thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-23 08:02:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

merge master

Browse Source
This commit is contained in:
Ivan Blinkov 2020-06-24 00:18:16 +03:00
commit 45d1ca2567
478 changed files with 10647 additions and 4031 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -13,8 +13,3 @@ ClickHouse is an open-source column-oriented database management system that all
* [Yandex.Messenger channel](https://yandex.ru/chat/#/join/20e380d9-c7be-4123-ab06-e95fb946975e) shares announcements and useful links in Russian.
* [Contacts](https://clickhouse.tech/#contacts) can help to get your questions answered if there are any.
* You can also [fill this form](https://clickhouse.tech/#meet) to meet Yandex ClickHouse team in person.
## Upcoming Events
* [ClickHouse Workshop in Novosibirsk](https://2020.codefest.ru/lecture/1628) on TBD date.
* [Yandex C++ Open-Source Sprints in Moscow](https://events.yandex.ru/events/otkrytyj-kod-v-yandek-28-03-2020) on TBD date.

79
base/daemon/BaseDaemon.cpp
View File

@ -52,6 +52,7 @@
#include <Common/getMultipleKeysFromConfig.h>
#include <Common/ClickHouseRevision.h>
#include <Common/Config/ConfigProcessor.h>
#include <Common/SymbolIndex.h>
#if !defined(ARCADIA_BUILD)
# include <Common/config_version.h>
@ -85,7 +86,8 @@ static const size_t signal_pipe_buf_size =
+ sizeof(ucontext_t)
+ sizeof(StackTrace)
+ sizeof(UInt32)
+ max_query_id_size + 1; /// query_id + varint encoded length
+ max_query_id_size + 1 /// query_id + varint encoded length
+ sizeof(void*);
using signal_function = void(int, siginfo_t*, void*);
@ -135,6 +137,7 @@ static void signalHandler(int sig, siginfo_t * info, void * context)
DB::writePODBinary(stack_trace, out);
DB::writeBinary(UInt32(getThreadId()), out);
DB::writeStringBinary(query_id, out);
DB::writePODBinary(DB::current_thread, out);
out.next();
@ -218,16 +221,18 @@ public:
StackTrace stack_trace(NoCapture{});
UInt32 thread_num;
std::string query_id;
DB::ThreadStatus * thread_ptr{};
DB::readPODBinary(info, in);
DB::readPODBinary(context, in);
DB::readPODBinary(stack_trace, in);
DB::readBinary(thread_num, in);
DB::readBinary(query_id, in);
DB::readPODBinary(thread_ptr, in);
/// This allows to receive more signals if failure happens inside onFault function.
/// Example: segfault while symbolizing stack trace.
std::thread([=, this] { onFault(sig, info, context, stack_trace, thread_num, query_id); }).detach();
std::thread([=, this] { onFault(sig, info, context, stack_trace, thread_num, query_id, thread_ptr); }).detach();
}
}
}
@ -238,7 +243,8 @@ private:
void onTerminate(const std::string & message, UInt32 thread_num) const
{
LOG_FATAL(log, "(version {}{}) (from thread {}) {}", VERSION_STRING, VERSION_OFFICIAL, thread_num, message);
LOG_FATAL(log, "(version {}{}, {}) (from thread {}) {}",
VERSION_STRING, VERSION_OFFICIAL, daemon.build_id_info, thread_num, message);
}
void onFault(
@ -247,21 +253,30 @@ private:
const ucontext_t & context,
const StackTrace & stack_trace,
UInt32 thread_num,
const std::string & query_id) const
const std::string & query_id,
DB::ThreadStatus * thread_ptr) const
{
DB::ThreadStatus thread_status;
/// Send logs from this thread to client if possible.
/// It will allow client to see failure messages directly.
if (thread_ptr)
{
if (auto logs_queue = thread_ptr->getInternalTextLogsQueue())
DB::CurrentThread::attachInternalTextLogsQueue(logs_queue, DB::LogsLevel::trace);
}
LOG_FATAL(log, "########################################");
if (query_id.empty())
{
std::stringstream message;
message << "(version " << VERSION_STRING << VERSION_OFFICIAL << ")";
message << " (from thread " << thread_num << ")";
if (query_id.empty())
message << " (no query)";
else
message << " (query_id: " << query_id << ")";
message << " Received signal " << strsignal(sig) << " (" << sig << ").";
LOG_FATAL(log, message.str());
LOG_FATAL(log, "(version {}{}, {}) (from thread {}) (no query) Received signal {} ({})",
VERSION_STRING, VERSION_OFFICIAL, daemon.build_id_info, thread_num, strsignal(sig), sig);
}
else
{
LOG_FATAL(log, "(version {}{}, {}) (from thread {}) (query_id: {}) Received signal {} ({})",
VERSION_STRING, VERSION_OFFICIAL, daemon.build_id_info, thread_num, query_id, strsignal(sig), sig);
}
LOG_FATAL(log, signalToErrorMessage(sig, info, context));
@ -282,8 +297,13 @@ private:
/// Write symbolized stack trace line by line for better grep-ability.
stack_trace.toStringEveryLine([&](const std::string & s) { LOG_FATAL(log, s); });
/// Send crash report if configured
/// Send crash report to developers (if configured)
SentryWriter::onFault(sig, info, context, stack_trace);
/// When everything is done, we will try to send these error messages to client.
if (thread_ptr)
thread_ptr->onFatalError();
}
};
@ -297,17 +317,15 @@ static void sanitizerDeathCallback()
StringRef query_id = DB::CurrentThread::getQueryId(); /// This is signal safe.
if (query_id.size == 0)
{
std::stringstream message;
message << "(version " << VERSION_STRING << VERSION_OFFICIAL << ")";
message << " (from thread " << getThreadId() << ")";
if (query_id.size == 0)
message << " (no query)";
else
message << " (query_id: " << query_id << ")";
message << " Sanitizer trap.";
LOG_FATAL(log, message.str());
LOG_FATAL(log, "(version {}{}) (from thread {}) (no query) Sanitizer trap.",
VERSION_STRING, VERSION_OFFICIAL, getThreadId());
}
else
{
LOG_FATAL(log, "(version {}{}) (from thread {}) (query_id: {}) Sanitizer trap.",
VERSION_STRING, VERSION_OFFICIAL, getThreadId(), query_id);
}
/// Just in case print our own stack trace. In case when llvm-symbolizer does not work.
@ -717,12 +735,23 @@ void BaseDaemon::initializeTerminationAndSignalProcessing()
signal_listener = std::make_unique<SignalListener>(*this);
signal_listener_thread.start(*signal_listener);
#if defined(__ELF__) && !defined(__FreeBSD__)
String build_id_hex = DB::SymbolIndex::instance().getBuildIDHex();
if (build_id_hex.empty())
build_id_info = "no build id";
else
build_id_info = "build id: " + build_id_hex;
#else
build_id_info = "no build id";
#endif
}
void BaseDaemon::logRevision() const
{
Poco::Logger::root().information("Starting " + std::string{VERSION_FULL}
+ " with revision " + std::to_string(ClickHouseRevision::get())
+ ", " + build_id_info
+ ", PID " + std::to_string(getpid()));
}

2
base/daemon/BaseDaemon.h
View File

@ -198,6 +198,8 @@ protected:
std::string config_path;
DB::ConfigProcessor::LoadedConfig loaded_config;
Poco::Util::AbstractConfiguration * last_configuration = nullptr;
String build_id_info;
};

10
cmake/autogenerated_versions.txt
View File

@ -1,9 +1,9 @@
# This strings autochanged from release_lib.sh:
SET(VERSION_REVISION 54435)
SET(VERSION_REVISION 54436)
SET(VERSION_MAJOR 20)
SET(VERSION_MINOR 5)
SET(VERSION_MINOR 6)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 91df18a906dcffdbee6816e5389df6c65f86e35f)
SET(VERSION_DESCRIBE v20.5.1.1-prestable)
SET(VERSION_STRING 20.5.1.1)
SET(VERSION_GITHASH efc57fb063b3fb4df968d916720ec4d4ced4642e)
SET(VERSION_DESCRIBE v20.6.1.1-prestable)
SET(VERSION_STRING 20.6.1.1)
# end of autochange

2
cmake/linux/default_libs.cmake
View File

@ -18,7 +18,7 @@ message(STATUS "Default libraries: ${DEFAULT_LIBS}")
set(CMAKE_CXX_STANDARD_LIBRARIES ${DEFAULT_LIBS})
set(CMAKE_C_STANDARD_LIBRARIES ${DEFAULT_LIBS})
# glibc-compatibility library relies to fixed version of libc headers
# glibc-compatibility library relies to constant version of libc headers
# (because minor changes in function attributes between different glibc versions will introduce incompatibilities)
# This is for x86_64. For other architectures we have separate toolchains.
if (ARCH_AMD64 AND NOT_UNBUNDLED)

56
contrib/jemalloc-cmake/CMakeLists.txt
View File

@ -1,23 +1,31 @@
option (ENABLE_JEMALLOC "Enable jemalloc allocator" ${ENABLE_LIBRARIES})
if (SANITIZE OR NOT OS_LINUX OR NOT (ARCH_AMD64 OR ARCH_ARM))
if (SANITIZE OR NOT (ARCH_AMD64 OR ARCH_ARM) OR NOT (OS_LINUX OR OS_FREEBSD))
set (ENABLE_JEMALLOC OFF)
message (STATUS "jemalloc is disabled implicitly: it doesn't work with sanitizers and can only be used on Linux with x86_64 or aarch64.")
message (STATUS "jemalloc is disabled implicitly: it doesn't work with sanitizers and can only be used with x86_64 or aarch64 on linux or freebsd.")
endif ()
if (ENABLE_JEMALLOC)
if (NOT OS_LINUX)
message (WARNING "jemalloc support on non-linux is EXPERIMENTAL")
endif()
option (USE_INTERNAL_JEMALLOC "Use internal jemalloc library" ${NOT_UNBUNDLED})
if (USE_INTERNAL_JEMALLOC)
# ThreadPool select job randomly, and there can be some threads that had been
# performed some memory heavy task before and will be inactive for some time,
# but until it will became active again, the memory will not be freed since by
# default each thread has it's own arena, but there should be not more then
# 4*CPU arenas (see opt.nareans description).
#
# 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,oversize_threshold:0")
if (OS_LINUX)
# ThreadPool select job randomly, and there can be some threads that had been
# performed some memory heavy task before and will be inactive for some time,
# but until it will became active again, the memory will not be freed since by
# default each thread has it's own arena, but there should be not more then
# 4*CPU arenas (see opt.nareans description).
#
# 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,oversize_threshold:0")
else()
set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0")
endif()
# 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" )
@ -71,14 +79,26 @@ if (ENABLE_JEMALLOC)
target_include_directories(jemalloc PRIVATE ${LIBRARY_DIR}/include)
target_include_directories(jemalloc SYSTEM PUBLIC include)
set(JEMALLOC_INCLUDE)
if (ARCH_AMD64)
set(JEMALLOC_INCLUDE_PREFIX include_linux_x86_64)
elseif (ARCH_ARM)
set(JEMALLOC_INCLUDE_PREFIX include_linux_aarch64)
set (JEMALLOC_INCLUDE_PREFIX)
# OS_
if (OS_LINUX)
set (JEMALLOC_INCLUDE_PREFIX "include_linux")
elseif (OS_FREEBSD)
set (JEMALLOC_INCLUDE_PREFIX "include_freebsd")
elseif (OS_DARWIN)
set (JEMALLOC_INCLUDE_PREFIX "include_darwin")
else ()
message (FATAL_ERROR "This OS is not supported")
endif ()
target_include_directories(jemalloc SYSTEM PUBLIC
${JEMALLOC_INCLUDE_PREFIX})
# ARCH_
if (ARCH_AMD64)
set(JEMALLOC_INCLUDE_PREFIX "${JEMALLOC_INCLUDE_PREFIX}_x86_64")
elseif (ARCH_ARM)
set(JEMALLOC_INCLUDE_PREFIX "${JEMALLOC_INCLUDE_PREFIX}_aarch64")
else ()
message (FATAL_ERROR "This arch is not supported")
endif ()
configure_file(${JEMALLOC_INCLUDE_PREFIX}/jemalloc/internal/jemalloc_internal_defs.h.in
${JEMALLOC_INCLUDE_PREFIX}/jemalloc/internal/jemalloc_internal_defs.h)
target_include_directories(jemalloc SYSTEM PRIVATE

0
contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h → contrib/jemalloc-cmake/include/jemalloc/internal/jemalloc_preamble.h
View File

10
contrib/jemalloc-cmake/include/jemalloc/jemalloc_protos.h
View File

@ -1,3 +1,13 @@
// OSX does not have this for system alloc functions, so you will get
// "exception specification in declaration" error.
#if defined(__APPLE__) || defined(__FreeBSD__)
# undef JEMALLOC_NOTHROW
# define JEMALLOC_NOTHROW
# undef JEMALLOC_CXX_THROW
# define JEMALLOC_CXX_THROW
#endif
/*
* The je_ prefix on the following public symbol declarations is an artifact
* of namespace management, and should be omitted in application code unless

372
contrib/jemalloc-cmake/include_darwin_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in Normal file
View File

@ -0,0 +1,372 @@
/* 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_
/*
* 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
* multiple allocators simultaneously.
*/
#define JEMALLOC_PREFIX "je_"
#define JEMALLOC_CPREFIX "JE_"
/*
* Define overrides for non-standard allocator-related functions if they are
* present on the system.
*/
/* #undef JEMALLOC_OVERRIDE___LIBC_CALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_FREE */
/* #undef JEMALLOC_OVERRIDE___LIBC_MALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_MEMALIGN */
/* #undef JEMALLOC_OVERRIDE___LIBC_REALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_VALLOC */
/* #undef JEMALLOC_OVERRIDE___POSIX_MEMALIGN */
/*
* JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs.
* For shared libraries, symbol visibility mechanisms prevent these symbols
* from being exported, but for static libraries, naming collisions are a real
* possibility.
*/
#define JEMALLOC_PRIVATE_NAMESPACE je_
/*
* Hyper-threaded CPUs may need a special instruction inside spin loops in
* order to yield to another virtual CPU.
*/
#define CPU_SPINWAIT
/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */
#define HAVE_CPU_SPINWAIT 0
/*
* Number of significant bits in virtual addresses. This may be less than the
* total number of bits in a pointer, e.g. on x64, for which the uppermost 16
* bits are the same as bit 47.
*/
#define LG_VADDR 48
/* Defined if C11 atomics are available. */
#define JEMALLOC_C11_ATOMICS 1
/* 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
/* and the 8-bit variant support. */
#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1
/*
* Defined if __builtin_clz() and __builtin_clzl() are available.
*/
#define JEMALLOC_HAVE_BUILTIN_CLZ
/*
* Defined if os_unfair_lock_*() functions are available, as provided by Darwin.
*/
#define JEMALLOC_OS_UNFAIR_LOCK
/* Defined if syscall(2) is usable. */
/* #undef JEMALLOC_USE_SYSCALL */
/*
* Defined if secure_getenv(3) is available.
*/
/* #undef JEMALLOC_HAVE_SECURE_GETENV */
/*
* Defined if issetugid(2) is available.
*/
#define JEMALLOC_HAVE_ISSETUGID
/* Defined if pthread_atfork(3) is available. */
#define JEMALLOC_HAVE_PTHREAD_ATFORK
/* Defined if pthread_setname_np(3) is available. */
/* #undef JEMALLOC_HAVE_PTHREAD_SETNAME_NP */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC */
/*
* Defined if mach_absolute_time() is available.
*/
#define JEMALLOC_HAVE_MACH_ABSOLUTE_TIME 1
/*
* Defined if clock_gettime(CLOCK_REALTIME, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_REALTIME 1
/*
* Defined if _malloc_thread_cleanup() exists. At least in the case of
* FreeBSD, pthread_key_create() allocates, which if used during malloc
* bootstrapping will cause recursion into the pthreads library. Therefore, if
* _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in
* malloc_tsd.
*/
/* #undef JEMALLOC_MALLOC_THREAD_CLEANUP */
/*
* Defined if threaded initialization is known to be safe on this platform.
* Among other things, it must be possible to initialize a mutex without
* triggering allocation in order for threaded allocation to be safe.
*/
/* #undef JEMALLOC_THREADED_INIT */
/*
* Defined if the pthreads implementation defines
* _pthread_mutex_init_calloc_cb(), in which case the function is used in order
* to avoid recursive allocation during mutex initialization.
*/
/* #undef JEMALLOC_MUTEX_INIT_CB */
/* Non-empty if the tls_model attribute is supported. */
#define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec")))
/*
* JEMALLOC_DEBUG enables assertions and other sanity checks, and disables
* inline functions.
*/
/* #undef JEMALLOC_DEBUG */
/* 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 */
/* Use libunwind for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBUNWIND */
/* Use libgcc for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBGCC */
/* Use gcc intrinsics for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_GCC */
/*
* JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage
* segment (DSS).
*/
/* #undef JEMALLOC_DSS */
/* Support memory filling (junk/zero). */
#define JEMALLOC_FILL
/* Support utrace(2)-based tracing. */
/* #undef JEMALLOC_UTRACE */
/* Support optional abort() on OOM. */
/* #undef JEMALLOC_XMALLOC */
/* Support lazy locking (avoid locking unless a second thread is launched). */
/* #undef JEMALLOC_LAZY_LOCK */
/*
* Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
* classes).
*/
/* #undef LG_QUANTUM */
/* One page is 2^LG_PAGE bytes. */
#define LG_PAGE 16
/*
* One huge page is 2^LG_HUGEPAGE bytes. Note that this is defined even if the
* system does not explicitly support huge pages; system calls that require
* explicit huge page support are separately configured.
*/
#define LG_HUGEPAGE 29
/*
* If defined, adjacent virtual memory mappings with identical attributes
* automatically coalesce, and they fragment when changes are made to subranges.
* This is the normal order of things for mmap()/munmap(), but on Windows
* VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e.
* mappings do *not* coalesce/fragment.
*/
#define JEMALLOC_MAPS_COALESCE
/*
* If defined, retain memory for later reuse by default rather than using e.g.
* munmap() to unmap freed extents. This is enabled on 64-bit Linux because
* common sequences of mmap()/munmap() calls will cause virtual memory map
* holes.
*/
/* #undef JEMALLOC_RETAIN */
/* TLS is used to map arenas and magazine caches to threads. */
/* #undef JEMALLOC_TLS */
/*
* Used to mark unreachable code to quiet "end of non-void" compiler warnings.
* Don't use this directly; instead use unreachable() from util.h
*/
#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable
/*
* ffs*() functions to use for bitmapping. Don't use these directly; instead,
* use ffs_*() from util.h.
*/
#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll
#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.
*/
#define JEMALLOC_CACHE_OBLIVIOUS
/*
* If defined, enable logging facilities. We make this a configure option to
* avoid taking extra branches everywhere.
*/
/* #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.
*/
#define JEMALLOC_ZONE
/*
* Methods for determining whether the OS overcommits.
* JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's
* /proc/sys/vm.overcommit_memory file.
* JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl.
*/
/* #undef JEMALLOC_SYSCTL_VM_OVERCOMMIT */
/* #undef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY */
/* Defined if madvise(2) is available. */
#define JEMALLOC_HAVE_MADVISE
/*
* Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
* arguments to madvise(2).
*/
/* #undef JEMALLOC_HAVE_MADVISE_HUGE */
/*
* Methods for purging unused pages differ between operating systems.
*
* madvise(..., MADV_FREE) : This marks pages as being unused, such that they
* will be discarded rather than swapped out.
* madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is
* defined, this immediately discards pages,
* such that new pages will be demand-zeroed if
* the address region is later touched;
* otherwise this behaves similarly to
* MADV_FREE, though typically with higher
* system overhead.
*/
#define JEMALLOC_PURGE_MADVISE_FREE
#define JEMALLOC_PURGE_MADVISE_DONTNEED
/* #undef JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS */
/* Defined if madvise(2) is available but MADV_FREE is not (x86 Linux only). */
/* #undef JEMALLOC_DEFINE_MADVISE_FREE */
/*
* Defined if MADV_DO[NT]DUMP is supported as an argument to madvise.
*/
/* #undef JEMALLOC_MADVISE_DONTDUMP */
/*
* Defined if transparent huge pages (THPs) are supported via the
* MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled.
*/
/* #undef JEMALLOC_THP */
/* Define if operating system has alloca.h header. */
/* #undef JEMALLOC_HAS_ALLOCA_H */
/* C99 restrict keyword supported. */
#define JEMALLOC_HAS_RESTRICT 1
/* For use by hash code. */
/* #undef JEMALLOC_BIG_ENDIAN */
/* sizeof(int) == 2^LG_SIZEOF_INT. */
#define LG_SIZEOF_INT 2
/* sizeof(long) == 2^LG_SIZEOF_LONG. */
#define LG_SIZEOF_LONG 3
/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */
#define LG_SIZEOF_LONG_LONG 3
/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */
#define LG_SIZEOF_INTMAX_T 3
/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */
/* #undef JEMALLOC_GLIBC_MALLOC_HOOK */
/* glibc memalign hook. */
/* #undef JEMALLOC_GLIBC_MEMALIGN_HOOK */
/* pthread support */
#define JEMALLOC_HAVE_PTHREAD
/* dlsym() support */
#define JEMALLOC_HAVE_DLSYM
/* Adaptive mutex support in pthreads. */
/* #undef JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP */
/* GNU specific sched_getcpu support */
/* #undef JEMALLOC_HAVE_SCHED_GETCPU */
/* GNU specific sched_setaffinity support */
/* #undef JEMALLOC_HAVE_SCHED_SETAFFINITY */
/*
* If defined, all the features necessary for background threads are present.
*/
/* #undef JEMALLOC_BACKGROUND_THREAD */
/*
* If defined, jemalloc symbols are not exported (doesn't work when
* JEMALLOC_PREFIX is not defined).
*/
/* #undef JEMALLOC_EXPORT */
/* config.malloc_conf options string. */
#define JEMALLOC_CONFIG_MALLOC_CONF "@JEMALLOC_CONFIG_MALLOC_CONF@"
/* If defined, jemalloc takes the malloc/free/etc. symbol names. */
/* #undef JEMALLOC_IS_MALLOC */
/*
* Defined if strerror_r returns char * if _GNU_SOURCE is defined.
*/
/* #undef JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE */
/* Performs additional safety checks when defined. */
/* #undef JEMALLOC_OPT_SAFETY_CHECKS */
#endif /* JEMALLOC_INTERNAL_DEFS_H_ */

372
contrib/jemalloc-cmake/include_darwin_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in Normal file
View File

@ -0,0 +1,372 @@
/* 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_
/*
* 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
* multiple allocators simultaneously.
*/
#define JEMALLOC_PREFIX "je_"
#define JEMALLOC_CPREFIX "JE_"
/*
* Define overrides for non-standard allocator-related functions if they are
* present on the system.
*/
/* #undef JEMALLOC_OVERRIDE___LIBC_CALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_FREE */
/* #undef JEMALLOC_OVERRIDE___LIBC_MALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_MEMALIGN */
/* #undef JEMALLOC_OVERRIDE___LIBC_REALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_VALLOC */
/* #undef JEMALLOC_OVERRIDE___POSIX_MEMALIGN */
/*
* JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs.
* For shared libraries, symbol visibility mechanisms prevent these symbols
* from being exported, but for static libraries, naming collisions are a real
* possibility.
*/
#define JEMALLOC_PRIVATE_NAMESPACE je_
/*
* Hyper-threaded CPUs may need a special instruction inside spin loops in
* order to yield to another virtual CPU.
*/
#define CPU_SPINWAIT __asm__ volatile("pause")
/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */
#define HAVE_CPU_SPINWAIT 1
/*
* Number of significant bits in virtual addresses. This may be less than the
* total number of bits in a pointer, e.g. on x64, for which the uppermost 16
* bits are the same as bit 47.
*/
#define LG_VADDR 48
/* Defined if C11 atomics are available. */
#define JEMALLOC_C11_ATOMICS 1
/* 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
/* and the 8-bit variant support. */
#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1
/*
* Defined if __builtin_clz() and __builtin_clzl() are available.
*/
#define JEMALLOC_HAVE_BUILTIN_CLZ
/*
* Defined if os_unfair_lock_*() functions are available, as provided by Darwin.
*/
#define JEMALLOC_OS_UNFAIR_LOCK
/* Defined if syscall(2) is usable. */
/* #undef JEMALLOC_USE_SYSCALL */
/*
* Defined if secure_getenv(3) is available.
*/
/* #undef JEMALLOC_HAVE_SECURE_GETENV */
/*
* Defined if issetugid(2) is available.
*/
#define JEMALLOC_HAVE_ISSETUGID
/* Defined if pthread_atfork(3) is available. */
#define JEMALLOC_HAVE_PTHREAD_ATFORK
/* Defined if pthread_setname_np(3) is available. */
/* #undef JEMALLOC_HAVE_PTHREAD_SETNAME_NP */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC */
/*
* Defined if mach_absolute_time() is available.
*/
#define JEMALLOC_HAVE_MACH_ABSOLUTE_TIME 1
/*
* Defined if clock_gettime(CLOCK_REALTIME, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_REALTIME 1
/*
* Defined if _malloc_thread_cleanup() exists. At least in the case of
* FreeBSD, pthread_key_create() allocates, which if used during malloc
* bootstrapping will cause recursion into the pthreads library. Therefore, if
* _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in
* malloc_tsd.
*/
/* #undef JEMALLOC_MALLOC_THREAD_CLEANUP */
/*
* Defined if threaded initialization is known to be safe on this platform.
* Among other things, it must be possible to initialize a mutex without
* triggering allocation in order for threaded allocation to be safe.
*/
/* #undef JEMALLOC_THREADED_INIT */
/*
* Defined if the pthreads implementation defines
* _pthread_mutex_init_calloc_cb(), in which case the function is used in order
* to avoid recursive allocation during mutex initialization.
*/
/* #undef JEMALLOC_MUTEX_INIT_CB */
/* Non-empty if the tls_model attribute is supported. */
#define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec")))
/*
* JEMALLOC_DEBUG enables assertions and other sanity checks, and disables
* inline functions.
*/
/* #undef JEMALLOC_DEBUG */
/* 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 */
/* Use libunwind for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBUNWIND */
/* Use libgcc for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBGCC */
/* Use gcc intrinsics for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_GCC */
/*
* JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage
* segment (DSS).
*/
/* #undef JEMALLOC_DSS */
/* Support memory filling (junk/zero). */
#define JEMALLOC_FILL
/* Support utrace(2)-based tracing. */
/* #undef JEMALLOC_UTRACE */
/* Support optional abort() on OOM. */
/* #undef JEMALLOC_XMALLOC */
/* Support lazy locking (avoid locking unless a second thread is launched). */
/* #undef JEMALLOC_LAZY_LOCK */
/*
* Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
* classes).
*/
/* #undef LG_QUANTUM */
/* One page is 2^LG_PAGE bytes. */
#define LG_PAGE 12
/*
* One huge page is 2^LG_HUGEPAGE bytes. Note that this is defined even if the
* system does not explicitly support huge pages; system calls that require
* explicit huge page support are separately configured.
*/
#define LG_HUGEPAGE 21
/*
* If defined, adjacent virtual memory mappings with identical attributes
* automatically coalesce, and they fragment when changes are made to subranges.
* This is the normal order of things for mmap()/munmap(), but on Windows
* VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e.
* mappings do *not* coalesce/fragment.
*/
#define JEMALLOC_MAPS_COALESCE
/*
* If defined, retain memory for later reuse by default rather than using e.g.
* munmap() to unmap freed extents. This is enabled on 64-bit Linux because
* common sequences of mmap()/munmap() calls will cause virtual memory map
* holes.
*/
/* #undef JEMALLOC_RETAIN */
/* TLS is used to map arenas and magazine caches to threads. */
/* #undef JEMALLOC_TLS */
/*
* Used to mark unreachable code to quiet "end of non-void" compiler warnings.
* Don't use this directly; instead use unreachable() from util.h
*/
#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable
/*
* ffs*() functions to use for bitmapping. Don't use these directly; instead,
* use ffs_*() from util.h.
*/
#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll
#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.
*/
#define JEMALLOC_CACHE_OBLIVIOUS
/*
* If defined, enable logging facilities. We make this a configure option to
* avoid taking extra branches everywhere.
*/
/* #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.
*/
#define JEMALLOC_ZONE
/*
* Methods for determining whether the OS overcommits.
* JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's
* /proc/sys/vm.overcommit_memory file.
* JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl.
*/
/* #undef JEMALLOC_SYSCTL_VM_OVERCOMMIT */
/* #undef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY */
/* Defined if madvise(2) is available. */
#define JEMALLOC_HAVE_MADVISE
/*
* Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
* arguments to madvise(2).
*/
/* #undef JEMALLOC_HAVE_MADVISE_HUGE */
/*
* Methods for purging unused pages differ between operating systems.
*
* madvise(..., MADV_FREE) : This marks pages as being unused, such that they
* will be discarded rather than swapped out.
* madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is
* defined, this immediately discards pages,
* such that new pages will be demand-zeroed if
* the address region is later touched;
* otherwise this behaves similarly to
* MADV_FREE, though typically with higher
* system overhead.
*/
#define JEMALLOC_PURGE_MADVISE_FREE
#define JEMALLOC_PURGE_MADVISE_DONTNEED
/* #undef JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS */
/* Defined if madvise(2) is available but MADV_FREE is not (x86 Linux only). */
/* #undef JEMALLOC_DEFINE_MADVISE_FREE */
/*
* Defined if MADV_DO[NT]DUMP is supported as an argument to madvise.
*/
/* #undef JEMALLOC_MADVISE_DONTDUMP */
/*
* Defined if transparent huge pages (THPs) are supported via the
* MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled.
*/
/* #undef JEMALLOC_THP */
/* Define if operating system has alloca.h header. */
/* #undef JEMALLOC_HAS_ALLOCA_H */
/* C99 restrict keyword supported. */
#define JEMALLOC_HAS_RESTRICT 1
/* For use by hash code. */
/* #undef JEMALLOC_BIG_ENDIAN */
/* sizeof(int) == 2^LG_SIZEOF_INT. */
#define LG_SIZEOF_INT 2
/* sizeof(long) == 2^LG_SIZEOF_LONG. */
#define LG_SIZEOF_LONG 3
/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */
#define LG_SIZEOF_LONG_LONG 3
/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */
#define LG_SIZEOF_INTMAX_T 3
/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */
/* #undef JEMALLOC_GLIBC_MALLOC_HOOK */
/* glibc memalign hook. */
/* #undef JEMALLOC_GLIBC_MEMALIGN_HOOK */
/* pthread support */
#define JEMALLOC_HAVE_PTHREAD
/* dlsym() support */
#define JEMALLOC_HAVE_DLSYM
/* Adaptive mutex support in pthreads. */
/* #undef JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP */
/* GNU specific sched_getcpu support */
/* #undef JEMALLOC_HAVE_SCHED_GETCPU */
/* GNU specific sched_setaffinity support */
/* #undef JEMALLOC_HAVE_SCHED_SETAFFINITY */
/*
* If defined, all the features necessary for background threads are present.
*/
/* #undef JEMALLOC_BACKGROUND_THREAD */
/*
* If defined, jemalloc symbols are not exported (doesn't work when
* JEMALLOC_PREFIX is not defined).
*/
/* #undef JEMALLOC_EXPORT */
/* config.malloc_conf options string. */
#define JEMALLOC_CONFIG_MALLOC_CONF "@JEMALLOC_CONFIG_MALLOC_CONF@"
/* If defined, jemalloc takes the malloc/free/etc. symbol names. */
/* #undef JEMALLOC_IS_MALLOC */
/*
* Defined if strerror_r returns char * if _GNU_SOURCE is defined.
*/
/* #undef JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE */
/* Performs additional safety checks when defined. */
/* #undef JEMALLOC_OPT_SAFETY_CHECKS */
#endif /* JEMALLOC_INTERNAL_DEFS_H_ */

373
contrib/jemalloc-cmake/include_freebsd_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in Normal file
View File

@ -0,0 +1,373 @@
/* 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_
/*
* 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
* multiple allocators simultaneously.
*/
/* #undef JEMALLOC_PREFIX */
/* #undef JEMALLOC_CPREFIX */
/*
* Define overrides for non-standard allocator-related functions if they are
* present on the system.
*/
/* #undef JEMALLOC_OVERRIDE___LIBC_CALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_FREE */
/* #undef JEMALLOC_OVERRIDE___LIBC_MALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_MEMALIGN */
/* #undef JEMALLOC_OVERRIDE___LIBC_REALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_VALLOC */
#define JEMALLOC_OVERRIDE___POSIX_MEMALIGN
/*
* JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs.
* For shared libraries, symbol visibility mechanisms prevent these symbols
* from being exported, but for static libraries, naming collisions are a real
* possibility.
*/
#define JEMALLOC_PRIVATE_NAMESPACE je_
/*
* Hyper-threaded CPUs may need a special instruction inside spin loops in
* order to yield to another virtual CPU.
*/
#define CPU_SPINWAIT
/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */
#define HAVE_CPU_SPINWAIT 0
/*
* Number of significant bits in virtual addresses. This may be less than the
* total number of bits in a pointer, e.g. on x64, for which the uppermost 16
* bits are the same as bit 47.
*/
#define LG_VADDR 48
/* Defined if C11 atomics are available. */
#define JEMALLOC_C11_ATOMICS 1
/* 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
/* and the 8-bit variant support. */
#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1
/*
* Defined if __builtin_clz() and __builtin_clzl() are available.
*/
#define JEMALLOC_HAVE_BUILTIN_CLZ
/*
* Defined if os_unfair_lock_*() functions are available, as provided by Darwin.
*/
/* #undef JEMALLOC_OS_UNFAIR_LOCK */
/* Defined if syscall(2) is usable. */
#define JEMALLOC_USE_SYSCALL
/*
* Defined if secure_getenv(3) is available.
*/
/* #undef JEMALLOC_HAVE_SECURE_GETENV */
/*
* Defined if issetugid(2) is available.
*/
#define JEMALLOC_HAVE_ISSETUGID
/* Defined if pthread_atfork(3) is available. */
#define JEMALLOC_HAVE_PTHREAD_ATFORK
/* Defined if pthread_setname_np(3) is available. */
// Only since 12.1-STABLE
// #define JEMALLOC_HAVE_PTHREAD_SETNAME_NP
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC 1
/*
* Defined if mach_absolute_time() is available.
*/
/* #undef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME */
/*
* Defined if clock_gettime(CLOCK_REALTIME, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_REALTIME 1
/*
* Defined if _malloc_thread_cleanup() exists. At least in the case of
* FreeBSD, pthread_key_create() allocates, which if used during malloc
* bootstrapping will cause recursion into the pthreads library. Therefore, if
* _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in
* malloc_tsd.
*/
#define JEMALLOC_MALLOC_THREAD_CLEANUP
/*
* Defined if threaded initialization is known to be safe on this platform.
* Among other things, it must be possible to initialize a mutex without
* triggering allocation in order for threaded allocation to be safe.
*/
/* #undef JEMALLOC_THREADED_INIT */
/*
* Defined if the pthreads implementation defines
* _pthread_mutex_init_calloc_cb(), in which case the function is used in order
* to avoid recursive allocation during mutex initialization.
*/
#define JEMALLOC_MUTEX_INIT_CB 1
/* Non-empty if the tls_model attribute is supported. */
#define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec")))
/*
* JEMALLOC_DEBUG enables assertions and other sanity checks, and disables
* inline functions.
*/
/* #undef JEMALLOC_DEBUG */
/* 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 */
/* Use libunwind for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBUNWIND */
/* Use libgcc for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBGCC */
/* Use gcc intrinsics for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_GCC */
/*
* JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage
* segment (DSS).
*/
#define JEMALLOC_DSS
/* Support memory filling (junk/zero). */
#define JEMALLOC_FILL
/* Support utrace(2)-based tracing. */
/* #undef JEMALLOC_UTRACE */
/* Support optional abort() on OOM. */
/* #undef JEMALLOC_XMALLOC */
/* Support lazy locking (avoid locking unless a second thread is launched). */
#define JEMALLOC_LAZY_LOCK
/*
* Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
* classes).
*/
/* #undef LG_QUANTUM */
/* One page is 2^LG_PAGE bytes. */
#define LG_PAGE 16
/*
* One huge page is 2^LG_HUGEPAGE bytes. Note that this is defined even if the
* system does not explicitly support huge pages; system calls that require
* explicit huge page support are separately configured.
*/
#define LG_HUGEPAGE 29
/*
* If defined, adjacent virtual memory mappings with identical attributes
* automatically coalesce, and they fragment when changes are made to subranges.
* This is the normal order of things for mmap()/munmap(), but on Windows
* VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e.
* mappings do *not* coalesce/fragment.
*/
#define JEMALLOC_MAPS_COALESCE
/*
* If defined, retain memory for later reuse by default rather than using e.g.
* munmap() to unmap freed extents. This is enabled on 64-bit Linux because
* common sequences of mmap()/munmap() calls will cause virtual memory map
* holes.
*/
/* #undef JEMALLOC_RETAIN */
/* TLS is used to map arenas and magazine caches to threads. */
#define JEMALLOC_TLS
/*
* Used to mark unreachable code to quiet "end of non-void" compiler warnings.
* Don't use this directly; instead use unreachable() from util.h
*/
#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable
/*
* ffs*() functions to use for bitmapping. Don't use these directly; instead,
* use ffs_*() from util.h.
*/
#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll
#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.
*/
#define JEMALLOC_CACHE_OBLIVIOUS
/*
* If defined, enable logging facilities. We make this a configure option to
* avoid taking extra branches everywhere.
*/
/* #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.
*/
/* #undef JEMALLOC_ZONE */
/*
* Methods for determining whether the OS overcommits.
* JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's
* /proc/sys/vm.overcommit_memory file.
* JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl.
*/
#define JEMALLOC_SYSCTL_VM_OVERCOMMIT
/* #undef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY */
/* Defined if madvise(2) is available. */
#define JEMALLOC_HAVE_MADVISE
/*
* Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
* arguments to madvise(2).
*/
/* #undef JEMALLOC_HAVE_MADVISE_HUGE */
/*
* Methods for purging unused pages differ between operating systems.
*
* madvise(..., MADV_FREE) : This marks pages as being unused, such that they
* will be discarded rather than swapped out.
* madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is
* defined, this immediately discards pages,
* such that new pages will be demand-zeroed if
* the address region is later touched;
* otherwise this behaves similarly to
* MADV_FREE, though typically with higher
* system overhead.
*/
#define JEMALLOC_PURGE_MADVISE_FREE
#define JEMALLOC_PURGE_MADVISE_DONTNEED
/* #undef JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS */
/* Defined if madvise(2) is available but MADV_FREE is not (x86 Linux only). */
/* #undef JEMALLOC_DEFINE_MADVISE_FREE */
/*
* Defined if MADV_DO[NT]DUMP is supported as an argument to madvise.
*/
/* #undef JEMALLOC_MADVISE_DONTDUMP */
/*
* Defined if transparent huge pages (THPs) are supported via the
* MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled.
*/
/* #undef JEMALLOC_THP */
/* Define if operating system has alloca.h header. */
/* #undef JEMALLOC_HAS_ALLOCA_H */
/* C99 restrict keyword supported. */
#define JEMALLOC_HAS_RESTRICT 1
/* For use by hash code. */
/* #undef JEMALLOC_BIG_ENDIAN */
/* sizeof(int) == 2^LG_SIZEOF_INT. */
#define LG_SIZEOF_INT 2
/* sizeof(long) == 2^LG_SIZEOF_LONG. */
#define LG_SIZEOF_LONG 3
/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */
#define LG_SIZEOF_LONG_LONG 3
/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */
#define LG_SIZEOF_INTMAX_T 3
/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */
/* #undef JEMALLOC_GLIBC_MALLOC_HOOK */
/* glibc memalign hook. */
/* #undef JEMALLOC_GLIBC_MEMALIGN_HOOK */
/* pthread support */
#define JEMALLOC_HAVE_PTHREAD
/* dlsym() support */
#define JEMALLOC_HAVE_DLSYM
/* Adaptive mutex support in pthreads. */
#define JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP
/* GNU specific sched_getcpu support */
/* #undef JEMALLOC_HAVE_SCHED_GETCPU */
/* GNU specific sched_setaffinity support */
/* #undef JEMALLOC_HAVE_SCHED_SETAFFINITY */
/*
* If defined, all the features necessary for background threads are present.
*/
#define JEMALLOC_BACKGROUND_THREAD 1
/*
* If defined, jemalloc symbols are not exported (doesn't work when
* JEMALLOC_PREFIX is not defined).
*/
/* #undef JEMALLOC_EXPORT */
/* config.malloc_conf options string. */
#define JEMALLOC_CONFIG_MALLOC_CONF "@JEMALLOC_CONFIG_MALLOC_CONF@"
/* If defined, jemalloc takes the malloc/free/etc. symbol names. */
#define JEMALLOC_IS_MALLOC 1
/*
* Defined if strerror_r returns char * if _GNU_SOURCE is defined.
*/
/* #undef JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE */
/* Performs additional safety checks when defined. */
/* #undef JEMALLOC_OPT_SAFETY_CHECKS */
#endif /* JEMALLOC_INTERNAL_DEFS_H_ */

373
contrib/jemalloc-cmake/include_freebsd_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in Normal file
View File

@ -0,0 +1,373 @@
/* 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_
/*
* 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
* multiple allocators simultaneously.
*/
/* #undef JEMALLOC_PREFIX */
/* #undef JEMALLOC_CPREFIX */
/*
* Define overrides for non-standard allocator-related functions if they are
* present on the system.
*/
/* #undef JEMALLOC_OVERRIDE___LIBC_CALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_FREE */
/* #undef JEMALLOC_OVERRIDE___LIBC_MALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_MEMALIGN */
/* #undef JEMALLOC_OVERRIDE___LIBC_REALLOC */
/* #undef JEMALLOC_OVERRIDE___LIBC_VALLOC */
#define JEMALLOC_OVERRIDE___POSIX_MEMALIGN
/*
* JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs.
* For shared libraries, symbol visibility mechanisms prevent these symbols
* from being exported, but for static libraries, naming collisions are a real
* possibility.
*/
#define JEMALLOC_PRIVATE_NAMESPACE je_
/*
* Hyper-threaded CPUs may need a special instruction inside spin loops in
* order to yield to another virtual CPU.
*/
#define CPU_SPINWAIT __asm__ volatile("pause")
/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */
#define HAVE_CPU_SPINWAIT 1
/*
* Number of significant bits in virtual addresses. This may be less than the
* total number of bits in a pointer, e.g. on x64, for which the uppermost 16
* bits are the same as bit 47.
*/
#define LG_VADDR 48
/* Defined if C11 atomics are available. */
#define JEMALLOC_C11_ATOMICS 1
/* 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
/* and the 8-bit variant support. */
#define JEMALLOC_GCC_U8_SYNC_ATOMICS 1
/*
* Defined if __builtin_clz() and __builtin_clzl() are available.
*/
#define JEMALLOC_HAVE_BUILTIN_CLZ
/*
* Defined if os_unfair_lock_*() functions are available, as provided by Darwin.
*/
/* #undef JEMALLOC_OS_UNFAIR_LOCK */
/* Defined if syscall(2) is usable. */
#define JEMALLOC_USE_SYSCALL
/*
* Defined if secure_getenv(3) is available.
*/
/* #undef JEMALLOC_HAVE_SECURE_GETENV */
/*
* Defined if issetugid(2) is available.
*/
#define JEMALLOC_HAVE_ISSETUGID
/* Defined if pthread_atfork(3) is available. */
#define JEMALLOC_HAVE_PTHREAD_ATFORK
/* Defined if pthread_setname_np(3) is available. */
// Only since 12.1-STABLE
// #define JEMALLOC_HAVE_PTHREAD_SETNAME_NP
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC 1
/*
* Defined if mach_absolute_time() is available.
*/
/* #undef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME */
/*
* Defined if clock_gettime(CLOCK_REALTIME, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_REALTIME 1
/*
* Defined if _malloc_thread_cleanup() exists. At least in the case of
* FreeBSD, pthread_key_create() allocates, which if used during malloc
* bootstrapping will cause recursion into the pthreads library. Therefore, if
* _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in
* malloc_tsd.
*/
#define JEMALLOC_MALLOC_THREAD_CLEANUP
/*
* Defined if threaded initialization is known to be safe on this platform.
* Among other things, it must be possible to initialize a mutex without
* triggering allocation in order for threaded allocation to be safe.
*/
/* #undef JEMALLOC_THREADED_INIT */
/*
* Defined if the pthreads implementation defines
* _pthread_mutex_init_calloc_cb(), in which case the function is used in order
* to avoid recursive allocation during mutex initialization.
*/
#define JEMALLOC_MUTEX_INIT_CB 1
/* Non-empty if the tls_model attribute is supported. */
#define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec")))
/*
* JEMALLOC_DEBUG enables assertions and other sanity checks, and disables
* inline functions.
*/
/* #undef JEMALLOC_DEBUG */
/* 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 */
/* Use libunwind for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBUNWIND */
/* Use libgcc for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_LIBGCC */
/* Use gcc intrinsics for profile backtracing if defined. */
/* #undef JEMALLOC_PROF_GCC */
/*
* JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage
* segment (DSS).
*/
#define JEMALLOC_DSS
/* Support memory filling (junk/zero). */
#define JEMALLOC_FILL
/* Support utrace(2)-based tracing. */
/* #undef JEMALLOC_UTRACE */
/* Support optional abort() on OOM. */
/* #undef JEMALLOC_XMALLOC */
/* Support lazy locking (avoid locking unless a second thread is launched). */
#define JEMALLOC_LAZY_LOCK
/*
* Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
* classes).
*/
/* #undef LG_QUANTUM */
/* One page is 2^LG_PAGE bytes. */
#define LG_PAGE 12
/*
* One huge page is 2^LG_HUGEPAGE bytes. Note that this is defined even if the
* system does not explicitly support huge pages; system calls that require
* explicit huge page support are separately configured.
*/
#define LG_HUGEPAGE 21
/*
* If defined, adjacent virtual memory mappings with identical attributes
* automatically coalesce, and they fragment when changes are made to subranges.
* This is the normal order of things for mmap()/munmap(), but on Windows
* VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e.
* mappings do *not* coalesce/fragment.
*/
#define JEMALLOC_MAPS_COALESCE
/*
* If defined, retain memory for later reuse by default rather than using e.g.
* munmap() to unmap freed extents. This is enabled on 64-bit Linux because
* common sequences of mmap()/munmap() calls will cause virtual memory map
* holes.
*/
/* #undef JEMALLOC_RETAIN */
/* TLS is used to map arenas and magazine caches to threads. */
#define JEMALLOC_TLS
/*
* Used to mark unreachable code to quiet "end of non-void" compiler warnings.
* Don't use this directly; instead use unreachable() from util.h
*/
#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable
/*
* ffs*() functions to use for bitmapping. Don't use these directly; instead,
* use ffs_*() from util.h.
*/
#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll
#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.
*/
#define JEMALLOC_CACHE_OBLIVIOUS
/*
* If defined, enable logging facilities. We make this a configure option to
* avoid taking extra branches everywhere.
*/
/* #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.
*/
/* #undef JEMALLOC_ZONE */
/*
* Methods for determining whether the OS overcommits.
* JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's
* /proc/sys/vm.overcommit_memory file.
* JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl.
*/
#define JEMALLOC_SYSCTL_VM_OVERCOMMIT
/* #undef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY */
/* Defined if madvise(2) is available. */
#define JEMALLOC_HAVE_MADVISE
/*
* Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
* arguments to madvise(2).
*/
/* #undef JEMALLOC_HAVE_MADVISE_HUGE */
/*
* Methods for purging unused pages differ between operating systems.
*
* madvise(..., MADV_FREE) : This marks pages as being unused, such that they
* will be discarded rather than swapped out.
* madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is
* defined, this immediately discards pages,
* such that new pages will be demand-zeroed if
* the address region is later touched;
* otherwise this behaves similarly to
* MADV_FREE, though typically with higher
* system overhead.
*/
#define JEMALLOC_PURGE_MADVISE_FREE
#define JEMALLOC_PURGE_MADVISE_DONTNEED
/* #undef JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS */
/* Defined if madvise(2) is available but MADV_FREE is not (x86 Linux only). */
/* #undef JEMALLOC_DEFINE_MADVISE_FREE */
/*
* Defined if MADV_DO[NT]DUMP is supported as an argument to madvise.
*/
/* #undef JEMALLOC_MADVISE_DONTDUMP */
/*
* Defined if transparent huge pages (THPs) are supported via the
* MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled.
*/
/* #undef JEMALLOC_THP */
/* Define if operating system has alloca.h header. */
/* #undef JEMALLOC_HAS_ALLOCA_H */
/* C99 restrict keyword supported. */
#define JEMALLOC_HAS_RESTRICT 1
/* For use by hash code. */
/* #undef JEMALLOC_BIG_ENDIAN */
/* sizeof(int) == 2^LG_SIZEOF_INT. */
#define LG_SIZEOF_INT 2
/* sizeof(long) == 2^LG_SIZEOF_LONG. */
#define LG_SIZEOF_LONG 3
/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */
#define LG_SIZEOF_LONG_LONG 3
/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */
#define LG_SIZEOF_INTMAX_T 3
/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */
/* #undef JEMALLOC_GLIBC_MALLOC_HOOK */
/* glibc memalign hook. */
/* #undef JEMALLOC_GLIBC_MEMALIGN_HOOK */
/* pthread support */
#define JEMALLOC_HAVE_PTHREAD
/* dlsym() support */
#define JEMALLOC_HAVE_DLSYM
/* Adaptive mutex support in pthreads. */
#define JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP
/* GNU specific sched_getcpu support */
/* #undef JEMALLOC_HAVE_SCHED_GETCPU */
/* GNU specific sched_setaffinity support */
/* #undef JEMALLOC_HAVE_SCHED_SETAFFINITY */
/*
* If defined, all the features necessary for background threads are present.
*/
#define JEMALLOC_BACKGROUND_THREAD 1
/*
* If defined, jemalloc symbols are not exported (doesn't work when
* JEMALLOC_PREFIX is not defined).
*/
/* #undef JEMALLOC_EXPORT */
/* config.malloc_conf options string. */
#define JEMALLOC_CONFIG_MALLOC_CONF "@JEMALLOC_CONFIG_MALLOC_CONF@"
/* If defined, jemalloc takes the malloc/free/etc. symbol names. */
#define JEMALLOC_IS_MALLOC 1
/*
* Defined if strerror_r returns char * if _GNU_SOURCE is defined.
*/
/* #undef JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE */
/* Performs additional safety checks when defined. */
/* #undef JEMALLOC_OPT_SAFETY_CHECKS */
#endif /* JEMALLOC_INTERNAL_DEFS_H_ */

2
contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -35,7 +35,7 @@
*/
#define CPU_SPINWAIT
/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */
#define HAVE_CPU_SPINWAIT 9
#define HAVE_CPU_SPINWAIT 0
/*
* Number of significant bits in virtual addresses. This may be less than the

213
contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_preamble.h
View File

@ -1,213 +0,0 @@
#ifndef JEMALLOC_PREAMBLE_H
#define JEMALLOC_PREAMBLE_H
#include "jemalloc_internal_defs.h"
#include "jemalloc/internal/jemalloc_internal_decls.h"
#ifdef JEMALLOC_UTRACE
#include <sys/ktrace.h>
#endif
#define JEMALLOC_NO_DEMANGLE
#ifdef JEMALLOC_JET
# undef JEMALLOC_IS_MALLOC
# define JEMALLOC_N(n) jet_##n
# include "jemalloc/internal/public_namespace.h"
# define JEMALLOC_NO_RENAME
# include "jemalloc/jemalloc.h"
# undef JEMALLOC_NO_RENAME
#else
# define JEMALLOC_N(n) je_##n
# include "jemalloc/jemalloc.h"
#endif
#if defined(JEMALLOC_OSATOMIC)
#include <libkern/OSAtomic.h>
#endif
#ifdef JEMALLOC_ZONE
#include <mach/mach_error.h>
#include <mach/mach_init.h>
#include <mach/vm_map.h>
#endif
#include "jemalloc/internal/jemalloc_internal_macros.h"
/*
* Note that the ordering matters here; the hook itself is name-mangled. We
* want the inclusion of hooks to happen early, so that we hook as much as
* possible.
*/
#ifndef JEMALLOC_NO_PRIVATE_NAMESPACE
# ifndef JEMALLOC_JET
# include "jemalloc/internal/private_namespace.h"
# else
# include "jemalloc/internal/private_namespace_jet.h"
# endif
#endif
#include "jemalloc/internal/test_hooks.h"
#ifdef JEMALLOC_DEFINE_MADVISE_FREE
# define JEMALLOC_MADV_FREE 8
#endif
static const bool config_debug =
#ifdef JEMALLOC_DEBUG
true
#else
false
#endif
;
static const bool have_dss =
#ifdef JEMALLOC_DSS
true
#else
false
#endif
;
static const bool have_madvise_huge =
#ifdef JEMALLOC_HAVE_MADVISE_HUGE
true
#else
false
#endif
;
static const bool config_fill =
#ifdef JEMALLOC_FILL
true
#else
false
#endif
;
static const bool config_lazy_lock =
#ifdef JEMALLOC_LAZY_LOCK
true
#else
false
#endif
;
static const char * const config_malloc_conf = JEMALLOC_CONFIG_MALLOC_CONF;
static const bool config_prof =
#ifdef JEMALLOC_PROF
true
#else
false
#endif
;
static const bool config_prof_libgcc =
#ifdef JEMALLOC_PROF_LIBGCC
true
#else
false
#endif
;
static const bool config_prof_libunwind =
#ifdef JEMALLOC_PROF_LIBUNWIND
true
#else
false
#endif
;
static const bool maps_coalesce =
#ifdef JEMALLOC_MAPS_COALESCE
true
#else
false
#endif
;
static const bool config_stats =
#ifdef JEMALLOC_STATS
true
#else
false
#endif
;
static const bool config_tls =
#ifdef JEMALLOC_TLS
true
#else
false
#endif
;
static const bool config_utrace =
#ifdef JEMALLOC_UTRACE
true
#else
false
#endif
;
static const bool config_xmalloc =
#ifdef JEMALLOC_XMALLOC
true
#else
false
#endif
;
static const bool config_cache_oblivious =
#ifdef JEMALLOC_CACHE_OBLIVIOUS
true
#else
false
#endif
;
/*
* Undocumented, for jemalloc development use only at the moment. See the note
* in jemalloc/internal/log.h.
*/
static const bool config_log =
#ifdef JEMALLOC_LOG
true
#else
false
#endif
;
/*
* 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
static const bool have_percpu_arena =
#ifdef JEMALLOC_PERCPU_ARENA
true
#else
false
#endif
;
/*
* Undocumented, and not recommended; the application should take full
* responsibility for tracking provenance.
*/
static const bool force_ivsalloc =
#ifdef JEMALLOC_FORCE_IVSALLOC
true
#else
false
#endif
;
static const bool have_background_thread =
#ifdef JEMALLOC_BACKGROUND_THREAD
true
#else
false
#endif
;
#endif /* JEMALLOC_PREAMBLE_H */

4
debian/changelog vendored
View File

@ -1,5 +1,5 @@
clickhouse (20.5.1.1) unstable; urgency=low
clickhouse (20.6.1.1) unstable; urgency=low
* Modified source code
-- clickhouse-release <clickhouse-release@yandex-team.ru> Tue, 28 Apr 2020 20:12:13 +0300
-- clickhouse-release <clickhouse-release@yandex-team.ru> Mon, 22 Jun 2020 20:40:23 +0300

2
docker/client/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.5.1.*
ARG version=20.6.1.*
RUN apt-get update \
&& apt-get install --yes --no-install-recommends \

2
docker/server/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.5.1.*
ARG version=20.6.1.*
ARG gosu_ver=1.10
RUN apt-get update \

2
docker/test/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.5.1.*
ARG version=20.6.1.*
RUN apt-get update && \
apt-get install -y apt-transport-https dirmngr && \

4
docker/test/integration/compose/docker_compose_postgres.yml
View File

@ -7,3 +7,7 @@ services:
POSTGRES_PASSWORD: mysecretpassword
ports:
- 5432:5432
networks:
default:
aliases:
- postgre-sql.local

7
docs/en/engines/index.md
View File

@ -5,4 +5,11 @@ toc_priority: 25
toc_title: hidden
---
# ClickHouse Engines
There are two key engine kinds in ClickHouse:
- [Table engines](table-engines/index.md)
- [Database engines](database-engines/index.md)
{## [Original article](https://clickhouse.tech/docs/en/engines/) ##}

4
docs/en/engines/table-engines/index.md
View File

@ -19,7 +19,7 @@ The table engine (type of table) determines:
### MergeTree {#mergetree}
The most universal and functional table engines for high-load tasks. The property shared by these engines is quick data insertion with subsequent background data processing. `MergeTree` family engines support data replication (with [Replicated\*](../../engines/table-engines/mergetree-family/replication.md#table_engines-replication) versions of engines), partitioning, and other features not supported in other engines.
The most universal and functional table engines for high-load tasks. The property shared by these engines is quick data insertion with subsequent background data processing. `MergeTree` family engines support data replication (with [Replicated\*](../../engines/table-engines/mergetree-family/replication.md#table_engines-replication) versions of engines), partitioning, secondary data-skipping indexes, and other features not supported in other engines.
Engines in the family:
@ -80,4 +80,4 @@ To select data from a virtual column, you must specify its name in the `SELECT`
If you create a table with a column that has the same name as one of the table virtual columns, the virtual column becomes inaccessible. We don’t recommend doing this. To help avoid conflicts, virtual column names are usually prefixed with an underscore.
[Original article](https://clickhouse.tech/docs/en/operations/table_engines/) <!--hide-->
[Original article](https://clickhouse.tech/docs/en/engines/table-engines/) <!--hide-->

58
docs/en/faq/general.md
View File

@ -1,58 +0,0 @@
---
toc_priority: 78
toc_title: General Questions
---
# General Questions {#general-questions}
## Why Not Use Something Like MapReduce? {#why-not-use-something-like-mapreduce}
We can refer to systems like MapReduce as distributed computing systems in which the reduce operation is based on distributed sorting. The most common open-source solution in this class is [Apache Hadoop](http://hadoop.apache.org). Yandex uses its in-house solution, YT.
These systems aren’t appropriate for online queries due to their high latency. In other words, they can’t be used as the back-end for a web interface. These types of systems aren’t useful for real-time data updates. Distributed sorting isn’t the best way to perform reduce operations if the result of the operation and all the intermediate results (if there are any) are located in the RAM of a single server, which is usually the case for online queries. In such a case, a hash table is an optimal way to perform reduce operations. A common approach to optimizing map-reduce tasks is pre-aggregation (partial reduce) using a hash table in RAM. The user performs this optimization manually. Distributed sorting is one of the main causes of reduced performance when running simple map-reduce tasks.
Most MapReduce implementations allow you to execute arbitrary code on a cluster. But a declarative query language is better suited to OLAP to run experiments quickly. For example, Hadoop has Hive and Pig. Also consider Cloudera Impala or Shark (outdated) for Spark, as well as Spark SQL, Presto, and Apache Drill. Performance when running such tasks is highly sub-optimal compared to specialized systems, but relatively high latency makes it unrealistic to use these systems as the backend for a web interface.
## What If I Have a Problem with Encodings When Using Oracle Through ODBC? {#oracle-odbc-encodings}
If you use Oracle through the ODBC driver as a source of external dictionaries, you need to set the correct value for the `NLS_LANG` environment variable in `/etc/default/clickhouse`. For more information, see the [Oracle NLS\_LANG FAQ](https://www.oracle.com/technetwork/products/globalization/nls-lang-099431.html).
**Example**
``` sql
NLS_LANG=RUSSIAN_RUSSIA.UTF8
```
## How Do I Export Data from ClickHouse to a File? {#how-to-export-to-file}
### Using INTO OUTFILE Clause {#using-into-outfile-clause}
Add an [INTO OUTFILE](../sql-reference/statements/select/into-outfile.md#into-outfile-clause) clause to your query.
For example:
``` sql
SELECT * FROM table INTO OUTFILE 'file'
```
By default, ClickHouse uses the [TabSeparated](../interfaces/formats.md#tabseparated) format for output data. To select the [data format](../interfaces/formats.md), use the [FORMAT clause](../sql-reference/statements/select/format.md#format-clause).
For example:
``` sql
SELECT * FROM table INTO OUTFILE 'file' FORMAT CSV
```
### Using a File-Engine Table {#using-a-file-engine-table}
See [File](../engines/table-engines/special/file.md).
### Using Command-Line Redirection {#using-command-line-redirection}
``` sql
$ clickhouse-client --query "SELECT * from table" --format FormatName > result.txt
```
See [clickhouse-client](../interfaces/cli.md).
{## [Original article](https://clickhouse.tech/docs/en/faq/general/) ##}

11
docs/en/faq/general/dbms-naming.md Normal file
View File

@ -0,0 +1,11 @@
---
toc_hidden: true
toc_priority: 10
---
# What Does “ClickHouse” Mean? {#what-does-clickhouse-mean}
It’s a combination of “**Click**stream” and “Data ware**house**”. It comes from the original use case at Yandex.Metrica, where ClickHouse was supposed to keep records of all clicks by people from all over the Internet and it still does the job. You can read more about this use case on [ClickHouse history](../../introduction/history.md) page.
!!! info "Fun fact"
Many years after ClickHouse got its name, this approach of combining two words that are meaningful on their own has been highlighted as the best way to name a database in a [research by Andy Pavlo](https://www.cs.cmu.edu/~pavlo/blog/2020/03/on-naming-a-database-management-system.html), an Associate Professor of Databases at Carnegie Mellon University. ClickHouse shared his “best database name of all time” award with Postgres.

18
docs/en/faq/general/index.md Normal file
View File

@ -0,0 +1,18 @@
---
toc_hidden_folder: true
toc_priority: 1
toc_title: General
---
# General Questions About ClickHouse {#general-questions}
Questions:
- [What does “ClickHouse” mean?](../../faq/general/dbms-naming.md)
- [What does “Не тормозит” mean?](../../faq/general/ne-tormozit.md)
- [Why not use something like MapReduce?](../../faq/general/mapreduce.md)
!!! info "Don’t see what you were looking for?"
Check out [other F.A.Q. categories](../../faq/index.md) or browse around main documentation articles found in the left sidebar.
{## [Original article](https://clickhouse.tech/docs/en/faq/general/) ##}

12
docs/en/faq/general/mapreduce.md Normal file
View File

@ -0,0 +1,12 @@
---
toc_hidden: true
toc_priority: 20
---
# Why Not Use Something Like MapReduce? {#why-not-use-something-like-mapreduce}
We can refer to systems like MapReduce as distributed computing systems in which the reduce operation is based on distributed sorting. The most common open-source solution in this class is [Apache Hadoop](http://hadoop.apache.org). Yandex uses its in-house solution, YT.
These systems aren’t appropriate for online queries due to their high latency. In other words, they can’t be used as the back-end for a web interface. These types of systems aren’t useful for real-time data updates. Distributed sorting isn’t the best way to perform reduce operations if the result of the operation and all the intermediate results (if there are any) are located in the RAM of a single server, which is usually the case for online queries. In such a case, a hash table is an optimal way to perform reduce operations. A common approach to optimizing map-reduce tasks is pre-aggregation (partial reduce) using a hash table in RAM. The user performs this optimization manually. Distributed sorting is one of the main causes of reduced performance when running simple map-reduce tasks.
Most MapReduce implementations allow you to execute arbitrary code on a cluster. But a declarative query language is better suited to OLAP to run experiments quickly. For example, Hadoop has Hive and Pig. Also consider Cloudera Impala or Shark (outdated) for Spark, as well as Spark SQL, Presto, and Apache Drill. Performance when running such tasks is highly sub-optimal compared to specialized systems, but relatively high latency makes it unrealistic to use these systems as the backend for a web interface.

24
docs/en/faq/general/ne-tormozit.md Normal file
View File

@ -0,0 +1,24 @@
---
toc_hidden: true
toc_priority: 11
---
# What Does “Не тормозит” mean? {#what-does-ne-tormozit-mean}
This question usually arises when people see official ClickHouse t-shirts. They have large words **“ClickHouse не тормозит”** on the front.
Before ClickHouse became open-source, it has been developed as an in-house storage system by the largest Russian IT company, [Yandex](https://yandex.com/company/). That’s why it initially got its slogan in Russian, which is “не тормозит”. After the open-source release we first produced some of those t-shirts for events in Russia and it was a no-brainer to use the slogan as-is.
One of the following batches of those t-shirts was supposed to be given away on events outside of Russia and we tried to make the English version of the slogan. Unfortunately, the Russian language is kind of elegant in terms of expressing stuff and there was a restriction of limited space on a t-shirt, so we failed to come up with good enough translation (most options appeared to be either long or inaccurate) and decided to keep the slogan in Russian even on t-shirts produced for international events. It appeared to be a great decision because people all over the world get positively surprised and curious when they see it.
So, what does it mean? Here are some ways to translate *“не тормозит”*:
- If you translate it literally, it’d be something like *“ClickHouse doesn’t press the brake pedal”*.
- If you’d want to express it as close to how it sounds to a Russian person with IT background, it’d be something like *“If you larger system lags, it’s not because it uses ClickHouse”*.
- Shorter, but not so precise versions could be *“ClickHouse is not slow”*, *“ClickHouse doesn’t lag”* or just *“ClickHouse is fast”*.
If you haven’t seen one of those t-shirts in person, you can check them out online in many ClickHouse-related videos. For example, this one:
![iframe](https://www.youtube.com/embed/bSyQahMVZ7w)
P.S. These t-shirts are not for sale, they are given away for free on most [ClickHouse Meetups](https://clickhouse.tech/#meet), usually for best questions or other forms of active participation.

11
docs/en/faq/index.md
View File

@ -2,7 +2,16 @@
toc_folder_title: F.A.Q.
toc_hidden: true
toc_priority: 76
toc_title: hidden
---
# ClickHouse F.A.Q {#clickhouse-f-a-q}
This section of the documentation is a place to collect answers to ClickHouse-related questions that arise often.
Categories:
- [General](../faq/general/index.md)
- [Operations](../faq/operations/index.md)
- [Integration](../faq/integration/index.md)
{## [Original article](https://clickhouse.tech/docs/en/faq) ##}

36
docs/en/faq/integration/file-export.md Normal file
View File

@ -0,0 +1,36 @@
---
toc_hidden: true
toc_priority: 10
---
# How Do I Export Data from ClickHouse to a File? {#how-to-export-to-file}
## Using INTO OUTFILE Clause {#using-into-outfile-clause}
Add an [INTO OUTFILE](../../sql-reference/statements/select/into-outfile.md#into-outfile-clause) clause to your query.
For example:
``` sql
SELECT * FROM table INTO OUTFILE 'file'
```
By default, ClickHouse uses the [TabSeparated](../../interfaces/formats.md#tabseparated) format for output data. To select the [data format](../../interfaces/formats.md), use the [FORMAT clause](../../sql-reference/statements/select/format.md#format-clause).
For example:
``` sql
SELECT * FROM table INTO OUTFILE 'file' FORMAT CSV
```
## Using a File-Engine Table {#using-a-file-engine-table}
See [File](../../engines/table-engines/special/file.md) table engine.
## Using Command-Line Redirection {#using-command-line-redirection}
``` sql
$ clickhouse-client --query "SELECT * from table" --format FormatName > result.txt
```
See [clickhouse-client](../../interfaces/cli.md).

17
docs/en/faq/integration/index.md Normal file
View File

@ -0,0 +1,17 @@
---
toc_hidden_folder: true
toc_priority: 3
toc_title: Integration
---
# Question About Integrating ClickHouse and Other Systems {#question-about-integrating-clickhouse-and-other-systems}
Questions:
- [How do I export data from ClickHouse to a file?](../../faq/integration/file-export.md)
- [What if I Have a problem with encodings when connecting to Oracle via ODBC?](../../faq/integration/oracle-odbc.md)
!!! info "Don’t see what you were looking for?"
Check out [other F.A.Q. categories](../../faq/index.md) or browse around main documentation articles found in the left sidebar.
{## [Original article](https://clickhouse.tech/docs/en/faq/integration/) ##}

14
docs/en/faq/integration/oracle-odbc.md Normal file
View File

@ -0,0 +1,14 @@
---
toc_hidden: true
toc_priority: 20
---
# What If I Have a Problem with Encodings When Using Oracle Via ODBC? {#oracle-odbc-encodings}
If you use Oracle as a source of ClickHouse external dictionaries via Oracle ODBC driver, you need to set the correct value for the `NLS_LANG` environment variable in `/etc/default/clickhouse`. For more information, see the [Oracle NLS\_LANG FAQ](https://www.oracle.com/technetwork/products/globalization/nls-lang-099431.html).
**Example**
``` sql
NLS_LANG=RUSSIAN_RUSSIA.UTF8
```

16
docs/en/faq/operations/index.md Normal file
View File

@ -0,0 +1,16 @@
---
toc_hidden_folder: true
toc_priority: 2
toc_title: Operations
---
# Question About Operating ClickHouse Servers and Clusters {#question-about-operating-clickhouse-servers-and-clusters}
Questions:
- [Which ClickHouse version to use in production?](../../faq/operations/production.md)
!!! info "Don’t see what you were looking for?"
Check out [other F.A.Q. categories](../../faq/index.md) or browse around main documentation articles found in the left sidebar.
{## [Original article](https://clickhouse.tech/docs/en/faq/production/) ##}

69
docs/en/faq/operations/production.md Normal file
View File

@ -0,0 +1,69 @@
---
toc_hidden: true
toc_priority: 10
---
# Which ClickHouse Version to Use in Production? {#which-clickhouse-version-to-use-in-production}
First of all, let’s discuss why people ask this question in the first place. There are two key reasons:
1. ClickHouse is developed with pretty high velocity and usually, there are 10+ stable releases per year. It makes a wide range of releases to choose from, which is not so trivial choice.
2. Some users want to avoid spending time figuring out which version works best for their use case and just follow someone else’s advice.
The second reason is more fundamental, so we’ll start with it and then get back to navigating through various ClickHouse releases.
## Which ClickHouse Version Do You Recommend? {#which-clickhouse-version-do-you-recommend}
It’s tempting to hire consultants or trust some known experts to get rid of responsibility for your production environment. You install some specific ClickHouse version that someone else recommended, now if there’s some issue with it - it’s not your fault, it’s someone else’s. This line of reasoning is a big trap. No external person knows better what’s going on in your company’s production environment.
So how to properly choose which ClickHouse version to upgrade to? Or how to choose your first ClickHouse version? First of all, you need to invest in setting up a **realistic pre-production environment**. In an ideal world, it could be a completely identical shadow copy, but that’s usually expensive.
Here’re some key points to get reasonable fidelity in a pre-production environment with not so high costs:
- Pre-production environment needs to run an as close set of queries as you intend to run in production:
- Don’t make it read-only with some frozen data.
- Don’t make it write-only with just copying data without building some typical reports.
- Don’t wipe it clean instead of applying schema migrations.
- Use a sample of real production data and queries. Try to choose a sample that’s still representative and makes `SELECT` queries return reasonable results. Use obfuscation if your data is sensitive and internal policies don’t allow it to leave the production environment.
- Make sure that pre-production is covered by your monitoring and alerting software the same way as your production environment does.
- If your production spans across multiple datacenters or regions, make your pre-production does the same.
- If your production uses complex features like replication, distributed table, cascading materialize views, make sure they are configured similarly in pre-production.
- There’s a trade-off on using the roughly same number of servers or VMs in pre-production as in production, but of smaller size, or much less of them, but of the same size. The first option might catch extra network-related issues, while the latter is easier to manage.
The second area to invest in is **automated testing infrastructure**. Don’t assume that if some kind of query has executed successfully once, it’ll continue to do so forever. It’s ok to have some unit tests where ClickHouse is mocked but make sure your product has a reasonable set of automated tests that are run against real ClickHouse and check that all important use cases are still working as expected.
Extra step forward could be contributing those automated tests to [ClickHouse’s open-source test infrastructure](https://github.com/ClickHouse/ClickHouse/tree/master/tests) that’s continuously used in its day-to-day development. It definitely will take some additional time and effort to learn [how to run it](../../development/tests.md) and then how to adapt your tests to this framework, but it’ll pay off by ensuring that ClickHouse releases are already tested against them when they are announced stable, instead of repeatedly losing time on reporting the issue after the fact and then waiting for a bugfix to be implemented, backported and released. Some companies even have such test contributions to infrastructure by its use as an internal policy, most notably it’s called [Beyonce’s Rule](https://www.oreilly.com/library/view/software-engineering-at/9781492082781/ch01.html#policies_that_scale_well) at Google.
When you have your pre-production environment and testing infrastructure in place, choosing the best version is straightforward:
1. Routinely run your automated tests against new ClickHouse releases. You can do it even for ClickHouse releases that are marked as `testing`, but going forward to the next steps with them is not recommended.
2. Deploy the ClickHouse release that passed the tests to pre-production and check that all processes are running as expected.
3. Report any issues you discovered to [ClickHouse GitHub Issues](https://github.com/ClickHouse/ClickHouse/issues).
4. If there were no major issues, it should be safe to start deploying ClickHouse release to your production environment. Investing in gradual release automation that implements an approach similar to [canary releases](https://martinfowler.com/bliki/CanaryRelease.html) or [green-blue deployments](https://martinfowler.com/bliki/BlueGreenDeployment.html) might further reduce the risk of issues in production.
As you might have noticed, there’s nothing specific to ClickHouse in the approach described above, people do that for any piece of infrastructure they rely on if they take their production environment seriously.
## How to Choose Between ClickHouse Releases? {#how-to-choose-between-clickhouse-releases}
If you look into contents of ClickHouse package repository, you’ll see four kinds of packages:
1. `testing`
2. `prestable`
3. `stable`
4. `lts` (long-term support)
As was mentioned earlier, `testing` is good mostly to notice issues early, running them in production is not recommended because each of them is not tested as thoroughly as other kinds of packages.
`prestable` is a release candidate which generally looks promising and is likely to become announced as `stable` soon. You can try them out in pre-production and report issues if you see any.
For production use, there are two key options: `stable` and `lts`. Here is some guidance on how to choose between them:
- `stable` is the kind of package we recommend by default. They are released roughly monthly (and thus provide new features with reasonable delay) and three latest stable releases are supported in terms of diagnostics and backporting of bugfixes.
- `lts` are released twice a year and are supported for a year after their initial release. You might prefer them over `stable` in the following cases:
- Your company has some internal policies that don’t allow for frequent upgrades or using non-LTS software.
- You are using ClickHouse in some secondary products that either doesn’t require any complex ClickHouse features and don’t have enough resources to keep it updated.
Many teams who initially thought that `lts` is the way to go, often switch to `stable` anyway because of some recent feature that’s important for their product.
!!! warning "Important"
One more thing to keep in mind when upgrading ClickHouse: we’re always keeping eye on compatibility across releases, but sometimes it’s not reasonable to keep and some minor details might change. So make sure you check the [changelog](../../whats-new/changelog/index.md) before upgrading to see if there are any notes about backward-incompatible changes.

12
docs/en/getting-started/install.md
View File

@ -94,6 +94,18 @@ For production environments, it’s recommended to use the latest `stable`-versi
To run ClickHouse inside Docker follow the guide on [Docker Hub](https://hub.docker.com/r/yandex/clickhouse-server/). Those images use official `deb` packages inside.
### From Precompiled Binaries for Non-Standard Environments {#from-binaries-non-linux}
For non-Linux operating systems and for AArch64 CPU arhitecture, ClickHouse builds are provided as a cross-compiled binary from the latest commit of the `master` branch (with a few hours delay).
- [macOS](https://builds.clickhouse.tech/master/macos/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/macos/clickhouse' && chmod a+x ./clickhouse`
- [FreeBSD](https://builds.clickhouse.tech/master/freebsd/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/freebsd/clickhouse' && chmod a+x ./clickhouse`
- [AArch64](https://builds.clickhouse.tech/master/aarch64/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/aarch64/clickhouse' && chmod a+x ./clickhouse`
After downloading, you can use the `clickhouse client` to connect to the server, or `clickhouse local` to process local data. To run `clickhouse server`, you have to additionally download [server](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/config.xml) and [users](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/users.xml) configuration files from GitHub.
These builds are not recommended for use in production environments because they are less thoroughly tested, but you can do so on your own risk. They also have only a subset of ClickHouse features available.
### From Sources {#from-sources}
To manually compile ClickHouse, follow the instructions for [Linux](../development/build.md) or [Mac OS X](../development/build-osx.md).

22
docs/en/operations/settings/settings.md
View File

@ -821,6 +821,10 @@ ClickHouse supports the following algorithms of choosing replicas:
- [First or random](#load_balancing-first_or_random)
- [Round robin](#load_balancing-round_robin)
See also:
- [distributed\_replica\_max\_ignored\_errors](#settings-distributed_replica_max_ignored_errors)
### Random (by Default) {#load_balancing-random}
``` sql
@ -1170,8 +1174,10 @@ Controls how fast errors in distributed tables are zeroed. If a replica is unava
See also:
- [load\_balancing](#load_balancing-round_robin)
- [Table engine Distributed](../../engines/table-engines/special/distributed.md)
- [distributed\_replica\_error\_cap](#settings-distributed_replica_error_cap)
- [distributed\_replica\_max\_ignored\_errors](#settings-distributed_replica_max_ignored_errors)
## distributed\_replica\_error\_cap {#settings-distributed_replica_error_cap}
@ -1182,8 +1188,24 @@ Error count of each replica is capped at this value, preventing a single replica
See also:
- [load\_balancing](#load_balancing-round_robin)
- [Table engine Distributed](../../engines/table-engines/special/distributed.md)
- [distributed\_replica\_error\_half\_life](#settings-distributed_replica_error_half_life)
- [distributed\_replica\_max\_ignored\_errors](#settings-distributed_replica_max_ignored_errors)
## distributed\_replica\_max\_ignored\_errors {#settings-distributed_replica_max_ignored_errors}
- Type: unsigned int
- Default value: 0
Number of errors that will be ignored while choosing replicas (according to `load_balancing` algorithm).
See also:
- [load\_balancing](#load_balancing-round_robin)
- [Table engine Distributed](../../engines/table-engines/special/distributed.md)
- [distributed\_replica\_error\_cap](#settings-distributed_replica_error_cap)
- [distributed\_replica\_error\_half\_life](#settings-distributed_replica_error_half_life)
## distributed\_directory\_monitor\_sleep\_time\_ms {#distributed_directory_monitor_sleep_time_ms}

1
docs/en/sql-reference/data-types/simpleaggregatefunction.md
View File

@ -9,6 +9,7 @@ The following aggregate functions are supported:
- [`min`](../../sql-reference/aggregate-functions/reference/min.md#agg_function-min)
- [`max`](../../sql-reference/aggregate-functions/reference/max.md#agg_function-max)
- [`sum`](../../sql-reference/aggregate-functions/reference/sum.md#agg_function-sum)
- [`sumWithOverflow`](../../sql-reference/aggregate-functions/reference/sumwithoverflow.md#sumwithoverflowx)
- [`groupBitAnd`](../../sql-reference/aggregate-functions/reference/groupbitand.md#groupbitand)
- [`groupBitOr`](../../sql-reference/aggregate-functions/reference/groupbitor.md#groupbitor)
- [`groupBitXor`](../../sql-reference/aggregate-functions/reference/groupbitxor.md#groupbitxor)

2
docs/en/sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md
View File

@ -206,7 +206,7 @@ Setting fields:
ClickHouse receives quoting symbols from ODBC-driver and quote all settings in queries to driver, so it’s necessary to set table name accordingly to table name case in database.
If you have a problems with encodings when using Oracle, see the corresponding [FAQ](../../../faq/general.md#oracle-odbc-encodings) article.
If you have a problems with encodings when using Oracle, see the corresponding [F.A.Q.](../../../faq/integration/oracle-odbc.md) item.
### Known Vulnerability of the ODBC Dictionary Functionality {#known-vulnerability-of-the-odbc-dictionary-functionality}

48
docs/en/sql-reference/functions/array-functions.md
View File

@ -176,6 +176,54 @@ hasAny(array1, array2)
`SELECT hasAll([[1, 2], [3, 4]], [[1, 2], [1, 2]])` returns `1`.
## hasSubstr {#hassubstr}
Checks whether all the elements of array2 appear in array1 in the same exact order. Therefore, the function will return 1, if and only if `array1 = prefix + array2 + suffix`.
``` sql
hasSubstr(array1, array2)
```
In other words, the functions will check whether all the elements of `array2` are contained in `array1` like
the `hasAll` function. In addition, it will check that the elements are observed in the same order in both `array1` and `array2`.
For Example:
- `hasSubstr([1,2,3,4], [2,3])` returns 1. However, `hasSubstr([1,2,3,4], [3,2])` will return `0`.
- `hasSubstr([1,2,3,4], [1,2,3])` returns 1. However, `hasSubstr([1,2,3,4], [1,2,4])` will return `0`.
**Parameters**
- `array1` – Array of any type with a set of elements.
- `array2` – Array of any type with a set of elements.
**Return values**
- `1`, if `array1` contains `array2`.
- `0`, otherwise.
**Peculiar properties**
- The function will return `1` if `array2` is empty.
- `Null` processed as a value. In other words `hasSubstr([1, 2, NULL, 3, 4], [2,3])` will return `0`. However, `hasSubstr([1, 2, NULL, 3, 4], [2,NULL,3])` will return `1`
- Order of values in both of arrays does matter.
**Examples**
`SELECT hasSubstr([], [])` returns 1.
`SELECT hasSubstr([1, Null], [Null])` returns 1.
`SELECT hasSubstr([1.0, 2, 3, 4], [1, 3])` returns 0.
`SELECT hasSubstr(['a', 'b'], ['a'])` returns 1.
`SELECT hasSubstr(['a', 'b' , 'c'], ['a', 'b'])` returns 1.
`SELECT hasSubstr(['a', 'b' , 'c'], ['a', 'c'])` returns 0.
`SELECT hasSubstr([[1, 2], [3, 4], [5, 6]], [[1, 2], [3, 4]])` returns 1.
## indexOf(arr, x) {#indexofarr-x}
Returns the index of the first ‘x’ element (starting from 1) if it is in the array, or 0 if it is not.

12
docs/ru/getting-started/install.md
View File

@ -82,6 +82,18 @@ sudo clickhouse-client-$LATEST_VERSION/install/doinst.sh
Для запуска ClickHouse в Docker нужно следовать инструкции на [Docker Hub](https://hub.docker.com/r/yandex/clickhouse-server/). Внутри образов используются официальные `deb` пакеты.
### Из исполняемых файлов для нестандартных окружений {#from-binaries-non-linux}
Для других операционных систем и арихитектуры AArch64, сборки ClickHouse предоставляются в виде кросс-компилированного бинарника с последнего коммита ветки master (с задержкой в несколько часов).
- [macOS](https://builds.clickhouse.tech/master/macos/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/macos/clickhouse' && chmod a+x ./clickhouse`
- [AArch64](https://builds.clickhouse.tech/master/aarch64/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/aarch64/clickhouse' && chmod a+x ./clickhouse`
- [FreeBSD](https://builds.clickhouse.tech/master/freebsd/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/freebsd/clickhouse' && chmod a+x ./clickhouse`
После скачивания, можно воспользоваться `clickhouse client` для подключения к серверу, или `clickhouse local` для обработки локальных данных. Для запуска `clickhouse server` необходимо скачать конфигурационные файлы [сервера](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/config.xml) и [пользователей](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/users.xml) с GitHub.
Данные сборки не рекомендуются для использования в продакшене, так как они недостаточно тщательно протестированны. Также, в них присутствуют не все возможности ClickHouse.
### Из исходного кода {#from-sources}
Для компиляции ClickHouse вручную, используйте инструкцию для [Linux](../development/build.md) или [Mac OS X](../development/build-osx.md).

2
docs/ru/interfaces/http.md
View File

@ -276,7 +276,7 @@ $ curl -sS 'http://localhost:8123/?max_result_bytes=4000000&buffer_size=3000000&
### Пример {#primer}
``` bash
$ curl -sS "<address>?param_id=2¶m_phrase=test" -d "SELECT * FROM table WHERE int_column = {id:UInt8} and string_column = {phrase:String}"
$ curl -sS "http://localhost:8123/?param_id=2&param_phrase=test" -d "SELECT * FROM table WHERE int_column = {id:UInt8} and string_column = {phrase:String}"
```
## Предопределенный HTTP интерфейс {#predefined_http_interface}

17
docs/tools/README.md
View File

@ -20,7 +20,18 @@ Usually those also have some way to preview how Markdown will look like, which a
It’ll take some effort to go through, but the result will be very close to production documentation.
For the first time you’ll need to install [wkhtmltopdf](https://wkhtmltopdf.org/) and set up virtualenv:
For the first time you’ll need to:
#### 1. Install [wkhtmltopdf](https://wkhtmltopdf.org/)
Follow the instructions on it's official website: <https://wkhtmltopdf.org/downloads.html>
#### 2. Install CLI tools from npm
1. `apt-get install npm` for Debian/Ubuntu or `brew install npm` on Mac OS X.
2. `npm install -g purifycss amphtml-validator`.
#### 3. Set up virtualenv
``` bash
$ cd ClickHouse/docs/tools
@ -30,7 +41,9 @@ $ source venv/bin/activate
$ pip3 install -r requirements.txt
```
Then running `build.py` without args (there are some, check `build.py --help`) will generate `ClickHouse/docs/build` folder with complete static html website.
#### 4. Run build.py
When all prerequisites are installed, running `build.py` without args (there are some, check `build.py --help`) will generate `ClickHouse/docs/build` folder with complete static html website.
The easiest way to see the result is to use `--livereload=8888` argument of build.py. Alternatively, you can manually launch a HTTP server to serve the docs, for example by running `cd ClickHouse/docs/build && python3 -m http.server 8888`. Then go to http://localhost:8888 in browser. Feel free to use any other port instead of 8888.

9
docs/tools/amp.py
View File

@ -85,6 +85,15 @@ def html_to_amp(content):
tag.attrs['width'] = '640'
if not tag.attrs.get('height'):
tag.attrs['height'] = '320'
if tag.name == 'iframe':
tag.name = 'amp-iframe'
tag.attrs['layout'] = 'responsive'
del tag.attrs['alt']
del tag.attrs['allowfullscreen']
if not tag.attrs.get('width'):
tag.attrs['width'] = '640'
if not tag.attrs.get('height'):
tag.attrs['height'] = '320'
elif tag.name == 'a':
href = tag.attrs.get('href')
if href:

7
docs/tools/nav.py
View File

@ -1,5 +1,6 @@
import collections
import datetime
import hashlib
import logging
import os
@ -39,13 +40,17 @@ def build_nav_entry(root, args):
title = meta.get('toc_folder_title', 'hidden')
prio = meta.get('toc_priority', 9999)
logging.debug(f'Nav entry: {prio}, {title}, {path}')
if not content.strip():
if meta.get('toc_hidden') or not content.strip():
title = 'hidden'
if title == 'hidden':
title = 'hidden-' + hashlib.sha1(content.encode('utf-8')).hexdigest()
if args.nav_limit and len(result_items) >= args.nav_limit:
break
result_items.append((prio, title, path))
result_items = sorted(result_items, key=lambda x: (x[0], x[1]))
result = collections.OrderedDict([(item[1], item[2]) for item in result_items])
if index_meta.get('toc_hidden_folder'):
current_title += '|hidden-folder'
return index_meta.get('toc_priority', 10000), current_title, result

1
docs/zh/commercial/support.md
View File

@ -1 +0,0 @@
../../en/commercial/support.md

23
docs/zh/commercial/support.md Normal file
View File

@ -0,0 +1,23 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_priority: 3
toc_title: "\u788C\u83BD\u7984Support:"
---
# ClickHouse商业支持服务提供商 {#clickhouse-commercial-support-service-providers}
!!! info "信息"
如果您已经推出ClickHouse商业支持服务，请随时 [打开拉取请求](https://github.com/ClickHouse/ClickHouse/edit/master/docs/en/commercial/support.md) 将其添加到以下列表。
## 敏锐性 {#altinity}
隆隆隆隆路虏脢..陇.貌.垄拢卢虏禄and陇.貌路.隆拢脳枚脢虏 隆隆隆隆路虏脢..陇.貌.垄拢卢虏禄.陇 访问 [www.altinity.com](https://www.altinity.com/) 欲了解更多信息.
## Mafiree {#mafiree}
[服务说明](http://mafiree.com/clickhouse-analytics-services.php)
## MinervaDB {#minervadb}
[服务说明](https://minervadb.com/index.php/clickhouse-consulting-and-support-by-minervadb/)

2
docs/zh/operations/monitoring.md
View File

@ -33,7 +33,7 @@ ClickHouse 收集的指标项：
- 服务用于计算的资源占用的各种指标。
- 关于查询处理的常见统计信息。
可以在 [系统指标](system-tables.md#system_tables-metrics) ，[系统事件](system-tables.md#system_tables-events) 以及[系统异步指标](system-tables.md#system_tables-asynchronous_metrics) 等系统表查看所有的指标项。
可以在 [系统指标](system-tables/metrics.md#system_tables-metrics) ，[系统事件](system-tables/events.md#system_tables-events) 以及[系统异步指标](system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) 等系统表查看所有的指标项。
可以配置ClickHouse 往 [石墨](https://github.com/graphite-project)导入指标。 参考 [石墨部分](server-configuration-parameters/settings.md#server_configuration_parameters-graphite) 配置文件。在配置指标导出之前，需要参考Graphite[官方教程](https://graphite.readthedocs.io/en/latest/install.html)搭建服务。

2
docs/zh/operations/optimizing-performance/sampling-query-profiler.md
View File

@ -13,7 +13,7 @@ ClickHouse运行允许分析查询执行的采样探查器。 使用探查器，
- 设置 [trace\_log](../server-configuration-parameters/settings.md#server_configuration_parameters-trace_log) 服务器配置部分。
本节配置 [trace\_log](../../operations/system-tables.md#system_tables-trace_log) 系统表包含探查器运行的结果。 它是默认配置的。 请记住，此表中的数据仅对正在运行的服务器有效。 服务器重新启动后，ClickHouse不会清理表，所有存储的虚拟内存地址都可能无效。
本节配置 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log) 系统表包含探查器运行的结果。 它是默认配置的。 请记住，此表中的数据仅对正在运行的服务器有效。 服务器重新启动后，ClickHouse不会清理表，所有存储的虚拟内存地址都可能无效。
- 设置 [query\_profiler\_cpu\_time\_period\_ns](../settings/settings.md#query_profiler_cpu_time_period_ns) 或 [query\_profiler\_real\_time\_period\_ns](../settings/settings.md#query_profiler_real_time_period_ns) 设置。 这两种设置可以同时使用。

16
docs/zh/operations/server-configuration-parameters/settings.md
View File

@ -145,10 +145,10 @@ ClickHouse每x秒重新加载内置字典。 这使得编辑字典 “on the fly
- interval – The interval for sending, in seconds.
- timeout – The timeout for sending data, in seconds.
- root\_path – Prefix for keys.
- metrics – Sending data from the [系统。指标](../../operations/system-tables.md#system_tables-metrics) 桌子
- events – Sending deltas data accumulated for the time period from the [系统。活动](../../operations/system-tables.md#system_tables-events) 桌子
- events\_cumulative – Sending cumulative data from the [系统。活动](../../operations/system-tables.md#system_tables-events) 桌子
- asynchronous\_metrics – Sending data from the [系统。asynchronous\_metrics](../../operations/system-tables.md#system_tables-asynchronous_metrics) 桌子
- metrics – Sending data from the [系统。指标](../../operations/system-tables/metrics.md#system_tables-metrics) 桌子
- events – Sending deltas data accumulated for the time period from the [系统。活动](../../operations/system-tables/events.md#system_tables-events) 桌子
- events\_cumulative – Sending cumulative data from the [系统。活动](../../operations/system-tables/events.md#system_tables-events) 桌子
- asynchronous\_metrics – Sending data from the [系统。asynchronous\_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) 桌子
您可以配置多个 `<graphite>` 条款 例如，您可以使用它以不同的时间间隔发送不同的数据。
@ -503,7 +503,7 @@ SSL客户端/服务器配置。
记录与之关联的事件 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md). 例如，添加或合并数据。 您可以使用日志来模拟合并算法并比较它们的特征。 您可以可视化合并过程。
查询记录在 [系统。part\_log](../../operations/system-tables.md#system_tables-part-log) 表，而不是在一个单独的文件。 您可以在以下命令中配置此表的名称 `table` 参数（见下文）。
查询记录在 [系统。part\_log](../../operations/system-tables/part_log.md#system_tables-part-log) 表，而不是在一个单独的文件。 您可以在以下命令中配置此表的名称 `table` 参数（见下文）。
使用以下参数配置日志记录:
@ -540,7 +540,7 @@ SSL客户端/服务器配置。
用于记录接收到的查询的设置 [log\_queries=1](../settings/settings.md) 设置。
查询记录在 [系统。query\_log](../../operations/system-tables.md#system_tables-query_log) 表，而不是在一个单独的文件。 您可以更改表的名称 `table` 参数（见下文）。
查询记录在 [系统。query\_log](../../operations/system-tables/query_log.md#system_tables-query_log) 表，而不是在一个单独的文件。 您可以更改表的名称 `table` 参数（见下文）。
使用以下参数配置日志记录:
@ -566,7 +566,7 @@ SSL客户端/服务器配置。
设置用于记录接收到的查询的线程 [log\_query\_threads=1](../settings/settings.md#settings-log-query-threads) 设置。
查询记录在 [系统。query\_thread\_log](../../operations/system-tables.md#system_tables-query-thread-log) 表，而不是在一个单独的文件。 您可以更改表的名称 `table` 参数（见下文）。
查询记录在 [系统。query\_thread\_log](../../operations/system-tables/query_thread_log.md#system_tables-query-thread-log) 表，而不是在一个单独的文件。 您可以更改表的名称 `table` 参数（见下文）。
使用以下参数配置日志记录:
@ -590,7 +590,7 @@ SSL客户端/服务器配置。
## trace\_log {#server_configuration_parameters-trace_log}
设置为 [trace\_log](../../operations/system-tables.md#system_tables-trace_log) 系统表操作。
设置为 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log) 系统表操作。
参数:

6
docs/zh/operations/settings/settings.md
View File

@ -1165,7 +1165,7 @@ ClickHouse生成异常
另请参阅:
- 系统表 [trace\_log](../../operations/system-tables.md#system_tables-trace_log)
- 系统表 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
## query\_profiler\_cpu\_time\_period\_ns {#query_profiler_cpu_time_period_ns}
@ -1188,7 +1188,7 @@ ClickHouse生成异常
另请参阅:
- 系统表 [trace\_log](../../operations/system-tables.md#system_tables-trace_log)
- 系统表 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
## allow\_introspection\_functions {#settings-allow_introspection_functions}
@ -1204,7 +1204,7 @@ ClickHouse生成异常
**另请参阅**
- [采样查询探查器](../optimizing-performance/sampling-query-profiler.md)
- 系统表 [trace\_log](../../operations/system-tables.md#system_tables-trace_log)
- 系统表 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
## input\_format\_parallel\_parsing {#input-format-parallel-parsing}

1168
docs/zh/operations/system-tables.md
View File

File diff suppressed because it is too large Load Diff

8
docs/zh/operations/system-tables/asynchronous_metric_log.md Normal file
View File

@ -0,0 +1,8 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
## 系统。asynchronous\_metric\_log {#system-tables-async-log}
包含以下内容的历史值 `system.asynchronous_log` （见 [系统。asynchronous\_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics))

41
docs/zh/operations/system-tables/asynchronous_metrics.md Normal file
View File

@ -0,0 +1,41 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。asynchronous\_metrics {#system_tables-asynchronous_metrics}
包含在后台定期计算的指标。 例如，在使用的RAM量。
列:
- `metric` ([字符串](../../sql-reference/data-types/string.md)) — Metric name.
- `value` ([Float64](../../sql-reference/data-types/float.md)) — Metric value.
**示例**
``` sql
SELECT * FROM system.asynchronous_metrics LIMIT 10
```
``` text
┌─metric──────────────────────────────────┬──────value─┐
│ jemalloc.background_thread.run_interval │ 0 │
│ jemalloc.background_thread.num_runs │ 0 │
│ jemalloc.background_thread.num_threads │ 0 │
│ jemalloc.retained │ 422551552 │
│ jemalloc.mapped │ 1682989056 │
│ jemalloc.resident │ 1656446976 │
│ jemalloc.metadata_thp │ 0 │
│ jemalloc.metadata │ 10226856 │
│ UncompressedCacheCells │ 0 │
│ MarkCacheFiles │ 0 │
└─────────────────────────────────────────┴────────────┘
```
**另请参阅**
- [监测](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.
- [系统。指标](../../operations/system-tables/metrics.md#system_tables-metrics) — Contains instantly calculated metrics.
- [系统。活动](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that have occurred.
- [系统。metric\_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` и `system.events`.

29
docs/zh/operations/system-tables/clusters.md Normal file
View File

@ -0,0 +1,29 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。集群 {#system-clusters}
包含有关配置文件中可用的集群及其中的服务器的信息。
列:
- `cluster` (String) — The cluster name.
- `shard_num` (UInt32) — The shard number in the cluster, starting from 1.
- `shard_weight` (UInt32) — The relative weight of the shard when writing data.
- `replica_num` (UInt32) — The replica number in the shard, starting from 1.
- `host_name` (String) — The host name, as specified in the config.
- `host_address` (String) — The host IP address obtained from DNS.
- `port` (UInt16) — The port to use for connecting to the server.
- `user` (String) — The name of the user for connecting to the server.
- `errors_count` (UInt32)-此主机无法到达副本的次数。
- `estimated_recovery_time` (UInt32)-剩下的秒数，直到副本错误计数归零，它被认为是恢复正常。
请注意 `errors_count` 每个查询集群更新一次，但 `estimated_recovery_time` 按需重新计算。 所以有可能是非零的情况 `errors_count` 和零 `estimated_recovery_time`，下一个查询将为零 `errors_count` 并尝试使用副本，就好像它没有错误。
**另请参阅**
- [表引擎分布式](../../engines/table-engines/special/distributed.md)
- [distributed\_replica\_error\_cap设置](../../operations/settings/settings.md#settings-distributed_replica_error_cap)
- [distributed\_replica\_error\_half\_life设置](../../operations/settings/settings.md#settings-distributed_replica_error_half_life)

27
docs/zh/operations/system-tables/columns.md Normal file
View File

@ -0,0 +1,27 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。列 {#system-columns}
包含有关所有表中列的信息。
您可以使用此表获取类似于以下内容的信息 [DESCRIBE TABLE](../../sql-reference/statements/misc.md#misc-describe-table) 查询，但对于多个表一次。
该 `system.columns` 表包含以下列（列类型显示在括号中):
- `database` (String) — Database name.
- `table` (String) — Table name.
- `name` (String) — Column name.
- `type` (String) — Column type.
- `default_kind` (String) — Expression type (`DEFAULT`, `MATERIALIZED`, `ALIAS`)为默认值，如果没有定义，则为空字符串。
- `default_expression` (String) — Expression for the default value, or an empty string if it is not defined.
- `data_compressed_bytes` (UInt64) — The size of compressed data, in bytes.
- `data_uncompressed_bytes` (UInt64) — The size of decompressed data, in bytes.
- `marks_bytes` (UInt64) — The size of marks, in bytes.
- `comment` (String) — Comment on the column, or an empty string if it is not defined.
- `is_in_partition_key` (UInt8) — Flag that indicates whether the column is in the partition expression.
- `is_in_sorting_key` (UInt8) — Flag that indicates whether the column is in the sorting key expression.
- `is_in_primary_key` (UInt8) — Flag that indicates whether the column is in the primary key expression.
- `is_in_sampling_key` (UInt8) — Flag that indicates whether the column is in the sampling key expression.

45
docs/zh/operations/system-tables/contributors.md Normal file
View File

@ -0,0 +1,45 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。贡献者 {#system-contributors}
包含有关贡献者的信息。 该顺序在查询执行时是随机的。
列:
- `name` (String) — Contributor (author) name from git log.
**示例**
``` sql
SELECT * FROM system.contributors LIMIT 10
```
``` text
┌─name─────────────┐
│ Olga Khvostikova │
│ Max Vetrov │
│ LiuYangkuan │
│ svladykin │
│ zamulla │
│ Šimon Podlipský │
│ BayoNet │
│ Ilya Khomutov │
│ Amy Krishnevsky │
│ Loud_Scream │
└──────────────────┘
```
要在表中找出自己，请使用查询:
``` sql
SELECT * FROM system.contributors WHERE name = 'Olga Khvostikova'
```
``` text
┌─name─────────────┐
│ Olga Khvostikova │
└──────────────────┘
```

39
docs/zh/operations/system-tables/data_type_families.md Normal file
View File

@ -0,0 +1,39 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。data\_type\_families {#system_tables-data_type_families}
包含有关受支持的信息 [数据类型](../../sql-reference/data-types/).
列:
- `name` ([字符串](../../sql-reference/data-types/string.md)) — Data type name.
- `case_insensitive` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Property that shows whether you can use a data type name in a query in case insensitive manner or not. For example, `Date` 和 `date` 都是有效的。
- `alias_to` ([字符串](../../sql-reference/data-types/string.md)) — Data type name for which `name` 是个化名
**示例**
``` sql
SELECT * FROM system.data_type_families WHERE alias_to = 'String'
```
``` text
┌─name───────┬─case_insensitive─┬─alias_to─┐
│ LONGBLOB │ 1 │ String │
│ LONGTEXT │ 1 │ String │
│ TINYTEXT │ 1 │ String │
│ TEXT │ 1 │ String │
│ VARCHAR │ 1 │ String │
│ MEDIUMBLOB │ 1 │ String │
│ BLOB │ 1 │ String │
│ TINYBLOB │ 1 │ String │
│ CHAR │ 1 │ String │
│ MEDIUMTEXT │ 1 │ String │
└────────────┴──────────────────┴──────────┘
```
**另请参阅**
- [语法](../../sql-reference/syntax.md) — Information about supported syntax.

12
docs/zh/operations/system-tables/databases.md Normal file
View File

@ -0,0 +1,12 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。数据库 {#system-databases}
此表包含一个名为"字符串"的列 ‘name’ – the name of a database.
服务器知道的每个数据库在表中都有相应的条目。
该系统表用于实现 `SHOW DATABASES` 查询。

14
docs/zh/operations/system-tables/detached_parts.md Normal file
View File

@ -0,0 +1,14 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。detached\_parts {#system_tables-detached_parts}
包含有关分离部分的信息 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 桌子 该 `reason` 列指定分离部件的原因。
对于用户分离的部件，原因是空的。 这些部件可以附加 [ALTER TABLE ATTACH PARTITION\|PART](../../sql-reference/statements/alter.md#alter_attach-partition) 指挥部
有关其他列的说明，请参阅 [系统。零件](../../operations/system-tables/parts.md#system_tables-parts).
如果部件名称无效，某些列的值可能为 `NULL`. 这些部分可以删除 [ALTER TABLE DROP DETACHED PART](../../sql-reference/statements/alter.md#alter_drop-detached).

66
docs/zh/operations/system-tables/dictionaries.md Normal file
View File

@ -0,0 +1,66 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。字典 {#system_tables-dictionaries}
包含以下信息 [外部字典](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md).
列:
- `database` ([字符串](../../sql-reference/data-types/string.md)) — Name of the database containing the dictionary created by DDL query. Empty string for other dictionaries.
- `name` ([字符串](../../sql-reference/data-types/string.md)) — [字典名称](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict.md).
- `status` ([枚举8](../../sql-reference/data-types/enum.md)) — Dictionary status. Possible values:
- `NOT_LOADED` — Dictionary was not loaded because it was not used.
- `LOADED` — Dictionary loaded successfully.
- `FAILED` — Unable to load the dictionary as a result of an error.
- `LOADING` — Dictionary is loading now.
- `LOADED_AND_RELOADING` — Dictionary is loaded successfully, and is being reloaded right now (frequent reasons: [SYSTEM RELOAD DICTIONARY](../../sql-reference/statements/system.md#query_language-system-reload-dictionary) 查询，超时，字典配置已更改）。
- `FAILED_AND_RELOADING` — Could not load the dictionary as a result of an error and is loading now.
- `origin` ([字符串](../../sql-reference/data-types/string.md)) — Path to the configuration file that describes the dictionary.
- `type` ([字符串](../../sql-reference/data-types/string.md)) — Type of a dictionary allocation. [在内存中存储字典](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-layout.md).
- `key` — [密钥类型](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-key):数字键 ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) or Сomposite key ([字符串](../../sql-reference/data-types/string.md)) — form “(type 1, type 2, …, type n)”.
- `attribute.names` ([阵列](../../sql-reference/data-types/array.md)([字符串](../../sql-reference/data-types/string.md))) — Array of [属性名称](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-attributes) 由字典提供。
- `attribute.types` ([阵列](../../sql-reference/data-types/array.md)([字符串](../../sql-reference/data-types/string.md))) — Corresponding array of [属性类型](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-attributes) 这是由字典提供。
- `bytes_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Amount of RAM allocated for the dictionary.
- `query_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of queries since the dictionary was loaded or since the last successful reboot.
- `hit_rate` ([Float64](../../sql-reference/data-types/float.md)) — For cache dictionaries, the percentage of uses for which the value was in the cache.
- `element_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of items stored in the dictionary.
- `load_factor` ([Float64](../../sql-reference/data-types/float.md)) — Percentage filled in the dictionary (for a hashed dictionary, the percentage filled in the hash table).
- `source` ([字符串](../../sql-reference/data-types/string.md)) — Text describing the [数据源](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md) 为了字典
- `lifetime_min` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Minimum [使用寿命](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-lifetime.md) 在内存中的字典，之后ClickHouse尝试重新加载字典（如果 `invalidate_query` 被设置，那么只有当它已经改变）。 在几秒钟内设置。
- `lifetime_max` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Maximum [使用寿命](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-lifetime.md) 在内存中的字典，之后ClickHouse尝试重新加载字典（如果 `invalidate_query` 被设置，那么只有当它已经改变）。 在几秒钟内设置。
- `loading_start_time` ([日期时间](../../sql-reference/data-types/datetime.md)) — Start time for loading the dictionary.
- `last_successful_update_time` ([日期时间](../../sql-reference/data-types/datetime.md)) — End time for loading or updating the dictionary. Helps to monitor some troubles with external sources and investigate causes.
- `loading_duration` ([Float32](../../sql-reference/data-types/float.md)) — Duration of a dictionary loading.
- `last_exception` ([字符串](../../sql-reference/data-types/string.md)) — Text of the error that occurs when creating or reloading the dictionary if the dictionary couldn't be created.
**示例**
配置字典。
``` sql
CREATE DICTIONARY dictdb.dict
(
`key` Int64 DEFAULT -1,
`value_default` String DEFAULT 'world',
`value_expression` String DEFAULT 'xxx' EXPRESSION 'toString(127 * 172)'
)
PRIMARY KEY key
SOURCE(CLICKHOUSE(HOST 'localhost' PORT 9000 USER 'default' TABLE 'dicttbl' DB 'dictdb'))
LIFETIME(MIN 0 MAX 1)
LAYOUT(FLAT())
```
确保字典已加载。
``` sql
SELECT * FROM system.dictionaries
```
``` text
┌─database─┬─name─┬─status─┬─origin──────┬─type─┬─key────┬─attribute.names──────────────────────┬─attribute.types─────┬─bytes_allocated─┬─query_count─┬─hit_rate─┬─element_count─┬───────────load_factor─┬─source─────────────────────┬─lifetime_min─┬─lifetime_max─┬──loading_start_time─┌──last_successful_update_time─┬──────loading_duration─┬─last_exception─┐
│ dictdb │ dict │ LOADED │ dictdb.dict │ Flat │ UInt64 │ ['value_default','value_expression'] │ ['String','String'] │ 74032 │ 0 │ 1 │ 1 │ 0.0004887585532746823 │ ClickHouse: dictdb.dicttbl │ 0 │ 1 │ 2020-03-04 04:17:34 │ 2020-03-04 04:30:34 │ 0.002 │ │
└──────────┴──────┴────────┴─────────────┴──────┴────────┴──────────────────────────────────────┴─────────────────────┴─────────────────┴─────────────┴──────────┴───────────────┴───────────────────────┴────────────────────────────┴──────────────┴──────────────┴─────────────────────┴──────────────────────────────┘───────────────────────┴────────────────┘
```

31
docs/zh/operations/system-tables/disks.md Normal file
View File

@ -0,0 +1,31 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。磁盘 {#system_tables-disks}
包含有关在定义的磁盘信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
列:
- `name` ([字符串](../../sql-reference/data-types/string.md)) — Name of a disk in the server configuration.
- `path` ([字符串](../../sql-reference/data-types/string.md)) — Path to the mount point in the file system.
- `free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Free space on disk in bytes.
- `total_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Disk volume in bytes.
- `keep_free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Amount of disk space that should stay free on disk in bytes. Defined in the `keep_free_space_bytes` 磁盘配置参数。
## 系统。storage\_policies {#system_tables-storage_policies}
包含有关存储策略和卷中定义的信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
列:
- `policy_name` ([字符串](../../sql-reference/data-types/string.md)) — Name of the storage policy.
- `volume_name` ([字符串](../../sql-reference/data-types/string.md)) — Volume name defined in the storage policy.
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Volume order number in the configuration.
- `disks` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Disk names, defined in the storage policy.
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
如果存储策略包含多个卷，则每个卷的信息将存储在表的单独行中。

37
docs/zh/operations/system-tables/events.md Normal file
View File

@ -0,0 +1,37 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。活动 {#system_tables-events}
包含有关系统中发生的事件数的信息。 例如，在表中，您可以找到多少 `SELECT` 自ClickHouse服务器启动以来已处理查询。
列:
- `event` ([字符串](../../sql-reference/data-types/string.md)) — Event name.
- `value` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Number of events occurred.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — Event description.
**示例**
``` sql
SELECT * FROM system.events LIMIT 5
```
``` text
┌─event─────────────────────────────────┬─value─┬─description────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Query │ 12 │ 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. │
│ SelectQuery │ 8 │ Same as Query, but only for SELECT queries. │
│ FileOpen │ 73 │ Number of files opened. │
│ ReadBufferFromFileDescriptorRead │ 155 │ Number of reads (read/pread) from a file descriptor. Does not include sockets. │
│ ReadBufferFromFileDescriptorReadBytes │ 9931 │ Number of bytes read from file descriptors. If the file is compressed, this will show the compressed data size. │
└───────────────────────────────────────┴───────┴────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
**另请参阅**
- [系统。asynchronous\_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.
- [系统。指标](../../operations/system-tables/metrics.md#system_tables-metrics) — Contains instantly calculated metrics.
- [系统。metric\_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` и `system.events`.
- [监测](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.

13
docs/zh/operations/system-tables/functions.md Normal file
View File

@ -0,0 +1,13 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。功能 {#system-functions}
包含有关正常函数和聚合函数的信息。
列:
- `name`(`String`) – The name of the function.
- `is_aggregate`(`UInt8`) — Whether the function is aggregate.

20
docs/zh/operations/system-tables/graphite_retentions.md Normal file
View File

@ -0,0 +1,20 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。graphite\_retentions {#system-graphite-retentions}
包含有关参数的信息 [graphite\_rollup](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-graphite) 这是在表中使用 [\*GraphiteMergeTree](../../engines/table-engines/mergetree-family/graphitemergetree.md) 引擎
列:
- `config_name` (字符串) - `graphite_rollup` 参数名称。
- `regexp` (String)-指标名称的模式。
- `function` (String)-聚合函数的名称。
- `age` (UInt64)-以秒为单位的数据的最小期限。
- `precision` （UInt64）-如何精确地定义以秒为单位的数据的年龄。
- `priority` (UInt16)-模式优先级。
- `is_default` (UInt8)-模式是否为默认值。
- `Tables.database` (Array(String))-使用数据库表名称的数组 `config_name` 参数。
- `Tables.table` (Array(String))-使用表名称的数组 `config_name` 参数。

50
docs/zh/operations/system-tables/index.md Normal file
View File

@ -0,0 +1,50 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_priority: 52
toc_title: "\u7CFB\u7EDF\u8868"
---
# 系统表 {#system-tables}
## 导言 {#system-tables-introduction}
系统表提供以下信息:
- 服务器状态、进程和环境。
- 服务器的内部进程。
系统表:
- 坐落于 `system` 数据库。
- 仅适用于读取数据。
- 不能删除或更改，但可以分离。
大多数系统表将数据存储在RAM中。 ClickHouse服务器在开始时创建此类系统表。
与其他系统表不同，系统表 [metric\_log](../../operations/system-tables/metric_log.md#system_tables-metric_log), [query\_log](../../operations/system-tables/query_log.md#system_tables-query_log), [query\_thread\_log](../../operations/system-tables/query_thread_log.md#system_tables-query_thread_log), [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log) 由 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 表引擎并将其数据存储在存储文件系统中。 如果从文件系统中删除表，ClickHouse服务器会在下一次写入数据时再次创建空表。 如果系统表架构在新版本中发生更改，则ClickHouse会重命名当前表并创建一个新表。
默认情况下，表增长是无限的。 要控制表的大小，可以使用 [TTL](../../sql-reference/statements/alter.md#manipulations-with-table-ttl) 删除过期日志记录的设置。 你也可以使用分区功能 `MergeTree`-发动机表。
## 系统指标的来源 {#system-tables-sources-of-system-metrics}
用于收集ClickHouse服务器使用的系统指标:
- `CAP_NET_ADMIN` 能力。
- [procfs](https://en.wikipedia.org/wiki/Procfs) （仅在Linux中）。
**procfs**
如果ClickHouse服务器没有 `CAP_NET_ADMIN` 能力，它试图回落到 `ProcfsMetricsProvider`. `ProcfsMetricsProvider` 允许收集每个查询系统指标（用于CPU和I/O）。
如果系统上支持并启用procfs，ClickHouse server将收集这些指标:
- `OSCPUVirtualTimeMicroseconds`
- `OSCPUWaitMicroseconds`
- `OSIOWaitMicroseconds`
- `OSReadChars`
- `OSWriteChars`
- `OSReadBytes`
- `OSWriteBytes`
[原始文章](https://clickhouse.tech/docs/en/operations/system-tables/) <!--hide-->

16
docs/zh/operations/system-tables/merge_tree_settings.md Normal file
View File

@ -0,0 +1,16 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。merge\_tree\_settings {#system-merge_tree_settings}
包含有关以下设置的信息 `MergeTree` 桌子
列:
- `name` (String) — Setting name.
- `value` (String) — Setting value.
- `description` (String) — Setting description.
- `type` (String) — Setting type (implementation specific string value).
- `changed` (UInt8) — Whether the setting was explicitly defined in the config or explicitly changed.

24
docs/zh/operations/system-tables/merges.md Normal file
View File

@ -0,0 +1,24 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。合并 {#system-merges}
包含有关MergeTree系列中表当前正在进行的合并和部件突变的信息。
列:
- `database` (String) — The name of the database the table is in.
- `table` (String) — Table name.
- `elapsed` (Float64) — The time elapsed (in seconds) since the merge started.
- `progress` (Float64) — The percentage of completed work from 0 to 1.
- `num_parts` (UInt64) — The number of pieces to be merged.
- `result_part_name` (String) — The name of the part that will be formed as the result of merging.
- `is_mutation` (UInt8)-1如果这个过程是一个部分突变.
- `total_size_bytes_compressed` (UInt64) — The total size of the compressed data in the merged chunks.
- `total_size_marks` (UInt64) — The total number of marks in the merged parts.
- `bytes_read_uncompressed` (UInt64) — Number of bytes read, uncompressed.
- `rows_read` (UInt64) — Number of rows read.
- `bytes_written_uncompressed` (UInt64) — Number of bytes written, uncompressed.
- `rows_written` (UInt64) — Number of rows written.

60
docs/zh/operations/system-tables/metric_log.md Normal file
View File

@ -0,0 +1,60 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。metric\_log {#system_tables-metric_log}
包含表中度量值的历史记录 `system.metrics` 和 `system.events`，定期刷新到磁盘。
打开指标历史记录收集 `system.metric_log`,创建 `/etc/clickhouse-server/config.d/metric_log.xml` 具有以下内容:
``` xml
<yandex>
<metric_log>
<database>system</database>
<table>metric_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
<collect_interval_milliseconds>1000</collect_interval_milliseconds>
</metric_log>
</yandex>
```
**示例**
``` sql
SELECT * FROM system.metric_log LIMIT 1 FORMAT Vertical;
```
``` text
Row 1:
──────
event_date: 2020-02-18
event_time: 2020-02-18 07:15:33
milliseconds: 554
ProfileEvent_Query: 0
ProfileEvent_SelectQuery: 0
ProfileEvent_InsertQuery: 0
ProfileEvent_FileOpen: 0
ProfileEvent_Seek: 0
ProfileEvent_ReadBufferFromFileDescriptorRead: 1
ProfileEvent_ReadBufferFromFileDescriptorReadFailed: 0
ProfileEvent_ReadBufferFromFileDescriptorReadBytes: 0
ProfileEvent_WriteBufferFromFileDescriptorWrite: 1
ProfileEvent_WriteBufferFromFileDescriptorWriteFailed: 0
ProfileEvent_WriteBufferFromFileDescriptorWriteBytes: 56
...
CurrentMetric_Query: 0
CurrentMetric_Merge: 0
CurrentMetric_PartMutation: 0
CurrentMetric_ReplicatedFetch: 0
CurrentMetric_ReplicatedSend: 0
CurrentMetric_ReplicatedChecks: 0
...
```
**另请参阅**
- [系统。asynchronous\_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.
- [系统。活动](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that occurred.
- [系统。指标](../../operations/system-tables/metrics.md#system_tables-metrics) — Contains instantly calculated metrics.
- [监测](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.

44
docs/zh/operations/system-tables/metrics.md Normal file
View File

@ -0,0 +1,44 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。指标 {#system_tables-metrics}
包含可以立即计算或具有当前值的指标。 例如，同时处理的查询的数量或当前副本的延迟。 此表始终是最新的。
列:
- `metric` ([字符串](../../sql-reference/data-types/string.md)) — Metric name.
- `value` ([Int64](../../sql-reference/data-types/int-uint.md)) — Metric value.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — Metric description.
支持的指标列表，您可以在 [src/Common/CurrentMetrics.cpp](https://github.com/ClickHouse/ClickHouse/blob/master/src/Common/CurrentMetrics.cpp) ClickHouse的源文件。
**示例**
``` sql
SELECT * FROM system.metrics LIMIT 10
```
``` text
┌─metric─────────────────────┬─value─┬─description──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Query │ 1 │ Number of executing queries │
│ Merge │ 0 │ Number of executing background merges │
│ PartMutation │ 0 │ Number of mutations (ALTER DELETE/UPDATE) │
│ ReplicatedFetch │ 0 │ Number of data parts being fetched from replicas │
│ ReplicatedSend │ 0 │ Number of data parts being sent to replicas │
│ ReplicatedChecks │ 0 │ Number of data parts checking for consistency │
│ BackgroundPoolTask │ 0 │ Number of active tasks in BackgroundProcessingPool (merges, mutations, fetches, or replication queue bookkeeping) │
│ BackgroundSchedulePoolTask │ 0 │ Number of active tasks in BackgroundSchedulePool. This pool is used for periodic ReplicatedMergeTree tasks, like cleaning old data parts, altering data parts, replica re-initialization, etc. │
│ DiskSpaceReservedForMerge │ 0 │ Disk space reserved for currently running background merges. It is slightly more than the total size of currently merging parts. │
│ DistributedSend │ 0 │ Number of connections to remote servers sending data that was INSERTed into Distributed tables. Both synchronous and asynchronous mode. │
└────────────────────────────┴───────┴──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
**另请参阅**
- [系统。asynchronous\_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.
- [系统。活动](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that occurred.
- [系统。metric\_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` и `system.events`.
- [监测](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.

30
docs/zh/operations/system-tables/mutations.md Normal file
View File

@ -0,0 +1,30 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。突变 {#system_tables-mutations}
该表包含以下信息 [突变](../../sql-reference/statements/alter.md#alter-mutations) MergeTree表及其进展。 每个突变命令由一行表示。 该表具有以下列:
**数据库**, **表** -应用突变的数据库和表的名称。
**mutation\_id** -变异的ID 对于复制的表，这些Id对应于znode中的名称 `<table_path_in_zookeeper>/mutations/` 动物园管理员的目录。 对于未复制的表，Id对应于表的数据目录中的文件名。
**命令** -Mutation命令字符串（查询后的部分 `ALTER TABLE [db.]table`).
**create\_time** -当这个突变命令被提交执行。
**block\_numbers.partition\_id**, **block\_numbers.编号** -嵌套列。 对于复制表的突变，它包含每个分区的一条记录：分区ID和通过突变获取的块编号（在每个分区中，只有包含编号小于该分区中突变获取的块编号的块的 在非复制表中，所有分区中的块编号形成一个序列。 这意味着对于非复制表的突变，该列将包含一条记录，其中包含由突变获取的单个块编号。
**parts\_to\_do** -为了完成突变，需要突变的数据部分的数量。
**is\_done** -变异完成了?？ 请注意，即使 `parts_to_do = 0` 由于长时间运行的INSERT将创建需要突变的新数据部分，因此可能尚未完成复制表的突变。
如果在改变某些部分时出现问题，以下列将包含其他信息:
**latest\_failed\_part** -不能变异的最新部分的名称。
**latest\_fail\_time** -最近的部分突变失败的时间。
**latest\_fail\_reason** -导致最近部件变异失败的异常消息。

12
docs/zh/operations/system-tables/numbers.md Normal file
View File

@ -0,0 +1,12 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。数字 {#system-numbers}
此表包含一个名为UInt64的列 `number` 它包含几乎所有从零开始的自然数。
您可以使用此表进行测试，或者如果您需要进行暴力搜索。
从此表中读取的内容不是并行的。

10
docs/zh/operations/system-tables/numbers_mt.md Normal file
View File

@ -0,0 +1,10 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。numbers\_mt {#system-numbers-mt}
一样的 [系统。数字](../../operations/system-tables/numbers.md) 但读取是并行的。 这些数字可以以任何顺序返回。
用于测试。

12
docs/zh/operations/system-tables/one.md Normal file
View File

@ -0,0 +1,12 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。一 {#system-one}
此表包含一行，其中包含一行 `dummy` UInt8列包含值0。
如果使用此表 `SELECT` 查询不指定 `FROM` 条款
这类似于 `DUAL` 表在其他Dbms中找到。

37
docs/zh/operations/system-tables/part_log.md Normal file
View File

@ -0,0 +1,37 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。part\_log {#system_tables-part-log}
该 `system.part_log` 表只有当创建 [part\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-part-log) 指定了服务器设置。
此表包含与以下情况发生的事件有关的信息 [数据部分](../../engines/table-engines/mergetree-family/custom-partitioning-key.md) 在 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 家庭表，例如添加或合并数据。
该 `system.part_log` 表包含以下列:
- `event_type` (Enum) — Type of the event that occurred with the data part. Can have one of the following values:
- `NEW_PART` — Inserting of a new data part.
- `MERGE_PARTS` — Merging of data parts.
- `DOWNLOAD_PART` — Downloading a data part.
- `REMOVE_PART` — Removing or detaching a data part using [DETACH PARTITION](../../sql-reference/statements/alter.md#alter_detach-partition).
- `MUTATE_PART` — Mutating of a data part.
- `MOVE_PART` — Moving the data part from the one disk to another one.
- `event_date` (Date) — Event date.
- `event_time` (DateTime) — Event time.
- `duration_ms` (UInt64) — Duration.
- `database` (String) — Name of the database the data part is in.
- `table` (String) — Name of the table the data part is in.
- `part_name` (String) — Name of the data part.
- `partition_id` (String) — ID of the partition that the data part was inserted to. The column takes the ‘all’ 值，如果分区是由 `tuple()`.
- `rows` (UInt64) — The number of rows in the data part.
- `size_in_bytes` (UInt64) — Size of the data part in bytes.
- `merged_from` (Array(String)) — An array of names of the parts which the current part was made up from (after the merge).
- `bytes_uncompressed` (UInt64) — Size of uncompressed bytes.
- `read_rows` (UInt64) — The number of rows was read during the merge.
- `read_bytes` (UInt64) — The number of bytes was read during the merge.
- `error` (UInt16) — The code number of the occurred error.
- `exception` (String) — Text message of the occurred error.
该 `system.part_log` 表的第一个插入数据到后创建 `MergeTree` 桌子

85
docs/zh/operations/system-tables/parts.md Normal file
View File

@ -0,0 +1,85 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。零件 {#system_tables-parts}
包含有关的部分信息 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 桌子
每行描述一个数据部分。
列:
- `partition` (String) – The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter.md#query_language_queries_alter) 查询。
格式:
- `YYYYMM` 用于按月自动分区。
- `any_string` 手动分区时。
- `name` (`String`) – Name of the data part.
- `active` (`UInt8`) – Flag that indicates whether the data part is active. If a data part is active, it's used in a table. Otherwise, it's deleted. Inactive data parts remain after merging.
- `marks` (`UInt64`) – The number of marks. To get the approximate number of rows in a data part, multiply `marks` 通过索引粒度（通常为8192）（此提示不适用于自适应粒度）。
- `rows` (`UInt64`) – The number of rows.
- `bytes_on_disk` (`UInt64`) – Total size of all the data part files in bytes.
- `data_compressed_bytes` (`UInt64`) – Total size of compressed data in the data part. All the auxiliary files (for example, files with marks) are not included.
- `data_uncompressed_bytes` (`UInt64`) – Total size of uncompressed data in the data part. All the auxiliary files (for example, files with marks) are not included.
- `marks_bytes` (`UInt64`) – The size of the file with marks.
- `modification_time` (`DateTime`) – The time the directory with the data part was modified. This usually corresponds to the time of data part creation.\|
- `remove_time` (`DateTime`) – The time when the data part became inactive.
- `refcount` (`UInt32`) – The number of places where the data part is used. A value greater than 2 indicates that the data part is used in queries or merges.
- `min_date` (`Date`) – The minimum value of the date key in the data part.
- `max_date` (`Date`) – The maximum value of the date key in the data part.
- `min_time` (`DateTime`) – The minimum value of the date and time key in the data part.
- `max_time`(`DateTime`) – The maximum value of the date and time key in the data part.
- `partition_id` (`String`) – ID of the partition.
- `min_block_number` (`UInt64`) – The minimum number of data parts that make up the current part after merging.
- `max_block_number` (`UInt64`) – The maximum number of data parts that make up the current part after merging.
- `level` (`UInt32`) – Depth of the merge tree. Zero means that the current part was created by insert rather than by merging other parts.
- `data_version` (`UInt64`) – Number that is used to determine which mutations should be applied to the data part (mutations with a version higher than `data_version`).
- `primary_key_bytes_in_memory` (`UInt64`) – The amount of memory (in bytes) used by primary key values.
- `primary_key_bytes_in_memory_allocated` (`UInt64`) – The amount of memory (in bytes) reserved for primary key values.
- `is_frozen` (`UInt8`) – Flag that shows that a partition data backup exists. 1, the backup exists. 0, the backup doesn't exist. For more details, see [FREEZE PARTITION](../../sql-reference/statements/alter.md#alter_freeze-partition)
- `database` (`String`) – Name of the database.
- `table` (`String`) – Name of the table.
- `engine` (`String`) – Name of the table engine without parameters.
- `path` (`String`) – Absolute path to the folder with data part files.
- `disk` (`String`) – Name of a disk that stores the data part.
- `hash_of_all_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 的压缩文件。
- `hash_of_uncompressed_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 未压缩的文件（带标记的文件，索引文件等。).
- `uncompressed_hash_of_compressed_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 压缩文件中的数据，就好像它们是未压缩的。
- `bytes` (`UInt64`) – Alias for `bytes_on_disk`.
- `marks_size` (`UInt64`) – Alias for `marks_bytes`.

20
docs/zh/operations/system-tables/processes.md Normal file
View File

@ -0,0 +1,20 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。流程 {#system_tables-processes}
该系统表用于实现 `SHOW PROCESSLIST` 查询。
列:
- `user` (String) – The user who made the query. Keep in mind that for distributed processing, queries are sent to remote servers under the `default` 用户。 该字段包含特定查询的用户名，而不是此查询启动的查询的用户名。
- `address` (String) – The IP address the request was made from. The same for distributed processing. To track where a distributed query was originally made from, look at `system.processes` 查询请求者服务器上。
- `elapsed` (Float64) – The time in seconds since request execution started.
- `rows_read` (UInt64) – The number of rows read from the table. For distributed processing, on the requestor server, this is the total for all remote servers.
- `bytes_read` (UInt64) – The number of uncompressed bytes read from the table. For distributed processing, on the requestor server, this is the total for all remote servers.
- `total_rows_approx` (UInt64) – The approximation of the total number of rows that should be read. For distributed processing, on the requestor server, this is the total for all remote servers. It can be updated during request processing, when new sources to process become known.
- `memory_usage` (UInt64) – Amount of RAM the request uses. It might not include some types of dedicated memory. See the [max\_memory\_usage](../../operations/settings/query-complexity.md#settings_max_memory_usage) 设置。
- `query` (String) – The query text. For `INSERT`，它不包括要插入的数据。
- `query_id` (String) – Query ID, if defined.

143
docs/zh/operations/system-tables/query_log.md Normal file
View File

@ -0,0 +1,143 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。query\_log {#system_tables-query_log}
包含有关已执行查询的信息，例如，开始时间、处理持续时间、错误消息。
!!! note "注"
此表不包含以下内容的摄取数据 `INSERT` 查询。
您可以更改查询日志记录的设置 [query\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query-log) 服务器配置部分。
您可以通过设置禁用查询日志记录 [log\_queries=0](../../operations/settings/settings.md#settings-log-queries). 我们不建议关闭日志记录，因为此表中的信息对于解决问题很重要。
数据的冲洗周期设置在 `flush_interval_milliseconds` 的参数 [query\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query-log) 服务器设置部分。 要强制冲洗，请使用 [SYSTEM FLUSH LOGS](../../sql-reference/statements/system.md#query_language-system-flush_logs) 查询。
ClickHouse不会自动从表中删除数据。 看 [导言](../../operations/system-tables/index.md#system-tables-introduction) 欲了解更多详情。
该 `system.query_log` 表注册两种查询:
1. 客户端直接运行的初始查询。
2. 由其他查询启动的子查询（用于分布式查询执行）。 对于这些类型的查询，有关父查询的信息显示在 `initial_*` 列。
每个查询创建一个或两个行中 `query_log` 表，这取决于状态（见 `type` 列）的查询:
1. 如果查询执行成功，则两行具有 `QueryStart` 和 `QueryFinish` 创建类型。
2. 如果在查询处理过程中发生错误，两个事件与 `QueryStart` 和 `ExceptionWhileProcessing` 创建类型。
3. 如果在启动查询之前发生错误，则单个事件具有 `ExceptionBeforeStart` 创建类型。
列:
- `type` ([枚举8](../../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` ([日期](../../sql-reference/data-types/date.md)) — Query starting date.
- `event_time` ([日期时间](../../sql-reference/data-types/datetime.md)) — Query starting time.
- `query_start_time` ([日期时间](../../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` 和 `JOIN`. 对于分布式查询 `read_rows` 包括在所有副本上读取的行总数。 每个副本发送它的 `read_rows` 值，并且查询的服务器-发起方汇总所有接收到的和本地的值。 缓存卷不会影响此值。
- `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` 和 `JOIN`. 对于分布式查询 `read_bytes` 包括在所有副本上读取的行总数。 每个副本发送它的 `read_bytes` 值，并且查询的服务器-发起方汇总所有接收到的和本地的值。 缓存卷不会影响此值。
- `written_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` 查询，写入的行数。 对于其他查询，列值为0。
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` 查询时，写入的字节数。 对于其他查询，列值为0。
- `result_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of rows in a result of the `SELECT` 查询，或者在一些行 `INSERT` 查询。
- `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` ([字符串](../../sql-reference/data-types/string.md)) — Query string.
- `exception` ([字符串](../../sql-reference/data-types/string.md)) — Exception message.
- `exception_code` ([Int32](../../sql-reference/data-types/int-uint.md)) — Code of an exception.
- `stack_trace` ([字符串](../../sql-reference/data-types/string.md)) — [堆栈跟踪](https://en.wikipedia.org/wiki/Stack_trace). 如果查询成功完成，则为空字符串。
- `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 as part of distributed query execution.
- `user` ([字符串](../../sql-reference/data-types/string.md)) — Name of the user who initiated the current query.
- `query_id` ([字符串](../../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` ([字符串](../../sql-reference/data-types/string.md)) — Name of the user who ran the initial query (for distributed query execution).
- `initial_query_id` ([字符串](../../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` ([字符串](../../sql-reference/data-types/string.md)) — Operating system username who runs [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md).
- `client_hostname` ([字符串](../../sql-reference/data-types/string.md)) — Hostname of the client machine where the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或者运行另一个TCP客户端。
- `client_name` ([字符串](../../sql-reference/data-types/string.md)) — The [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端名称。
- `client_revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Revision of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_major` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Major version of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_minor` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Minor version of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_patch` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Patch component of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端版本。
- `http_method` (UInt8) — HTTP method that initiated the query. Possible values:
- 0 — The query was launched from the TCP interface.
- 1 — `GET` 方法被使用。
- 2 — `POST` 方法被使用。
- `http_user_agent` ([字符串](../../sql-reference/data-types/string.md)) — The `UserAgent` http请求中传递的标头。
- `quota_key` ([字符串](../../sql-reference/data-types/string.md)) — The “quota key” 在指定 [配额](../../operations/quotas.md) 设置（见 `keyed`).
- `revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — ClickHouse revision.
- `thread_numbers` ([数组(UInt32)](../../sql-reference/data-types/array.md)) — Number of threads that are participating in query execution.
- `ProfileEvents.Names` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Counters that measure different metrics. The description of them could be found in the table [系统。活动](../../operations/system-tables/events.md#system_tables-events)
- `ProfileEvents.Values` ([数组(UInt64)](../../sql-reference/data-types/array.md)) — Values of metrics that are listed in the `ProfileEvents.Names` 列。
- `Settings.Names` ([数组（字符串)](../../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` 参数为1。
- `Settings.Values` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Values of settings that are listed in the `Settings.Names` 列。
**示例**
``` sql
SELECT * FROM system.query_log LIMIT 1 FORMAT Vertical;
```
``` 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']
```
**另请参阅**
- [系统。query\_thread\_log](../../operations/system-tables/query_thread_log.md#system_tables-query_thread_log) — This table contains information about each query execution thread.

118
docs/zh/operations/system-tables/query_thread_log.md Normal file
View File

@ -0,0 +1,118 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。query\_thread\_log {#system_tables-query_thread_log}
包含有关执行查询的线程的信息，例如，线程名称、线程开始时间、查询处理的持续时间。
开始记录:
1. 在配置参数 [query\_thread\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) 科。
2. 设置 [log\_query\_threads](../../operations/settings/settings.md#settings-log-query-threads) 到1。
数据的冲洗周期设置在 `flush_interval_milliseconds` 的参数 [query\_thread\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) 服务器设置部分。 要强制冲洗，请使用 [SYSTEM FLUSH LOGS](../../sql-reference/statements/system.md#query_language-system-flush_logs) 查询。
ClickHouse不会自动从表中删除数据。 看 [导言](../../operations/system-tables/index.md#system-tables-introduction) 欲了解更多详情。
列:
- `event_date` ([日期](../../sql-reference/data-types/date.md)) — The date when the thread has finished execution of the query.
- `event_time` ([日期时间](../../sql-reference/data-types/datetime.md)) — The date and time when the thread has finished execution of the query.
- `query_start_time` ([日期时间](../../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.
- `read_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of read rows.
- `read_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of read bytes.
- `written_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` 查询，写入的行数。 对于其他查询，列值为0。
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` 查询时，写入的字节数。 对于其他查询，列值为0。
- `memory_usage` ([Int64](../../sql-reference/data-types/int-uint.md)) — The difference between the amount of allocated and freed memory in context of this thread.
- `peak_memory_usage` ([Int64](../../sql-reference/data-types/int-uint.md)) — The maximum difference between the amount of allocated and freed memory in context of this thread.
- `thread_name` ([字符串](../../sql-reference/data-types/string.md)) — Name of the thread.
- `thread_number` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Internal thread ID.
- `thread_id` ([Int32](../../sql-reference/data-types/int-uint.md)) — thread ID.
- `master_thread_id` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — OS initial ID of initial thread.
- `query` ([字符串](../../sql-reference/data-types/string.md)) — Query string.
- `is_initial_query` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Query type. Possible values:
- 1 — Query was initiated by the client.
- 0 — Query was initiated by another query for distributed query execution.
- `user` ([字符串](../../sql-reference/data-types/string.md)) — Name of the user who initiated the current query.
- `query_id` ([字符串](../../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#uint-ranges)) — The client port that was used to make the query.
- `initial_user` ([字符串](../../sql-reference/data-types/string.md)) — Name of the user who ran the initial query (for distributed query execution).
- `initial_query_id` ([字符串](../../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#uint-ranges)) — The client port that was used to make the parent query.
- `interface` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Interface that the query was initiated from. Possible values:
- 1 — TCP.
- 2 — HTTP.
- `os_user` ([字符串](../../sql-reference/data-types/string.md)) — OS's username who runs [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md).
- `client_hostname` ([字符串](../../sql-reference/data-types/string.md)) — Hostname of the client machine where the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或者运行另一个TCP客户端。
- `client_name` ([字符串](../../sql-reference/data-types/string.md)) — The [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端名称。
- `client_revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Revision of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_major` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Major version of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_minor` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Minor version of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端。
- `client_version_patch` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Patch component of the [ﾂ环板clientｮﾂ嘉ｯﾂ偲](../../interfaces/cli.md) 或另一个TCP客户端版本。
- `http_method` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — HTTP method that initiated the query. Possible values:
- 0 — The query was launched from the TCP interface.
- 1 — `GET` 方法被使用。
- 2 — `POST` 方法被使用。
- `http_user_agent` ([字符串](../../sql-reference/data-types/string.md)) — The `UserAgent` http请求中传递的标头。
- `quota_key` ([字符串](../../sql-reference/data-types/string.md)) — The “quota key” 在指定 [配额](../../operations/quotas.md) 设置（见 `keyed`).
- `revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — ClickHouse revision.
- `ProfileEvents.Names` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Counters that measure different metrics for this thread. The description of them could be found in the table [系统。活动](#system_tables-events).
- `ProfileEvents.Values` ([数组(UInt64)](../../sql-reference/data-types/array.md)) — Values of metrics for this thread that are listed in the `ProfileEvents.Names` 列。
**示例**
``` sql
SELECT * FROM system.query_thread_log LIMIT 1 FORMAT Vertical
```
``` text
Row 1:
──────
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: 1
read_bytes: 1
written_rows: 0
written_bytes: 0
memory_usage: 0
peak_memory_usage: 0
thread_name: QueryPipelineEx
thread_id: 28952
master_thread_id: 28924
query: SELECT 1
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
ProfileEvents.Names: ['ContextLock','RealTimeMicroseconds','UserTimeMicroseconds','OSCPUWaitMicroseconds','OSCPUVirtualTimeMicroseconds']
ProfileEvents.Values: [1,97,81,5,81]
...
```
**另请参阅**
- [系统。query\_log](../../operations/system-tables/query_log.md#system_tables-query_log) — Description of the `query_log` 系统表，其中包含有关查询执行的公共信息。

126
docs/zh/operations/system-tables/replicas.md Normal file
View File

@ -0,0 +1,126 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。副本 {#system_tables-replicas}
包含驻留在本地服务器上的复制表的信息和状态。
此表可用于监视。 该表对于每个已复制的\*表都包含一行。
示例:
``` sql
SELECT *
FROM system.replicas
WHERE table = 'visits'
FORMAT Vertical
```
``` text
Row 1:
──────
database: merge
table: visits
engine: ReplicatedCollapsingMergeTree
is_leader: 1
can_become_leader: 1
is_readonly: 0
is_session_expired: 0
future_parts: 1
parts_to_check: 0
zookeeper_path: /clickhouse/tables/01-06/visits
replica_name: example01-06-1.yandex.ru
replica_path: /clickhouse/tables/01-06/visits/replicas/example01-06-1.yandex.ru
columns_version: 9
queue_size: 1
inserts_in_queue: 0
merges_in_queue: 1
part_mutations_in_queue: 0
queue_oldest_time: 2020-02-20 08:34:30
inserts_oldest_time: 0000-00-00 00:00:00
merges_oldest_time: 2020-02-20 08:34:30
part_mutations_oldest_time: 0000-00-00 00:00:00
oldest_part_to_get:
oldest_part_to_merge_to: 20200220_20284_20840_7
oldest_part_to_mutate_to:
log_max_index: 596273
log_pointer: 596274
last_queue_update: 2020-02-20 08:34:32
absolute_delay: 0
total_replicas: 2
active_replicas: 2
```
列:
- `database` (`String`)-数据库名称
- `table` (`String`)-表名
- `engine` (`String`)-表引擎名称
- `is_leader` (`UInt8`)-副本是否是领导者。
一次只有一个副本可以成为领导者。 领导者负责选择要执行的后台合并。
请注意，可以对任何可用且在ZK中具有会话的副本执行写操作，而不管该副本是否为leader。
- `can_become_leader` (`UInt8`)-副本是否可以当选为领导者。
- `is_readonly` (`UInt8`)-副本是否处于只读模式。
如果配置没有ZooKeeper的部分，如果在ZooKeeper中重新初始化会话时发生未知错误，以及在ZooKeeper中重新初始化会话时发生未知错误，则此模式将打开。
- `is_session_expired` (`UInt8`)-与ZooKeeper的会话已经过期。 基本上一样 `is_readonly`.
- `future_parts` (`UInt32`)-由于尚未完成的插入或合并而显示的数据部分的数量。
- `parts_to_check` (`UInt32`)-队列中用于验证的数据部分的数量。 如果怀疑零件可能已损坏，则将其放入验证队列。
- `zookeeper_path` (`String`)-在ZooKeeper中的表数据路径。
- `replica_name` (`String`)-在动物园管理员副本名称. 同一表的不同副本具有不同的名称。
- `replica_path` (`String`)-在ZooKeeper中的副本数据的路径。 与连接相同 ‘zookeeper\_path/replicas/replica\_path’.
- `columns_version` (`Int32`)-表结构的版本号。 指示执行ALTER的次数。 如果副本有不同的版本，这意味着一些副本还没有做出所有的改变。
- `queue_size` (`UInt32`)-等待执行的操作的队列大小。 操作包括插入数据块、合并和某些其他操作。 它通常与 `future_parts`.
- `inserts_in_queue` (`UInt32`)-需要插入数据块的数量。 插入通常复制得相当快。 如果这个数字很大，这意味着有什么不对劲。
- `merges_in_queue` (`UInt32`)-等待进行合并的数量。 有时合并时间很长，因此此值可能长时间大于零。
- `part_mutations_in_queue` (`UInt32`）-等待进行的突变的数量。
- `queue_oldest_time` (`DateTime`)-如果 `queue_size` 大于0，显示何时将最旧的操作添加到队列中。
- `inserts_oldest_time` (`DateTime`）-看 `queue_oldest_time`
- `merges_oldest_time` (`DateTime`）-看 `queue_oldest_time`
- `part_mutations_oldest_time` (`DateTime`）-看 `queue_oldest_time`
接下来的4列只有在有ZK活动会话的情况下才具有非零值。
- `log_max_index` (`UInt64`)-一般活动日志中的最大条目数。
- `log_pointer` (`UInt64`)-副本复制到其执行队列的常规活动日志中的最大条目数加一。 如果 `log_pointer` 比 `log_max_index`，有点不对劲。
- `last_queue_update` (`DateTime`)-上次更新队列时。
- `absolute_delay` (`UInt64`）-当前副本有多大滞后秒。
- `total_replicas` (`UInt8`)-此表的已知副本总数。
- `active_replicas` (`UInt8`)-在ZooKeeper中具有会话的此表的副本的数量（即正常运行的副本的数量）。
如果您请求所有列，表可能会工作得有点慢，因为每行都会从ZooKeeper进行几次读取。
如果您没有请求最后4列（log\_max\_index，log\_pointer，total\_replicas，active\_replicas），表工作得很快。
例如，您可以检查一切是否正常工作，如下所示:
``` sql
SELECT
database,
table,
is_leader,
is_readonly,
is_session_expired,
future_parts,
parts_to_check,
columns_version,
queue_size,
inserts_in_queue,
merges_in_queue,
log_max_index,
log_pointer,
total_replicas,
active_replicas
FROM system.replicas
WHERE
is_readonly
OR is_session_expired
OR future_parts > 20
OR parts_to_check > 10
OR queue_size > 20
OR inserts_in_queue > 10
OR log_max_index - log_pointer > 10
OR total_replicas < 2
OR active_replicas < total_replicas
```
如果这个查询没有返回任何东西，这意味着一切都很好。

55
docs/zh/operations/system-tables/settings.md Normal file
View File

@ -0,0 +1,55 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。设置 {#system-tables-system-settings}
包含有关当前用户的会话设置的信息。
列:
- `name` ([字符串](../../sql-reference/data-types/string.md)) — Setting name.
- `value` ([字符串](../../sql-reference/data-types/string.md)) — Setting value.
- `changed` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Shows whether a setting is changed from its default value.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — Short setting description.
- `min` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — Minimum value of the setting, if any is set via [制约因素](../../operations/settings/constraints-on-settings.md#constraints-on-settings). 如果设置没有最小值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `max` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — Maximum value of the setting, if any is set via [制约因素](../../operations/settings/constraints-on-settings.md#constraints-on-settings). 如果设置没有最大值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `readonly` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Shows whether the current user can change the setting:
- `0` — Current user can change the setting.
- `1` — Current user can't change the setting.
**示例**
下面的示例演示如何获取有关名称包含的设置的信息 `min_i`.
``` sql
SELECT *
FROM system.settings
WHERE name LIKE '%min_i%'
```
``` text
┌─name────────────────────────────────────────┬─value─────┬─changed─┬─description───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┬─min──┬─max──┬─readonly─┐
│ min_insert_block_size_rows │ 1048576 │ 0 │ Squash blocks passed to INSERT query to specified size in rows, if blocks are not big enough. │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ 0 │
│ min_insert_block_size_bytes │ 268435456 │ 0 │ Squash blocks passed to INSERT query to specified size in bytes, if blocks are not big enough. │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ 0 │
│ read_backoff_min_interval_between_events_ms │ 1000 │ 0 │ Settings to reduce the number of threads in case of slow reads. Do not pay attention to the event, if the previous one has passed less than a certain amount of time. │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ 0 │
└─────────────────────────────────────────────┴───────────┴─────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┴──────┴──────┴──────────┘
```
使用 `WHERE changed` 可以是有用的，例如，当你想检查:
- 配置文件中的设置是否正确加载并正在使用。
- 在当前会话中更改的设置。
<!-- -->
``` sql
SELECT * FROM system.settings WHERE changed AND name='load_balancing'
```
**另请参阅**
- [设置](../../operations/settings/index.md#session-settings-intro)
- [查询权限](../../operations/settings/permissions-for-queries.md#settings_readonly)
- [对设置的限制](../../operations/settings/constraints-on-settings.md)

19
docs/zh/operations/system-tables/storage_policies.md Normal file
View File

@ -0,0 +1,19 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。storage\_policies {#system_tables-storage_policies}
包含有关存储策略和卷中定义的信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
列:
- `policy_name` ([字符串](../../sql-reference/data-types/string.md)) — Name of the storage policy.
- `volume_name` ([字符串](../../sql-reference/data-types/string.md)) — Volume name defined in the storage policy.
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Volume order number in the configuration.
- `disks` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Disk names, defined in the storage policy.
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
如果存储策略包含多个卷，则每个卷的信息将存储在表的单独行中。

40
docs/zh/operations/system-tables/table_engines.md Normal file
View File

@ -0,0 +1,40 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。表\_engines {#system-table-engines}
包含服务器支持的表引擎的描述及其功能支持信息。
此表包含以下列（列类型显示在括号中):
- `name` (String) — The name of table engine.
- `supports_settings` (UInt8) — Flag that indicates if table engine supports `SETTINGS` 条款
- `supports_skipping_indices` (UInt8) — Flag that indicates if table engine supports [跳过索引](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-data_skipping-indexes).
- `supports_ttl` (UInt8) — Flag that indicates if table engine supports [TTL](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `supports_sort_order` (UInt8) — Flag that indicates if table engine supports clauses `PARTITION_BY`, `PRIMARY_KEY`, `ORDER_BY` 和 `SAMPLE_BY`.
- `supports_replication` (UInt8) — Flag that indicates if table engine supports [数据复制](../../engines/table-engines/mergetree-family/replication.md).
- `supports_duduplication` (UInt8) — Flag that indicates if table engine supports data deduplication.
示例:
``` sql
SELECT *
FROM system.table_engines
WHERE name in ('Kafka', 'MergeTree', 'ReplicatedCollapsingMergeTree')
```
``` text
┌─name──────────────────────────┬─supports_settings─┬─supports_skipping_indices─┬─supports_sort_order─┬─supports_ttl─┬─supports_replication─┬─supports_deduplication─┐
│ Kafka │ 1 │ 0 │ 0 │ 0 │ 0 │ 0 │
│ MergeTree │ 1 │ 1 │ 1 │ 1 │ 0 │ 0 │
│ ReplicatedCollapsingMergeTree │ 1 │ 1 │ 1 │ 1 │ 1 │ 1 │
└───────────────────────────────┴───────────────────┴───────────────────────────┴─────────────────────┴──────────────┴──────────────────────┴────────────────────────┘
```
**另请参阅**
- 梅树家族 [查询子句](../../engines/table-engines/mergetree-family/mergetree.md#mergetree-query-clauses)
- 卡夫卡 [设置](../../engines/table-engines/integrations/kafka.md#table_engine-kafka-creating-a-table)
- 加入我们 [设置](../../engines/table-engines/special/join.md#join-limitations-and-settings)

54
docs/zh/operations/system-tables/tables.md Normal file
View File

@ -0,0 +1,54 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。表 {#system-tables}
包含服务器知道的每个表的元数据。 分离的表不显示在 `system.tables`.
此表包含以下列（列类型显示在括号中):
- `database` (String) — The name of the database the table is in.
- `name` (String) — Table name.
- `engine` (String) — Table engine name (without parameters).
- `is_temporary` (UInt8)-指示表是否是临时的标志。
- `data_path` (String)-文件系统中表数据的路径。
- `metadata_path` (String)-文件系统中表元数据的路径。
- `metadata_modification_time` (DateTime)-表元数据的最新修改时间。
- `dependencies_database` (数组(字符串))-数据库依赖关系.
- `dependencies_table` （数组（字符串））-表依赖关系 ([MaterializedView](../../engines/table-engines/special/materializedview.md) 基于当前表的表）。
- `create_table_query` (String)-用于创建表的查询。
- `engine_full` (String)-表引擎的参数。
- `partition_key` (String)-表中指定的分区键表达式。
- `sorting_key` (String)-表中指定的排序键表达式。
- `primary_key` (String)-表中指定的主键表达式。
- `sampling_key` (String)-表中指定的采样键表达式。
- `storage_policy` (字符串)-存储策略:
- [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes)
- [分布](../../engines/table-engines/special/distributed.md#distributed)
- `total_rows` (Nullable(UInt64))-总行数，如果可以快速确定表中的确切行数，否则 `Null` （包括内衣 `Buffer` 表）。
- `total_bytes` (Nullable(UInt64))-总字节数，如果可以快速确定存储表的确切字节数，否则 `Null` (**不** 包括任何底层存储）。
- If the table stores data on disk, returns used space on disk (i.e. compressed).
- 如果表在内存中存储数据,返回在内存中使用的近似字节数.
该 `system.tables` 表中使用 `SHOW TABLES` 查询实现。

31
docs/zh/operations/system-tables/text_log.md Normal file
View File

@ -0,0 +1,31 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。text\_log {#system-tables-text-log}
包含日志记录条目。 进入该表的日志记录级别可以通过以下方式进行限制 `text_log.level` 服务器设置。
列:
- `event_date` (Date) — Date of the entry.
- `event_time` (DateTime) — Time of the entry.
- `microseconds` (UInt32) — Microseconds of the entry.
- `thread_name` (String) — Name of the thread from which the logging was done.
- `thread_id` (UInt64) — OS thread ID.
- `level` (`Enum8`) — Entry level. Possible values:
- `1` 或 `'Fatal'`.
- `2` 或 `'Critical'`.
- `3` 或 `'Error'`.
- `4` 或 `'Warning'`.
- `5` 或 `'Notice'`.
- `6` 或 `'Information'`.
- `7` 或 `'Debug'`.
- `8` 或 `'Trace'`.
- `query_id` (String) — ID of the query.
- `logger_name` (LowCardinality(String)) — Name of the logger (i.e. `DDLWorker`).
- `message` (String) — The message itself.
- `revision` (UInt32) — ClickHouse revision.
- `source_file` (LowCardinality(String)) — Source file from which the logging was done.
- `source_line` (UInt64) — Source line from which the logging was done.

53
docs/zh/operations/system-tables/trace_log.md Normal file
View File

@ -0,0 +1,53 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。trace\_log {#system_tables-trace_log}
包含采样查询探查器收集的堆栈跟踪。
ClickHouse创建此表时 [trace\_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-trace_log) 服务器配置部分被设置。 也是 [query\_profiler\_real\_time\_period\_ns](../../operations/settings/settings.md#query_profiler_real_time_period_ns) 和 [query\_profiler\_cpu\_time\_period\_ns](../../operations/settings/settings.md#query_profiler_cpu_time_period_ns) 应设置设置。
要分析日志，请使用 `addressToLine`, `addressToSymbol` 和 `demangle` 内省功能。
列:
- `event_date` ([日期](../../sql-reference/data-types/date.md)) — Date of sampling moment.
- `event_time` ([日期时间](../../sql-reference/data-types/datetime.md)) — Timestamp of the sampling moment.
- `timestamp_ns` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Timestamp of the sampling moment in nanoseconds.
- `revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — ClickHouse server build revision.
通过以下方式连接到服务器 `clickhouse-client`，你看到的字符串类似于 `Connected to ClickHouse server version 19.18.1 revision 54429.`. 该字段包含 `revision`，但不是 `version` 的服务器。
- `timer_type` ([枚举8](../../sql-reference/data-types/enum.md)) — Timer type:
- `Real` 表示挂钟时间。
- `CPU` 表示CPU时间。
- `thread_number` ([UInt32](../../sql-reference/data-types/int-uint.md)) — Thread identifier.
- `query_id` ([字符串](../../sql-reference/data-types/string.md)) — Query identifier that can be used to get details about a query that was running from the [query\_log](#system_tables-query_log) 系统表.
- `trace` ([数组(UInt64)](../../sql-reference/data-types/array.md)) — Stack trace at the moment of sampling. Each element is a virtual memory address inside ClickHouse server process.
**示例**
``` sql
SELECT * FROM system.trace_log LIMIT 1 \G
```
``` text
Row 1:
──────
event_date: 2019-11-15
event_time: 2019-11-15 15:09:38
revision: 54428
timer_type: Real
thread_number: 48
query_id: acc4d61f-5bd1-4a3e-bc91-2180be37c915
trace: [94222141367858,94222152240175,94222152325351,94222152329944,94222152330796,94222151449980,94222144088167,94222151682763,94222144088167,94222151682763,94222144088167,94222144058283,94222144059248,94222091840750,94222091842302,94222091831228,94222189631488,140509950166747,140509942945935]
```

75
docs/zh/operations/system-tables/zookeeper.md Normal file
View File

@ -0,0 +1,75 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 系统。动物园管理员 {#system-zookeeper}
如果未配置ZooKeeper，则表不存在。 允许从配置中定义的ZooKeeper集群读取数据。
查询必须具有 ‘path’ WHERE子句中的平等条件。 这是ZooKeeper中您想要获取数据的孩子的路径。
查询 `SELECT * FROM system.zookeeper WHERE path = '/clickhouse'` 输出对所有孩子的数据 `/clickhouse` 节点。
要输出所有根节点的数据，write path= ‘/’.
如果在指定的路径 ‘path’ 不存在，将引发异常。
列:
- `name` (String) — The name of the node.
- `path` (String) — The path to the node.
- `value` (String) — Node value.
- `dataLength` (Int32) — Size of the value.
- `numChildren` (Int32) — Number of descendants.
- `czxid` (Int64) — ID of the transaction that created the node.
- `mzxid` (Int64) — ID of the transaction that last changed the node.
- `pzxid` (Int64) — ID of the transaction that last deleted or added descendants.
- `ctime` (DateTime) — Time of node creation.
- `mtime` (DateTime) — Time of the last modification of the node.
- `version` (Int32) — Node version: the number of times the node was changed.
- `cversion` (Int32) — Number of added or removed descendants.
- `aversion` (Int32) — Number of changes to the ACL.
- `ephemeralOwner` (Int64) — For ephemeral nodes, the ID of the session that owns this node.
示例:
``` sql
SELECT *
FROM system.zookeeper
WHERE path = '/clickhouse/tables/01-08/visits/replicas'
FORMAT Vertical
```
``` text
Row 1:
──────
name: example01-08-1.yandex.ru
value:
czxid: 932998691229
mzxid: 932998691229
ctime: 2015-03-27 16:49:51
mtime: 2015-03-27 16:49:51
version: 0
cversion: 47
aversion: 0
ephemeralOwner: 0
dataLength: 0
numChildren: 7
pzxid: 987021031383
path: /clickhouse/tables/01-08/visits/replicas
Row 2:
──────
name: example01-08-2.yandex.ru
value:
czxid: 933002738135
mzxid: 933002738135
ctime: 2015-03-27 16:57:01
mtime: 2015-03-27 16:57:01
version: 0
cversion: 37
aversion: 0
ephemeralOwner: 0
dataLength: 0
numChildren: 7
pzxid: 987021252247
path: /clickhouse/tables/01-08/visits/replicas
```

2
docs/zh/sql-reference/dictionaries/external-dictionaries/external-dicts.md
View File

@ -19,7 +19,7 @@ ClickHouse:
字典可以在服务器启动或首次使用时加载，具体取决于 [dictionaries\_lazy\_load](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-dictionaries_lazy_load) 设置。
该 [字典](../../../operations/system-tables.md#system_tables-dictionaries) 系统表包含有关在服务器上配置的字典的信息。 对于每个字典，你可以在那里找到:
该 [字典](../../../operations/system-tables/dictionaries.md#system_tables-dictionaries) 系统表包含有关在服务器上配置的字典的信息。 对于每个字典，你可以在那里找到:
- 字典的状态。
- 配置参数。

2
docs/zh/sql-reference/functions/introspection.md
View File

@ -20,7 +20,7 @@ toc_title: "\u81EA\u7701"
For security reasons introspection functions are disabled by default.
ClickHouse将探查器报告保存到 [trace\_log](../../operations/system-tables.md#system_tables-trace_log) 系统表. 确保正确配置了表和探查器。
ClickHouse将探查器报告保存到 [trace\_log](../../operations/system-tables/trace_log.md#system_tables-trace_log) 系统表. 确保正确配置了表和探查器。
## addressToLine {#addresstoline}

1
docs/zh/sql-reference/operators/in.md
View File

@ -1 +0,0 @@
../../../en/sql-reference/operators/in.md

204
docs/zh/sql-reference/operators/in.md Normal file
View File

@ -0,0 +1,204 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# 在运营商 {#select-in-operators}
该 `IN`, `NOT IN`, `GLOBAL IN`，和 `GLOBAL NOT IN` 运算符是单独复盖的，因为它们的功能相当丰富。
运算符的左侧是单列或元组。
例:
``` sql
SELECT UserID IN (123, 456) FROM ...
SELECT (CounterID, UserID) IN ((34, 123), (101500, 456)) FROM ...
```
如果左侧是索引中的单列，而右侧是一组常量，则系统将使用索引处理查询。
Don't list too many values explicitly (i.e. millions). If a data set is large, put it in a temporary table (for example, see the section “External data for query processing”），然后使用子查询。
运算符的右侧可以是一组常量表达式、一组带有常量表达式的元组（如上面的示例所示），或括号中的数据库表或SELECT子查询的名称。
如果运算符的右侧是表的名称（例如, `UserID IN users`），这相当于子查询 `UserID IN (SELECT * FROM users)`. 使用与查询一起发送的外部数据时，请使用此选项。 例如，查询可以与一组用户Id一起发送到 ‘users’ 应过滤的临时表。
如果运算符的右侧是具有Set引擎的表名（始终位于RAM中的准备好的数据集），则不会为每个查询重新创建数据集。
子查询可以指定多个用于筛选元组的列。
示例:
``` sql
SELECT (CounterID, UserID) IN (SELECT CounterID, UserID FROM ...) FROM ...
```
IN运算符左侧和右侧的列应具有相同的类型。
IN运算符和子查询可能出现在查询的任何部分，包括聚合函数和lambda函数。
示例:
``` sql
SELECT
EventDate,
avg(UserID IN
(
SELECT UserID
FROM test.hits
WHERE EventDate = toDate('2014-03-17')
)) AS ratio
FROM test.hits
GROUP BY EventDate
ORDER BY EventDate ASC
```
``` text
┌──EventDate─┬────ratio─┐
│ 2014-03-17 │ 1 │
│ 2014-03-18 │ 0.807696 │
│ 2014-03-19 │ 0.755406 │
│ 2014-03-20 │ 0.723218 │
│ 2014-03-21 │ 0.697021 │
│ 2014-03-22 │ 0.647851 │
│ 2014-03-23 │ 0.648416 │
└────────────┴──────────┘
```
对于3月17日后的每一天，计算3月17日访问该网站的用户所做的浏览量百分比。
IN子句中的子查询始终只在单个服务器上运行一次。 没有依赖子查询。
## 空处理 {#in-null-processing}
在请求处理过程中， `IN` 运算符假定运算的结果 [NULL](../../sql-reference/syntax.md#null-literal) 总是等于 `0`，无论是否 `NULL` 位于操作员的右侧或左侧。 `NULL` 值不包含在任何数据集中，彼此不对应，并且在以下情况下无法进行比较 [transform\_null\_in=0](../../operations/settings/settings.md#transform_null_in).
下面是一个例子 `t_null` 表:
``` text
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
运行查询 `SELECT x FROM t_null WHERE y IN (NULL,3)` 为您提供以下结果:
``` text
┌─x─┐
│ 2 │
└───┘
```
你可以看到，在其中的行 `y = NULL` 被抛出的查询结果。 这是因为ClickHouse无法决定是否 `NULL` 包含在 `(NULL,3)` 设置，返回 `0` 作为操作的结果，和 `SELECT` 从最终输出中排除此行。
``` sql
SELECT y IN (NULL, 3)
FROM t_null
```
``` text
┌─in(y, tuple(NULL, 3))─┐
│ 0 │
│ 1 │
└───────────────────────┘
```
## 分布式子查询 {#select-distributed-subqueries}
带子查询的IN-s有两个选项（类似于连接）：normal `IN` / `JOIN` 和 `GLOBAL IN` / `GLOBAL JOIN`. 它们在分布式查询处理的运行方式上有所不同。
!!! attention "注意"
请记住，下面描述的算法可能会有不同的工作方式取决于 [设置](../../operations/settings/settings.md) `distributed_product_mode` 设置。
当使用常规IN时，查询被发送到远程服务器，并且它们中的每个服务器都在运行子查询 `IN` 或 `JOIN` 条款
使用时 `GLOBAL IN` / `GLOBAL JOINs`，首先所有的子查询都运行 `GLOBAL IN` / `GLOBAL JOINs`，并将结果收集在临时表中。 然后将临时表发送到每个远程服务器，其中使用此临时数据运行查询。
对于非分布式查询，请使用常规 `IN` / `JOIN`.
在使用子查询时要小心 `IN` / `JOIN` 用于分布式查询处理的子句。
让我们来看看一些例子。 假设集群中的每个服务器都有一个正常的 **local\_table**. 每个服务器还具有 **distributed\_table** 表与 **分布** 类型，它查看群集中的所有服务器。
对于查询 **distributed\_table**，查询将被发送到所有远程服务器，并使用以下命令在其上运行 **local\_table**.
例如，查询
``` sql
SELECT uniq(UserID) FROM distributed_table
```
将被发送到所有远程服务器
``` sql
SELECT uniq(UserID) FROM local_table
```
并且并行运行它们中的每一个，直到达到可以结合中间结果的阶段。 然后将中间结果返回给请求者服务器并在其上合并，并将最终结果发送给客户端。
现在让我们检查一个查询IN:
``` sql
SELECT uniq(UserID) FROM distributed_table WHERE CounterID = 101500 AND UserID IN (SELECT UserID FROM local_table WHERE CounterID = 34)
```
- 计算两个网站的受众的交集。
此查询将以下列方式发送到所有远程服务器
``` sql
SELECT uniq(UserID) FROM local_table WHERE CounterID = 101500 AND UserID IN (SELECT UserID FROM local_table WHERE CounterID = 34)
```
换句话说，IN子句中的数据集将在每台服务器上独立收集，仅在每台服务器上本地存储的数据中收集。
如果您已经为此情况做好准备，并且已经将数据分散到群集服务器上，以便单个用户Id的数据完全驻留在单个服务器上，则这将正常和最佳地工作。 在这种情况下，所有必要的数据将在每台服务器上本地提供。 否则，结果将是不准确的。 我们将查询的这种变体称为 “local IN”.
若要更正数据在群集服务器上随机传播时查询的工作方式，可以指定 **distributed\_table** 在子查询中。 查询如下所示:
``` sql
SELECT uniq(UserID) FROM distributed_table WHERE CounterID = 101500 AND UserID IN (SELECT UserID FROM distributed_table WHERE CounterID = 34)
```
此查询将以下列方式发送到所有远程服务器
``` sql
SELECT uniq(UserID) FROM local_table WHERE CounterID = 101500 AND UserID IN (SELECT UserID FROM distributed_table WHERE CounterID = 34)
```
子查询将开始在每个远程服务器上运行。 由于子查询使用分布式表，因此每个远程服务器上的子查询将重新发送到每个远程服务器
``` sql
SELECT UserID FROM local_table WHERE CounterID = 34
```
例如，如果您有100台服务器的集群，则执行整个查询将需要10,000个基本请求，这通常被认为是不可接受的。
在这种情况下，应始终使用GLOBAL IN而不是IN。 让我们来看看它是如何工作的查询
``` sql
SELECT uniq(UserID) FROM distributed_table WHERE CounterID = 101500 AND UserID GLOBAL IN (SELECT UserID FROM distributed_table WHERE CounterID = 34)
```
请求者服务器将运行子查询
``` sql
SELECT UserID FROM distributed_table WHERE CounterID = 34
```
结果将被放在RAM中的临时表中。 然后请求将被发送到每个远程服务器
``` sql
SELECT uniq(UserID) FROM local_table WHERE CounterID = 101500 AND UserID GLOBAL IN _data1
```
和临时表 `_data1` 将通过查询发送到每个远程服务器（临时表的名称是实现定义的）。
这比使用正常IN更优化。 但是，请记住以下几点:
1. 创建临时表时，数据不是唯一的。 要减少通过网络传输的数据量，请在子查询中指定DISTINCT。 （你不需要为正常人做这个。)
2. 临时表将被发送到所有远程服务器。 传输不考虑网络拓扑。 例如，如果10个远程服务器驻留在与请求者服务器非常远程的数据中心中，则数据将通过通道发送10次到远程数据中心。 使用GLOBAL IN时尽量避免使用大型数据集。
3. 将数据传输到远程服务器时，无法配置网络带宽限制。 您可能会使网络过载。
4. 尝试跨服务器分发数据，以便您不需要定期使用GLOBAL IN。
5. 如果您需要经常使用GLOBAL IN，请规划ClickHouse集群的位置，以便单个副本组驻留在不超过一个数据中心中，并且它们之间具有快速网络，以便可以完全在单个数据中心内处理查询。
这也是有意义的，在指定一个本地表 `GLOBAL IN` 子句，以防此本地表仅在请求者服务器上可用，并且您希望在远程服务器上使用来自它的数据。

2
docs/zh/sql-reference/statements/alter.md
View File

@ -113,7 +113,7 @@ MODIFY COLUMN [IF EXISTS] name [type] [default_expr] [TTL]
- TTL
有关修改列TTL的示例，请参见 [Column TTL](../engines/table_engines/mergetree_family/mergetree.md#mergetree-column-ttl).
有关修改列TTL的示例，请参见 [Column TTL](../../engines/table-engines/mergetree-family/mergetree.md#mergetree-column-ttl).
如果语句中包含 `IF EXISTS` ，遇到不存在的列，sql执行不会报错。

2
docs/zh/sql-reference/statements/misc.md
View File

@ -223,7 +223,7 @@ KILL MUTATION [ON CLUSTER cluster]
[FORMAT format]
```
尝试取消和删除 [突变](alter.md#alter-mutations) 当前正在执行。 要取消的突变选自 [`system.mutations`](../../operations/system-tables.md#system_tables-mutations) 表使用由指定的过滤器 `WHERE` 《公约》条款 `KILL` 查询。
尝试取消和删除 [突变](alter.md#alter-mutations) 当前正在执行。 要取消的突变选自 [`system.mutations`](../../operations/system-tables/mutations.md#system_tables-mutations) 表使用由指定的过滤器 `WHERE` 《公约》条款 `KILL` 查询。
测试查询 (`TEST`）仅检查用户的权限并显示要停止的查询列表。

1
docs/zh/sql-reference/statements/select/array-join.md
View File

@ -1 +0,0 @@
../../../../en/sql-reference/statements/select/array-join.md

283
docs/zh/sql-reference/statements/select/array-join.md Normal file
View File

@ -0,0 +1,283 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_title: ARRAY JOIN
---
# ARRAY JOIN子句 {#select-array-join-clause}
对于包含数组列的表来说，这是一种常见的操作，用于生成一个新表，该表具有包含该初始列的每个单独数组元素的列，而其他列的值将被重复。 这是什么基本情况 `ARRAY JOIN` 子句有
它的名字来自这样一个事实，即它可以被视为执行 `JOIN` 具有数组或嵌套数据结构。 意图类似于 [arrayJoin](../../../sql-reference/functions/array-join.md#functions_arrayjoin) 功能，但该子句功能更广泛。
语法:
``` sql
SELECT <expr_list>
FROM <left_subquery>
[LEFT] ARRAY JOIN <array>
[WHERE|PREWHERE <expr>]
...
```
您只能指定一个 `ARRAY JOIN` a中的条款 `SELECT` 查询。
支持的类型 `ARRAY JOIN` 下面列出:
- `ARRAY JOIN` -在基本情况下，空数组不包括在结果中 `JOIN`.
- `LEFT ARRAY JOIN` -的结果 `JOIN` 包含具有空数组的行。 空数组的值设置为数组元素类型的默认值（通常为0、空字符串或NULL）。
## 基本数组连接示例 {#basic-array-join-examples}
下面的例子演示的用法 `ARRAY JOIN` 和 `LEFT ARRAY JOIN` 条款 让我们创建一个表 [阵列](../../../sql-reference/data-types/array.md) 键入column并在其中插入值:
``` sql
CREATE TABLE arrays_test
(
s String,
arr Array(UInt8)
) ENGINE = Memory;
INSERT INTO arrays_test
VALUES ('Hello', [1,2]), ('World', [3,4,5]), ('Goodbye', []);
```
``` text
┌─s───────────┬─arr─────┐
│ Hello │ [1,2] │
│ World │ [3,4,5] │
│ Goodbye │ [] │
└─────────────┴─────────┘
```
下面的例子使用 `ARRAY JOIN` 条款:
``` sql
SELECT s, arr
FROM arrays_test
ARRAY JOIN arr;
```
``` text
┌─s─────┬─arr─┐
│ Hello │ 1 │
│ Hello │ 2 │
│ World │ 3 │
│ World │ 4 │
│ World │ 5 │
└───────┴─────┘
```
下一个示例使用 `LEFT ARRAY JOIN` 条款:
``` sql
SELECT s, arr
FROM arrays_test
LEFT ARRAY JOIN arr;
```
``` text
┌─s───────────┬─arr─┐
│ Hello │ 1 │
│ Hello │ 2 │
│ World │ 3 │
│ World │ 4 │
│ World │ 5 │
│ Goodbye │ 0 │
└─────────────┴─────┘
```
## 使用别名 {#using-aliases}
可以为数组中的别名指定 `ARRAY JOIN` 条款 在这种情况下，数组项目可以通过此别名访问，但数组本身可以通过原始名称访问。 示例:
``` sql
SELECT s, arr, a
FROM arrays_test
ARRAY JOIN arr AS a;
```
``` text
┌─s─────┬─arr─────┬─a─┐
│ Hello │ [1,2] │ 1 │
│ Hello │ [1,2] │ 2 │
│ World │ [3,4,5] │ 3 │
│ World │ [3,4,5] │ 4 │
│ World │ [3,4,5] │ 5 │
└───────┴─────────┴───┘
```
使用别名，您可以执行 `ARRAY JOIN` 与外部阵列。 例如:
``` sql
SELECT s, arr_external
FROM arrays_test
ARRAY JOIN [1, 2, 3] AS arr_external;
```
``` text
┌─s───────────┬─arr_external─┐
│ Hello │ 1 │
│ Hello │ 2 │
│ Hello │ 3 │
│ World │ 1 │
│ World │ 2 │
│ World │ 3 │
│ Goodbye │ 1 │
│ Goodbye │ 2 │
│ Goodbye │ 3 │
└─────────────┴──────────────┘
```
多个数组可以在逗号分隔 `ARRAY JOIN` 条款 在这种情况下, `JOIN` 与它们同时执行（直接和，而不是笛卡尔积）。 请注意，所有数组必须具有相同的大小。 示例:
``` sql
SELECT s, arr, a, num, mapped
FROM arrays_test
ARRAY JOIN arr AS a, arrayEnumerate(arr) AS num, arrayMap(x -> x + 1, arr) AS mapped;
```
``` text
┌─s─────┬─arr─────┬─a─┬─num─┬─mapped─┐
│ Hello │ [1,2] │ 1 │ 1 │ 2 │
│ Hello │ [1,2] │ 2 │ 2 │ 3 │
│ World │ [3,4,5] │ 3 │ 1 │ 4 │
│ World │ [3,4,5] │ 4 │ 2 │ 5 │
│ World │ [3,4,5] │ 5 │ 3 │ 6 │
└───────┴─────────┴───┴─────┴────────┘
```
下面的例子使用 [arrayEnumerate](../../../sql-reference/functions/array-functions.md#array_functions-arrayenumerate) 功能:
``` sql
SELECT s, arr, a, num, arrayEnumerate(arr)
FROM arrays_test
ARRAY JOIN arr AS a, arrayEnumerate(arr) AS num;
```
``` text
┌─s─────┬─arr─────┬─a─┬─num─┬─arrayEnumerate(arr)─┐
│ Hello │ [1,2] │ 1 │ 1 │ [1,2] │
│ Hello │ [1,2] │ 2 │ 2 │ [1,2] │
│ World │ [3,4,5] │ 3 │ 1 │ [1,2,3] │
│ World │ [3,4,5] │ 4 │ 2 │ [1,2,3] │
│ World │ [3,4,5] │ 5 │ 3 │ [1,2,3] │
└───────┴─────────┴───┴─────┴─────────────────────┘
```
## 具有嵌套数据结构的数组连接 {#array-join-with-nested-data-structure}
`ARRAY JOIN` 也适用于 [嵌套数据结构](../../../sql-reference/data-types/nested-data-structures/nested.md):
``` sql
CREATE TABLE nested_test
(
s String,
nest Nested(
x UInt8,
y UInt32)
) ENGINE = Memory;
INSERT INTO nested_test
VALUES ('Hello', [1,2], [10,20]), ('World', [3,4,5], [30,40,50]), ('Goodbye', [], []);
```
``` text
┌─s───────┬─nest.x──┬─nest.y─────┐
│ Hello │ [1,2] │ [10,20] │
│ World │ [3,4,5] │ [30,40,50] │
│ Goodbye │ [] │ [] │
└─────────┴─────────┴────────────┘
```
``` sql
SELECT s, `nest.x`, `nest.y`
FROM nested_test
ARRAY JOIN nest;
```
``` text
┌─s─────┬─nest.x─┬─nest.y─┐
│ Hello │ 1 │ 10 │
│ Hello │ 2 │ 20 │
│ World │ 3 │ 30 │
│ World │ 4 │ 40 │
│ World │ 5 │ 50 │
└───────┴────────┴────────┘
```
当指定嵌套数据结构的名称 `ARRAY JOIN`，意思是一样的 `ARRAY JOIN` 它包含的所有数组元素。 下面列出了示例:
``` sql
SELECT s, `nest.x`, `nest.y`
FROM nested_test
ARRAY JOIN `nest.x`, `nest.y`;
```
``` text
┌─s─────┬─nest.x─┬─nest.y─┐
│ Hello │ 1 │ 10 │
│ Hello │ 2 │ 20 │
│ World │ 3 │ 30 │
│ World │ 4 │ 40 │
│ World │ 5 │ 50 │
└───────┴────────┴────────┘
```
这种变化也是有道理的:
``` sql
SELECT s, `nest.x`, `nest.y`
FROM nested_test
ARRAY JOIN `nest.x`;
```
``` text
┌─s─────┬─nest.x─┬─nest.y─────┐
│ Hello │ 1 │ [10,20] │
│ Hello │ 2 │ [10,20] │
│ World │ 3 │ [30,40,50] │
│ World │ 4 │ [30,40,50] │
│ World │ 5 │ [30,40,50] │
└───────┴────────┴────────────┘
```
可以将别名用于嵌套数据结构，以便选择 `JOIN` 结果或源数组。 示例:
``` sql
SELECT s, `n.x`, `n.y`, `nest.x`, `nest.y`
FROM nested_test
ARRAY JOIN nest AS n;
```
``` text
┌─s─────┬─n.x─┬─n.y─┬─nest.x──┬─nest.y─────┐
│ Hello │ 1 │ 10 │ [1,2] │ [10,20] │
│ Hello │ 2 │ 20 │ [1,2] │ [10,20] │
│ World │ 3 │ 30 │ [3,4,5] │ [30,40,50] │
│ World │ 4 │ 40 │ [3,4,5] │ [30,40,50] │
│ World │ 5 │ 50 │ [3,4,5] │ [30,40,50] │
└───────┴─────┴─────┴─────────┴────────────┘
```
使用的例子 [arrayEnumerate](../../../sql-reference/functions/array-functions.md#array_functions-arrayenumerate) 功能:
``` sql
SELECT s, `n.x`, `n.y`, `nest.x`, `nest.y`, num
FROM nested_test
ARRAY JOIN nest AS n, arrayEnumerate(`nest.x`) AS num;
```
``` text
┌─s─────┬─n.x─┬─n.y─┬─nest.x──┬─nest.y─────┬─num─┐
│ Hello │ 1 │ 10 │ [1,2] │ [10,20] │ 1 │
│ Hello │ 2 │ 20 │ [1,2] │ [10,20] │ 2 │
│ World │ 3 │ 30 │ [3,4,5] │ [30,40,50] │ 1 │
│ World │ 4 │ 40 │ [3,4,5] │ [30,40,50] │ 2 │
│ World │ 5 │ 50 │ [3,4,5] │ [30,40,50] │ 3 │
└───────┴─────┴─────┴─────────┴────────────┴─────┘
```
## 实施细节 {#implementation-details}
运行时优化查询执行顺序 `ARRAY JOIN`. 虽然 `ARRAY JOIN` 必须始终之前指定 [WHERE](../../../sql-reference/statements/select/where.md)/[PREWHERE](../../../sql-reference/statements/select/prewhere.md) 子句中的查询，从技术上讲，它们可以以任何顺序执行，除非结果 `ARRAY JOIN` 用于过滤。 处理顺序由查询优化器控制。

1
docs/zh/sql-reference/statements/select/distinct.md
View File

@ -1 +0,0 @@
../../../../en/sql-reference/statements/select/distinct.md

64
docs/zh/sql-reference/statements/select/distinct.md Normal file
View File

@ -0,0 +1,64 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_title: DISTINCT
---
# DISTINCT子句 {#select-distinct}
如果 `SELECT DISTINCT` 如果指定，则查询结果中只保留唯一行。 因此，在结果中所有完全匹配的行集合中，只有一行将保留。
## 空处理 {#null-processing}
`DISTINCT` 适用于 [NULL](../../../sql-reference/syntax.md#null-literal) 就好像 `NULL` 是一个特定的值，并且 `NULL==NULL`. 换句话说，在 `DISTINCT` 结果，不同的组合 `NULL` 仅发生一次。 它不同于 `NULL` 在大多数其他上下文中进行处理。
## 替代办法 {#alternatives}
通过应用可以获得相同的结果 [GROUP BY](../../../sql-reference/statements/select/group-by.md) 在同一组值指定为 `SELECT` 子句，而不使用任何聚合函数。 但有几个区别 `GROUP BY` 方法:
- `DISTINCT` 可以一起应用 `GROUP BY`.
- 当 [ORDER BY](../../../sql-reference/statements/select/order-by.md) 省略和 [LIMIT](../../../sql-reference/statements/select/limit.md) 定义时，查询在读取所需数量的不同行后立即停止运行。
- 数据块在处理时输出，而无需等待整个查询完成运行。
## 限制 {#limitations}
`DISTINCT` 如果不支持 `SELECT` 具有至少一个数组列。
## 例 {#examples}
ClickHouse支持使用 `DISTINCT` 和 `ORDER BY` 一个查询中不同列的子句。 该 `DISTINCT` 子句之前执行 `ORDER BY` 条款
示例表:
``` text
┌─a─┬─b─┐
│ 2 │ 1 │
│ 1 │ 2 │
│ 3 │ 3 │
│ 2 │ 4 │
└───┴───┘
```
当与选择数据 `SELECT DISTINCT a FROM t1 ORDER BY b ASC` 查询，我们得到以下结果:
``` text
┌─a─┐
│ 2 │
│ 1 │
│ 3 │
└───┘
```
如果我们改变排序方向 `SELECT DISTINCT a FROM t1 ORDER BY b DESC`，我们得到以下结果:
``` text
┌─a─┐
│ 3 │
│ 1 │
│ 2 │
└───┘
```
行 `2, 4` 分拣前被切割。
在编程查询时考虑这种实现特异性。

1
docs/zh/sql-reference/statements/select/format.md
View File

@ -1 +0,0 @@
../../../../en/sql-reference/statements/select/format.md

19
docs/zh/sql-reference/statements/select/format.md Normal file
View File

@ -0,0 +1,19 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_title: FORMAT
---
# 格式子句 {#format-clause}
ClickHouse支持广泛的 [序列化格式](../../../interfaces/formats.md) 可用于查询结果等。 有多种方法可以选择以下格式 `SELECT` 输出，其中之一是指定 `FORMAT format` 在查询结束时以任何特定格式获取结果数据。
特定的格式可以用于方便使用，与其他系统集成或性能增益。
## 默认格式 {#default-format}
如果 `FORMAT` 省略子句，使用默认格式，这取决于用于访问ClickHouse服务器的设置和接口。 为 [HTTP接口](../../../interfaces/http.md) 和 [命令行客户端](../../../interfaces/cli.md) 在批处理模式下，默认格式为 `TabSeparated`. 对于交互模式下的命令行客户端，默认格式为 `PrettyCompact` （它生成紧凑的人类可读表）。
## 实施细节 {#implementation-details}
使用命令行客户端时，数据始终以内部高效格式通过网络传递 (`Native`). 客户端独立解释 `FORMAT` 查询子句并格式化数据本身（从而减轻网络和服务器的额外负载）。

1
docs/zh/sql-reference/statements/select/from.md
View File

@ -1 +0,0 @@
../../../../en/sql-reference/statements/select/from.md

45
docs/zh/sql-reference/statements/select/from.md Normal file
View File

@ -0,0 +1,45 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_title: FROM
---
# FROM条款 {#select-from}
该 `FROM` 子句指定从中读取数据的源:
- [表](../../../engines/table-engines/index.md)
- [子查询](../../../sql-reference/statements/select/index.md) {## TODO: better link ##}
- [表函数](../../../sql-reference/table-functions/index.md#table-functions)
[JOIN](../../../sql-reference/statements/select/join.md) 和 [ARRAY JOIN](../../../sql-reference/statements/select/array-join.md) 子句也可以用来扩展的功能 `FROM` 条款
子查询是另一个 `SELECT` 可以在括号内指定的查询 `FROM` 条款
`FROM` 子句可以包含多个数据源，用逗号分隔，这相当于执行 [CROSS JOIN](../../../sql-reference/statements/select/join.md) 在他们身上
## 最终修饰符 {#select-from-final}
当 `FINAL` 如果指定，ClickHouse会在返回结果之前完全合并数据，从而执行给定表引擎合并期间发生的所有数据转换。
它适用于从使用 [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md)-发动机系列（除了 `GraphiteMergeTree`). 还支持:
- [复制](../../../engines/table-engines/mergetree-family/replication.md) 版本 `MergeTree` 引擎
- [查看](../../../engines/table-engines/special/view.md), [缓冲区](../../../engines/table-engines/special/buffer.md), [分布](../../../engines/table-engines/special/distributed.md)，和 [MaterializedView](../../../engines/table-engines/special/materializedview.md) 在其他引擎上运行的引擎，只要它们是在创建 `MergeTree`-发动机表。
### 缺点 {#drawbacks}
使用的查询 `FINAL` 执行速度不如类似的查询那么快，因为:
- 查询在单个线程中执行，并在查询执行期间合并数据。
- 查询与 `FINAL` 除了读取查询中指定的列之外，还读取主键列。
**在大多数情况下，避免使用 `FINAL`.** 常见的方法是使用假设后台进程的不同查询 `MergeTree` 引擎还没有发生，并通过应用聚合（例如，丢弃重复项）来处理它。 {## TODO: examples ##}
## 实施细节 {#implementation-details}
如果 `FROM` 子句被省略，数据将从读取 `system.one` 桌子
该 `system.one` 表只包含一行（此表满足与其他Dbms中找到的双表相同的目的）。
若要执行查询，将从相应的表中提取查询中列出的所有列。 外部查询不需要的任何列都将从子查询中抛出。
如果查询未列出任何列（例如, `SELECT count() FROM t`），无论如何都会从表中提取一些列（最小的列是首选），以便计算行数。

1
docs/zh/sql-reference/statements/select/group-by.md
View File

@ -1 +0,0 @@
../../../../en/sql-reference/statements/select/group-by.md

133
docs/zh/sql-reference/statements/select/group-by.md Normal file
View File

@ -0,0 +1,133 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
toc_title: GROUP BY
---
# GROUP BY子句 {#select-group-by-clause}
`GROUP BY` 子句切换 `SELECT` 查询转换为聚合模式，其工作原理如下:
- `GROUP BY` 子句包含表达式列表（或单个表达式，其被认为是长度为1的列表）。 这份名单充当 “grouping key”，而每个单独的表达式将被称为 “key expressions”.
- 在所有的表达式 [SELECT](../../../sql-reference/statements/select/index.md), [HAVING](../../../sql-reference/statements/select/having.md)，和 [ORDER BY](../../../sql-reference/statements/select/order-by.md) 条款 **必须** 基于键表达式进行计算 **或** 上 [聚合函数](../../../sql-reference/aggregate-functions/index.md) 在非键表达式（包括纯列）上。 换句话说，从表中选择的每个列必须用于键表达式或聚合函数内，但不能同时使用。
- 聚合结果 `SELECT` 查询将包含尽可能多的行，因为有唯一值 “grouping key” 在源表中。 通常这会显着减少行数，通常是数量级，但不一定：如果所有行数保持不变 “grouping key” 值是不同的。
!!! note "注"
还有一种额外的方法可以在表上运行聚合。 如果查询仅在聚合函数中包含表列，则 `GROUP BY clause` 可以省略，并且通过一个空的键集合来假定聚合。 这样的查询总是只返回一行。
## 空处理 {#null-processing}
对于分组，ClickHouse解释 [NULL](../../../sql-reference/syntax.md#null-literal) 作为一个值，并且 `NULL==NULL`. 它不同于 `NULL` 在大多数其他上下文中进行处理。
这里有一个例子来说明这意味着什么。
假设你有这张桌子:
``` text
┌─x─┬────y─┐
│ 1 │ 2 │
│ 2 │ ᴺᵁᴸᴸ │
│ 3 │ 2 │
│ 3 │ 3 │
│ 3 │ ᴺᵁᴸᴸ │
└───┴──────┘
```
查询 `SELECT sum(x), y FROM t_null_big GROUP BY y` 结果:
``` text
┌─sum(x)─┬────y─┐
│ 4 │ 2 │
│ 3 │ 3 │
│ 5 │ ᴺᵁᴸᴸ │
└────────┴──────┘
```
你可以看到 `GROUP BY` 为 `y = NULL` 总结 `x`，仿佛 `NULL` 是这个值。
如果你通过几个键 `GROUP BY`，结果会给你选择的所有组合，就好像 `NULL` 是一个特定的值。
## 使用总计修饰符 {#with-totals-modifier}
如果 `WITH TOTALS` 指定修饰符，将计算另一行。 此行将具有包含默认值（零或空行）的关键列，以及包含跨所有行计算值的聚合函数列（ “total” 值）。
这个额外的行仅产生于 `JSON*`, `TabSeparated*`，和 `Pretty*` 格式，与其他行分开:
- 在 `JSON*` 格式，这一行是作为一个单独的输出 ‘totals’ 场。
- 在 `TabSeparated*` 格式，该行位于主结果之后，前面有一个空行（在其他数据之后）。
- 在 `Pretty*` 格式时，该行在主结果之后作为单独的表输出。
- 在其他格式中，它不可用。
`WITH TOTALS` 可以以不同的方式运行时 [HAVING](../../../sql-reference/statements/select/having.md) 是存在的。 该行为取决于 `totals_mode` 设置。
### 配置合计处理 {#configuring-totals-processing}
默认情况下, `totals_mode = 'before_having'`. 在这种情况下, ‘totals’ 是跨所有行计算，包括那些不通过具有和 `max_rows_to_group_by`.
其他替代方案仅包括通过具有在 ‘totals’，并与设置不同的行为 `max_rows_to_group_by` 和 `group_by_overflow_mode = 'any'`.
`after_having_exclusive` – Don't include rows that didn't pass through `max_rows_to_group_by`. 换句话说, ‘totals’ 将有少于或相同数量的行，因为它会 `max_rows_to_group_by` 被省略。
`after_having_inclusive` – Include all the rows that didn't pass through ‘max\_rows\_to\_group\_by’ 在 ‘totals’. 换句话说, ‘totals’ 将有多个或相同数量的行，因为它会 `max_rows_to_group_by` 被省略。
`after_having_auto` – Count the number of rows that passed through HAVING. If it is more than a certain amount (by default, 50%), include all the rows that didn't pass through ‘max\_rows\_to\_group\_by’ 在 ‘totals’. 否则，不包括它们。
`totals_auto_threshold` – By default, 0.5. The coefficient for `after_having_auto`.
如果 `max_rows_to_group_by` 和 `group_by_overflow_mode = 'any'` 不使用，所有的变化 `after_having` 是相同的，你可以使用它们中的任何一个（例如, `after_having_auto`).
您可以使用 `WITH TOTALS` 在子查询中，包括在子查询 [JOIN](../../../sql-reference/statements/select/join.md) 子句（在这种情况下，将各自的总值合并）。
## 例 {#examples}
示例:
``` sql
SELECT
count(),
median(FetchTiming > 60 ? 60 : FetchTiming),
count() - sum(Refresh)
FROM hits
```
但是，与标准SQL相比，如果表没有任何行（根本没有任何行，或者在使用WHERE to filter之后没有任何行），则返回一个空结果，而不是来自包含聚合函数初始值的行之
相对于MySQL（并且符合标准SQL），您无法获取不在键或聚合函数（常量表达式除外）中的某些列的某些值。 要解决此问题，您可以使用 ‘any’ 聚合函数（获取第一个遇到的值）或 ‘min/max’.
示例:
``` sql
SELECT
domainWithoutWWW(URL) AS domain,
count(),
any(Title) AS title -- getting the first occurred page header for each domain.
FROM hits
GROUP BY domain
```
对于遇到的每个不同的键值, `GROUP BY` 计算一组聚合函数值。
`GROUP BY` 不支持数组列。
不能将常量指定为聚合函数的参数。 示例: `sum(1)`. 相反，你可以摆脱常数。 示例: `count()`.
## 实施细节 {#implementation-details}
聚合是面向列的DBMS最重要的功能之一，因此它的实现是ClickHouse中最优化的部分之一。 默认情况下，聚合使用哈希表在内存中完成。 它有40+的专业化是自动选择取决于 “grouping key” 数据类型。
### 在外部存储器中分组 {#select-group-by-in-external-memory}
您可以启用将临时数据转储到磁盘以限制内存使用期间 `GROUP BY`.
该 [max\_bytes\_before\_external\_group\_by](../../../operations/settings/settings.md#settings-max_bytes_before_external_group_by) 设置确定倾销的阈值RAM消耗 `GROUP BY` 临时数据到文件系统。 如果设置为0（默认值），它将被禁用。
使用时 `max_bytes_before_external_group_by`，我们建议您设置 `max_memory_usage` 大约两倍高。 这是必要的，因为聚合有两个阶段：读取数据和形成中间数据（1）和合并中间数据（2）。 将数据转储到文件系统只能在阶段1中发生。 如果未转储临时数据，则阶段2可能需要与阶段1相同的内存量。
例如，如果 [max\_memory\_usage](../../../operations/settings/settings.md#settings_max_memory_usage) 设置为10000000000，你想使用外部聚合，这是有意义的设置 `max_bytes_before_external_group_by` 到10000000000，和 `max_memory_usage` 到200亿。 当触发外部聚合（如果至少有一个临时数据转储）时，RAM的最大消耗仅略高于 `max_bytes_before_external_group_by`.
通过分布式查询处理，在远程服务器上执行外部聚合。 为了使请求者服务器只使用少量的RAM，设置 `distributed_aggregation_memory_efficient` 到1。
当合并数据刷新到磁盘时，以及当合并来自远程服务器的结果时， `distributed_aggregation_memory_efficient` 设置被启用，消耗高达 `1/256 * the_number_of_threads` 从RAM的总量。
当启用外部聚合时，如果有小于 `max_bytes_before_external_group_by` of data (i.e. data was not flushed), the query runs just as fast as without external aggregation. If any temporary data was flushed, the run time will be several times longer (approximately three times).
如果你有一个 [ORDER BY](../../../sql-reference/statements/select/order-by.md) 用一个 [LIMIT](../../../sql-reference/statements/select/limit.md) 后 `GROUP BY`，然后使用的RAM的量取决于数据的量 `LIMIT`，不是在整个表。 但如果 `ORDER BY` 没有 `LIMIT`，不要忘记启用外部排序 (`max_bytes_before_external_sort`).

Some files were not shown because too many files have changed in this diff Show More