BBA48E274634&email=dGV4LnJ1&source=mn 3851759707 +2020-02-17 2020-02-17 14:09:55 EMC vmlDYHpCg270cyeLJZBJTwBBnnJHH99Av l9FPMTHyyKlHijgeO]2oJK90OO8hWvntXS8 0 0Xu7Ha8eqQdwcG3pm#GNMw6HzEsxoAszdK mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=BtYWlsLnJ1&source=mn 2783694582 +2020-02-17 2020-02-17 15:31:52 EMC WIzjCT0n1XqAlOuRi2YskEx619ZjBaFe4g z_NGqjbLB0IhQV1SxDRMNG0DlMUxPlqaQ6 0 bv75_7V5B4pBB2aNK\fRwnBDQm0ngrcFPLN mn 187 Ru ru 7.0.32 /confirm/vipstatus ?key=158193628FA603193692&email=bmFA934&userId=265&ts=158192YW5haWwucnU%3D&source=pcap 722494088 +2020-02-17 2020-02-17 06:28:37 EMC 434gE67EZuzQL3ssU31NIt0eoeEpm8YplE7RGkXuG https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6source%3Dpc&c=swm&r=http&o=mail.ru/redir?u=https://click.mail.ru/redir?u=http&o=mail&v=2&s=974578Fvipstatus%3Fkey mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=1581938C8193634&email=a29t&source=mn 4267472950 +2020-02-17 2020-02-17 03:43:33 EMC TAl7tSOQaATLUUMZTx90iv0sqRoADhEn2r zvCR7ostHdMiQuVI8uxOyYGf0mm6k3ckHSL 32488481 9kFERwTF"AWKxn0YPOUv_tA8c5X2cdy4bA pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=1581936292&email=a256F095&ts=158192&userId=274695&userId=27465D84D65D8B8E7EA692YW5haWwucnU%3D&source 1722142578 +2020-02-17 2020-02-17 04:06:30 EMC kL0p32eE J8hj51lGJQdDpzRytjcc2_AnA eO7MVT5A47viQfb3A01JapoD001J0l_UAt 23078127 KDZSswsocsumoOtSx\\phTvuffYOTHGNoUa mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=7724D&source=mn 2669624134 +2020-02-17 2020-02-17 04:23:38 EMC q3PyeDUQPYw7QN9BwE1eP\nDzWsZDAv3GTN u3GnfRRy>bOqpqFvSDikeB8V0zHacc0ur 26965394 CxxiDtfVM9T6WuleL1P4mMbzF9k0TLWLF pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=58193695&ts=1581942095&email=bWFpbC5ydQ%3D%3D&source=mn 2552851257 +2020-02-17 2020-02-17 05:36:35 EMC ipti_lG94H8P5RgFwKzaoxUwWNEV9beK zolMT7vt_ttY|BmlD2PSejtg6O7WzJ2S_ 31107154 ha6rDRxktOKPjl2gzz7R2TpQu2KKta9Q mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=4942095&ts=15819369266&userId=274692158193634&userId=2745523552D695 1459132007 +2020-02-17 2020-02-17 00:45:31 EMC hXw0ETb7piXc>PKMzqxhV_F_UdWZnFB5O VXB5E4w28OrrZT0X1Sn9SrTWuJhjff7I 19656120 v06fJehG\'_m057sFduiQBx(mS5JnuSD6jph mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=B193695&ts=15819346165D85jb20%3D&source=pcap 1300966980 +2020-02-17 2020-02-17 03:44:40 EMC 0Q0EMlWcxIACIHUsZX4mEhJnxPpCJV6Qe ZqVPZ1Yb>rFSB\tzEMNdTEjoWIHLaQ2o5vI_E 17361913 AuRaBJOGvceRXWiMb9\'wolUnAGR0hxXQgOS pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=725634&email=bWFpbC5ydQ%3D%3D&source=mn 1552491257 +2020-02-17 2020-02-17 02:35:40 EMC mSk0tnq0soJQslU0KlkSmfnXFu6fqRw0A hjlyHsr0&gybjsAJ0WRqdLJz32l3lmiEgDN 32664890 YAoxYQxl"Ce8HvY2j90VWzKQxlGCTNRAyJ mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=6459&ts=158194464089&userId=27465D82&userId=27455229t&source=mn 3051884197 +2020-02-17 2020-02-17 13:44:36 EMC znOwy_e4iHG8(NdCh2qgz1tjBR0ZjsFus eNSFOPi9oax3Ru7x01JA4TWeX66Ev8T9U 18979240 LosZ3fZjVY8hXjH8AJgKx:O3FNAMVDRGlZ mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=71581944027465D819384019215819397327457AbWFpbC5ydQ%3D%3D&source=mn 1828619156 +2020-02-17 2020-02-17 02:07:55 EMC yvDmRiaYkm43iWRNnnW3YDPBqq55XWVXr 7gpmg2PirkSp]TYhcY7i6]DawnwV9tqC0b 22858229 yDybPZi3Oc7m,JVxfltuRtWm8TmiHQJOjY https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail%3DZG1haWwucnU%253D%26source%3Dmn&c=swm&r=http&o=mail%3DZG1haWwucnU%253D%26source%3Dmn&c=swm&r=http&o=mail&v=2&s=9158192YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=3Dmn&c=swm&r=https://click.mail.ru/redir?u=http&o=mail%3DYm_ce%3Dmn mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=158189721581939265D89&email=dG1haWwuY29t&source=pcap 1735264694 +2020-02-17 2020-02-17 00:39:49 EMC BOA0kaQben9xa\fOjQ8YZt2L9UV_FYiMKYa3n 0BL0DaCp3weXj7aIq4ZBhaKzr0Uwpdpm 21820865 xATcz14a2hYJcGJb2gRsIIQ9K2A5fOGo https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://mail.ru/redir?u=https://mail&v=2&s=90BtYWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6ts%3D158192YWlsLnJ1%26source%3Dmn&c=swm&r=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D27457%26ts%3D158192YWlsLnJ1%26source%3Dmn&c=swm&r=http&o=mail.ru/redir?u=http&o=mail.ru/redir?u=http mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=77256160&userId=274634&email=bWFpbC5ydQ%3D%3D&source=mn 1855925025 +2020-02-17 2020-02-17 01:38:01 EMC uNpwiDVW2_p6HEMl4YIHw0z_vOpEqPyir napvpdbMVeSjy KJz5spT94Yu6wGCm_xgkX 27148457 R8wZY_PRklNkxX0Dn6uA{sGHEPaMT3kc8 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=3C3274695&userId=2745528194401908193467BD9189&ts=1581926&ts=1581939772B67B6AE4CD2DBD910B392YW5haWwucnU 2249892028 +2020-02-17 2020-02-17 23:32:22 EMC uKrr0IYx5Kt1\'QPtv@toS9nQ4ZcrvAD0l8 4dWFNMPK50HO0z6ZPSoX6g02Ceu35kLzjtB 25390020 CXq72Vsbolj2.WJUoa8UoTZlw2wHUHxWX https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail%3DYWlsLnJ1%26source%3Dmn&c=swm&r=https%3A%2F%2Fwwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email&v=2&s=3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D67972 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=BE304F9CDBC6&ts=1581934&email=YW5haWwuY29t&source=mn 3489237198 +2020-02-17 2020-02-17 22:36:42 EMC hQkEQSurISp_uy9ORd05 yjXxg7QByQH9 FURnnJ51xl2NiQHcN\r6hpIkfYa17e26Mt8 25551409 NBIMBrwi mVoYYuxJq_8Df0CM8CZkrZezFE mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=158194463465&userId=25616C3D&source=mn 2913713687 +2020-02-17 2020-02-17 20:19:16 EMC Xahxt0V3`JlMo+tyHm8MxJFT9NEywdtAZeD YV0_62kSEM9X 0GW7eHjXxF95KfKoarfR 27982291 iuEEgZrUYV04*QSEQg_uWbYo8cewVWPriGO mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=DFD92Y29t&source=mn 1136043092 +2020-02-17 2020-02-17 20:05:44 EMC gAraBOGNzDEdkz8qxSB68sQXrgyTFpX6 KC9GBYXCc2sL;fDL4#6DMT%2ELzdoqHtjMp 27849879 hmvHfcpQ7YcXyk6byq3rSqEUfDuei6M62h mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=71&source=mn 795793408 +2020-02-17 2020-02-17 01:03:41 EMC Sujwqk4khZF0dd3dRrn0zsOYRdkd9ynAR NaKyF0O3rR3r0wXNLf_3KSANWona7Ftry 30475228 calDaEsa910bkYOkR\bbKjQeUvAOoR7CQJH https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6source%3Dmn&c=swm&r=http&o=mail%3DYWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=B1581918970&userId=274634&userId=27457&email=YW5hce=mn 3165615449 +2020-02-17 2020-02-17 18:40:14 EMC zBHwSrKIMfAFFJxuvWtIsZ2DA_nAX98Aa NQiRPz123luXCH0fvH?59tbjHdGAlVgiHhc 26251034 0KbAptV7u8SZ?V4N7WHvx[0vY5D_saLU2G https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail%3DYWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=9158192Ymail&v=2&s=936source%3Dmn&c=swm&r=http&o=mail%3DbW9%26userId%3D2746158192YWlsLnJ1%26source mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5&userId=274552746887BF4LnJ1&source=mn 115808044 +2020-02-17 2020-02-17 22:03:35 EMC dvrVwEyocDVpJ3YEozYAH1XuC51DQcby59 wcCGF71wVXRj0pz2h131p\\1c7jnQYzejlC 24153343 mHlXjDvel9Ab8kZxtR6ELtFOSq7X1Q8_7 https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D65 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=A63468874692&email=ce=pcap 1125992029 +2020-02-17 2020-02-17 13:11:31 EMC ELifUEthNP3xZTZ5RZd2tIgUWpctZJNKkdp 3qxE4qStGm1jIRPc9,JCHKxNAJqeRRgVaJ5 32523658 opEAQkCl*DGc0VozrkcYlaUmWvfN0IAYa https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail%3DYWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=3%26userId%3D274570%26userId%3D274615819383%26userId%3D2745746193%26userId%3D2745745776source%3Dmn&c=swm&r=http&o=mail&v=2&s=34Fww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6source%3Dmn&c=swm&r=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6126source%3Dmn&c=swm&r=https://click.mail%3DbWFpbC5ydQ%253D%253D mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=616&userId=27465&email=YWlsLmNvbQ%3D%3D&source=pcap 660510007 +2020-02-17 2020-02-17 23:08:20 EMC Ww8aun1EXuPT3stlfv12_A4nVx4RfDfGaK Gj6ixLDK{FkfiIQ0ZqHK9IsJMWys80zowLQy 28692974 nB20Riv63uMc]E9s0Bv7x1XcxILAKq2zwc pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=3D&source=pcap 458549627 +2020-02-17 2020-02-17 15:45:11 EMC _nkKyF0NV20B2AAxI@oOj8uSGus_lOrqBS 0vXB63kVoAv97D8cUCQSR\bmet_h2UhiQ4X 31753811 zA7KKsesYWPrI1KD"FFmdemMIJ3AcxwZr https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail%3DZG1haWwucnU%253D%26source%3Dmn&c=swm&r=http&o=mail&v=2&s=9%26ts%3D1581944577457EC6source%3Dmn&c=swm&r=https://click.mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D67D492YWlsLnJ1%26source%3Dmn&c=swm&r=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D685764%26email&v=2&s=9%26email.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=DA8189&email=a2DC9serId=274634&userId=25695&userId=274688&userId=27465 4039013194 +2020-02-17 2020-02-17 14:54:17 EMC wHTfVQKqlnQp!PXzWG80qc0oWU1pvtKeL EaNVlRXuzZ33\fLB0Fmjet29f3xaJplvaiX 30992376 vJnOh3mpOb0h!xPw1slS0e[Ehj1AIx920Jo https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail.ru/redir?u=https://click.mail&v=2&s=3c pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=7462B60&email=cnU%3D&source=mn 2569826295 +2020-02-17 2020-02-17 22:51:48 EMC C1a6zgET p1v0mSMHJJgMxp8w7uJ7zN14J9Z 5cn50cUip60T6nRihVzsSRarErtllzgH6 26715992 0D4M2m041DlURNuFG9QJtIcjHVkp5_TEZ https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail&v=2&s=9446158194419447 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=DEBE34&email=Z21haWwucnU%3D&source=mn 1504060974 +2020-02-17 2020-02-17 13:53:54 EMC 5a2rniMpduiEUzYFsgZjKHqgoZWbDYts ziqQkEkD3tYgLGhe&QwROPlb3hkAIZW_UI 32696355 0rSWK9UmGDPuRvPwXqs3mK9cF0balOqbS http&o=mail.ru/redir?u=http&o=mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=77274552E&ts=158192158192YXNvbQ%3D%3D&source=pcap 1675780127 +2020-02-17 2020-02-17 20:08:49 EMC 0IBozTjy/SMIkY5tY\\_GAd\'0VIzFgFK2VSY V0fFnEjkPzK3.y_ng3Nfs1oJtBLCWPq35z 33102601 NQhlj1k9bLy234WJi\rKtOd2239rJDYJSKh https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail.ru/redir?u=http&o=mail.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D61haWwucnU%253D%253D%26source%3Dmn&c=swm&r=https://click.mail%3DYWlsLnJ1%26source%3Dmn&c=swm&r=http&o=mail.ru/redir?u=https://click.mail.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69%26userId%3D2746193A%2F%2Fwwwwwww.wildberries.ru%2Fconfirm%2Fvipstatus mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=D8BD7B082&ts=15819392YW5haWwuY29t&source=mn 832387252 +2020-02-17 2020-02-17 21:39:56 EMC 3aiRtPZF[Sjelo0e2EVnauTwl0tsW9SRi7f i8OkH4au\rfMiBV0E4frxZu9WJpRG5bhp4 29554136 gzPJTobNMGgG1kUYVe9sOwfpHmKiF1p0 https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=http&o=mail%3DbW97B365 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=AE&ts=158194466&ts=15819213CD274688&ts=1581934688&email=Ymn 74272104 +2020-02-17 2020-02-17 17:21:43 EMC yqM2AqiUS2Lmo0S5KNYR-RKGxDrME0w5U T1Q2fyBqs8qhiWB_JBE3Ko_Ro0VD79pT0 18406884 mVoGr7MMzfVX0HtUKAYeCVX68_NOaiQY https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email%3DbWFpbC5ydQ%253D%253D%26source%3Dmn&c=swm&r=http&o=mail&v=2&s=9158192YWlsLnJ1%26source%3Dmn&c=swm&r=https mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5819392&userId=27465D8B446887AF95&email=bWFpbC5ydQ%3D%3D&source=pcap 1422459332 +2020-02-17 2020-02-17 15:06:14 EMC NXf_EKmdwAkZZIKr0N0w4HuVTpNqZ30Ldk0 PpN_0d7ywY45Y_Wm#L2S01pN5klv0Wbsa 21385681 JH3MQSLtn6gUIe92ilJPT.EFDSucrCuGHZ mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=A4627465D819397D96AE65&email=dG1haWwuY29t&source=pcap 959722117 +2020-02-17 2020-02-17 19:52:47 EMC OY90Zcjc8ebLcK_uULQHDNvpwO1hN3MwIat ASdCffiid6DweXoVjmpL8~5DHOzhFnPRuW 33422761 4T1zxu2F4evId\rETTryZBYsCBkTxsXLeuC9 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=E97265D8A70F&ts=15819403193634&userId=2746887&email=ce=mn 997133189 +2020-02-17 2020-02-17 17:55:20 EMC ManEZ_qtzd0v\bdxdB07LpVWqoZUfpDzZW MnNRUoUE2ASWag8ClKK5l0yPRafHb0gsw 29428950 clyoRyW5\00F6wDd5P188B6k_OdKCbUFQqT mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=52666799692&email=dGF7470E634&email=ce=mn 3015790084 +2020-02-17 2020-02-17 20:07:34 EMC pr7D2hoMay0bwJjvH6UaPLZpeDXtq0Njs bDlkkbc3OnwzdcNZHDcBkR|V0ApitIVgPOv 22120090 TC2aVmxXNfOhSL0y2oqzb=drQElfeo0_OQ mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=581943D&source=mn 2666495492 +2020-02-17 2020-02-17 18:20:19 EMC a_EpwBGWRXNSTY_FyAhRB25SpX8Gw8JaW 0XDllB5u!HDENidqN/CRrkxwnjTXLeEKIyb 32607759 OKByJYVH3pLb:BWhWwvLnnpw0urPjP04i https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D27461203Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email&v=2&s=3D158192YWlsLnJ1%26source%3Dpc&c=swm&r=https mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=BC66&ts=158193926&userId=256BFC35FD2AEAZ21haWwucnU%3D&source=mn 590291581 +2020-02-17 2020-02-17 10:27:11 EMC bn8x3TAHKlMOsdlmzybH0S*iDc0hYull7Zt 7PY8hsBErbSTnpoU7iPxD8CFjIMxK8eN8F 30559777 lgByHEG2ffmexKgJXv5rC6CW78KV4Kia mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=6667&email=bWFpbC5ydQ%3D%3D&source=mn 1898373016 +2020-02-17 2020-02-17 14:09:12 EMC jYFR0DCE2eTkEFCuAIyAHVYLUy9ENh9Cqc dhe0lvmTDchj8XhgtsZ3mCPzv5hTGPM8Q 24813187 Y7MmPfU2YhtaY85K"2xIfqNraWWqBp5QvK https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6source%3Dmn&c=swm&r=http&o=mail&v=2&s=96email%3DZG1haWwucnU%253D%26source%3Dmn&c=swm&r=http&o=mail&v=2&s=944576userId%3D27461819443Fkey%3D646192YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D274615819360 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=AD9397158192&userId=25616AEBD63465D88&email=bmRleC5ydQ%3D%3D&source=mn 1726149098 +2020-02-17 2020-02-17 18:27:00 EMC VnzEdMoo2lhW?Yr6AQyNVw yFnUj_l0pBiG EnQ5CpnJt3LM1hiuC7lsqJChM0i4JMZ0 28169388 zBJ8p4pSlPo_bkk4\t2ObECW2ReYnHoWrQH https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D27461203Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email&v=2&s=3D158192YWlsLnJ1%26source%3Dmn&c=swm&r=https mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=397729t&source=mn 1102313974 +2020-02-17 2020-02-17 19:49:07 EMC fxpHcK20ouDlcjYFRhFT4DMtbMML0qb8ds hBF63Vf_qZrpsfD4EOfd6YGUBvflIJqF 22835697 TkBqOH2Jjp0wH35uDnjAxqgyb2P4HqtznK https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D2746158192YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=9158192YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=92YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail%3DbWFpbC5ydQ%253D%253D%26source%3Dpc&c=swm&r=http&o=mail%3DZG1haWwucnU%253D%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=9%26source%3Dpc&c pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=ADDABAA48E95&userId=2746346887D9420%3D&source=mn 3497823576 +2020-02-17 2020-02-17 13:28:56 EMC hZbZqj2vRV2FpCXlvxIEyqdeQrwceKg35 8fpYiVLE9gfSIzfP_$dzlj1H8tMzVbcg59 20129530 8bY0GHO5KMpHW9cIAke4yQQ94oQfvoHBxY mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=C5ydQ%3D%3D&source=mn 3102735519 +2020-02-17 2020-02-17 21:37:19 EMC TAlSFJzIsXzTWbuEymOTU320iUcNXmLT5j J2Vf06b6CMLFAvwH_wsUNOv4O9nnCy20 17587521 nEczrivzdrNaBYYvdnQRUT2pBBo8hu3kCvI mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=66&email=YWlsLnJ1&source=mn 1613554206 +2020-02-17 2020-02-17 21:58:32 EMC XPXxpWq0wHcK2FB4$JaOa9xIGhEaajLeS l59HKsiwgQuXgAweGZRZrEkN0Pqk_plZ4c 24296347 3s8mV_3W&hisrcwCm6QXCg_0zgLyr6nnqPB https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D274616 pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=467105695&email=a2YWlsLnJ1&source=pcap 2033387311 +2020-02-17 2020-02-17 16:54:16 EMC 2beVLC_ZYMmZuZbJZ1mjV LQeoXV0BsZKq J4Y22CvJx36nq6KNDMXBg!H5lUx1Z7BoFf 31434491 dabaBlCY351pXUW0HdErDTW_XGkqwmta https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6userId%3D27461203Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6Fconfirm%2Fvipstatus%3Fkey%3D661076userId%3D27457CD15819444613 mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=76031938874634&userId=2564BFA93626&userId=256&email=ce=mn 1613641575 +2020-02-17 2020-02-17 00:27:36 EMC Au3PRMFCW0Ij8iL0ZtsrryAvKJowqXJ8k ntqK0ayP8ltR0twuGraE`Vwgcmux6jFwg 21307924 ruixkHLKjmENcmpbvvbrrLU8FDLIpWOFtU https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://click.mail.ru/redir?u=https%3A%2F%2Fwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6email.ru/redir?u=https%3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D6CD2745785dQ mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=A41E772FFC5ydQ%3D%3D&source=pcap 2395792653 +2020-02-17 2020-02-17 22:03:46 EMC Tc9EmNpb5Xy0edNdTCLg7X2eLmGuTdEkIt YsCMp8oiUBPyhHBsDmEZs0xvixA2L6atY 23431515 Bh67PWI6jKZ6Q102nTeN(YP6e8kLoqiVA https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://mail&v=2&s=96userId%3D274616 pcap 1 Ru ru 7.0.32 /confirm/vipstatus ?key=5D819446&userId=27465D8191897C7462F400&userId=27463465D8192&email=Z21haWwuY29t&source=pcap 2211382541 +2020-02-17 2020-02-17 06:34:15 EMC S13SmJGaHVUBXqd3bs\tRpB3G_hXZBJjxOt6 FP_GWMlfw2REi3Up5Cqu0qWcA99YlCduy 27883082 xJ1eD6ixour7M0K_l6Ziv6awoxMpnzsaW https://click.mail%3DYmail%3Dberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D69444%26email.ru/redir?u=https://mail%3Dby%3D6%26ts%3D158193DBDB3A%2F%2Fwwww.wildberries.ru%2Fconfirm%2Fvipstatus%3Fkey%3D63158192YWlsLnJ1%26source%3Dmn&c=swm&r=https://click.mail&v=2&s=92YWlsLnJ1%26source mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=15819362hQG1haWwuY29t&source=pcap 2045856196 +2020-02-17 2020-02-17 00:36:06 EMC 2mjWiSh70SN_1xOBst7vbYq1z5EL26Z0i 7e5aIak4Pca2woYGZIJi!P_gRQdnPpHDP 28784173 b5hw0LlyfMCyYstJ9XbB6Pq7VN5hO9kIy mn 1 Ru ru 7.0.32 /confirm/vipstatus ?key=15819387AE3634&email=cnU%3D&source=mn 1255281910 diff --git a/tests/queries/0_stateless/01286_constraints_on_default.reference b/tests/queries/0_stateless/01286_constraints_on_default.reference new file mode 100644 index 00000000000..aa47d0d46d4 --- /dev/null +++ b/tests/queries/0_stateless/01286_constraints_on_default.reference @@ -0,0 +1,2 @@ +0 +0 diff --git a/tests/queries/0_stateless/01286_constraints_on_default.sql b/tests/queries/0_stateless/01286_constraints_on_default.sql new file mode 100644 index 00000000000..d150bac15b5 --- /dev/null +++ b/tests/queries/0_stateless/01286_constraints_on_default.sql @@ -0,0 +1,29 @@ +DROP TABLE IF EXISTS default_constraints; +CREATE TABLE default_constraints +( + x UInt8, + y UInt8 DEFAULT x + 1, + CONSTRAINT c CHECK y < 5 +) ENGINE = Memory; + +INSERT INTO default_constraints (x) SELECT number FROM system.numbers LIMIT 5; -- { serverError 469 } +INSERT INTO default_constraints (x) VALUES (0),(1),(2),(3),(4); -- { serverError 469 } + +SELECT y, throwIf(NOT y < 5) FROM default_constraints; +SELECT count() FROM default_constraints; + +DROP TABLE default_constraints; + + +CREATE TEMPORARY TABLE default_constraints +( + x UInt8, + y UInt8 DEFAULT x + 1, + CONSTRAINT c CHECK y < 5 +); + +INSERT INTO default_constraints (x) SELECT number FROM system.numbers LIMIT 5; -- { serverError 469 } +INSERT INTO default_constraints (x) VALUES (0),(1),(2),(3),(4); -- { serverError 469 } + +SELECT y, throwIf(NOT y < 5) FROM default_constraints; +SELECT count() FROM default_constraints; diff --git a/tests/queries/0_stateless/01290_empty_array_index_analysis.reference b/tests/queries/0_stateless/01290_empty_array_index_analysis.reference new file mode 100644 index 00000000000..5037a64c0f0 --- /dev/null +++ b/tests/queries/0_stateless/01290_empty_array_index_analysis.reference @@ -0,0 +1,50 @@ +--- notEmpty + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- empty + [] 1 +--- = [] + [] 1 +--- != [] + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- > [] + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- < [] +--- >= [] + [] 1 + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- <= [] + [] 1 +--- +--- notEmpty + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- empty + [] 1 +--- = [] + [] 1 +--- != [] + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- > [] + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- < [] +--- >= [] + [] 1 + ['a'] 2 + ['a','b','c'] 3 + ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'] 4 +--- <= [] + [] 1 +--- diff --git a/tests/queries/0_stateless/01290_empty_array_index_analysis.sql b/tests/queries/0_stateless/01290_empty_array_index_analysis.sql new file mode 100644 index 00000000000..b1b6067945d --- /dev/null +++ b/tests/queries/0_stateless/01290_empty_array_index_analysis.sql @@ -0,0 +1,66 @@ +drop table if exists count_lc_test; + +CREATE TABLE count_lc_test +( + `s` LowCardinality(String), + `arr` Array(LowCardinality(String)), + `num` UInt64 +) +ENGINE = MergeTree +ORDER BY (s, arr); + +INSERT INTO count_lc_test(num, arr) VALUES (1,[]),(2,['a']),(3,['a','b','c']),(4,['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa']); + +SELECT '--- notEmpty'; +select * from count_lc_test where notEmpty(arr); +SELECT '--- empty'; +select * from count_lc_test where empty(arr); +SELECT '--- = []'; +select * from count_lc_test where arr = []; +SELECT '--- != []'; +select * from count_lc_test where arr != []; +SELECT '--- > []'; +select * from count_lc_test where arr > []; +SELECT '--- < []'; +select * from count_lc_test where arr < []; +SELECT '--- >= []'; +select * from count_lc_test where arr >= []; +SELECT '--- <= []'; +select * from count_lc_test where arr <= []; +SELECT '---'; + +DROP TABLE count_lc_test; + + +drop table if exists count_lc_test; + +CREATE TABLE count_lc_test +( + `s` LowCardinality(String), + `arr` Array(String), + `num` UInt64 +) +ENGINE = MergeTree +ORDER BY (s, arr); + +INSERT INTO count_lc_test(num, arr) VALUES (1,[]),(2,['a']),(3,['a','b','c']),(4,['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa']); + +SELECT '--- notEmpty'; +select * from count_lc_test where notEmpty(arr); +SELECT '--- empty'; +select * from count_lc_test where empty(arr); +SELECT '--- = []'; +select * from count_lc_test where arr = []; +SELECT '--- != []'; +select * from count_lc_test where arr != []; +SELECT '--- > []'; +select * from count_lc_test where arr > []; +SELECT '--- < []'; +select * from count_lc_test where arr < []; +SELECT '--- >= []'; +select * from count_lc_test where arr >= []; +SELECT '--- <= []'; +select * from count_lc_test where arr <= []; +SELECT '---'; + +DROP TABLE count_lc_test; diff --git a/tests/queries/1_stateful/00155_date_datetime_key_condition.sql b/tests/queries/1_stateful/00155_date_datetime_key_condition.sql deleted file mode 100644 index cee1c7cfb46..00000000000 --- a/tests/queries/1_stateful/00155_date_datetime_key_condition.sql +++ /dev/null @@ -1,22 +0,0 @@ -DROP TABLE IF EXISTS test.date_datetime_key_condition; - -CREATE TABLE test.date_datetime_key_condition (dt DateTime) ENGINE = MergeTree() ORDER BY dt; -INSERT INTO test.date_datetime_key_condition VALUES ('2020-01-01 00:00:00'), ('2020-01-01 10:00:00'), ('2020-01-02 00:00:00'); - --- partial -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt > toDate('2020-01-01') AND dt < toDate('2020-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt >= toDate('2020-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt < toDate('2020-01-02'); - --- inside -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt > toDate('2019-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt < toDate('2021-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt >= toDate('2019-01-02') AND dt < toDate('2021-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt > toDate('2019-01-02') OR dt <= toDate('2021-01-02'); - --- outside -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt < toDate('2019-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt > toDate('2021-01-02'); -SELECT groupArray(dt) from test.date_datetime_key_condition WHERE dt < toDate('2019-01-02') OR dt > toDate('2021-01-02'); - -DROP TABLE test.date_datetime_key_condition; \ No newline at end of file diff --git a/utils/ci/docker-multiarch/update.sh b/utils/ci/docker-multiarch/update.sh index 6e3e18047de..6abcf339607 100755 --- a/utils/ci/docker-multiarch/update.sh +++ b/utils/ci/docker-multiarch/update.sh @@ -37,27 +37,27 @@ fi # get the image if \ - wget -q --spider "$baseUrl/current" \ - && wget -q --spider "$baseUrl/current/$thisTar" \ - ; then - baseUrl+='/current' + wget -q --spider "$baseUrl/current" \ + && wget -q --spider "$baseUrl/current/$thisTar" \ + ; then + baseUrl+='/current' fi wget -qN "$baseUrl/"{{MD5,SHA{1,256}}SUMS{,.gpg},"$thisTarBase.manifest",'unpacked/build-info.txt'} || true wget -N "$baseUrl/$thisTar" # check checksum if [ -f SHA256SUMS ]; then - sha256sum="$(sha256sum "$thisTar" | cut -d' ' -f1)" - if ! grep -q "$sha256sum" SHA256SUMS; then - echo >&2 "error: '$thisTar' has invalid SHA256" - exit 1 - fi + sha256sum="$(sha256sum "$thisTar" | cut -d' ' -f1)" + if ! grep -q "$sha256sum" SHA256SUMS; then + echo >&2 "error: '$thisTar' has invalid SHA256" + exit 1 + fi fi cat > Dockerfile <<-EOF - FROM scratch - ADD $thisTar / - ENV ARCH=${ARCH} UBUNTU_SUITE=${VERSION} DOCKER_REPO=${DOCKER_REPO} + FROM scratch + ADD $thisTar / + ENV ARCH=${ARCH} UBUNTU_SUITE=${VERSION} DOCKER_REPO=${DOCKER_REPO} EOF # add qemu-user-static binary @@ -70,26 +70,26 @@ EOF fi cat >> Dockerfile <<-EOF - # a few minor docker-specific tweaks - # see https://github.com/docker/docker/blob/master/contrib/mkimage/debootstrap - RUN echo '#!/bin/sh' > /usr/sbin/policy-rc.d \\ - && echo 'exit 101' >> /usr/sbin/policy-rc.d \\ - && chmod +x /usr/sbin/policy-rc.d \\ - && dpkg-divert --local --rename --add /sbin/initctl \\ - && cp -a /usr/sbin/policy-rc.d /sbin/initctl \\ - && sed -i 's/^exit.*/exit 0/' /sbin/initctl \\ - && echo 'force-unsafe-io' > /etc/dpkg/dpkg.cfg.d/docker-apt-speedup \\ - && echo 'DPkg::Post-Invoke { "rm -f /var/cache/apt/archives/*.deb /var/cache/apt/archives/partial/*.deb /var/cache/apt/*.bin || true"; };' > /etc/apt/apt.conf.d/docker-clean \\ - && echo 'APT::Update::Post-Invoke { "rm -f /var/cache/apt/archives/*.deb /var/cache/apt/archives/partial/*.deb /var/cache/apt/*.bin || true"; };' >> /etc/apt/apt.conf.d/docker-clean \\ - && echo 'Dir::Cache::pkgcache ""; Dir::Cache::srcpkgcache "";' >> /etc/apt/apt.conf.d/docker-clean \\ - && echo 'Acquire::Languages "none";' > /etc/apt/apt.conf.d/docker-no-languages \\ - && echo 'Acquire::GzipIndexes "true"; Acquire::CompressionTypes::Order:: "gz";' > /etc/apt/apt.conf.d/docker-gzip-indexes + # a few minor docker-specific tweaks + # see https://github.com/docker/docker/blob/master/contrib/mkimage/debootstrap + RUN echo '#!/bin/sh' > /usr/sbin/policy-rc.d \\ + && echo 'exit 101' >> /usr/sbin/policy-rc.d \\ + && chmod +x /usr/sbin/policy-rc.d \\ + && dpkg-divert --local --rename --add /sbin/initctl \\ + && cp -a /usr/sbin/policy-rc.d /sbin/initctl \\ + && sed -i 's/^exit.*/exit 0/' /sbin/initctl \\ + && echo 'force-unsafe-io' > /etc/dpkg/dpkg.cfg.d/docker-apt-speedup \\ + && echo 'DPkg::Post-Invoke { "rm -f /var/cache/apt/archives/*.deb /var/cache/apt/archives/partial/*.deb /var/cache/apt/*.bin || true"; };' > /etc/apt/apt.conf.d/docker-clean \\ + && echo 'APT::Update::Post-Invoke { "rm -f /var/cache/apt/archives/*.deb /var/cache/apt/archives/partial/*.deb /var/cache/apt/*.bin || true"; };' >> /etc/apt/apt.conf.d/docker-clean \\ + && echo 'Dir::Cache::pkgcache ""; Dir::Cache::srcpkgcache "";' >> /etc/apt/apt.conf.d/docker-clean \\ + && echo 'Acquire::Languages "none";' > /etc/apt/apt.conf.d/docker-no-languages \\ + && echo 'Acquire::GzipIndexes "true"; Acquire::CompressionTypes::Order:: "gz";' > /etc/apt/apt.conf.d/docker-gzip-indexes - # enable the universe - RUN sed -i 's/^#\s*\(deb.*universe\)$/\1/g' /etc/apt/sources.list + # enable the universe + RUN sed -i 's/^#\s*\(deb.*universe\)$/\1/g' /etc/apt/sources.list - # overwrite this with 'CMD []' in a dependent Dockerfile - CMD ["/bin/bash"] + # overwrite this with 'CMD []' in a dependent Dockerfile + CMD ["/bin/bash"] EOF docker build -t "${DOCKER_REPO}:${TAG_ARCH}-${VERSION}" . diff --git a/utils/release/release_lib.sh b/utils/release/release_lib.sh index 2e700593523..569e1dfb9f2 100644 --- a/utils/release/release_lib.sh +++ b/utils/release/release_lib.sh @@ -12,10 +12,10 @@ function gen_version_string { function get_version { if [ -z "$VERSION_MAJOR" ] && [ -z "$VERSION_MINOR" ] && [ -z "$VERSION_PATCH" ]; then BASEDIR=$(dirname "${BASH_SOURCE[0]}")/../../ - VERSION_REVISION=`grep "set(VERSION_REVISION" ${BASEDIR}/cmake/version.cmake | sed 's/^.*VERSION_REVISION \(.*\)$/\1/' | sed 's/[) ].*//'` - VERSION_MAJOR=`grep "set(VERSION_MAJOR" ${BASEDIR}/cmake/version.cmake | sed 's/^.*VERSION_MAJOR \(.*\)/\1/' | sed 's/[) ].*//'` - VERSION_MINOR=`grep "set(VERSION_MINOR" ${BASEDIR}/cmake/version.cmake | sed 's/^.*VERSION_MINOR \(.*\)/\1/' | sed 's/[) ].*//'` - VERSION_PATCH=`grep "set(VERSION_PATCH" ${BASEDIR}/cmake/version.cmake | sed 's/^.*VERSION_PATCH \(.*\)/\1/' | sed 's/[) ].*//'` + VERSION_REVISION=`grep "SET(VERSION_REVISION" ${BASEDIR}/cmake/autogenerated_versions.txt | sed 's/^.*VERSION_REVISION \(.*\)$/\1/' | sed 's/[) ].*//'` + VERSION_MAJOR=`grep "SET(VERSION_MAJOR" ${BASEDIR}/cmake/autogenerated_versions.txt | sed 's/^.*VERSION_MAJOR \(.*\)/\1/' | sed 's/[) ].*//'` + VERSION_MINOR=`grep "SET(VERSION_MINOR" ${BASEDIR}/cmake/autogenerated_versions.txt | sed 's/^.*VERSION_MINOR \(.*\)/\1/' | sed 's/[) ].*//'` + VERSION_PATCH=`grep "SET(VERSION_PATCH" ${BASEDIR}/cmake/autogenerated_versions.txt | sed 's/^.*VERSION_PATCH \(.*\)/\1/' | sed 's/[) ].*//'` fi VERSION_PREFIX="${VERSION_PREFIX:-v}" VERSION_POSTFIX_TAG="${VERSION_POSTFIX:--testing}" @@ -90,28 +90,28 @@ function gen_revision_author { git_describe=`git describe` git_hash=`git rev-parse HEAD` - sed -i -e "s/set(VERSION_REVISION [^) ]*/set(VERSION_REVISION $VERSION_REVISION/g;" \ - -e "s/set(VERSION_DESCRIBE [^) ]*/set(VERSION_DESCRIBE $git_describe/g;" \ - -e "s/set(VERSION_GITHASH [^) ]*/set(VERSION_GITHASH $git_hash/g;" \ - -e "s/set(VERSION_MAJOR [^) ]*/set(VERSION_MAJOR $VERSION_MAJOR/g;" \ - -e "s/set(VERSION_MINOR [^) ]*/set(VERSION_MINOR $VERSION_MINOR/g;" \ - -e "s/set(VERSION_PATCH [^) ]*/set(VERSION_PATCH $VERSION_PATCH/g;" \ - -e "s/set(VERSION_STRING [^) ]*/set(VERSION_STRING $VERSION_STRING/g;" \ - cmake/version.cmake + sed -i -e "s/SET(VERSION_REVISION [^) ]*/SET(VERSION_REVISION $VERSION_REVISION/g;" \ + -e "s/SET(VERSION_DESCRIBE [^) ]*/SET(VERSION_DESCRIBE $git_describe/g;" \ + -e "s/SET(VERSION_GITHASH [^) ]*/SET(VERSION_GITHASH $git_hash/g;" \ + -e "s/SET(VERSION_MAJOR [^) ]*/SET(VERSION_MAJOR $VERSION_MAJOR/g;" \ + -e "s/SET(VERSION_MINOR [^) ]*/SET(VERSION_MINOR $VERSION_MINOR/g;" \ + -e "s/SET(VERSION_PATCH [^) ]*/SET(VERSION_PATCH $VERSION_PATCH/g;" \ + -e "s/SET(VERSION_STRING [^) ]*/SET(VERSION_STRING $VERSION_STRING/g;" \ + cmake/autogenerated_versions.txt gen_changelog "$VERSION_STRING" "" "$AUTHOR" "" gen_dockerfiles "$VERSION_STRING" src/Storages/System/StorageSystemContributors.sh ||: utils/list-versions/list-versions.sh > utils/list-versions/version_date.tsv - git commit -m "$auto_message [$VERSION_STRING] [$VERSION_REVISION]" cmake/version.cmake debian/changelog docker/*/Dockerfile src/Storages/System/StorageSystemContributors.generated.cpp utils/list-versions/version_date.tsv + git commit -m "$auto_message [$VERSION_STRING] [$VERSION_REVISION]" cmake/autogenerated_versions.txt debian/changelog docker/*/Dockerfile src/Storages/System/StorageSystemContributors.generated.cpp utils/list-versions/version_date.tsv if [ -z $NO_PUSH ]; then git push fi echo "Generated version: ${VERSION_STRING}, revision: ${VERSION_REVISION}." - # Second tag for correct version information in version.cmake inside tag + # Second tag for correct version information in autogenerated_versions.txt inside tag if git tag --force -a "$tag" -m "$tag" then if [ -z $NO_PUSH ]; then diff --git a/website/css/docs.css b/website/css/docs.css index 18bf40de13b..2c175b18db6 100644 --- a/website/css/docs.css +++ b/website/css/docs.css @@ -69,7 +69,6 @@ summary { #content code { color: #111; background: #eee; - padding: 2px; } diff --git a/website/templates/common_meta.html b/website/templates/common_meta.html index 8b65e67d780..84bd93d5175 100644 --- a/website/templates/common_meta.html +++ b/website/templates/common_meta.html @@ -22,6 +22,9 @@ +{% if config and (config.extra.single_page or config.extra.version_prefix) %} + +{% endif %} {% if config and page %} {% for code, name in config.extra.languages.items() %} diff --git a/website/templates/docs/amp.html b/website/templates/docs/amp.html index a60270d23d0..0cff614035f 100644 --- a/website/templates/docs/amp.html +++ b/website/templates/docs/amp.html @@ -7,6 +7,9 @@ {% include "templates/docs/ld_json.html" %} + {% if config.extra.single_page or config.extra.version_prefix %} + + {% endif %}