Merge master

.clang-tidy

@@ -210,3 +210,6 @@ CheckOptions:
     value: false
   - key: performance-move-const-arg.CheckTriviallyCopyableMove
     value: false
+    # Workaround clang-tidy bug: https://github.com/llvm/llvm-project/issues/46097
+  - key: readability-identifier-naming.TypeTemplateParameterIgnoredRegexp
+    value: expr-type

CHANGELOG.md

@@ -11,6 +11,7 @@
 
 * Make `arrayCompact` function behave as other higher-order functions: perform compaction not of lambda function results but on the original array. If you're using nontrivial lambda functions in arrayCompact you may restore old behaviour by wrapping `arrayCompact` arguments into `arrayMap`. Closes [#34010](https://github.com/ClickHouse/ClickHouse/issues/34010) [#18535](https://github.com/ClickHouse/ClickHouse/issues/18535) [#14778](https://github.com/ClickHouse/ClickHouse/issues/14778). [#34795](https://github.com/ClickHouse/ClickHouse/pull/34795) ([Alexandre Snarskii](https://github.com/snar)).
 * Change implementation specific behavior on overflow of function `toDatetime`. It will be saturated to the nearest min/max supported instant of datetime instead of wraparound. This change is highlighted as "backward incompatible" because someone may unintentionally rely on the old behavior. [#32898](https://github.com/ClickHouse/ClickHouse/pull/32898) ([HaiBo Li](https://github.com/marising)).
+* Make function `cast(value, 'IPv4')`, `cast(value, 'IPv6')` behave same as `toIPv4`, `toIPv6` functions. Changed behavior of incorrect IP address passed into functions `toIPv4`,` toIPv6`,  now if invalid IP address passes into this functions exception will be raised, before this function return default value. Added functions `IPv4StringToNumOrDefault`, `IPv4StringToNumOrNull`, `IPv6StringToNumOrDefault`, `IPv6StringOrNull` `toIPv4OrDefault`, `toIPv4OrNull`, `toIPv6OrDefault`, `toIPv6OrNull`. Functions `IPv4StringToNumOrDefault `, `toIPv4OrDefault `, `toIPv6OrDefault ` should be used if previous logic relied on `IPv4StringToNum`, `toIPv4`, `toIPv6` returning default value for invalid address. Added setting `cast_ipv4_ipv6_default_on_conversion_error`, if this setting enabled, then IP address conversion functions will behave as before. Closes [#22825](https://github.com/ClickHouse/ClickHouse/issues/22825). Closes [#5799](https://github.com/ClickHouse/ClickHouse/issues/5799). Closes [#35156](https://github.com/ClickHouse/ClickHouse/issues/35156). [#35240](https://github.com/ClickHouse/ClickHouse/pull/35240) ([Maksim Kita](https://github.com/kitaisreal)).
 
 #### New Feature
 

CMakeLists.txt

@@ -261,12 +261,12 @@ endif ()
 # Add a section with the hash of the compiled machine code for integrity checks.
 # Only for official builds, because adding a section can be time consuming (rewrite of several GB).
 # And cross compiled binaries are not supported (since you cannot execute clickhouse hash-binary)
-if (OBJCOPY_PATH AND YANDEX_OFFICIAL_BUILD AND (NOT CMAKE_TOOLCHAIN_FILE))
+if (OBJCOPY_PATH AND CLICKHOUSE_OFFICIAL_BUILD AND (NOT CMAKE_TOOLCHAIN_FILE))
     set (USE_BINARY_HASH 1)
 endif ()
 
 # Allows to build stripped binary in a separate directory
-if (OBJCOPY_PATH AND READELF_PATH)
+if (OBJCOPY_PATH AND STRIP_PATH)
     option(INSTALL_STRIPPED_BINARIES "Build stripped binaries with debug info in separate directory" OFF)
     if (INSTALL_STRIPPED_BINARIES)
         set(STRIPPED_BINARIES_OUTPUT "stripped" CACHE STRING "A separate directory for stripped information")

base/glibc-compatibility/CMakeLists.txt

@@ -51,6 +51,6 @@ if (GLIBC_COMPATIBILITY)
 
     message (STATUS "Some symbols from glibc will be replaced for compatibility")
 
-elseif (YANDEX_OFFICIAL_BUILD)
+elseif (CLICKHOUSE_OFFICIAL_BUILD)
     message (WARNING "Option GLIBC_COMPATIBILITY must be turned on for production builds.")
 endif ()

cmake/strip.sh

@@ -1,28 +0,0 @@
-#!/usr/bin/env bash
-
-BINARY_PATH=$1
-BINARY_NAME=$(basename "$BINARY_PATH")
-DESTINATION_STRIPPED_DIR=$2
-OBJCOPY_PATH=${3:objcopy}
-READELF_PATH=${4:readelf}
-
-BUILD_ID=$($READELF_PATH -n "$1" | sed -n '/Build ID/ { s/.*: //p; q; }')
-BUILD_ID_PREFIX=${BUILD_ID:0:2}
-BUILD_ID_SUFFIX=${BUILD_ID:2}
-
-DESTINATION_DEBUG_INFO_DIR="$DESTINATION_STRIPPED_DIR/lib/debug/.build-id"
-DESTINATION_STRIP_BINARY_DIR="$DESTINATION_STRIPPED_DIR/bin"
-
-mkdir -p "$DESTINATION_DEBUG_INFO_DIR/$BUILD_ID_PREFIX"
-mkdir -p "$DESTINATION_STRIP_BINARY_DIR"
-
-
-cp "$BINARY_PATH" "$DESTINATION_STRIP_BINARY_DIR/$BINARY_NAME"
-
-$OBJCOPY_PATH --only-keep-debug --compress-debug-sections "$DESTINATION_STRIP_BINARY_DIR/$BINARY_NAME" "$DESTINATION_DEBUG_INFO_DIR/$BUILD_ID_PREFIX/$BUILD_ID_SUFFIX.debug"
-chmod 0644 "$DESTINATION_DEBUG_INFO_DIR/$BUILD_ID_PREFIX/$BUILD_ID_SUFFIX.debug"
-chown 0:0 "$DESTINATION_DEBUG_INFO_DIR/$BUILD_ID_PREFIX/$BUILD_ID_SUFFIX.debug"
-
-strip --remove-section=.comment --remove-section=.note "$DESTINATION_STRIP_BINARY_DIR/$BINARY_NAME"
-
-$OBJCOPY_PATH --add-gnu-debuglink "$DESTINATION_DEBUG_INFO_DIR/$BUILD_ID_PREFIX/$BUILD_ID_SUFFIX.debug" "$DESTINATION_STRIP_BINARY_DIR/$BINARY_NAME"

cmake/strip_binary.cmake

@@ -11,16 +11,43 @@ macro(clickhouse_strip_binary)
        message(FATAL_ERROR "A binary path name must be provided for stripping binary")
    endif()
 
-
    if (NOT DEFINED STRIP_DESTINATION_DIR)
        message(FATAL_ERROR "Destination directory for stripped binary must be provided")
    endif()
 
    add_custom_command(TARGET ${STRIP_TARGET} POST_BUILD
-     COMMAND bash ${ClickHouse_SOURCE_DIR}/cmake/strip.sh ${STRIP_BINARY_PATH} ${STRIP_DESTINATION_DIR} ${OBJCOPY_PATH} ${READELF_PATH}
+       COMMAND mkdir -p "${STRIP_DESTINATION_DIR}/lib/debug/bin"
+       COMMAND mkdir -p "${STRIP_DESTINATION_DIR}/bin"
+       COMMAND cp "${STRIP_BINARY_PATH}" "${STRIP_DESTINATION_DIR}/bin/${STRIP_TARGET}"
+       COMMAND "${OBJCOPY_PATH}" --only-keep-debug --compress-debug-sections "${STRIP_DESTINATION_DIR}/bin/${STRIP_TARGET}" "${STRIP_DESTINATION_DIR}/lib/debug/bin/${STRIP_TARGET}.debug"
+       COMMAND chmod 0644 "${STRIP_DESTINATION_DIR}/lib/debug/bin/${STRIP_TARGET}.debug"
+       COMMAND "${STRIP_PATH}" --remove-section=.comment --remove-section=.note "${STRIP_DESTINATION_DIR}/bin/${STRIP_TARGET}"
+       COMMAND "${OBJCOPY_PATH}" --add-gnu-debuglink "${STRIP_DESTINATION_DIR}/lib/debug/bin/${STRIP_TARGET}.debug" "${STRIP_DESTINATION_DIR}/bin/${STRIP_TARGET}"
        COMMENT "Stripping clickhouse binary" VERBATIM
    )
 
    install(PROGRAMS ${STRIP_DESTINATION_DIR}/bin/${STRIP_TARGET} DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse)
-   install(DIRECTORY ${STRIP_DESTINATION_DIR}/lib/debug DESTINATION ${CMAKE_INSTALL_LIBDIR} COMPONENT clickhouse)
+   install(FILES ${STRIP_DESTINATION_DIR}/lib/debug/bin/${STRIP_TARGET}.debug DESTINATION ${CMAKE_INSTALL_LIBDIR}/debug/${CMAKE_INSTALL_FULL_BINDIR}/${STRIP_TARGET}.debug COMPONENT clickhouse)
+endmacro()
+
+
+macro(clickhouse_make_empty_debug_info_for_nfpm)
+   set(oneValueArgs TARGET DESTINATION_DIR)
+   cmake_parse_arguments(EMPTY_DEBUG "" "${oneValueArgs}" "" ${ARGN})
+
+   if (NOT DEFINED EMPTY_DEBUG_TARGET)
+       message(FATAL_ERROR "A target name must be provided for stripping binary")
+   endif()
+
+   if (NOT DEFINED EMPTY_DEBUG_DESTINATION_DIR)
+       message(FATAL_ERROR "Destination directory for empty debug must be provided")
+   endif()
+
+   add_custom_command(TARGET ${EMPTY_DEBUG_TARGET} POST_BUILD
+       COMMAND mkdir -p "${EMPTY_DEBUG_DESTINATION_DIR}/lib/debug"
+       COMMAND touch "${EMPTY_DEBUG_DESTINATION_DIR}/lib/debug/${EMPTY_DEBUG_TARGET}.debug"
+       COMMENT "Addiding empty debug info for NFPM" VERBATIM
+   )
+
+   install(FILES "${EMPTY_DEBUG_DESTINATION_DIR}/lib/debug/${EMPTY_DEBUG_TARGET}.debug" DESTINATION "${CMAKE_INSTALL_LIBDIR}/debug/${CMAKE_INSTALL_FULL_BINDIR}" COMPONENT clickhouse)
 endmacro()

cmake/tools.cmake

@@ -170,32 +170,32 @@ else ()
     message (FATAL_ERROR "Cannot find objcopy.")
 endif ()
 
-# Readelf (FIXME copypaste)
+# Strip (FIXME copypaste)
 
 if (COMPILER_GCC)
-    find_program (READELF_PATH NAMES "llvm-readelf" "llvm-readelf-13" "llvm-readelf-12" "llvm-readelf-11" "readelf")
+    find_program (STRIP_PATH NAMES "llvm-strip" "llvm-strip-13" "llvm-strip-12" "llvm-strip-11" "strip")
 else ()
-    find_program (READELF_PATH NAMES "llvm-readelf-${COMPILER_VERSION_MAJOR}" "llvm-readelf" "readelf")
+    find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
 endif ()
 
-if (NOT READELF_PATH AND OS_DARWIN)
+if (NOT STRIP_PATH AND OS_DARWIN)
     find_program (BREW_PATH NAMES "brew")
     if (BREW_PATH)
         execute_process (COMMAND ${BREW_PATH} --prefix llvm ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE LLVM_PREFIX)
         if (LLVM_PREFIX)
-            find_program (READELF_PATH NAMES "llvm-readelf" PATHS "${LLVM_PREFIX}/bin" NO_DEFAULT_PATH)
+            find_program (STRIP_PATH NAMES "llvm-strip" PATHS "${LLVM_PREFIX}/bin" NO_DEFAULT_PATH)
         endif ()
-        if (NOT READELF_PATH)
+        if (NOT STRIP_PATH)
             execute_process (COMMAND ${BREW_PATH} --prefix binutils ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE BINUTILS_PREFIX)
             if (BINUTILS_PREFIX)
-                find_program (READELF_PATH NAMES "readelf" PATHS "${BINUTILS_PREFIX}/bin" NO_DEFAULT_PATH)
+                find_program (STRIP_PATH NAMES "strip" PATHS "${BINUTILS_PREFIX}/bin" NO_DEFAULT_PATH)
             endif ()
         endif ()
     endif ()
 endif ()
 
-if (READELF_PATH)
+if (STRIP_PATH)
-    message (STATUS "Using readelf: ${READELF_PATH}")
+    message (STATUS "Using strip: ${STRIP_PATH}")
 else ()
-    message (FATAL_ERROR "Cannot find readelf.")
+    message (FATAL_ERROR "Cannot find strip.")
 endif ()

cmake/version.cmake

@@ -18,6 +18,6 @@ set (VERSION_STRING_SHORT "${VERSION_MAJOR}.${VERSION_MINOR}")
 
 math (EXPR VERSION_INTEGER "${VERSION_PATCH} + ${VERSION_MINOR}*1000 + ${VERSION_MAJOR}*1000000")
 
-if(YANDEX_OFFICIAL_BUILD)
+if(CLICKHOUSE_OFFICIAL_BUILD)
     set(VERSION_OFFICIAL " (official build)")
 endif()

contrib/hyperscan

@@ -1 +1 @@
-Subproject commit e9f08df0213fc637aac0a5bbde9beeaeba2fe9fa
+Subproject commit 5edc68c5ac68d2d4f876159e9ee84def6d3dc87c

contrib/libcxx

@@ -1 +1 @@
-Subproject commit 61e60294b1de01483caa9f5d00f437c99b674de6
+Subproject commit 172b2ae074f6755145b91c53a95c8540c1468239

contrib/libcxx-cmake/CMakeLists.txt

@@ -18,12 +18,14 @@ set(SRCS
 "${LIBCXX_SOURCE_DIR}/src/filesystem/directory_iterator.cpp"
 "${LIBCXX_SOURCE_DIR}/src/filesystem/int128_builtins.cpp"
 "${LIBCXX_SOURCE_DIR}/src/filesystem/operations.cpp"
+"${LIBCXX_SOURCE_DIR}/src/format.cpp"
 "${LIBCXX_SOURCE_DIR}/src/functional.cpp"
 "${LIBCXX_SOURCE_DIR}/src/future.cpp"
 "${LIBCXX_SOURCE_DIR}/src/hash.cpp"
 "${LIBCXX_SOURCE_DIR}/src/ios.cpp"
 "${LIBCXX_SOURCE_DIR}/src/ios.instantiations.cpp"
 "${LIBCXX_SOURCE_DIR}/src/iostream.cpp"
+"${LIBCXX_SOURCE_DIR}/src/legacy_pointer_safety.cpp"
 "${LIBCXX_SOURCE_DIR}/src/locale.cpp"
 "${LIBCXX_SOURCE_DIR}/src/memory.cpp"
 "${LIBCXX_SOURCE_DIR}/src/mutex.cpp"
@@ -33,6 +35,9 @@ set(SRCS
 "${LIBCXX_SOURCE_DIR}/src/random.cpp"
 "${LIBCXX_SOURCE_DIR}/src/random_shuffle.cpp"
 "${LIBCXX_SOURCE_DIR}/src/regex.cpp"
+"${LIBCXX_SOURCE_DIR}/src/ryu/d2fixed.cpp"
+"${LIBCXX_SOURCE_DIR}/src/ryu/d2s.cpp"
+"${LIBCXX_SOURCE_DIR}/src/ryu/f2s.cpp"
 "${LIBCXX_SOURCE_DIR}/src/shared_mutex.cpp"
 "${LIBCXX_SOURCE_DIR}/src/stdexcept.cpp"
 "${LIBCXX_SOURCE_DIR}/src/string.cpp"
@@ -49,7 +54,9 @@ set(SRCS
 add_library(cxx ${SRCS})
 set_target_properties(cxx PROPERTIES FOLDER "contrib/libcxx-cmake")
 
-target_include_directories(cxx SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}/include>)
+target_include_directories(cxx SYSTEM BEFORE PUBLIC
+        $<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}/include>
+        $<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}>/src)
 target_compile_definitions(cxx PRIVATE -D_LIBCPP_BUILDING_LIBRARY -DLIBCXX_BUILDING_LIBCXXABI)
 
 # Enable capturing stack traces for all exceptions.

contrib/libcxxabi

@@ -1 +1 @@
-Subproject commit df8f1e727dbc9e2bedf2282096fa189dc3fe0076
+Subproject commit 6eb7cc7a7bdd779e6734d1b9fb451df2274462d7

contrib/libcxxabi-cmake/CMakeLists.txt

@@ -1,24 +1,24 @@
 set(LIBCXXABI_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/libcxxabi")
 
 set(SRCS
-"${LIBCXXABI_SOURCE_DIR}/src/stdlib_stdexcept.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_virtual.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_thread_atexit.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/fallback_malloc.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_guard.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_default_handlers.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_personality.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/stdlib_exception.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/abort_message.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_aux_runtime.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_default_handlers.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/cxa_demangle.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/cxa_exception.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_handlers.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/cxa_exception_storage.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/private_typeinfo.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_guard.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/stdlib_typeinfo.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_handlers.cpp"
-"${LIBCXXABI_SOURCE_DIR}/src/cxa_aux_runtime.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_personality.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_thread_atexit.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/cxa_vector.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/cxa_virtual.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/fallback_malloc.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/private_typeinfo.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/stdlib_exception.cpp"
 "${LIBCXXABI_SOURCE_DIR}/src/stdlib_new_delete.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/stdlib_stdexcept.cpp"
+"${LIBCXXABI_SOURCE_DIR}/src/stdlib_typeinfo.cpp"
 )
 
 add_library(cxxabi ${SRCS})
@@ -30,6 +30,7 @@ target_compile_options(cxxabi PRIVATE -w)
 target_include_directories(cxxabi SYSTEM BEFORE
     PUBLIC $<BUILD_INTERFACE:${LIBCXXABI_SOURCE_DIR}/include>
     PRIVATE $<BUILD_INTERFACE:${LIBCXXABI_SOURCE_DIR}/../libcxx/include>
+    PRIVATE $<BUILD_INTERFACE:${LIBCXXABI_SOURCE_DIR}/../libcxx/src>
 )
 target_compile_definitions(cxxabi PRIVATE -D_LIBCPP_BUILDING_LIBRARY)
 target_compile_options(cxxabi PRIVATE -nostdinc++ -fno-sanitize=undefined -Wno-macro-redefined) # If we don't disable UBSan, infinite recursion happens in dynamic_cast.

contrib/replxx

@@ -1 +1 @@
-Subproject commit 9460e5e0fc10f78f460af26a6bd928798cac864d
+Subproject commit 6f0b6f151ae2a044625ae93acd19ca365fcea64d

docker/docs/check/Dockerfile

@@ -1,4 +1,3 @@
-# rebuild in #33610
 # docker build -t clickhouse/docs-check .
 ARG FROM_TAG=latest
 FROM clickhouse/docs-builder:$FROM_TAG

docker/packager/packager

@@ -163,6 +163,7 @@ def parse_env_variables(
         cmake_flags.append("-DCMAKE_INSTALL_PREFIX=/usr")
         cmake_flags.append("-DCMAKE_INSTALL_SYSCONFDIR=/etc")
         cmake_flags.append("-DCMAKE_INSTALL_LOCALSTATEDIR=/var")
+        cmake_flags.append("-DBUILD_STANDALONE_KEEPER=ON")
         if is_release_build(build_type, package_type, sanitizer, split_binary):
             cmake_flags.append("-DINSTALL_STRIPPED_BINARIES=ON")
 
@@ -244,7 +245,7 @@ def parse_env_variables(
         result.append(f"AUTHOR='{author}'")
 
     if official:
-        cmake_flags.append("-DYANDEX_OFFICIAL_BUILD=1")
+        cmake_flags.append("-DCLICKHOUSE_OFFICIAL_BUILD=1")
 
     result.append('CMAKE_FLAGS="' + " ".join(cmake_flags) + '"')
 

docker/test/fasttest/run.sh

@@ -267,6 +267,7 @@ function run_tests
     local test_opts=(
         --hung-check
         --fast-tests-only
+        --no-random-settings
         --no-long
         --testname
         --shard

docker/test/fuzzer/run-fuzzer.sh

@@ -13,7 +13,7 @@ script_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 echo "$script_dir"
 repo_dir=ch
 BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-13_debug_none_bundled_unsplitted_disable_False_binary"}
-BINARY_URL_TO_DOWNLOAD=${BINARY_URL_TO_DOWNLOAD:="https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/$BINARY_TO_DOWNLOAD/clickhouse"}
+BINARY_URL_TO_DOWNLOAD=${BINARY_URL_TO_DOWNLOAD:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/$BINARY_TO_DOWNLOAD/clickhouse"}
 
 function clone
 {

docker/test/keeper-jepsen/run.sh

@@ -2,7 +2,7 @@
 set -euo pipefail
 
 
-CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-13_relwithdebuginfo_none_bundled_unsplitted_disable_False_binary/clickhouse"}
+CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-13_relwithdebuginfo_none_bundled_unsplitted_disable_False_binary/clickhouse"}
 CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}
 
 
@@ -10,7 +10,7 @@ if [ -z "$CLICKHOUSE_REPO_PATH" ]; then
     CLICKHOUSE_REPO_PATH=ch
     rm -rf ch ||:
     mkdir ch ||:
-    wget -nv -nd -c "https://clickhouse-test-reports.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/repo/clickhouse_no_subs.tar.gz"
+    wget -nv -nd -c "https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/repo/clickhouse_no_subs.tar.gz"
     tar -C ch --strip-components=1 -xf clickhouse_no_subs.tar.gz
     ls -lath ||:
 fi

docker/test/performance-comparison/compare.sh

@@ -1294,15 +1294,15 @@ create table ci_checks engine File(TSVWithNamesAndTypes, 'ci-checks.tsv')
         select '' test_name,
             '$(sed -n 's/.*<!--message: \(.*\)-->/\1/p' report.html)' test_status,
             0 test_duration_ms,
-            'https://clickhouse-test-reports.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#fail1' report_url
+            'https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#fail1' report_url
         union all
             select test || ' #' || toString(query_index), 'slower' test_status, 0 test_duration_ms,
-                'https://clickhouse-test-reports.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#changes-in-performance.'
+                'https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#changes-in-performance.'
                     || test || '.' || toString(query_index) report_url
             from queries where changed_fail != 0 and diff > 0
         union all
             select test || ' #' || toString(query_index), 'unstable' test_status, 0 test_duration_ms,
-                'https://clickhouse-test-reports.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#unstable-queries.'
+                'https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/performance_comparison/report.html#unstable-queries.'
                     || test || '.' || toString(query_index) report_url
             from queries where unstable_fail != 0
     )

docker/test/performance-comparison/download.sh

@@ -16,26 +16,17 @@ right_sha=$4
 datasets=${CHPC_DATASETS-"hits1 hits10 hits100 values"}
 
 declare -A dataset_paths
-if [[ $S3_URL == *"s3.amazonaws.com"* ]]; then
 dataset_paths["hits10"]="https://clickhouse-private-datasets.s3.amazonaws.com/hits_10m_single/partitions/hits_10m_single.tar"
 dataset_paths["hits100"]="https://clickhouse-private-datasets.s3.amazonaws.com/hits_100m_single/partitions/hits_100m_single.tar"
 dataset_paths["hits1"]="https://clickhouse-datasets.s3.amazonaws.com/hits/partitions/hits_v1.tar"
 dataset_paths["values"]="https://clickhouse-datasets.s3.amazonaws.com/values_with_expressions/partitions/test_values.tar"
-else
-    dataset_paths["hits10"]="https://s3.mds.yandex.net/clickhouse-private-datasets/hits_10m_single/partitions/hits_10m_single.tar"
-    dataset_paths["hits100"]="https://s3.mds.yandex.net/clickhouse-private-datasets/hits_100m_single/partitions/hits_100m_single.tar"
-    dataset_paths["hits1"]="https://clickhouse-datasets.s3.yandex.net/hits/partitions/hits_v1.tar"
-    dataset_paths["values"]="https://clickhouse-datasets.s3.yandex.net/values_with_expressions/partitions/test_values.tar"
-fi
 
 
 function download
 {
     # Historically there were various paths for the performance test package.
     # Test all of them.
-    declare -a urls_to_try=("https://s3.amazonaws.com/clickhouse-builds/$left_pr/$left_sha/performance/performance.tgz"
+    declare -a urls_to_try=("https://s3.amazonaws.com/clickhouse-builds/$left_pr/$left_sha/performance/performance.tgz")
-                            "https://clickhouse-builds.s3.yandex.net/$left_pr/$left_sha/clickhouse_build_check/performance/performance.tgz"
-                           )
 
     for path in "${urls_to_try[@]}"
     do

docker/test/performance-comparison/entrypoint.sh

@@ -4,7 +4,7 @@ set -ex
 CHPC_CHECK_START_TIMESTAMP="$(date +%s)"
 export CHPC_CHECK_START_TIMESTAMP
 
-S3_URL=${S3_URL:="https://clickhouse-builds.s3.yandex.net"}
+S3_URL=${S3_URL:="https://clickhouse-builds.s3.amazonaws.com"}
 
 COMMON_BUILD_PREFIX="/clickhouse_build_check"
 if [[ $S3_URL == *"s3.amazonaws.com"* ]]; then
@@ -64,9 +64,7 @@ function find_reference_sha
         # Historically there were various path for the performance test package,
         # test all of them.
         unset found
-        declare -a urls_to_try=("https://s3.amazonaws.com/clickhouse-builds/0/$REF_SHA/performance/performance.tgz"
+        declare -a urls_to_try=("https://s3.amazonaws.com/clickhouse-builds/0/$REF_SHA/performance/performance.tgz")
-                                "https://clickhouse-builds.s3.yandex.net/0/$REF_SHA/clickhouse_build_check/performance/performance.tgz"
-                               )
         for path in "${urls_to_try[@]}"
         do
             if curl_with_retry "$path"

docker/test/stateful/Dockerfile

@@ -11,7 +11,7 @@ RUN apt-get update -y \
 
 COPY s3downloader /s3downloader
 
-ENV S3_URL="https://clickhouse-datasets.s3.yandex.net"
+ENV S3_URL="https://clickhouse-datasets.s3.amazonaws.com"
 ENV DATASETS="hits visits"
 ENV EXPORT_S3_STORAGE_POLICIES=1
 

docker/test/stateful/s3downloader

@@ -10,7 +10,7 @@ import requests
 import tempfile
 
 
-DEFAULT_URL = 'https://clickhouse-datasets.s3.yandex.net'
+DEFAULT_URL = 'https://clickhouse-datasets.s3.amazonaws.com'
 
 AVAILABLE_DATASETS = {
     'hits': 'hits_v1.tar',

docker/test/stress/Dockerfile

@@ -29,7 +29,7 @@ COPY ./download_previous_release /download_previous_release
 COPY run.sh /
 
 ENV DATASETS="hits visits"
-ENV S3_URL="https://clickhouse-datasets.s3.yandex.net"
+ENV S3_URL="https://clickhouse-datasets.s3.amazonaws.com"
 ENV EXPORT_S3_STORAGE_POLICIES=1
 
 CMD ["/bin/bash", "/run.sh"]

docs/en/engines/table-engines/integrations/hive.md

@@ -137,7 +137,7 @@ CREATE TABLE test.test_orc
     `f_array_array_float` Array(Array(Float32)),
     `day` String
 )
-ENGINE = Hive('thrift://202.168.117.26:9083', 'test', 'test_orc')
+ENGINE = Hive('thrift://localhost:9083', 'test', 'test_orc')
 PARTITION BY day
 
 ```

docs/en/operations/server-configuration-parameters/settings.md

@@ -1616,3 +1616,14 @@ Possible values:
 
 Default value: `10000`.
 
+## global_memory_usage_overcommit_max_wait_microseconds {#global_memory_usage_overcommit_max_wait_microseconds}
+
+Sets maximum waiting time for global overcommit tracker.
+
+Possible values:
+
+-   Positive integer.
+
+Default value: `0`.
+
+

docs/en/operations/settings/memory-overcommit.md

@@ -0,0 +1,31 @@
+# Memory overcommit
+
+Memory overcommit is an experimental technique intended to allow to set more flexible memory limits for queries.
+
+The idea of this technique is to introduce settings which can represent guaranteed amount of memory a query can use.
+When memory overcommit is enabled and the memory limit is reached ClickHouse will select the most overcommitted query and try to free memory by killing this query.
+
+When memory limit is reached any query will wait some time during atempt to allocate new memory.
+If timeout is passed and memory is freed, the query continues execution. Otherwise an exception will be thrown and the query is killed.
+
+Selection of query to stop or kill is performed by either global or user overcommit trackers depending on what memory limit is reached.
+
+## User overcommit tracker
+
+User overcommit tracker finds a query with the biggest overcommit ratio in the user's query list.
+Overcommit ratio is computed as number of allocated bytes divided by value of `max_guaranteed_memory_usage` setting.
+
+Waiting timeout is set by `memory_usage_overcommit_max_wait_microseconds` setting.
+
+**Example**
+
+```sql
+SELECT number FROM numbers(1000) GROUP BY number SETTINGS max_guaranteed_memory_usage=4000, memory_usage_overcommit_max_wait_microseconds=500
+```
+
+## Global overcommit tracker
+
+Global overcommit tracker finds a query with the biggest overcommit ratio in the list of all queries.
+In this case overcommit ratio is computed as number of allocated bytes divided by value of `max_guaranteed_memory_usage_for_user` setting.
+
+Waiting timeout is set by `global_memory_usage_overcommit_max_wait_microseconds` parameter in the configuration file.

docs/en/operations/settings/settings.md

@@ -4220,10 +4220,36 @@ Possible values:
 -   0 — Disabled.
 -   1 — Enabled. The wait time equal shutdown_wait_unfinished config.
 
-Default value: 0.
+Default value: `0`.
 
 ## shutdown_wait_unfinished
 
 The waiting time in seconds for currently handled connections when shutdown server.
 
-Default Value: 5.
+Default Value: `5`.
+
+## max_guaranteed_memory_usage
+
+Maximum guaranteed memory usage for processing of single query.
+It represents soft limit in case when hard limit is reached on user level.
+Zero means unlimited.
+Read more about [memory overcommit](memory-overcommit.md).
+
+Default value: `0`.
+
+## memory_usage_overcommit_max_wait_microseconds
+
+Maximum time thread will wait for memory to be freed in the case of memory overcommit on a user level.
+If the timeout is reached and memory is not freed, an exception is thrown.
+Read more about [memory overcommit](memory-overcommit.md).
+
+Default value: `0`.
+
+## max_guaranteed_memory_usage_for_user
+
+Maximum guaranteed memory usage for processing all concurrently running queries for the user.
+It represents soft limit in case when hard limit is reached on global level.
+Zero means unlimited.
+Read more about [memory overcommit](memory-overcommit.md).
+
+Default value: `0`.

docs/tools/requirements.txt

@@ -10,7 +10,7 @@ cssmin==0.2.0
 future==0.18.2
 htmlmin==0.1.12
 idna==2.10
-Jinja2>=3.0.3
+Jinja2==3.0.3
 jinja2-highlight==0.6.1
 jsmin==3.0.0
 livereload==2.6.3

docs/zh/engines/table-engines/integrations/hive.md

@@ -140,7 +140,7 @@ CREATE TABLE test.test_orc
     `f_array_array_float` Array(Array(Float32)),
     `day` String
 )
-ENGINE = Hive('thrift://202.168.117.26:9083', 'test', 'test_orc')
+ENGINE = Hive('thrift://localhost:9083', 'test', 'test_orc')
 PARTITION BY day
 
 ```

packages/clickhouse-common-static-dbg.yaml

@@ -21,8 +21,12 @@ description: |
     This package contains the debugging symbols for clickhouse-common.
 
 contents:
-- src: root/usr/lib/debug
+- src: root/usr/lib/debug/usr/bin/clickhouse.debug
-  dst: /usr/lib/debug
+  dst: /usr/lib/debug/usr/bin/clickhouse.debug
+- src: root/usr/lib/debug/usr/bin/clickhouse-odbc-bridge.debug
+  dst: /usr/lib/debug/usr/bin/clickhouse-odbc-bridge.debug
+- src: root/usr/lib/debug/usr/bin/clickhouse-library-bridge.debug
+  dst: /usr/lib/debug/usr/bin/clickhouse-library-bridge.debug
 # docs
 - src: ../AUTHORS
   dst: /usr/share/doc/clickhouse-common-static-dbg/AUTHORS

packages/clickhouse-keeper-dbg.yaml

@@ -0,0 +1,28 @@
+# package sources should be placed in ${PWD}/root
+# nfpm should run from the same directory with a config
+name: "clickhouse-keeper-dbg"
+arch: "${DEB_ARCH}" # amd64, arm64
+platform: "linux"
+version: "${CLICKHOUSE_VERSION_STRING}"
+vendor: "ClickHouse Inc."
+homepage: "https://clickhouse.com"
+license: "Apache"
+section: "database"
+priority: "optional"
+maintainer: "ClickHouse Dev Team <packages+linux@clickhouse.com>"
+description: |
+  debugging symbols for clickhouse-keeper
+    This package contains the debugging symbols for clickhouse-keeper.
+
+contents:
+- src: root/usr/lib/debug/usr/bin/clickhouse-keeper.debug
+  dst: /usr/lib/debug/usr/bin/clickhouse-keeper.debug
+# docs
+- src: ../AUTHORS
+  dst: /usr/share/doc/clickhouse-keeper-dbg/AUTHORS
+- src: ../CHANGELOG.md
+  dst: /usr/share/doc/clickhouse-keeper-dbg/CHANGELOG.md
+- src: ../LICENSE
+  dst: /usr/share/doc/clickhouse-keeper-dbg/LICENSE
+- src: ../README.md
+  dst: /usr/share/doc/clickhouse-keeper-dbg/README.md

packages/clickhouse-keeper.yaml

@@ -0,0 +1,40 @@
+# package sources should be placed in ${PWD}/root
+# nfpm should run from the same directory with a config
+name: "clickhouse-keeper"
+arch: "${DEB_ARCH}" # amd64, arm64
+platform: "linux"
+version: "${CLICKHOUSE_VERSION_STRING}"
+vendor: "ClickHouse Inc."
+homepage: "https://clickhouse.com"
+license: "Apache"
+section: "database"
+priority: "optional"
+
+conflicts:
+- clickhouse-server
+depends:
+- adduser
+suggests:
+- clickhouse-keeper-dbg
+
+maintainer: "ClickHouse Dev Team <packages+linux@clickhouse.com>"
+description: |
+  Static clickhouse-keeper binary
+    A stand-alone clickhouse-keeper package
+
+
+contents:
+- src: root/etc/clickhouse-keeper
+  dst: /etc/clickhouse-keeper
+  type: config
+- src: root/usr/bin/clickhouse-keeper
+  dst: /usr/bin/clickhouse-keeper
+# docs
+- src: ../AUTHORS
+  dst: /usr/share/doc/clickhouse-keeper/AUTHORS
+- src: ../CHANGELOG.md
+  dst: /usr/share/doc/clickhouse-keeper/CHANGELOG.md
+- src: ../LICENSE
+  dst: /usr/share/doc/clickhouse-keeper/LICENSE
+- src: ../README.md
+  dst: /usr/share/doc/clickhouse-keeper/README.md

programs/CMakeLists.txt

@@ -473,18 +473,11 @@ else ()
     if (INSTALL_STRIPPED_BINARIES)
         clickhouse_strip_binary(TARGET clickhouse DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/${STRIPPED_BINARIES_OUTPUT} BINARY_PATH clickhouse)
     else()
+        clickhouse_make_empty_debug_info_for_nfpm(TARGET clickhouse DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/${STRIPPED_BINARIES_OUTPUT})
         install (TARGETS clickhouse RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse)
     endif()
 endif()
 
-if (NOT INSTALL_STRIPPED_BINARIES)
-    # Install dunny debug directory
-    # TODO: move logic to every place where clickhouse_strip_binary is used
-    add_custom_command(TARGET clickhouse POST_BUILD COMMAND echo > .empty )
-    install(FILES "${CMAKE_CURRENT_BINARY_DIR}/.empty" DESTINATION ${CMAKE_INSTALL_LIBDIR}/debug/.empty)
-endif()
-
-
 if (ENABLE_TESTS)
     set (CLICKHOUSE_UNIT_TESTS_TARGETS unit_tests_dbms)
     add_custom_target (clickhouse-tests ALL DEPENDS ${CLICKHOUSE_UNIT_TESTS_TARGETS})

programs/keeper/CMakeLists.txt

@@ -71,17 +71,11 @@ if (BUILD_STANDALONE_KEEPER)
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressedReadBuffer.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressedReadBufferFromFile.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressedWriteBuffer.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecDelta.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecDoubleDelta.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecEncrypted.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecGorilla.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecLZ4.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecMultiple.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecNone.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecT64.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionCodecZSTD.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/CompressionFactory.cpp
-        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/getCompressionCodecForFile.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/ICompressionCodec.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Compression/LZ4_decompress_faster.cpp
 
@@ -137,5 +131,10 @@ if (BUILD_STANDALONE_KEEPER)
     add_dependencies(clickhouse-keeper clickhouse_keeper_configs)
     set_target_properties(clickhouse-keeper PROPERTIES RUNTIME_OUTPUT_DIRECTORY ../)
 
+    if (INSTALL_STRIPPED_BINARIES)
+        clickhouse_strip_binary(TARGET clickhouse-keeper DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT} BINARY_PATH ../clickhouse-keeper)
+    else()
+        clickhouse_make_empty_debug_info_for_nfpm(TARGET clickhouse-keeper DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT})
         install(TARGETS clickhouse-keeper RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse)
     endif()
+endif()

programs/library-bridge/CMakeLists.txt

@@ -27,5 +27,6 @@ set_target_properties(clickhouse-library-bridge PROPERTIES RUNTIME_OUTPUT_DIRECT
 if (INSTALL_STRIPPED_BINARIES)
     clickhouse_strip_binary(TARGET clickhouse-library-bridge DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT} BINARY_PATH ../clickhouse-library-bridge)
 else()
+    clickhouse_make_empty_debug_info_for_nfpm(TARGET clickhouse-library-bridge DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT})
     install(TARGETS clickhouse-library-bridge RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse)
 endif()

programs/odbc-bridge/CMakeLists.txt

@@ -42,6 +42,7 @@ endif()
 if (INSTALL_STRIPPED_BINARIES)
     clickhouse_strip_binary(TARGET clickhouse-odbc-bridge DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT} BINARY_PATH ../clickhouse-odbc-bridge)
 else()
+    clickhouse_make_empty_debug_info_for_nfpm(TARGET clickhouse-odbc-bridge DESTINATION_DIR ${CMAKE_CURRENT_BINARY_DIR}/../${STRIPPED_BINARIES_OUTPUT})
     install(TARGETS clickhouse-odbc-bridge RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse)
 endif()
 

src/Access/Common/QuotaDefs.h

@@ -13,7 +13,7 @@ enum class QuotaType
 {
     QUERIES,        /// Number of queries.
     QUERY_SELECTS,  /// Number of select queries.
-    QUERY_INSERTS,  /// Number of inserts queries.
+    QUERY_INSERTS,  /// Number of insert queries.
     ERRORS,         /// Number of queries with exceptions.
     RESULT_ROWS,    /// Number of rows returned as result.
     RESULT_BYTES,   /// Number of bytes returned as result.

src/Common/FiberStack.h

@@ -31,8 +31,8 @@ public:
     /// probably it worth to try to increase stack size for coroutines.
     ///
     /// Current value is just enough for all tests in our CI. It's not selected in some special
-    /// way. We will have 40 pages with 4KB page size.
+    /// way. We will have 80 pages with 4KB page size.
-    static constexpr size_t default_stack_size = 192 * 1024; /// 64KB was not enough for tests
+    static constexpr size_t default_stack_size = 320 * 1024; /// 64KB was not enough for tests
 
     explicit FiberStack(size_t stack_size_ = default_stack_size) : stack_size(stack_size_)
     {

src/Common/OvercommitTracker.cpp

@@ -23,6 +23,12 @@ void OvercommitTracker::setMaxWaitTime(UInt64 wait_time)
 
 bool OvercommitTracker::needToStopQuery(MemoryTracker * tracker)
 {
+    // NOTE: Do not change the order of locks
+    //
+    // global_mutex must be acquired before overcommit_m, because
+    // method OvercommitTracker::unsubscribe(MemoryTracker *) is
+    // always called with already acquired global_mutex in
+    // ProcessListEntry::~ProcessListEntry().
     std::unique_lock<std::mutex> global_lock(global_mutex);
     std::unique_lock<std::mutex> lk(overcommit_m);
 
@@ -76,7 +82,7 @@ void UserOvercommitTracker::pickQueryToExcludeImpl()
     MemoryTracker * query_tracker = nullptr;
     OvercommitRatio current_ratio{0, 0};
     // At this moment query list must be read only.
-    // BlockQueryIfMemoryLimit is used in ProcessList to guarantee this.
+    // This is guaranteed by locking global_mutex in OvercommitTracker::needToStopQuery.
     auto & queries = user_process_list->queries;
     LOG_DEBUG(logger, "Trying to choose query to stop from {} queries", queries.size());
     for (auto const & query : queries)
@@ -111,9 +117,9 @@ void GlobalOvercommitTracker::pickQueryToExcludeImpl()
     MemoryTracker * query_tracker = nullptr;
     OvercommitRatio current_ratio{0, 0};
     // At this moment query list must be read only.
-    // BlockQueryIfMemoryLimit is used in ProcessList to guarantee this.
+    // This is guaranteed by locking global_mutex in OvercommitTracker::needToStopQuery.
-    LOG_DEBUG(logger, "Trying to choose query to stop");
+    LOG_DEBUG(logger, "Trying to choose query to stop from {} queries", process_list->size());
-    process_list->processEachQueryStatus([&](DB::QueryStatus const & query)
+    for (auto const & query : process_list->processes)
     {
         if (query.isKilled())
             return;
@@ -134,7 +140,7 @@ void GlobalOvercommitTracker::pickQueryToExcludeImpl()
             query_tracker = memory_tracker;
             current_ratio   = ratio;
         }
-    });
+    }
     LOG_DEBUG(logger, "Selected to stop query with overcommit ratio {}/{}",
         current_ratio.committed, current_ratio.soft_limit);
     picked_tracker = query_tracker;

src/Common/OvercommitTracker.h

@@ -43,8 +43,6 @@ class MemoryTracker;
 // is killed to free memory.
 struct OvercommitTracker : boost::noncopyable
 {
-    explicit OvercommitTracker(std::mutex & global_mutex_);
-
     void setMaxWaitTime(UInt64 wait_time);
 
     bool needToStopQuery(MemoryTracker * tracker);
@@ -54,8 +52,12 @@ struct OvercommitTracker : boost::noncopyable
     virtual ~OvercommitTracker() = default;
 
 protected:
+    explicit OvercommitTracker(std::mutex & global_mutex_);
+
     virtual void pickQueryToExcludeImpl() = 0;
 
+    // This mutex is used to disallow concurrent access
+    // to picked_tracker and cancelation_state variables.
     mutable std::mutex overcommit_m;
     mutable std::condition_variable cv;
 
@@ -87,6 +89,11 @@ private:
         }
     }
 
+    // Global mutex which is used in ProcessList to synchronize
+    // insertion and deletion of queries.
+    // OvercommitTracker::pickQueryToExcludeImpl() implementations
+    // require this mutex to be locked, because they read list (or sublist)
+    // of queries.
     std::mutex & global_mutex;
 };
 

src/Common/ProfileEvents.cpp

@@ -9,6 +9,7 @@
     M(SelectQuery, "Same as Query, but only for SELECT queries.") \
     M(InsertQuery, "Same as Query, but only for INSERT queries.") \
     M(AsyncInsertQuery, "Same as InsertQuery, but only for asynchronous INSERT queries.") \
+    M(AsyncInsertBytes, "Data size in bytes of asynchronous INSERT queries.") \
     M(FailedQuery, "Number of failed queries.") \
     M(FailedSelectQuery, "Same as FailedQuery, but only for SELECT queries.") \
     M(FailedInsertQuery, "Same as FailedQuery, but only for INSERT queries.") \

src/Common/formatIPv6.h

@@ -11,7 +11,7 @@
 constexpr size_t IPV4_BINARY_LENGTH = 4;
 constexpr size_t IPV6_BINARY_LENGTH = 16;
 constexpr size_t IPV4_MAX_TEXT_LENGTH = 15;     /// Does not count tail zero byte.
-constexpr size_t IPV6_MAX_TEXT_LENGTH = 39;
+constexpr size_t IPV6_MAX_TEXT_LENGTH = 45;     /// Does not count tail zero byte.
 
 namespace DB
 {

src/Compression/CompressionFactory.cpp

@@ -165,25 +165,36 @@ void registerCodecNone(CompressionCodecFactory & factory);
 void registerCodecLZ4(CompressionCodecFactory & factory);
 void registerCodecLZ4HC(CompressionCodecFactory & factory);
 void registerCodecZSTD(CompressionCodecFactory & factory);
+void registerCodecMultiple(CompressionCodecFactory & factory);
+
+
+/// Keeper use only general-purpose codecs, so we don't need these special codecs
+/// in standalone build
+#ifndef KEEPER_STANDALONE_BUILD
+
 void registerCodecDelta(CompressionCodecFactory & factory);
 void registerCodecT64(CompressionCodecFactory & factory);
 void registerCodecDoubleDelta(CompressionCodecFactory & factory);
 void registerCodecGorilla(CompressionCodecFactory & factory);
 void registerCodecEncrypted(CompressionCodecFactory & factory);
-void registerCodecMultiple(CompressionCodecFactory & factory);
+
+#endif
 
 CompressionCodecFactory::CompressionCodecFactory()
 {
-    registerCodecLZ4(*this);
     registerCodecNone(*this);
+    registerCodecLZ4(*this);
     registerCodecZSTD(*this);
     registerCodecLZ4HC(*this);
+    registerCodecMultiple(*this);
+
+#ifndef KEEPER_STANDALONE_BUILD
     registerCodecDelta(*this);
     registerCodecT64(*this);
     registerCodecDoubleDelta(*this);
     registerCodecGorilla(*this);
     registerCodecEncrypted(*this);
-    registerCodecMultiple(*this);
+#endif
 
     default_codec = get("LZ4", {});
 }

src/Core/Block.cpp

@@ -13,6 +13,7 @@
 
 #include <iterator>
 #include <base/sort.h>
+#include <boost/algorithm/string.hpp>
 
 
 namespace DB
@@ -269,8 +270,18 @@ const ColumnWithTypeAndName & Block::safeGetByPosition(size_t position) const
 }
 
 
-const ColumnWithTypeAndName * Block::findByName(const std::string & name) const
+const ColumnWithTypeAndName * Block::findByName(const std::string & name, bool case_insensitive) const
 {
+    if (case_insensitive)
+    {
+        auto found = std::find_if(data.begin(), data.end(), [&](const auto & column) { return boost::iequals(column.name, name); });
+        if (found == data.end())
+        {
+            return nullptr;
+        }
+        return &*found;
+    }
+
     auto it = index_by_name.find(name);
     if (index_by_name.end() == it)
     {
@@ -280,19 +291,23 @@ const ColumnWithTypeAndName * Block::findByName(const std::string & name) const
 }
 
 
-const ColumnWithTypeAndName & Block::getByName(const std::string & name) const
+const ColumnWithTypeAndName & Block::getByName(const std::string & name, bool case_insensitive) const
 {
-    const auto * result = findByName(name);
+    const auto * result = findByName(name, case_insensitive);
     if (!result)
-        throw Exception("Not found column " + name + " in block. There are only columns: " + dumpNames()
+        throw Exception(
-            , ErrorCodes::NOT_FOUND_COLUMN_IN_BLOCK);
+            "Not found column " + name + " in block. There are only columns: " + dumpNames(), ErrorCodes::NOT_FOUND_COLUMN_IN_BLOCK);
 
     return *result;
 }
 
 
-bool Block::has(const std::string & name) const
+bool Block::has(const std::string & name, bool case_insensitive) const
 {
+    if (case_insensitive)
+        return std::find_if(data.begin(), data.end(), [&](const auto & column) { return boost::iequals(column.name, name); })
+            != data.end();
+
     return index_by_name.end() != index_by_name.find(name);
 }
 
@@ -301,8 +316,8 @@ size_t Block::getPositionByName(const std::string & name) const
 {
     auto it = index_by_name.find(name);
     if (index_by_name.end() == it)
-        throw Exception("Not found column " + name + " in block. There are only columns: " + dumpNames()
+        throw Exception(
-            , ErrorCodes::NOT_FOUND_COLUMN_IN_BLOCK);
+            "Not found column " + name + " in block. There are only columns: " + dumpNames(), ErrorCodes::NOT_FOUND_COLUMN_IN_BLOCK);
 
     return it->second;
 }

src/Core/Block.h

@@ -60,21 +60,21 @@ public:
     ColumnWithTypeAndName & safeGetByPosition(size_t position);
     const ColumnWithTypeAndName & safeGetByPosition(size_t position) const;
 
-    ColumnWithTypeAndName* findByName(const std::string & name)
+    ColumnWithTypeAndName* findByName(const std::string & name, bool case_insensitive = false)
     {
         return const_cast<ColumnWithTypeAndName *>(
-            const_cast<const Block *>(this)->findByName(name));
+            const_cast<const Block *>(this)->findByName(name, case_insensitive));
     }
 
-    const ColumnWithTypeAndName * findByName(const std::string & name) const;
+    const ColumnWithTypeAndName * findByName(const std::string & name, bool case_insensitive = false) const;
 
-    ColumnWithTypeAndName & getByName(const std::string & name)
+    ColumnWithTypeAndName & getByName(const std::string & name, bool case_insensitive = false)
     {
         return const_cast<ColumnWithTypeAndName &>(
-            const_cast<const Block *>(this)->getByName(name));
+            const_cast<const Block *>(this)->getByName(name, case_insensitive));
     }
 
-    const ColumnWithTypeAndName & getByName(const std::string & name) const;
+    const ColumnWithTypeAndName & getByName(const std::string & name, bool case_insensitive = false) const;
 
     Container::iterator begin() { return data.begin(); }
     Container::iterator end() { return data.end(); }
@@ -83,7 +83,7 @@ public:
     Container::const_iterator cbegin() const { return data.cbegin(); }
     Container::const_iterator cend() const { return data.cend(); }
 
-    bool has(const std::string & name) const;
+    bool has(const std::string & name, bool case_insensitive = false) const;
 
     size_t getPositionByName(const std::string & name) const;
 

src/Core/Settings.h

@@ -616,11 +616,13 @@ class IColumn;
     M(Bool, input_format_tsv_empty_as_default, false, "Treat empty fields in TSV input as default values.", 0) \
     M(Bool, input_format_tsv_enum_as_number, false, "Treat inserted enum values in TSV formats as enum indices \\N", 0) \
     M(Bool, input_format_null_as_default, true, "For text input formats initialize null fields with default values if data type of this field is not nullable", 0) \
-    M(Bool, input_format_use_lowercase_column_name, false, "Use lowercase column name while reading input formats", 0) \
     M(Bool, input_format_arrow_import_nested, false, "Allow to insert array of structs into Nested table in Arrow input format.", 0) \
+    M(Bool, input_format_arrow_case_insensitive_column_matching, false, "Ignore case when matching Arrow columns with CH columns.", 0) \
     M(Bool, input_format_orc_import_nested, false, "Allow to insert array of structs into Nested table in ORC input format.", 0) \
     M(Int64, input_format_orc_row_batch_size, 100'000, "Batch size when reading ORC stripes.", 0) \
+    M(Bool, input_format_orc_case_insensitive_column_matching, false, "Ignore case when matching ORC columns with CH columns.", 0) \
     M(Bool, input_format_parquet_import_nested, false, "Allow to insert array of structs into Nested table in Parquet input format.", 0) \
+    M(Bool, input_format_parquet_case_insensitive_column_matching, false, "Ignore case when matching Parquet columns with CH columns.", 0) \
     M(Bool, input_format_allow_seeks, true, "Allow seeks while reading in ORC/Parquet/Arrow input formats", 0) \
     M(Bool, input_format_orc_allow_missing_columns, false, "Allow missing columns while reading ORC input formats", 0) \
     M(Bool, input_format_parquet_allow_missing_columns, false, "Allow missing columns while reading Parquet input formats", 0) \

src/DataTypes/NestedUtils.cpp

@@ -15,6 +15,8 @@
 
 #include <Parsers/IAST.h>
 
+#include <boost/algorithm/string/case_conv.hpp>
+
 
 namespace DB
 {
@@ -227,14 +229,17 @@ void validateArraySizes(const Block & block)
 }
 
 
-std::unordered_set<String> getAllTableNames(const Block & block)
+std::unordered_set<String> getAllTableNames(const Block & block, bool to_lower_case)
 {
     std::unordered_set<String> nested_table_names;
-    for (auto & name : block.getNames())
+    for (const auto & name : block.getNames())
     {
         auto nested_table_name = Nested::extractTableName(name);
+        if (to_lower_case)
+            boost::to_lower(nested_table_name);
+
         if (!nested_table_name.empty())
-            nested_table_names.insert(nested_table_name);
+            nested_table_names.insert(std::move(nested_table_name));
     }
     return nested_table_names;
 }

src/DataTypes/NestedUtils.h

@@ -32,7 +32,7 @@ namespace Nested
     void validateArraySizes(const Block & block);
 
     /// Get all nested tables names from a block.
-    std::unordered_set<String> getAllTableNames(const Block & block);
+    std::unordered_set<String> getAllTableNames(const Block & block, bool to_lower_case = false);
 }
 
 }

src/Databases/DatabaseReplicated.cpp

@@ -88,6 +88,9 @@ DatabaseReplicated::DatabaseReplicated(
     /// If zookeeper chroot prefix is used, path should start with '/', because chroot concatenates without it.
     if (zookeeper_path.front() != '/')
         zookeeper_path = "/" + zookeeper_path;
+
+    if (!db_settings.collection_name.value.empty())
+        fillClusterAuthInfo(db_settings.collection_name.value, context_->getConfigRef());
 }
 
 String DatabaseReplicated::getFullReplicaName() const
@@ -191,22 +194,36 @@ ClusterPtr DatabaseReplicated::getClusterImpl() const
         shards.back().emplace_back(unescapeForFileName(host_port));
     }
 
-    String username = db_settings.cluster_username;
-    String password = db_settings.cluster_password;
     UInt16 default_port = getContext()->getTCPPort();
-    bool secure = db_settings.cluster_secure_connection;
 
     bool treat_local_as_remote = false;
     bool treat_local_port_as_remote = getContext()->getApplicationType() == Context::ApplicationType::LOCAL;
     return std::make_shared<Cluster>(
         getContext()->getSettingsRef(),
         shards,
-        username,
+        cluster_auth_info.cluster_username,
-        password,
+        cluster_auth_info.cluster_password,
         default_port,
         treat_local_as_remote,
         treat_local_port_as_remote,
-        secure);
+        cluster_auth_info.cluster_secure_connection,
+        /*priority=*/1,
+        database_name,
+        cluster_auth_info.cluster_secret);
+}
+
+
+void DatabaseReplicated::fillClusterAuthInfo(String collection_name, const Poco::Util::AbstractConfiguration & config_ref)
+{
+    const auto & config_prefix = fmt::format("named_collections.{}", collection_name);
+
+    if (!config_ref.has(config_prefix))
+            throw Exception(ErrorCodes::BAD_ARGUMENTS, "There is no collection named `{}` in config", collection_name);
+
+    cluster_auth_info.cluster_username = config_ref.getString(config_prefix + ".cluster_username", "");
+    cluster_auth_info.cluster_password = config_ref.getString(config_prefix + ".cluster_password", "");
+    cluster_auth_info.cluster_secret = config_ref.getString(config_prefix + ".cluster_secret", "");
+    cluster_auth_info.cluster_secure_connection = config_ref.getBool(config_prefix + ".cluster_secure_connection", false);
 }
 
 void DatabaseReplicated::tryConnectToZooKeeperAndInitDatabase(bool force_attach)

src/Databases/DatabaseReplicated.h

@@ -75,6 +75,16 @@ private:
     bool createDatabaseNodesInZooKeeper(const ZooKeeperPtr & current_zookeeper);
     void createReplicaNodesInZooKeeper(const ZooKeeperPtr & current_zookeeper);
 
+    struct
+    {
+        String cluster_username{"default"};
+        String cluster_password;
+        String cluster_secret;
+        bool cluster_secure_connection{false};
+    } cluster_auth_info;
+
+    void fillClusterAuthInfo(String collection_name, const Poco::Util::AbstractConfiguration & config);
+
     void checkQueryValid(const ASTPtr & query, ContextPtr query_context) const;
 
     void recoverLostReplica(const ZooKeeperPtr & current_zookeeper, UInt32 our_log_ptr, UInt32 max_log_ptr);

src/Databases/DatabaseReplicatedSettings.h

@@ -11,9 +11,8 @@ class ASTStorage;
     M(Float,  max_broken_tables_ratio, 0.5, "Do not recover replica automatically if the ratio of staled tables to all tables is greater", 0) \
     M(UInt64, max_replication_lag_to_enqueue, 10, "Replica will throw exception on attempt to execute query if its replication lag greater", 0) \
     M(UInt64, wait_entry_commited_timeout_sec, 3600, "Replicas will try to cancel query if timeout exceed, but initiator host has not executed it yet", 0) \
-    M(String, cluster_username, "default", "Username to use when connecting to hosts of cluster", 0) \
+    M(String, collection_name, "", "A name of a collection defined in server's config where all info for cluster authentication is defined", 0) \
-    M(String, cluster_password, "", "Password to use when connecting to hosts of cluster", 0) \
+
-    M(Bool, cluster_secure_connection, false, "Enable TLS when connecting to hosts of cluster", 0) \
 
 DECLARE_SETTINGS_TRAITS(DatabaseReplicatedSettingsTraits, LIST_OF_DATABASE_REPLICATED_SETTINGS)
 

src/Formats/FormatFactory.cpp

@@ -89,10 +89,10 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
     format_settings.json.quote_64bit_integers = settings.output_format_json_quote_64bit_integers;
     format_settings.json.quote_denormals = settings.output_format_json_quote_denormals;
     format_settings.null_as_default = settings.input_format_null_as_default;
-    format_settings.use_lowercase_column_name = settings.input_format_use_lowercase_column_name;
     format_settings.decimal_trailing_zeros = settings.output_format_decimal_trailing_zeros;
     format_settings.parquet.row_group_size = settings.output_format_parquet_row_group_size;
     format_settings.parquet.import_nested = settings.input_format_parquet_import_nested;
+    format_settings.parquet.case_insensitive_column_matching = settings.input_format_parquet_case_insensitive_column_matching;
     format_settings.parquet.allow_missing_columns = settings.input_format_parquet_allow_missing_columns;
     format_settings.pretty.charset = settings.output_format_pretty_grid_charset.toString() == "ASCII" ? FormatSettings::Pretty::Charset::ASCII : FormatSettings::Pretty::Charset::UTF8;
     format_settings.pretty.color = settings.output_format_pretty_color;
@@ -123,9 +123,11 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
     format_settings.arrow.low_cardinality_as_dictionary = settings.output_format_arrow_low_cardinality_as_dictionary;
     format_settings.arrow.import_nested = settings.input_format_arrow_import_nested;
     format_settings.arrow.allow_missing_columns = settings.input_format_arrow_allow_missing_columns;
+    format_settings.arrow.case_insensitive_column_matching = settings.input_format_arrow_case_insensitive_column_matching;
     format_settings.orc.import_nested = settings.input_format_orc_import_nested;
     format_settings.orc.allow_missing_columns = settings.input_format_orc_allow_missing_columns;
     format_settings.orc.row_batch_size = settings.input_format_orc_row_batch_size;
+    format_settings.orc.case_insensitive_column_matching = settings.input_format_orc_case_insensitive_column_matching;
     format_settings.defaults_for_omitted_fields = settings.input_format_defaults_for_omitted_fields;
     format_settings.capn_proto.enum_comparing_mode = settings.format_capn_proto_enum_comparising_mode;
     format_settings.seekable_read = settings.input_format_allow_seeks;

src/Formats/FormatSettings.h

@@ -32,7 +32,6 @@ struct FormatSettings
     bool null_as_default = true;
     bool decimal_trailing_zeros = false;
     bool defaults_for_omitted_fields = true;
-    bool use_lowercase_column_name = false;
 
     bool seekable_read = true;
     UInt64 max_rows_to_read_for_schema_inference = 100;
@@ -75,6 +74,7 @@ struct FormatSettings
         bool low_cardinality_as_dictionary = false;
         bool import_nested = false;
         bool allow_missing_columns = false;
+        bool case_insensitive_column_matching = false;
     } arrow;
 
     struct
@@ -137,6 +137,7 @@ struct FormatSettings
         UInt64 row_group_size = 1000000;
         bool import_nested = false;
         bool allow_missing_columns = false;
+        bool case_insensitive_column_matching = false;
     } parquet;
 
     struct Pretty
@@ -217,6 +218,7 @@ struct FormatSettings
         bool import_nested = false;
         bool allow_missing_columns = false;
         int64_t row_batch_size = 100'000;
+        bool case_insensitive_column_matching = false;
     } orc;
 
     /// For capnProto format we should determine how to

src/Formats/registerFormats.cpp

@@ -13,6 +13,7 @@ void registerFileSegmentationEngineCSV(FormatFactory & factory);
 void registerFileSegmentationEngineJSONEachRow(FormatFactory & factory);
 void registerFileSegmentationEngineRegexp(FormatFactory & factory);
 void registerFileSegmentationEngineJSONAsString(FormatFactory & factory);
+void registerFileSegmentationEngineJSONAsObject(FormatFactory & factory);
 void registerFileSegmentationEngineJSONCompactEachRow(FormatFactory & factory);
 
 /// Formats for both input/output.
@@ -103,6 +104,7 @@ void registerProtobufSchemaReader(FormatFactory & factory);
 void registerProtobufListSchemaReader(FormatFactory & factory);
 void registerLineAsStringSchemaReader(FormatFactory & factory);
 void registerJSONAsStringSchemaReader(FormatFactory & factory);
+void registerJSONAsObjectSchemaReader(FormatFactory & factory);
 void registerRawBLOBSchemaReader(FormatFactory & factory);
 void registerMsgPackSchemaReader(FormatFactory & factory);
 void registerCapnProtoSchemaReader(FormatFactory & factory);
@@ -123,6 +125,7 @@ void registerFormats()
     registerFileSegmentationEngineJSONEachRow(factory);
     registerFileSegmentationEngineRegexp(factory);
     registerFileSegmentationEngineJSONAsString(factory);
+    registerFileSegmentationEngineJSONAsObject(factory);
     registerFileSegmentationEngineJSONCompactEachRow(factory);
 
     registerInputFormatNative(factory);
@@ -207,6 +210,7 @@ void registerFormats()
     registerProtobufListSchemaReader(factory);
     registerLineAsStringSchemaReader(factory);
     registerJSONAsStringSchemaReader(factory);
+    registerJSONAsObjectSchemaReader(factory);
     registerRawBLOBSchemaReader(factory);
     registerMsgPackSchemaReader(factory);
     registerCapnProtoSchemaReader(factory);

src/Functions/caseWithExpression.cpp

@@ -43,6 +43,9 @@ public:
         for (size_t i = 2; i < args.size() - 1; i += 2)
             dst_array_types.push_back(args[i]);
 
+        // Type of the ELSE branch
+        dst_array_types.push_back(args.back());
+
         return getLeastSupertype(dst_array_types);
     }
 

src/Interpreters/AsynchronousInsertQueue.cpp

@@ -32,6 +32,7 @@ namespace CurrentMetrics
 namespace ProfileEvents
 {
     extern const Event AsyncInsertQuery;
+    extern const Event AsyncInsertBytes;
 }
 
 namespace DB
@@ -222,7 +223,9 @@ void AsynchronousInsertQueue::pushImpl(InsertData::EntryPtr entry, QueueIterator
     if (!data)
         data = std::make_unique<InsertData>();
 
-    data->size += entry->bytes.size();
+    size_t entry_data_size = entry->bytes.size();
+
+    data->size += entry_data_size;
     data->last_update = std::chrono::steady_clock::now();
     data->entries.emplace_back(entry);
 
@@ -239,6 +242,7 @@ void AsynchronousInsertQueue::pushImpl(InsertData::EntryPtr entry, QueueIterator
 
     CurrentMetrics::add(CurrentMetrics::PendingAsyncInsert);
     ProfileEvents::increment(ProfileEvents::AsyncInsertQuery);
+    ProfileEvents::increment(ProfileEvents::AsyncInsertBytes, entry_data_size);
 }
 
 void AsynchronousInsertQueue::waitForProcessingQuery(const String & query_id, const Milliseconds & timeout)

src/Interpreters/Cluster.cpp

@@ -132,7 +132,9 @@ Cluster::Address::Address(
     bool secure_,
     Int64 priority_,
     UInt32 shard_index_,
-    UInt32 replica_index_)
+    UInt32 replica_index_,
+    String cluster_name_,
+    String cluster_secret_)
     : user(user_), password(password_)
 {
     bool can_be_local = true;
@@ -164,6 +166,8 @@ Cluster::Address::Address(
     is_local = can_be_local && isLocal(clickhouse_port);
     shard_index = shard_index_;
     replica_index = replica_index_;
+    cluster = cluster_name_;
+    cluster_secret = cluster_secret_;
 }
 
 
@@ -537,10 +541,14 @@ Cluster::Cluster(
     bool treat_local_as_remote,
     bool treat_local_port_as_remote,
     bool secure,
-    Int64 priority)
+    Int64 priority,
+    String cluster_name,
+    String cluster_secret)
 {
     UInt32 current_shard_num = 1;
 
+    secret = cluster_secret;
+
     for (const auto & shard : names)
     {
         Addresses current;
@@ -554,7 +562,9 @@ Cluster::Cluster(
                 secure,
                 priority,
                 current_shard_num,
-                current.size() + 1);
+                current.size() + 1,
+                cluster_name,
+                cluster_secret);
 
         addresses_with_failover.emplace_back(current);
 
@@ -690,6 +700,9 @@ Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Setti
         }
     }
 
+    secret = from.secret;
+    name = from.name;
+
     initMisc();
 }
 
@@ -704,6 +717,9 @@ Cluster::Cluster(Cluster::SubclusterTag, const Cluster & from, const std::vector
             addresses_with_failover.emplace_back(from.addresses_with_failover.at(index));
     }
 
+    secret = from.secret;
+    name = from.name;
+
     initMisc();
 }
 

src/Interpreters/Cluster.h

@@ -55,7 +55,9 @@ public:
         bool treat_local_as_remote,
         bool treat_local_port_as_remote,
         bool secure = false,
-        Int64 priority = 1);
+        Int64 priority = 1,
+        String cluster_name = "",
+        String cluster_secret = "");
 
     Cluster(const Cluster &)= delete;
     Cluster & operator=(const Cluster &) = delete;
@@ -127,7 +129,9 @@ public:
             bool secure_ = false,
             Int64 priority_ = 1,
             UInt32 shard_index_ = 0,
-            UInt32 replica_index_ = 0);
+            UInt32 replica_index_ = 0,
+            String cluster_name = "",
+            String cluster_secret_ = "");
 
         /// Returns 'escaped_host_name:port'
         String toString() const;

src/Interpreters/ExpressionAnalyzer.cpp

@@ -100,20 +100,9 @@ bool checkPositionalArguments(ASTPtr & argument, const ASTSelectQuery * select_q
 {
     auto columns = select_query->select()->children;
 
-    const auto * group_by_expr_with_alias = dynamic_cast<const ASTWithAlias *>(argument.get());
+    const auto * expr_with_alias = dynamic_cast<const ASTWithAlias *>(argument.get());
-    if (group_by_expr_with_alias && !group_by_expr_with_alias->alias.empty())
+    if (expr_with_alias && !expr_with_alias->alias.empty())
-    {
-        for (const auto & column : columns)
-        {
-            const auto * col_with_alias = dynamic_cast<const ASTWithAlias *>(column.get());
-            if (col_with_alias)
-            {
-                const auto & alias = col_with_alias->alias;
-                if (!alias.empty() && alias == group_by_expr_with_alias->alias)
         return false;
-            }
-        }
-    }
 
     const auto * ast_literal = typeid_cast<const ASTLiteral *>(argument.get());
     if (!ast_literal)
@@ -130,7 +119,7 @@ bool checkPositionalArguments(ASTPtr & argument, const ASTSelectQuery * select_q
                         pos, columns.size());
 
     const auto & column = columns[--pos];
-    if (typeid_cast<const ASTIdentifier *>(column.get()))
+    if (typeid_cast<const ASTIdentifier *>(column.get()) || typeid_cast<const ASTLiteral *>(column.get()))
     {
         argument = column->clone();
     }
@@ -1324,8 +1313,10 @@ ActionsDAGPtr SelectQueryExpressionAnalyzer::appendOrderBy(ExpressionActionsChai
             throw Exception("Bad ORDER BY expression AST", ErrorCodes::UNKNOWN_TYPE_OF_AST_NODE);
 
         if (getContext()->getSettingsRef().enable_positional_arguments)
+        {
             replaceForPositionalArguments(ast->children.at(0), select_query, ASTSelectQuery::Expression::ORDER_BY);
         }
+    }
 
     getRootActions(select_query->orderBy(), only_types, step.actions());
 

src/Interpreters/HashJoin.cpp

@@ -962,18 +962,29 @@ public:
             /// If it's joinGetOrNull, we need to wrap not-nullable columns in StorageJoin.
             for (size_t j = 0, size = right_indexes.size(); j < size; ++j)
             {
-                const auto & column = *block.getByPosition(right_indexes[j]).column;
+                auto column_from_block = block.getByPosition(right_indexes[j]);
-                if (auto * nullable_col = typeid_cast<ColumnNullable *>(columns[j].get()); nullable_col && !column.isNullable())
+                if (type_name[j].type->lowCardinality() != column_from_block.type->lowCardinality())
-                    nullable_col->insertFromNotNullable(column, row_num);
+                {
+                    JoinCommon::changeLowCardinalityInplace(column_from_block);
+                }
+
+                if (auto * nullable_col = typeid_cast<ColumnNullable *>(columns[j].get());
+                    nullable_col && !column_from_block.column->isNullable())
+                    nullable_col->insertFromNotNullable(*column_from_block.column, row_num);
                 else
-                    columns[j]->insertFrom(column, row_num);
+                    columns[j]->insertFrom(*column_from_block.column, row_num);
             }
         }
         else
         {
             for (size_t j = 0, size = right_indexes.size(); j < size; ++j)
             {
-                columns[j]->insertFrom(*block.getByPosition(right_indexes[j]).column, row_num);
+                auto column_from_block = block.getByPosition(right_indexes[j]);
+                if (type_name[j].type->lowCardinality() != column_from_block.type->lowCardinality())
+                {
+                    JoinCommon::changeLowCardinalityInplace(column_from_block);
+                }
+                columns[j]->insertFrom(*column_from_block.column, row_num);
             }
         }
     }
@@ -1013,6 +1024,7 @@ private:
 
     void addColumn(const ColumnWithTypeAndName & src_column, const std::string & qualified_name)
     {
+
         columns.push_back(src_column.column->cloneEmpty());
         columns.back()->reserve(src_column.column->size());
         type_name.emplace_back(src_column.type, src_column.name, qualified_name);

src/Interpreters/InterpreterCreateQuery.cpp

@@ -1180,11 +1180,10 @@ bool InterpreterCreateQuery::doCreateTable(ASTCreateQuery & create,
         /// old instance of the storage. For example, AsynchronousMetrics may cause ATTACH to fail,
         /// so we allow waiting here. If database_atomic_wait_for_drop_and_detach_synchronously is disabled
         /// and old storage instance still exists it will throw exception.
-        bool throw_if_table_in_use = getContext()->getSettingsRef().database_atomic_wait_for_drop_and_detach_synchronously;
+        if (getContext()->getSettingsRef().database_atomic_wait_for_drop_and_detach_synchronously)
-        if (throw_if_table_in_use)
-            database->checkDetachedTableNotInUse(create.uuid);
-        else
             database->waitDetachedTableNotInUse(create.uuid);
+        else
+            database->checkDetachedTableNotInUse(create.uuid);
     }
 
     StoragePtr res;

src/Interpreters/ProcessList.h

@@ -351,15 +351,6 @@ public:
         max_size = max_size_;
     }
 
-    // Before calling this method you should be sure
-    // that lock is acquired.
-    template <typename F>
-    void processEachQueryStatus(F && func) const
-    {
-        for (auto && query : processes)
-            func(query);
-    }
-
     void setMaxInsertQueriesAmount(size_t max_insert_queries_amount_)
     {
         std::lock_guard lock(mutex);

src/Interpreters/TreeRewriter.cpp

@@ -345,7 +345,10 @@ void replaceWithSumCount(String column_name, ASTFunction & func)
     {
         /// Rewrite "avg" to sumCount().1 / sumCount().2
         auto new_arg1 = makeASTFunction("tupleElement", func_base, std::make_shared<ASTLiteral>(UInt8(1)));
-        auto new_arg2 = makeASTFunction("tupleElement", func_base, std::make_shared<ASTLiteral>(UInt8(2)));
+        auto new_arg2 = makeASTFunction("CAST",
+            makeASTFunction("tupleElement", func_base, std::make_shared<ASTLiteral>(UInt8(2))),
+            std::make_shared<ASTLiteral>("Float64"));
+
         func.name = "divide";
         exp_list->children.push_back(new_arg1);
         exp_list->children.push_back(new_arg2);

src/Interpreters/join_common.cpp

@@ -326,9 +326,10 @@ ColumnRawPtrMap materializeColumnsInplaceMap(Block & block, const Names & names)
 
     for (const auto & column_name : names)
     {
-        auto & column = block.getByName(column_name).column;
+        auto & column = block.getByName(column_name);
-        column = recursiveRemoveLowCardinality(column->convertToFullColumnIfConst());
+        column.column = recursiveRemoveLowCardinality(column.column->convertToFullColumnIfConst());
-        ptrs[column_name] = column.get();
+        column.type = recursiveRemoveLowCardinality(column.type);
+        ptrs[column_name] = column.column.get();
     }
 
     return ptrs;

src/Processors/Formats/Impl/ArrowBlockInputFormat.cpp

@@ -139,7 +139,11 @@ void ArrowBlockInputFormat::prepareReader()
     }
 
     arrow_column_to_ch_column = std::make_unique<ArrowColumnToCHColumn>(
-        getPort().getHeader(), "Arrow", format_settings.arrow.import_nested, format_settings.arrow.allow_missing_columns);
+        getPort().getHeader(),
+        "Arrow",
+        format_settings.arrow.import_nested,
+        format_settings.arrow.allow_missing_columns,
+        format_settings.arrow.case_insensitive_column_matching);
     missing_columns = arrow_column_to_ch_column->getMissingColumns(*schema);
 
     if (stream)

src/Processors/Formats/Impl/ArrowColumnToCHColumn.cpp

@@ -31,6 +31,7 @@
 #include <algorithm>
 #include <arrow/builder.h>
 #include <arrow/array.h>
+#include <boost/algorithm/string/case_conv.hpp>
 
 /// UINT16 and UINT32 are processed separately, see comments in readColumnFromArrowColumn.
 #define FOR_ARROW_NUMERIC_TYPES(M) \
@@ -484,15 +485,18 @@ static void checkStatus(const arrow::Status & status, const String & column_name
         throw Exception{ErrorCodes::UNKNOWN_EXCEPTION, "Error with a {} column '{}': {}.", format_name, column_name, status.ToString()};
 }
 
-Block ArrowColumnToCHColumn::arrowSchemaToCHHeader(const arrow::Schema & schema, const std::string & format_name, const Block * hint_header)
+Block ArrowColumnToCHColumn::arrowSchemaToCHHeader(
+    const arrow::Schema & schema, const std::string & format_name, const Block * hint_header, bool ignore_case)
 {
     ColumnsWithTypeAndName sample_columns;
     std::unordered_set<String> nested_table_names;
     if (hint_header)
-        nested_table_names = Nested::getAllTableNames(*hint_header);
+        nested_table_names = Nested::getAllTableNames(*hint_header, ignore_case);
+
     for (const auto & field : schema.fields())
     {
-        if (hint_header && !hint_header->has(field->name()) && !nested_table_names.contains(field->name()))
+        if (hint_header && !hint_header->has(field->name(), ignore_case)
+            && !nested_table_names.contains(ignore_case ? boost::to_lower_copy(field->name()) : field->name()))
             continue;
 
         /// Create empty arrow column by it's type and convert it to ClickHouse column.
@@ -516,20 +520,31 @@ Block ArrowColumnToCHColumn::arrowSchemaToCHHeader(const arrow::Schema & schema,
 }
 
 ArrowColumnToCHColumn::ArrowColumnToCHColumn(
-    const Block & header_, const std::string & format_name_, bool import_nested_, bool allow_missing_columns_)
+    const Block & header_,
-    : header(header_), format_name(format_name_), import_nested(import_nested_), allow_missing_columns(allow_missing_columns_)
+    const std::string & format_name_,
+    bool import_nested_,
+    bool allow_missing_columns_,
+    bool case_insensitive_matching_)
+    : header(header_)
+    , format_name(format_name_)
+    , import_nested(import_nested_)
+    , allow_missing_columns(allow_missing_columns_)
+    , case_insensitive_matching(case_insensitive_matching_)
 {
 }
 
 void ArrowColumnToCHColumn::arrowTableToCHChunk(Chunk & res, std::shared_ptr<arrow::Table> & table)
 {
     NameToColumnPtr name_to_column_ptr;
-    for (const auto & column_name : table->ColumnNames())
+    for (auto column_name : table->ColumnNames())
     {
         std::shared_ptr<arrow::ChunkedArray> arrow_column = table->GetColumnByName(column_name);
         if (!arrow_column)
             throw Exception(ErrorCodes::DUPLICATE_COLUMN, "Column '{}' is duplicated", column_name);
-        name_to_column_ptr[column_name] = arrow_column;
+
+        if (case_insensitive_matching)
+            boost::to_lower(column_name);
+        name_to_column_ptr[std::move(column_name)] = arrow_column;
     }
 
     arrowColumnsToCHChunk(res, name_to_column_ptr);
@@ -548,22 +563,31 @@ void ArrowColumnToCHColumn::arrowColumnsToCHChunk(Chunk & res, NameToColumnPtr &
     {
         const ColumnWithTypeAndName & header_column = header.getByPosition(column_i);
 
+        auto search_column_name = header_column.name;
+        if (case_insensitive_matching)
+            boost::to_lower(search_column_name);
+
         bool read_from_nested = false;
         String nested_table_name = Nested::extractTableName(header_column.name);
-        if (!name_to_column_ptr.contains(header_column.name))
+        String search_nested_table_name = nested_table_name;
+        if (case_insensitive_matching)
+            boost::to_lower(search_nested_table_name);
+
+        if (!name_to_column_ptr.contains(search_column_name))
         {
             /// Check if it's a column from nested table.
-            if (import_nested && name_to_column_ptr.contains(nested_table_name))
+            if (import_nested && name_to_column_ptr.contains(search_nested_table_name))
             {
-                if (!nested_tables.contains(nested_table_name))
+                if (!nested_tables.contains(search_nested_table_name))
                 {
-                    std::shared_ptr<arrow::ChunkedArray> arrow_column = name_to_column_ptr[nested_table_name];
+                    std::shared_ptr<arrow::ChunkedArray> arrow_column = name_to_column_ptr[search_nested_table_name];
-                    ColumnsWithTypeAndName cols = {readColumnFromArrowColumn(arrow_column, nested_table_name, format_name, false, dictionary_values, true)};
+                    ColumnsWithTypeAndName cols
+                        = {readColumnFromArrowColumn(arrow_column, nested_table_name, format_name, false, dictionary_values, true)};
                     Block block(cols);
-                    nested_tables[nested_table_name] = std::make_shared<Block>(Nested::flatten(block));
+                    nested_tables[search_nested_table_name] = std::make_shared<Block>(Nested::flatten(block));
                 }
 
-                read_from_nested = nested_tables[nested_table_name]->has(header_column.name);
+                read_from_nested = nested_tables[search_nested_table_name]->has(header_column.name, case_insensitive_matching);
             }
 
             if (!read_from_nested)
@@ -580,13 +604,19 @@ void ArrowColumnToCHColumn::arrowColumnsToCHChunk(Chunk & res, NameToColumnPtr &
             }
         }
 
-        std::shared_ptr<arrow::ChunkedArray> arrow_column = name_to_column_ptr[header_column.name];
 
         ColumnWithTypeAndName column;
         if (read_from_nested)
-            column = nested_tables[nested_table_name]->getByName(header_column.name);
+        {
+            column = nested_tables[search_nested_table_name]->getByName(header_column.name, case_insensitive_matching);
+            if (case_insensitive_matching)
+                column.name = header_column.name;
+        }
         else
+        {
+            auto arrow_column = name_to_column_ptr[search_column_name];
             column = readColumnFromArrowColumn(arrow_column, header_column.name, format_name, false, dictionary_values, true);
+        }
 
         try
         {
@@ -594,8 +624,11 @@ void ArrowColumnToCHColumn::arrowColumnsToCHChunk(Chunk & res, NameToColumnPtr &
         }
         catch (Exception & e)
         {
-            e.addMessage(fmt::format("while converting column {} from type {} to type {}",
+            e.addMessage(fmt::format(
-                backQuote(header_column.name), column.type->getName(), header_column.type->getName()));
+                "while converting column {} from type {} to type {}",
+                backQuote(header_column.name),
+                column.type->getName(),
+                header_column.type->getName()));
             throw;
         }
 
@@ -609,22 +642,23 @@ void ArrowColumnToCHColumn::arrowColumnsToCHChunk(Chunk & res, NameToColumnPtr &
 std::vector<size_t> ArrowColumnToCHColumn::getMissingColumns(const arrow::Schema & schema) const
 {
     std::vector<size_t> missing_columns;
-    auto block_from_arrow = arrowSchemaToCHHeader(schema, format_name, &header);
+    auto block_from_arrow = arrowSchemaToCHHeader(schema, format_name, &header, case_insensitive_matching);
     auto flatten_block_from_arrow = Nested::flatten(block_from_arrow);
+
     for (size_t i = 0, columns = header.columns(); i < columns; ++i)
     {
-        const auto & column = header.getByPosition(i);
+        const auto & header_column = header.getByPosition(i);
         bool read_from_nested = false;
-        String nested_table_name = Nested::extractTableName(column.name);
+        String nested_table_name = Nested::extractTableName(header_column.name);
-        if (!block_from_arrow.has(column.name))
+        if (!block_from_arrow.has(header_column.name, case_insensitive_matching))
         {
-            if (import_nested && block_from_arrow.has(nested_table_name))
+            if (import_nested && block_from_arrow.has(nested_table_name, case_insensitive_matching))
-                read_from_nested = flatten_block_from_arrow.has(column.name);
+                read_from_nested = flatten_block_from_arrow.has(header_column.name, case_insensitive_matching);
 
             if (!read_from_nested)
             {
                 if (!allow_missing_columns)
-                    throw Exception{ErrorCodes::THERE_IS_NO_COLUMN, "Column '{}' is not presented in input data.", column.name};
+                    throw Exception{ErrorCodes::THERE_IS_NO_COLUMN, "Column '{}' is not presented in input data.", header_column.name};
 
                 missing_columns.push_back(i);
             }

src/Processors/Formats/Impl/ArrowColumnToCHColumn.h

@@ -25,7 +25,8 @@ public:
         const Block & header_,
         const std::string & format_name_,
         bool import_nested_,
-        bool allow_missing_columns_);
+        bool allow_missing_columns_,
+        bool case_insensitive_matching_ = false);
 
     void arrowTableToCHChunk(Chunk & res, std::shared_ptr<arrow::Table> & table);
 
@@ -36,7 +37,8 @@ public:
 
     /// Transform arrow schema to ClickHouse header. If hint_header is provided,
     /// we will skip columns in schema that are not in hint_header.
-    static Block arrowSchemaToCHHeader(const arrow::Schema & schema, const std::string & format_name, const Block * hint_header = nullptr);
+    static Block arrowSchemaToCHHeader(
+        const arrow::Schema & schema, const std::string & format_name, const Block * hint_header = nullptr, bool ignore_case = false);
 
 private:
     const Block & header;
@@ -44,6 +46,7 @@ private:
     bool import_nested;
     /// If false, throw exception if some columns in header not exists in arrow table.
     bool allow_missing_columns;
+    bool case_insensitive_matching;
 
     /// Map {column name : dictionary column}.
     /// To avoid converting dictionary from Arrow Dictionary

src/Processors/Formats/Impl/JSONAsStringRowInputFormat.cpp

@@ -228,6 +228,14 @@ void registerNonTrivialPrefixAndSuffixCheckerJSONAsString(FormatFactory & factor
     factory.registerNonTrivialPrefixAndSuffixChecker("JSONAsString", nonTrivialPrefixAndSuffixCheckerJSONEachRowImpl);
 }
 
+void registerJSONAsStringSchemaReader(FormatFactory & factory)
+{
+    factory.registerExternalSchemaReader("JSONAsString", [](const FormatSettings &)
+    {
+        return std::make_shared<JSONAsStringExternalSchemaReader>();
+    });
+}
+
 void registerInputFormatJSONAsObject(FormatFactory & factory)
 {
     factory.registerInputFormat("JSONAsObject", [](
@@ -245,11 +253,16 @@ void registerNonTrivialPrefixAndSuffixCheckerJSONAsObject(FormatFactory & factor
     factory.registerNonTrivialPrefixAndSuffixChecker("JSONAsObject", nonTrivialPrefixAndSuffixCheckerJSONEachRowImpl);
 }
 
-void registerJSONAsStringSchemaReader(FormatFactory & factory)
+void registerFileSegmentationEngineJSONAsObject(FormatFactory & factory)
 {
-    factory.registerExternalSchemaReader("JSONAsString", [](const FormatSettings &)
+    factory.registerFileSegmentationEngine("JSONAsObject", &fileSegmentationEngineJSONEachRow);
+}
+
+void registerJSONAsObjectSchemaReader(FormatFactory & factory)
 {
-        return std::make_shared<JSONAsStringExternalSchemaReader>();
+    factory.registerExternalSchemaReader("JSONAsObject", [](const FormatSettings &)
+    {
+        return std::make_shared<JSONAsObjectExternalSchemaReader>();
     });
 }
 

src/Processors/Formats/Impl/JSONAsStringRowInputFormat.h

@@ -5,6 +5,7 @@
 #include <Formats/FormatFactory.h>
 #include <IO/PeekableReadBuffer.h>
 #include <DataTypes/DataTypeString.h>
+#include <DataTypes/DataTypeObject.h>
 
 namespace DB
 {
@@ -73,4 +74,13 @@ public:
     }
 };
 
+class JSONAsObjectExternalSchemaReader : public IExternalSchemaReader
+{
+public:
+    NamesAndTypesList readSchema() override
+    {
+        return {{"json", std::make_shared<DataTypeObject>("json", false)}};
+    }
+};
+
 }

src/Processors/Formats/Impl/ORCBlockInputFormat.cpp

@@ -53,9 +53,6 @@ Chunk ORCBlockInputFormat::generate()
     if (!table || !table->num_rows())
         return res;
 
-    if (format_settings.use_lowercase_column_name)
-        table = *table->RenameColumns(include_column_names);
-
     arrow_column_to_ch_column->arrowTableToCHChunk(res, table);
     /// If defaults_for_omitted_fields is true, calculate the default values from default expression for omitted fields.
     /// Otherwise fill the missing columns with zero values of its type.
@@ -73,7 +70,6 @@ void ORCBlockInputFormat::resetParser()
 
     file_reader.reset();
     include_indices.clear();
-    include_column_names.clear();
     block_missing_values.clear();
 }
 
@@ -125,20 +121,6 @@ static void getFileReaderAndSchema(
     if (!read_schema_result.ok())
         throw Exception(read_schema_result.status().ToString(), ErrorCodes::BAD_ARGUMENTS);
     schema = std::move(read_schema_result).ValueOrDie();
-
-    if (format_settings.use_lowercase_column_name)
-    {
-        std::vector<std::shared_ptr<::arrow::Field>> fields;
-        fields.reserve(schema->num_fields());
-        for (int i = 0; i < schema->num_fields(); ++i)
-        {
-            const auto& field = schema->field(i);
-            auto name = field->name();
-            boost::to_lower(name);
-            fields.push_back(field->WithName(name));
-        }
-        schema = arrow::schema(fields, schema->metadata());
-    }
 }
 
 void ORCBlockInputFormat::prepareReader()
@@ -149,12 +131,17 @@ void ORCBlockInputFormat::prepareReader()
         return;
 
     arrow_column_to_ch_column = std::make_unique<ArrowColumnToCHColumn>(
-        getPort().getHeader(), "ORC", format_settings.orc.import_nested, format_settings.orc.allow_missing_columns);
+        getPort().getHeader(),
+        "ORC",
+        format_settings.orc.import_nested,
+        format_settings.orc.allow_missing_columns,
+        format_settings.orc.case_insensitive_column_matching);
     missing_columns = arrow_column_to_ch_column->getMissingColumns(*schema);
 
+    const bool ignore_case = format_settings.orc.case_insensitive_column_matching;
     std::unordered_set<String> nested_table_names;
     if (format_settings.orc.import_nested)
-        nested_table_names = Nested::getAllTableNames(getPort().getHeader());
+        nested_table_names = Nested::getAllTableNames(getPort().getHeader(), ignore_case);
 
     /// In ReadStripe column indices should be started from 1,
     /// because 0 indicates to select all columns.
@@ -165,19 +152,18 @@ void ORCBlockInputFormat::prepareReader()
         /// so we should recursively count the number of indices we need for this type.
         int indexes_count = countIndicesForType(schema->field(i)->type());
         const auto & name = schema->field(i)->name();
-        if (getPort().getHeader().has(name) || nested_table_names.contains(name))
+        if (getPort().getHeader().has(name, ignore_case) || nested_table_names.contains(ignore_case ? boost::to_lower_copy(name) : name))
         {
             for (int j = 0; j != indexes_count; ++j)
-            {
                 include_indices.push_back(index + j);
-                include_column_names.push_back(name);
-            }
         }
+
         index += indexes_count;
     }
 }
 
-ORCSchemaReader::ORCSchemaReader(ReadBuffer & in_, const FormatSettings & format_settings_) : ISchemaReader(in_), format_settings(format_settings_)
+ORCSchemaReader::ORCSchemaReader(ReadBuffer & in_, const FormatSettings & format_settings_)
+    : ISchemaReader(in_), format_settings(format_settings_)
 {
 }
 

src/Processors/Formats/Impl/ORCBlockInputFormat.h

@@ -47,7 +47,6 @@ private:
 
     // indices of columns to read from ORC file
     std::vector<int> include_indices;
-    std::vector<String> include_column_names;
 
     std::vector<size_t> missing_columns;
     BlockMissingValues block_missing_values;

src/Processors/Formats/Impl/ParquetBlockInputFormat.cpp

@@ -53,11 +53,7 @@ Chunk ParquetBlockInputFormat::generate()
     std::shared_ptr<arrow::Table> table;
     arrow::Status read_status = file_reader->ReadRowGroup(row_group_current, column_indices, &table);
     if (!read_status.ok())
-        throw ParsingException{"Error while reading Parquet data: " + read_status.ToString(),
+        throw ParsingException{"Error while reading Parquet data: " + read_status.ToString(), ErrorCodes::CANNOT_READ_ALL_DATA};
-                        ErrorCodes::CANNOT_READ_ALL_DATA};
-
-    if (format_settings.use_lowercase_column_name)
-        table = *table->RenameColumns(column_names);
 
     ++row_group_current;
 
@@ -78,7 +74,6 @@ void ParquetBlockInputFormat::resetParser()
 
     file_reader.reset();
     column_indices.clear();
-    column_names.clear();
     row_group_current = 0;
     block_missing_values.clear();
 }
@@ -123,20 +118,6 @@ static void getFileReaderAndSchema(
         return;
     THROW_ARROW_NOT_OK(parquet::arrow::OpenFile(std::move(arrow_file), arrow::default_memory_pool(), &file_reader));
     THROW_ARROW_NOT_OK(file_reader->GetSchema(&schema));
-
-    if (format_settings.use_lowercase_column_name)
-    {
-        std::vector<std::shared_ptr<::arrow::Field>> fields;
-        fields.reserve(schema->num_fields());
-        for (int i = 0; i < schema->num_fields(); ++i)
-        {
-            const auto& field = schema->field(i);
-            auto name = field->name();
-            boost::to_lower(name);
-            fields.push_back(field->WithName(name));
-        }
-        schema = arrow::schema(fields, schema->metadata());
-    }
 }
 
 void ParquetBlockInputFormat::prepareReader()
@@ -149,12 +130,18 @@ void ParquetBlockInputFormat::prepareReader()
     row_group_total = file_reader->num_row_groups();
     row_group_current = 0;
 
-    arrow_column_to_ch_column = std::make_unique<ArrowColumnToCHColumn>(getPort().getHeader(), "Parquet", format_settings.parquet.import_nested, format_settings.parquet.allow_missing_columns);
+    arrow_column_to_ch_column = std::make_unique<ArrowColumnToCHColumn>(
+        getPort().getHeader(),
+        "Parquet",
+        format_settings.parquet.import_nested,
+        format_settings.parquet.allow_missing_columns,
+        format_settings.parquet.case_insensitive_column_matching);
     missing_columns = arrow_column_to_ch_column->getMissingColumns(*schema);
 
+    const bool ignore_case = format_settings.parquet.case_insensitive_column_matching;
     std::unordered_set<String> nested_table_names;
     if (format_settings.parquet.import_nested)
-        nested_table_names = Nested::getAllTableNames(getPort().getHeader());
+        nested_table_names = Nested::getAllTableNames(getPort().getHeader(), ignore_case);
 
     int index = 0;
     for (int i = 0; i < schema->num_fields(); ++i)
@@ -164,19 +151,19 @@ void ParquetBlockInputFormat::prepareReader()
         /// count the number of indices we need for this type.
         int indexes_count = countIndicesForType(schema->field(i)->type());
         const auto & name = schema->field(i)->name();
-        if (getPort().getHeader().has(name) || nested_table_names.contains(name))
+
+        if (getPort().getHeader().has(name, ignore_case) || nested_table_names.contains(ignore_case ? boost::to_lower_copy(name) : name))
         {
             for (int j = 0; j != indexes_count; ++j)
-            {
                 column_indices.push_back(index + j);
-                column_names.push_back(name);
-            }
         }
+
         index += indexes_count;
     }
 }
 
-ParquetSchemaReader::ParquetSchemaReader(ReadBuffer & in_, const FormatSettings & format_settings_) : ISchemaReader(in_), format_settings(format_settings_)
+ParquetSchemaReader::ParquetSchemaReader(ReadBuffer & in_, const FormatSettings & format_settings_)
+    : ISchemaReader(in_), format_settings(format_settings_)
 {
 }
 

src/Processors/Formats/Impl/ParquetBlockInputFormat.h

@@ -40,7 +40,6 @@ private:
     int row_group_total = 0;
     // indices of columns to read from Parquet file
     std::vector<int> column_indices;
-    std::vector<String> column_names;
     std::unique_ptr<ArrowColumnToCHColumn> arrow_column_to_ch_column;
     int row_group_current = 0;
     std::vector<size_t> missing_columns;

src/Processors/QueryPlan/QueryPlan.cpp

@@ -1,16 +1,22 @@
-#include <Processors/QueryPlan/QueryPlan.h>
+#include <stack>
-#include <Processors/QueryPlan/IQueryPlanStep.h>
+
-#include <QueryPipeline/QueryPipelineBuilder.h>
+#include <Common/JSONBuilder.h>
-#include <IO/WriteBuffer.h>
+
-#include <IO/Operators.h>
 #include <Interpreters/ActionsDAG.h>
 #include <Interpreters/ArrayJoinAction.h>
-#include <stack>
+
+#include <IO/Operators.h>
+#include <IO/WriteBuffer.h>
+
+#include <Processors/QueryPlan/BuildQueryPipelineSettings.h>
+#include <Processors/QueryPlan/IQueryPlanStep.h>
 #include <Processors/QueryPlan/Optimizations/Optimizations.h>
 #include <Processors/QueryPlan/Optimizations/QueryPlanOptimizationSettings.h>
-#include <Processors/QueryPlan/BuildQueryPipelineSettings.h>
+#include <Processors/QueryPlan/QueryPlan.h>
 #include <Processors/QueryPlan/ReadFromMergeTree.h>
-#include <Common/JSONBuilder.h>
+
+#include <QueryPipeline/QueryPipelineBuilder.h>
+
 
 namespace DB
 {
@@ -388,6 +394,7 @@ void QueryPlan::explainPlan(WriteBuffer & buffer, const ExplainPlanOptions & opt
 static void explainPipelineStep(IQueryPlanStep & step, IQueryPlanStep::FormatSettings & settings)
 {
     settings.out << String(settings.offset, settings.indent_char) << "(" << step.getName() << ")\n";
+
     size_t current_offset = settings.offset;
     step.describePipeline(settings);
     if (current_offset == settings.offset)

src/Processors/QueryPlan/ReadFromMergeTree.cpp

@@ -112,6 +112,9 @@ ReadFromMergeTree::ReadFromMergeTree(
 
     if (enable_parallel_reading)
         read_task_callback = context->getMergeTreeReadTaskCallback();
+
+    /// Add explicit description.
+    setStepDescription(data.getStorageID().getFullNameNotQuoted());
 }
 
 Pipe ReadFromMergeTree::readFromPool(

src/Processors/QueryPlan/ReadFromMergeTree.h

@@ -100,7 +100,8 @@ public:
         bool enable_parallel_reading
     );
 
-    String getName() const override { return "ReadFromMergeTree"; }
+    static constexpr auto name = "ReadFromMergeTree";
+    String getName() const override { return name; }
 
     void initializePipeline(QueryPipelineBuilder & pipeline, const BuildQueryPipelineSettings &) override;
 

src/Storages/ExternalDataSourceConfiguration.cpp

@@ -325,6 +325,7 @@ void URLBasedDataSourceConfiguration::set(const URLBasedDataSourceConfiguration
     compression_method = conf.compression_method;
     structure = conf.structure;
     http_method = conf.http_method;
+    headers = conf.headers;
 }
 
 
@@ -364,6 +365,10 @@ std::optional<URLBasedDataSourceConfig> getURLBasedDataSourceConfiguration(const
             {
                 configuration.structure = config.getString(config_prefix + ".structure", "");
             }
+            else if (key == "compression_method")
+            {
+                configuration.compression_method = config.getString(config_prefix + ".compression_method", "");
+            }
             else if (key == "headers")
             {
                 Poco::Util::AbstractConfiguration::Keys header_keys;

src/Storages/MergeTree/MergeFromLogEntryTask.cpp

@@ -279,14 +279,17 @@ bool MergeFromLogEntryTask::finalize(ReplicatedMergeMutateTaskBase::PartLogWrite
             ProfileEvents::increment(ProfileEvents::DataAfterMergeDiffersFromReplica);
 
             LOG_ERROR(log,
-                "{}. Data after merge is not byte-identical to data on another replicas. There could be several"
+                "{}. Data after merge is not byte-identical to data on another replicas. There could be several reasons:"
-                " reasons: 1. Using newer version of compression library after server update. 2. Using another"
+                " 1. Using newer version of compression library after server update."
-                " compression method. 3. Non-deterministic compression algorithm (highly unlikely). 4."
+                " 2. Using another compression method."
-                " Non-deterministic merge algorithm due to logical error in code. 5. Data corruption in memory due"
+                " 3. Non-deterministic compression algorithm (highly unlikely)."
-                " to bug in code. 6. Data corruption in memory due to hardware issue. 7. Manual modification of"
+                " 4. Non-deterministic merge algorithm due to logical error in code."
-                " source data after server startup. 8. Manual modification of checksums stored in ZooKeeper. 9."
+                " 5. Data corruption in memory due to bug in code."
-                " Part format related settings like 'enable_mixed_granularity_parts' are different on different"
+                " 6. Data corruption in memory due to hardware issue."
-                " replicas. We will download merged part from replica to force byte-identical result.",
+                " 7. Manual modification of source data after server startup."
+                " 8. Manual modification of checksums stored in ZooKeeper."
+                " 9. Part format related settings like 'enable_mixed_granularity_parts' are different on different replicas."
+                " We will download merged part from replica to force byte-identical result.",
                 getCurrentExceptionMessage(false));
 
             write_part_log(ExecutionStatus::fromCurrentException());

src/Storages/MergeTree/MutateFromLogEntryTask.cpp

@@ -185,7 +185,8 @@ bool MutateFromLogEntryTask::finalize(ReplicatedMergeMutateTaskBase::PartLogWrit
 
             ProfileEvents::increment(ProfileEvents::DataAfterMutationDiffersFromReplica);
 
-            LOG_ERROR(log, "{}. Data after mutation is not byte-identical to data on another replicas. We will download merged part from replica to force byte-identical result.", getCurrentExceptionMessage(false));
+            LOG_ERROR(log, "{}. Data after mutation is not byte-identical to data on another replicas. "
+                           "We will download merged part from replica to force byte-identical result.", getCurrentExceptionMessage(false));
 
             write_part_log(ExecutionStatus::fromCurrentException());
 

src/Storages/PostgreSQL/MaterializedPostgreSQLConsumer.cpp

@@ -98,8 +98,24 @@ MaterializedPostgreSQLConsumer::StorageData::Buffer::Buffer(
 }
 
 
+void MaterializedPostgreSQLConsumer::assertCorrectInsertion(StorageData::Buffer & buffer, size_t column_idx)
+{
+    if (column_idx >= buffer.description.sample_block.columns()
+        || column_idx >= buffer.description.types.size()
+        || column_idx >= buffer.columns.size())
+        throw Exception(
+            ErrorCodes::LOGICAL_ERROR,
+            "Attempt to insert into buffer at position: {}, but block columns size is {}, types size: {}, columns size: {}, buffer structure: {}",
+            column_idx,
+            buffer.description.sample_block.columns(), buffer.description.types.size(), buffer.columns.size(),
+            buffer.description.sample_block.dumpStructure());
+}
+
+
 void MaterializedPostgreSQLConsumer::insertValue(StorageData::Buffer & buffer, const std::string & value, size_t column_idx)
 {
+    assertCorrectInsertion(buffer, column_idx);
+
     const auto & sample = buffer.description.sample_block.getByPosition(column_idx);
     bool is_nullable = buffer.description.types[column_idx].second;
 
@@ -134,6 +150,8 @@ void MaterializedPostgreSQLConsumer::insertValue(StorageData::Buffer & buffer, c
 
 void MaterializedPostgreSQLConsumer::insertDefaultValue(StorageData::Buffer & buffer, size_t column_idx)
 {
+    assertCorrectInsertion(buffer, column_idx);
+
     const auto & sample = buffer.description.sample_block.getByPosition(column_idx);
     insertDefaultPostgreSQLValue(*buffer.columns[column_idx], *sample.column);
 }
@@ -514,14 +532,15 @@ void MaterializedPostgreSQLConsumer::processReplicationMessage(const char * repl
 
 
 void MaterializedPostgreSQLConsumer::syncTables()
-{
-    try
 {
     for (const auto & table_name : tables_to_sync)
     {
         auto & storage_data = storages.find(table_name)->second;
         Block result_rows = storage_data.buffer.description.sample_block.cloneWithColumns(std::move(storage_data.buffer.columns));
+        storage_data.buffer.columns = storage_data.buffer.description.sample_block.cloneEmptyColumns();
 
+        try
+        {
             if (result_rows.rows())
             {
                 auto storage = storage_data.storage;
@@ -543,13 +562,18 @@ void MaterializedPostgreSQLConsumer::syncTables()
 
                 CompletedPipelineExecutor executor(io.pipeline);
                 executor.execute();
-
+            }
-                storage_data.buffer.columns = storage_data.buffer.description.sample_block.cloneEmptyColumns();
+        }
+        catch (...)
+        {
+            tryLogCurrentException(__PRETTY_FUNCTION__);
         }
     }
 
     LOG_DEBUG(log, "Table sync end for {} tables, last lsn: {} = {}, (attempted lsn {})", tables_to_sync.size(), current_lsn, getLSNValue(current_lsn), getLSNValue(final_lsn));
 
+    try
+    {
         auto tx = std::make_shared<pqxx::nontransaction>(connection->getRef());
         current_lsn = advanceLSN(tx);
         tables_to_sync.clear();

src/Storages/PostgreSQL/MaterializedPostgreSQLConsumer.h

@@ -122,6 +122,8 @@ private:
 
     void markTableAsSkipped(Int32 relation_id, const String & relation_name);
 
+    static void assertCorrectInsertion(StorageData::Buffer & buffer, size_t column_idx);
+
     /// lsn - log sequnce nuumber, like wal offset (64 bit).
     static Int64 getLSNValue(const std::string & lsn)
     {

src/Storages/PostgreSQL/PostgreSQLReplicationHandler.cpp

@@ -64,8 +64,8 @@ PostgreSQLReplicationHandler::PostgreSQLReplicationHandler(
     bool is_attach_,
     const MaterializedPostgreSQLSettings & replication_settings,
     bool is_materialized_postgresql_database_)
-    : log(&Poco::Logger::get("PostgreSQLReplicationHandler"))
+    : WithContext(context_->getGlobalContext())
-    , context(context_)
+    , log(&Poco::Logger::get("PostgreSQLReplicationHandler"))
     , is_attach(is_attach_)
     , postgres_database(postgres_database_)
     , postgres_schema(replication_settings.materialized_postgresql_schema)
@@ -94,9 +94,9 @@ PostgreSQLReplicationHandler::PostgreSQLReplicationHandler(
     }
     publication_name = fmt::format("{}_ch_publication", replication_identifier);
 
-    startup_task = context->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ checkConnectionAndStart(); });
+    startup_task = getContext()->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ checkConnectionAndStart(); });
-    consumer_task = context->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ consumerFunc(); });
+    consumer_task = getContext()->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ consumerFunc(); });
-    cleanup_task = context->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ cleanupFunc(); });
+    cleanup_task = getContext()->getSchedulePool().createTask("PostgreSQLReplicaStartup", [this]{ cleanupFunc(); });
 }
 
 
@@ -296,7 +296,7 @@ void PostgreSQLReplicationHandler::startSynchronization(bool throw_on_error)
     /// (Apart from the case, when shutdownFinal is called).
     /// Handler uses it only for loadFromSnapshot and shutdown methods.
     consumer = std::make_shared<MaterializedPostgreSQLConsumer>(
-            context,
+            getContext(),
             std::move(tmp_connection),
             replication_slot,
             publication_name,
@@ -921,9 +921,9 @@ void PostgreSQLReplicationHandler::reloadFromSnapshot(const std::vector<std::pai
 
             for (const auto & [relation_id, table_name] : relation_data)
             {
-                auto storage = DatabaseCatalog::instance().getTable(StorageID(current_database_name, table_name), context);
+                auto storage = DatabaseCatalog::instance().getTable(StorageID(current_database_name, table_name), getContext());
                 auto * materialized_storage = storage->as <StorageMaterializedPostgreSQL>();
-                auto materialized_table_lock = materialized_storage->lockForShare(String(), context->getSettingsRef().lock_acquire_timeout);
+                auto materialized_table_lock = materialized_storage->lockForShare(String(), getContext()->getSettingsRef().lock_acquire_timeout);
 
                 /// If for some reason this temporary table already exists - also drop it.
                 auto temp_materialized_storage = materialized_storage->createTemporary();

src/Storages/PostgreSQL/PostgreSQLReplicationHandler.h

@@ -13,7 +13,7 @@ namespace DB
 class StorageMaterializedPostgreSQL;
 struct SettingChange;
 
-class PostgreSQLReplicationHandler
+class PostgreSQLReplicationHandler : WithContext
 {
 friend class TemporaryReplicationSlot;
 
@@ -98,7 +98,6 @@ private:
     std::pair<String, String> getSchemaAndTableName(const String & table_name) const;
 
     Poco::Logger * log;
-    ContextPtr context;
 
     /// If it is not attach, i.e. a create query, then if publication already exists - always drop it.
     bool is_attach;

src/Storages/StorageReplicatedMergeTree.cpp

@@ -1312,10 +1312,14 @@ void StorageReplicatedMergeTree::checkPartChecksumsAndAddCommitOps(const zkutil:
 
         if (replica_part_header.getColumnsHash() != local_part_header.getColumnsHash())
         {
-            /// Either it's a bug or ZooKeeper contains broken data.
+            /// Currently there are two (known) cases when it may happen:
-            /// TODO Fix KILL MUTATION and replace CHECKSUM_DOESNT_MATCH with LOGICAL_ERROR
+            ///  - KILL MUTATION query had removed mutation before all replicas have executed assigned MUTATE_PART entries.
-            /// (some replicas may skip killed mutation even if it was executed on other replicas)
+            ///    Some replicas may skip this mutation and update part version without actually applying any changes.
-            throw Exception(ErrorCodes::CHECKSUM_DOESNT_MATCH, "Part {} from {} has different columns hash", part_name, replica);
+            ///    It leads to mismatching checksum if changes were applied on other replicas.
+            ///  - ALTER_METADATA and MERGE_PARTS were reordered on some replicas.
+            ///    It may lead to different number of columns in merged parts on these replicas.
+            throw Exception(ErrorCodes::CHECKSUM_DOESNT_MATCH, "Part {} from {} has different columns hash "
+                            "(it may rarely happen on race condition with KILL MUTATION or ALTER COLUMN).", part_name, replica);
         }
 
         replica_part_header.getChecksums().checkEqual(local_part_header.getChecksums(), true);

tests/ci/ast_fuzzer_check.py

@@ -9,11 +9,10 @@ from github import Github
 
 from env_helper import (
     GITHUB_REPOSITORY,
-    TEMP_PATH,
+    GITHUB_RUN_URL,
-    REPO_COPY,
     REPORTS_PATH,
-    GITHUB_SERVER_URL,
+    REPO_COPY,
-    GITHUB_RUN_ID,
+    TEMP_PATH,
 )
 from s3_helper import S3Helper
 from get_robot_token import get_best_robot_token
@@ -126,7 +125,7 @@ if __name__ == "__main__":
             logging.info("Exception uploading file %s text %s", f, ex)
             paths[f] = ""
 
-    report_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
+    report_url = GITHUB_RUN_URL
     if paths["runlog.log"]:
         report_url = paths["runlog.log"]
     if paths["main.log"]:

tests/ci/build_report_check.py

@@ -11,7 +11,7 @@ from env_helper import (
     TEMP_PATH,
     GITHUB_REPOSITORY,
     GITHUB_SERVER_URL,
-    GITHUB_RUN_ID,
+    GITHUB_RUN_URL,
 )
 from report import create_build_html_report
 from s3_helper import S3Helper
@@ -148,6 +148,17 @@ if __name__ == "__main__":
                         build_name,
                     )
 
+    some_builds_are_missing = len(build_reports_map) < len(reports_order)
+
+    if some_builds_are_missing:
+        logging.info(
+            "Expected to get %s build results, got %s",
+            len(reports_order),
+            len(build_reports_map),
+        )
+    else:
+        logging.info("Got exactly %s builds", len(build_reports_map))
+
     build_reports = [
         build_reports_map[build_name]
         for build_name in reports_order
@@ -180,9 +191,7 @@ if __name__ == "__main__":
         branch_name = "PR #{}".format(pr_info.number)
         branch_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/pull/{pr_info.number}"
     commit_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/commit/{pr_info.sha}"
-    task_url = (
+    task_url = GITHUB_RUN_URL
-        f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID or '0'}"
-    )
     report = create_build_html_report(
         build_check_name,
         build_results,
@@ -221,10 +230,10 @@ if __name__ == "__main__":
         if build_result.status == "success":
             ok_builds += 1
 
-    if ok_builds == 0:
+    if ok_builds == 0 or some_builds_are_missing:
         summary_status = "error"
 
-    description = "{}/{} builds are OK".format(ok_builds, total_builds)
+    description = f"{ok_builds}/{total_builds} builds are OK"
 
     print("::notice ::Report url: {}".format(url))
 

tests/ci/clickhouse_helper.py

@@ -8,30 +8,16 @@ from get_robot_token import get_parameter_from_ssm
 
 
 class ClickHouseHelper:
-    def __init__(self, url=None, user=None, password=None):
+    def __init__(self, url=None):
-        self.url2 = None
-        self.auth2 = None
-
         if url is None:
-            url = get_parameter_from_ssm("clickhouse-test-stat-url")
+            self.url = get_parameter_from_ssm("clickhouse-test-stat-url2")
-            self.url2 = get_parameter_from_ssm("clickhouse-test-stat-url2")
+            self.auth = {
-            self.auth2 = {
                 "X-ClickHouse-User": get_parameter_from_ssm(
                     "clickhouse-test-stat-login2"
                 ),
                 "X-ClickHouse-Key": "",
             }
 
-        self.url = url
-        self.auth = {
-            "X-ClickHouse-User": user
-            if user is not None
-            else get_parameter_from_ssm("clickhouse-test-stat-login"),
-            "X-ClickHouse-Key": password
-            if password is not None
-            else get_parameter_from_ssm("clickhouse-test-stat-password"),
-        }
-
     @staticmethod
     def _insert_json_str_info_impl(url, auth, db, table, json_str):
         params = {
@@ -78,8 +64,6 @@ class ClickHouseHelper:
 
     def _insert_json_str_info(self, db, table, json_str):
         self._insert_json_str_info_impl(self.url, self.auth, db, table, json_str)
-        if self.url2:
-            self._insert_json_str_info_impl(self.url2, self.auth2, db, table, json_str)
 
     def insert_event_into(self, db, table, event):
         event_str = json.dumps(event)

tests/ci/docker_images_check.py

@@ -11,7 +11,7 @@ from typing import Dict, List, Optional, Set, Tuple, Union
 
 from github import Github
 
-from env_helper import GITHUB_WORKSPACE, RUNNER_TEMP
+from env_helper import GITHUB_WORKSPACE, RUNNER_TEMP, GITHUB_RUN_URL
 from s3_helper import S3Helper
 from pr_info import PRInfo
 from get_robot_token import get_best_robot_token, get_parameter_from_ssm
@@ -234,6 +234,7 @@ def build_and_push_one_image(
     with open(build_log, "wb") as bl:
         cmd = (
             "docker buildx build --builder default "
+            f"--label build-url={GITHUB_RUN_URL} "
             f"{from_tag_arg}"
             f"--build-arg BUILDKIT_INLINE_CACHE=1 "
             f"--tag {image.repo}:{version_string} "

tests/ci/docker_test.py

@@ -4,6 +4,7 @@ import os
 import unittest
 from unittest.mock import patch
 
+from env_helper import GITHUB_RUN_URL
 from pr_info import PRInfo
 import docker_images_check as di
 
@@ -117,7 +118,8 @@ class TestDockerImageCheck(unittest.TestCase):
         mock_popen.assert_called_once()
         mock_machine.assert_not_called()
         self.assertIn(
-            "docker buildx build --builder default --build-arg FROM_TAG=version "
+            f"docker buildx build --builder default --label build-url={GITHUB_RUN_URL} "
+            "--build-arg FROM_TAG=version "
             "--build-arg BUILDKIT_INLINE_CACHE=1 --tag name:version --cache-from "
             "type=registry,ref=name:version --push --progress plain path",
             mock_popen.call_args.args,
@@ -133,7 +135,8 @@ class TestDockerImageCheck(unittest.TestCase):
         mock_popen.assert_called_once()
         mock_machine.assert_not_called()
         self.assertIn(
-            "docker buildx build --builder default --build-arg FROM_TAG=version2 "
+            f"docker buildx build --builder default --label build-url={GITHUB_RUN_URL} "
+            "--build-arg FROM_TAG=version2 "
             "--build-arg BUILDKIT_INLINE_CACHE=1 --tag name:version2 --cache-from "
             "type=registry,ref=name:version2 --progress plain path",
             mock_popen.call_args.args,
@@ -149,7 +152,7 @@ class TestDockerImageCheck(unittest.TestCase):
         mock_popen.assert_called_once()
         mock_machine.assert_not_called()
         self.assertIn(
-            "docker buildx build --builder default "
+            f"docker buildx build --builder default --label build-url={GITHUB_RUN_URL} "
             "--build-arg BUILDKIT_INLINE_CACHE=1 --tag name:version2 --cache-from "
             "type=registry,ref=name:version2 --progress plain path",
             mock_popen.call_args.args,

tests/ci/env_helper.py

@@ -7,9 +7,10 @@ CACHES_PATH = os.getenv("CACHES_PATH", TEMP_PATH)
 CLOUDFLARE_TOKEN = os.getenv("CLOUDFLARE_TOKEN")
 GITHUB_EVENT_PATH = os.getenv("GITHUB_EVENT_PATH")
 GITHUB_REPOSITORY = os.getenv("GITHUB_REPOSITORY", "ClickHouse/ClickHouse")
-GITHUB_RUN_ID = os.getenv("GITHUB_RUN_ID")
+GITHUB_RUN_ID = os.getenv("GITHUB_RUN_ID", "0")
 GITHUB_SERVER_URL = os.getenv("GITHUB_SERVER_URL", "https://github.com")
 GITHUB_WORKSPACE = os.getenv("GITHUB_WORKSPACE", os.path.abspath("../../"))
+GITHUB_RUN_URL = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
 IMAGES_PATH = os.getenv("IMAGES_PATH")
 REPORTS_PATH = os.getenv("REPORTS_PATH", "./reports")
 REPO_COPY = os.getenv("REPO_COPY", os.path.abspath("../../"))

tests/ci/finish_check.py

@@ -2,7 +2,7 @@
 import logging
 from github import Github
 
-from env_helper import GITHUB_SERVER_URL, GITHUB_REPOSITORY, GITHUB_RUN_ID
+from env_helper import GITHUB_RUN_URL
 from pr_info import PRInfo
 from get_robot_token import get_best_robot_token
 from commit_status_helper import get_commit
@@ -33,7 +33,7 @@ if __name__ == "__main__":
     gh = Github(get_best_robot_token())
     commit = get_commit(gh, pr_info.sha)
 
-    url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
+    url = GITHUB_RUN_URL
     statuses = filter_statuses(list(commit.get_statuses()))
     if NAME in statuses and statuses[NAME].state == "pending":
         commit.create_status(

tests/ci/performance_comparison_check.py

@@ -11,6 +11,7 @@ import re
 
 from github import Github
 
+from env_helper import GITHUB_RUN_URL
 from pr_info import PRInfo
 from s3_helper import S3Helper
 from get_robot_token import get_best_robot_token
@@ -88,9 +89,9 @@ if __name__ == "__main__":
     else:
         pr_link = f"https://github.com/ClickHouse/ClickHouse/pull/{pr_info.number}"
 
-    task_url = f"https://github.com/ClickHouse/ClickHouse/actions/runs/{os.getenv('GITHUB_RUN_ID')}"
+    docker_env += (
-    docker_env += ' -e CHPC_ADD_REPORT_LINKS="<a href={}>Job (actions)</a> <a href={}>Tested commit</a>"'.format(
+        f' -e CHPC_ADD_REPORT_LINKS="<a href={GITHUB_RUN_URL}>'
-        task_url, pr_link
+        f'Job (actions)</a> <a href={pr_link}>Tested commit</a>"'
     )
 
     if "RUN_BY_HASH_TOTAL" in os.environ:
@@ -199,7 +200,7 @@ if __name__ == "__main__":
         status = "failure"
         message = "No message in report."
 
-    report_url = task_url
+    report_url = GITHUB_RUN_URL
 
     if paths["runlog.log"]:
         report_url = paths["runlog.log"]

tests/ci/pr_info.py

@@ -8,7 +8,7 @@ from build_download_helper import get_with_retries
 from env_helper import (
     GITHUB_REPOSITORY,
     GITHUB_SERVER_URL,
-    GITHUB_RUN_ID,
+    GITHUB_RUN_URL,
     GITHUB_EVENT_PATH,
 )
 
@@ -111,7 +111,7 @@ class PRInfo:
                 self.sha = github_event["pull_request"]["head"]["sha"]
 
             repo_prefix = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}"
-            self.task_url = f"{repo_prefix}/actions/runs/{GITHUB_RUN_ID or '0'}"
+            self.task_url = GITHUB_RUN_URL
 
             self.repo_full_name = GITHUB_REPOSITORY
             self.commit_html_url = f"{repo_prefix}/commits/{self.sha}"
@@ -142,7 +142,7 @@ class PRInfo:
             self.sha = github_event["after"]
             pull_request = get_pr_for_commit(self.sha, github_event["ref"])
             repo_prefix = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}"
-            self.task_url = f"{repo_prefix}/actions/runs/{GITHUB_RUN_ID or '0'}"
+            self.task_url = GITHUB_RUN_URL
             self.commit_html_url = f"{repo_prefix}/commits/{self.sha}"
             self.repo_full_name = GITHUB_REPOSITORY
             if pull_request is None or pull_request["state"] == "closed":
@@ -180,7 +180,7 @@ class PRInfo:
             self.number = 0
             self.labels = {}
             repo_prefix = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}"
-            self.task_url = f"{repo_prefix}/actions/runs/{GITHUB_RUN_ID or '0'}"
+            self.task_url = GITHUB_RUN_URL
             self.commit_html_url = f"{repo_prefix}/commits/{self.sha}"
             self.repo_full_name = GITHUB_REPOSITORY
             self.pr_html_url = f"{repo_prefix}/commits/{ref}"

tests/ci/run_check.py

@@ -5,7 +5,7 @@ import re
 from typing import Tuple
 
 from github import Github
-from env_helper import GITHUB_RUN_ID, GITHUB_REPOSITORY, GITHUB_SERVER_URL
+from env_helper import GITHUB_RUN_URL, GITHUB_REPOSITORY, GITHUB_SERVER_URL
 from pr_info import PRInfo
 from get_robot_token import get_best_robot_token
 from commit_status_helper import get_commit
@@ -231,7 +231,7 @@ if __name__ == "__main__":
         )
         sys.exit(1)
 
-    url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
+    url = GITHUB_RUN_URL
     if not can_run:
         print("::notice ::Cannot run")
         commit.create_status(

tests/ci/upload_result_helper.py

@@ -2,7 +2,7 @@ import os
 import logging
 import ast
 
-from env_helper import GITHUB_SERVER_URL, GITHUB_REPOSITORY, GITHUB_RUN_ID
+from env_helper import GITHUB_SERVER_URL, GITHUB_REPOSITORY, GITHUB_RUN_URL
 from report import ReportColorTheme, create_test_html_report
 
 
@@ -66,7 +66,7 @@ def upload_results(
         branch_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/pull/{pr_number}"
     commit_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/commit/{commit_sha}"
 
-    task_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
+    task_url = GITHUB_RUN_URL
 
     if additional_urls:
         raw_log_url = additional_urls[0]

tests/ci/version_helper.py

@@ -238,7 +238,7 @@ def _update_dockerfile(repo_path: str, version: ClickHouseVersion):
 def update_version_local(repo_path, version, version_type="testing"):
     update_contributors()
     version.with_description(version_type)
-    update_cmake_version(version, version_type)
+    update_cmake_version(version)
     _update_changelog(repo_path, version)
     _update_dockerfile(repo_path, version)
 

tests/ci/workflow_approve_rerun_lambda/app.py

@@ -379,12 +379,16 @@ def check_need_to_rerun(workflow_description):
 
 def rerun_workflow(workflow_description, token):
     print("Going to rerun workflow")
+    try:
+        _exec_post_with_retry(f"{workflow_description.rerun_url}-failed-jobs", token)
+    except Exception:
         _exec_post_with_retry(workflow_description.rerun_url, token)
 
 
 def main(event):
     token = get_token_from_aws()
     event_data = json.loads(event["body"])
+    print("The body received:", event_data)
     workflow_description = get_workflow_description_from_event(event_data)
 
     print("Got workflow description", workflow_description)

tests/clickhouse-test

@@ -374,7 +374,7 @@ class SettingsRandomizer:
         "output_format_parallel_formatting": lambda: random.randint(0, 1),
         "input_format_parallel_parsing": lambda: random.randint(0, 1),
         "min_chunk_bytes_for_parallel_parsing": lambda: max(1024, int(random.gauss(10 * 1024 * 1024, 5 * 1000 * 1000))),
-        "max_read_buffer_size": lambda: random.randint(1, 20) if random.random() < 0.1 else random.randint(500000, 1048576),
+        "max_read_buffer_size": lambda: random.randint(500000, 1048576),
         "prefer_localhost_replica": lambda: random.randint(0, 1),
         "max_block_size": lambda: random.randint(8000, 100000),
         "max_threads": lambda: random.randint(1, 64),
@@ -468,9 +468,11 @@ class TestCase:
 
         return testcase_args
 
-    def add_random_settings(self, client_options):
+    def add_random_settings(self, args, client_options):
         if self.tags and 'no-random-settings' in self.tags:
             return client_options
+        if args.no_random_settings:
+            return client_options
 
         if len(self.base_url_params) == 0:
             os.environ['CLICKHOUSE_URL_PARAMS'] = '&'.join(self.random_settings)
@@ -485,9 +487,11 @@ class TestCase:
         os.environ['CLICKHOUSE_URL_PARAMS'] = self.base_url_params
         os.environ['CLICKHOUSE_CLIENT_OPT'] = self.base_client_options
 
-    def add_info_about_settings(self, description):
+    def add_info_about_settings(self, args, description):
         if self.tags and 'no-random-settings' in self.tags:
             return description
+        if args.no_random_settings:
+            return description
 
         return description + "\n" + "Settings used in the test: " + "--" + " --".join(self.random_settings) + "\n"
 
@@ -788,13 +792,13 @@ class TestCase:
 
             self.runs_count += 1
             self.testcase_args = self.configure_testcase_args(args, self.case_file, suite.suite_tmp_path)
-            client_options = self.add_random_settings(client_options)
+            client_options = self.add_random_settings(args, client_options)
             proc, stdout, stderr, total_time = self.run_single_test(server_logs_level, client_options)
 
             result = self.process_result_impl(proc, stdout, stderr, total_time)
             result.check_if_need_retry(args, stdout, stderr, self.runs_count)
             if result.status == TestStatus.FAIL:
-                result.description = self.add_info_about_settings(result.description)
+                result.description = self.add_info_about_settings(args, result.description)
             return result
         except KeyboardInterrupt as e:
             raise e
@@ -802,12 +806,12 @@ class TestCase:
             return TestResult(self.name, TestStatus.FAIL,
                               FailureReason.INTERNAL_QUERY_FAIL,
                               0.,
-                              self.add_info_about_settings(self.get_description_from_exception_info(sys.exc_info())))
+                              self.add_info_about_settings(args, self.get_description_from_exception_info(sys.exc_info())))
         except (ConnectionRefusedError, ConnectionResetError):
             return TestResult(self.name, TestStatus.FAIL,
                               FailureReason.SERVER_DIED,
                               0.,
-                              self.add_info_about_settings(self.get_description_from_exception_info(sys.exc_info())))
+                              self.add_info_about_settings(args, self.get_description_from_exception_info(sys.exc_info())))
         except:
             return TestResult(self.name, TestStatus.UNKNOWN,
                               FailureReason.INTERNAL_ERROR,
@@ -1501,6 +1505,7 @@ if __name__ == '__main__':
     parser.add_argument('--print-time', action='store_true', dest='print_time', help='Print test time')
     parser.add_argument('--check-zookeeper-session', action='store_true', help='Check ZooKeeper session uptime to determine if failed test should be retried')
     parser.add_argument('--s3-storage', action='store_true', default=False, help='Run tests over s3 storage')
+    parser.add_argument('--no-random-settings', action='store_true', default=False, help='Disable settings randomization')
 
     parser.add_argument('--run-by-hash-num', type=int, help='Run tests matching crc32(test_name) % run_by_hash_total == run_by_hash_num')
     parser.add_argument('--run-by-hash-total', type=int, help='Total test groups for crc32(test_name) % run_by_hash_total == run_by_hash_num')