thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 23:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into ianton-ru-MDB-15474

Browse Source
This commit is contained in:
alesapin 2021-12-29 19:01:43 +03:00
commit 7a3c874651
705 changed files with 17719 additions and 9784 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/backport_branches.yml vendored
View File

@ -95,6 +95,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -139,6 +140,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -183,6 +185,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -227,6 +230,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}

44
.github/workflows/jepsen.yml vendored Normal file
View File

@ -0,0 +1,44 @@
name: JepsenWorkflow
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
concurrency:
group: jepsen
on: # yamllint disable-line rule:truthy
schedule:
- cron: '0 */6 * * *'
workflow_run:
workflows: ["CIGithubActions"]
types:
- completed
workflow_dispatch:
jobs:
KeeperJepsenRelease:
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/keeper_jepsen
REPO_COPY=${{runner.temp}}/keeper_jepsen/ClickHouse
EOF
- name: Clear repository
run: |
sudo rm -fr $GITHUB_WORKSPACE && mkdir $GITHUB_WORKSPACE
- name: Check out repository code
uses: actions/checkout@v2
with:
fetch-depth: 0
- name: Jepsen Test
run: |
sudo rm -fr $TEMP_PATH
mkdir -p $TEMP_PATH
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci
python3 keeper_jepsen_check.py
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
docker rm -f $(docker ps -a -q) ||:
sudo rm -fr $TEMP_PATH

20
.github/workflows/main.yml vendored
View File

@ -236,6 +236,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -280,6 +281,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -324,6 +326,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -365,6 +368,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -409,6 +413,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -453,6 +458,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -497,6 +503,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -541,6 +548,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -585,6 +593,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -632,6 +641,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -676,6 +686,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -720,6 +731,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -764,6 +776,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -808,6 +821,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -852,6 +866,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -896,6 +911,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -920,7 +936,7 @@ jobs:
- BuilderDebMsan
- BuilderDebDebug
runs-on: [self-hosted, style-checker]
if: always()
if: ${{ success() || failure() }}
steps:
- name: Set envs
run: |
@ -960,7 +976,7 @@ jobs:
- BuilderBinDarwinAarch64
- BuilderBinPPC64
runs-on: [self-hosted, style-checker]
if: always()
if: ${{ success() || failure() }}
steps:
- name: Set envs
run: |

15
.github/workflows/master.yml vendored
View File

@ -157,6 +157,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -201,6 +202,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -246,6 +248,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -290,6 +293,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -334,6 +338,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -378,6 +383,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -422,6 +428,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -466,6 +473,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -514,6 +522,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -559,6 +568,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -604,6 +614,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -649,6 +660,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -694,6 +706,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -739,6 +752,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -784,6 +798,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}

6
.github/workflows/release_branches.yml vendored
View File

@ -98,6 +98,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -142,6 +143,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -186,6 +188,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -230,6 +233,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -274,6 +278,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}
@ -318,6 +323,7 @@ jobs:
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 build_check.py "$CHECK_NAME" $BUILD_NAME
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
with:
name: ${{ env.BUILD_NAME }}

42
.github/workflows/woboq.yml vendored Normal file
View File

@ -0,0 +1,42 @@
name: WoboqBuilder
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
concurrency:
group: woboq
on: # yamllint disable-line rule:truthy
schedule:
- cron: '0 */18 * * *'
workflow_dispatch:
jobs:
# don't use dockerhub push because this image updates so rarely
WoboqCodebrowser:
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/codebrowser
REPO_COPY=${{runner.temp}}/codebrowser/ClickHouse
IMAGES_PATH=${{runner.temp}}/images_path
EOF
- name: Clear repository
run: |
sudo rm -fr $GITHUB_WORKSPACE && mkdir $GITHUB_WORKSPACE
- name: Check out repository code
uses: actions/checkout@v2
with:
submodules: 'true'
- name: Codebrowser
run: |
sudo rm -fr $TEMP_PATH
mkdir -p $TEMP_PATH
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 codebrowser_check.py
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
docker rm -f $(docker ps -a -q) ||:
sudo rm -fr $TEMP_PATH

8
.gitmodules vendored
View File

@ -54,8 +54,8 @@
url = https://github.com/ClickHouse-Extras/Turbo-Base64.git
[submodule "contrib/arrow"]
path = contrib/arrow
url = https://github.com/ClickHouse-Extras/arrow
branch = clickhouse-arrow-2.0.0
url = https://github.com/ClickHouse-Extras/arrow.git
branch = blessed/release-6.0.1
[submodule "contrib/thrift"]
path = contrib/thrift
url = https://github.com/apache/thrift.git
@ -190,8 +190,8 @@
url = https://github.com/xz-mirror/xz
[submodule "contrib/abseil-cpp"]
path = contrib/abseil-cpp
url = https://github.com/ClickHouse-Extras/abseil-cpp.git
branch = lts_2020_02_25
url = https://github.com/abseil/abseil-cpp.git
branch = lts_2021_11_02
[submodule "contrib/dragonbox"]
path = contrib/dragonbox
url = https://github.com/ClickHouse-Extras/dragonbox.git

10
CMakeLists.txt
View File

@ -424,6 +424,11 @@ if (OS_LINUX AND NOT SANITIZE)
set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,--no-undefined")
endif ()
# Increase stack size on Musl. We need big stack for our recursive-descend parser.
if (USE_MUSL)
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-z,stack-size=2097152")
endif ()
include(cmake/dbms_glob_sources.cmake)
if (OS_LINUX OR OS_ANDROID)
@ -451,6 +456,11 @@ if (MAKE_STATIC_LIBRARIES)
endif ()
else ()
set (CMAKE_POSITION_INDEPENDENT_CODE ON)
# This is required for clang on Arch linux, that uses PIE by default.
# See enable-SSP-and-PIE-by-default.patch [1].
#
# [1]: https://github.com/archlinux/svntogit-packages/blob/6e681aa860e65ad46a1387081482eb875c2200f2/trunk/enable-SSP-and-PIE-by-default.patch
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -no-pie")
endif ()
if (ENABLE_TESTS)

4
base/CMakeLists.txt
View File

@ -9,7 +9,3 @@ add_subdirectory (pcg-random)
add_subdirectory (widechar_width)
add_subdirectory (readpassphrase)
add_subdirectory (bridge)
if (USE_MYSQL)
add_subdirectory (mysqlxx)
endif ()

3
base/base/CMakeLists.txt
View File

@ -1,8 +1,6 @@
set (SRCS
argsToConfig.cpp
coverage.cpp
DateLUT.cpp
DateLUTImpl.cpp
demangle.cpp
getFQDNOrHostName.cpp
getMemoryAmount.cpp
@ -18,7 +16,6 @@ set (SRCS
sleep.cpp
terminalColors.cpp
errnoToString.cpp
getResource.cpp
StringRef.cpp
)

7
base/base/getPageSize.cpp
View File

@ -1,8 +1,11 @@
#include <base/getPageSize.h>
#include <unistd.h>
#include <cstdlib>
Int64 getPageSize()
{
return sysconf(_SC_PAGESIZE);
Int64 page_size = sysconf(_SC_PAGESIZE);
if (page_size < 0)
abort();
return page_size;
}

8
base/base/phdr_cache.cpp
View File

@ -123,6 +123,12 @@ bool hasPHDRCache()
#else
void updatePHDRCache() {}
bool hasPHDRCache() { return false; }
#if defined(USE_MUSL)
/// With statically linked with musl, dl_iterate_phdr is immutable.
bool hasPHDRCache() { return true; }
#else
bool hasPHDRCache() { return false; }
#endif
#endif

23
base/harmful/harmful.c
View File

@ -182,7 +182,6 @@ TRAP(vlimit)
TRAP(wcsnrtombs)
TRAP(wcsrtombs)
TRAP(wctomb)
TRAP(wordexp)
TRAP(basename)
TRAP(catgets)
TRAP(dbm_clearerr)
@ -195,9 +194,8 @@ TRAP(dbm_nextkey)
TRAP(dbm_open)
TRAP(dbm_store)
TRAP(dirname)
#if !defined(SANITIZER)
TRAP(dlerror) // Used by tsan
#endif
// TRAP(dlerror) // It is not thread-safe. But it is used by dynamic linker to load some name resolution plugins. Also used by TSan.
/// Note: we should better get rid of glibc, dynamic linking and all that sort of annoying garbage altogether.
TRAP(ftw)
TRAP(getc_unlocked)
//TRAP(getenv) // Ok at program startup
@ -245,4 +243,21 @@ TRAP(lgammaf32x)
TRAP(lgammaf64)
TRAP(lgammaf64x)
/// These functions are unused by ClickHouse and we should be aware if they are accidentally get used.
/// Sometimes people report that these function contain vulnerabilities (these reports are bogus for ClickHouse).
TRAP(mq_close)
TRAP(mq_getattr)
TRAP(mq_setattr)
TRAP(mq_notify)
TRAP(mq_open)
TRAP(mq_receive)
TRAP(mq_send)
TRAP(mq_unlink)
TRAP(mq_timedsend)
TRAP(mq_timedreceive)
/// These functions are also unused by ClickHouse.
TRAP(wordexp)
TRAP(wordfree)
#endif

61
base/mysqlxx/CMakeLists.txt
View File

@ -1,61 +0,0 @@
add_library (mysqlxx
Connection.cpp
Exception.cpp
Query.cpp
ResultBase.cpp
UseQueryResult.cpp
Row.cpp
Value.cpp
Pool.cpp
PoolFactory.cpp
PoolWithFailover.cpp
)
target_include_directories (mysqlxx PUBLIC ..)
if (NOT USE_INTERNAL_MYSQL_LIBRARY)
set(PLATFORM_LIBRARIES ${CMAKE_DL_LIBS})
if (USE_MYSQL)
target_include_directories (mysqlxx SYSTEM PRIVATE ${MYSQL_INCLUDE_DIR})
endif ()
if (APPLE)
find_library (ICONV_LIBRARY iconv)
set (MYSQLCLIENT_LIBRARIES ${MYSQLCLIENT_LIBRARIES} ${STATIC_MYSQLCLIENT_LIB} ${ICONV_LIBRARY})
elseif (USE_STATIC_LIBRARIES AND STATIC_MYSQLCLIENT_LIB)
set (MYSQLCLIENT_LIBRARIES ${STATIC_MYSQLCLIENT_LIB})
endif ()
endif ()
target_link_libraries (mysqlxx
PUBLIC
common
PRIVATE
${MYSQLCLIENT_LIBRARIES}
${ZLIB_LIBRARIES}
)
if(OPENSSL_LIBRARIES)
target_link_libraries(mysqlxx PRIVATE ${OPENSSL_LIBRARIES})
endif()
target_link_libraries(mysqlxx PRIVATE ${PLATFORM_LIBRARIES})
if (NOT USE_INTERNAL_MYSQL_LIBRARY AND OPENSSL_INCLUDE_DIR)
target_include_directories (mysqlxx SYSTEM PRIVATE ${OPENSSL_INCLUDE_DIR})
endif ()
target_no_warning(mysqlxx reserved-macro-identifier)
if (NOT USE_INTERNAL_MYSQL_LIBRARY AND USE_STATIC_LIBRARIES)
message(WARNING "Statically linking with system mysql/mariadb only works "
"if mysql client libraries are built with same openssl version as "
"we are going to use now. It wouldn't work if GnuTLS is used. "
"Try -D\"USE_INTERNAL_MYSQL_LIBRARY\"=ON or -D\"ENABLE_MYSQL\"=OFF or "
"-D\"USE_STATIC_LIBRARIES\"=OFF")
endif ()
if (ENABLE_TESTS)
add_subdirectory (tests)
endif ()

12
cmake/find/ccache.cmake
View File

@ -32,11 +32,6 @@ if (CCACHE_FOUND AND NOT COMPILER_MATCHES_CCACHE)
if (CCACHE_VERSION VERSION_GREATER "3.2.0" OR NOT CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
message(STATUS "Using ${CCACHE_FOUND} ${CCACHE_VERSION}")
set (CMAKE_CXX_COMPILER_LAUNCHER ${CCACHE_FOUND} ${CMAKE_CXX_COMPILER_LAUNCHER})
set (CMAKE_C_COMPILER_LAUNCHER ${CCACHE_FOUND} ${CMAKE_C_COMPILER_LAUNCHER})
set_property (GLOBAL PROPERTY RULE_LAUNCH_LINK ${CCACHE_FOUND})
# debian (debhelpers) set SOURCE_DATE_EPOCH environment variable, that is
# filled from the debian/changelog or current time.
#
@ -49,11 +44,14 @@ if (CCACHE_FOUND AND NOT COMPILER_MATCHES_CCACHE)
# - 4.0+ will ignore SOURCE_DATE_EPOCH environment variable.
if (CCACHE_VERSION VERSION_GREATER_EQUAL "4.2")
message(STATUS "ccache is 4.2+ no quirks for SOURCE_DATE_EPOCH required")
set(LAUNCHER ${CCACHE_FOUND})
elseif (CCACHE_VERSION VERSION_GREATER_EQUAL "4.0")
message(STATUS "Ignore SOURCE_DATE_EPOCH for ccache")
set_property (GLOBAL PROPERTY RULE_LAUNCH_COMPILE "env -u SOURCE_DATE_EPOCH")
set_property (GLOBAL PROPERTY RULE_LAUNCH_LINK "env -u SOURCE_DATE_EPOCH")
set(LAUNCHER env -u SOURCE_DATE_EPOCH ${CCACHE_FOUND})
endif()
set (CMAKE_CXX_COMPILER_LAUNCHER ${LAUNCHER} ${CMAKE_CXX_COMPILER_LAUNCHER})
set (CMAKE_C_COMPILER_LAUNCHER ${LAUNCHER} ${CMAKE_C_COMPILER_LAUNCHER})
else ()
message(${RECONFIGURE_MESSAGE_LEVEL} "Not using ${CCACHE_FOUND} ${CCACHE_VERSION} bug: https://bugzilla.samba.org/show_bug.cgi?id=8118")
endif ()

8
cmake/target.cmake
View File

@ -42,6 +42,14 @@ if (CMAKE_CROSSCOMPILING)
message (FATAL_ERROR "Trying to cross-compile to unsupported system: ${CMAKE_SYSTEM_NAME}!")
endif ()
if (USE_MUSL)
set (USE_SENTRY OFF CACHE INTERNAL "")
set (ENABLE_ODBC OFF CACHE INTERNAL "")
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_HDFS OFF CACHE INTERNAL "")
set (ENABLE_EMBEDDED_COMPILER OFF CACHE INTERNAL "")
endif ()
# Don't know why but CXX_STANDARD doesn't work for cross-compilation
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++20")

2
contrib/NuRaft vendored

@ -1 +1 @@
Subproject commit bb69d48e0ee35c87a0f19e509a09a914f71f0cff
Subproject commit ff100a8713146e1ca4b4158dd6cc4eef9af47fc3

2
contrib/abseil-cpp vendored

@ -1 +1 @@
Subproject commit b004a8a02418b83de8b686caa0b0f6e39ac2191f
Subproject commit 215105818dfde3174fe799600bb0f3cae233d0bf

2
contrib/abseil-cpp-cmake/CMakeLists.txt
View File

@ -2,6 +2,8 @@ set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
if(NOT EXISTS "${ABSL_ROOT_DIR}/CMakeLists.txt")
message(FATAL_ERROR " submodule third_party/abseil-cpp is missing. To fix try run: \n git submodule update --init --recursive")
endif()
set(BUILD_TESTING OFF)
set(ABSL_PROPAGATE_CXX_STD ON)
add_subdirectory("${ABSL_ROOT_DIR}" "${ClickHouse_BINARY_DIR}/contrib/abseil-cpp")
add_library(abseil_swiss_tables INTERFACE)

2
contrib/arrow vendored

@ -1 +1 @@
Subproject commit 078e21bad344747b7656ef2d7a4f7410a0a303eb
Subproject commit aa9a7a698e33e278abe053f4634170b3b026e48e

224
contrib/arrow-cmake/CMakeLists.txt
View File

@ -1,5 +1,22 @@
set (CMAKE_CXX_STANDARD 17)
set(ARROW_VERSION "6.0.1")
string(REGEX MATCH "^[0-9]+\\.[0-9]+\\.[0-9]+" ARROW_BASE_VERSION "${ARROW_VERSION}")
set(ARROW_VERSION_MAJOR "6")
set(ARROW_VERSION_MINOR "0")
set(ARROW_VERSION_PATCH "1")
if(ARROW_VERSION_MAJOR STREQUAL "0")
# Arrow 0.x.y => SO version is "x", full SO version is "x.y.0"
set(ARROW_SO_VERSION "${ARROW_VERSION_MINOR}")
set(ARROW_FULL_SO_VERSION "${ARROW_SO_VERSION}.${ARROW_VERSION_PATCH}.0")
else()
# Arrow 1.x.y => SO version is "10x", full SO version is "10x.y.0"
math(EXPR ARROW_SO_VERSION "${ARROW_VERSION_MAJOR} * 100 + ${ARROW_VERSION_MINOR}")
set(ARROW_FULL_SO_VERSION "${ARROW_SO_VERSION}.${ARROW_VERSION_PATCH}.0")
endif()
# === thrift
set(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/thrift/lib/cpp")
@ -93,6 +110,9 @@ add_subdirectory(${FLATBUFFERS_SRC_DIR} "${FLATBUFFERS_BINARY_DIR}")
message(STATUS "FLATBUFFERS_LIBRARY: ${FLATBUFFERS_LIBRARY}")
# === hdfs
set(HDFS_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/libhdfs3/include/hdfs/")
# arrow-cmake cmake file calling orc cmake subroutine which detects certain compiler features.
# Apple Clang compiler failed to compile this code without specifying c++11 standard.
# As result these compiler features detected as absent. In result it failed to compile orc itself.
@ -114,6 +134,7 @@ configure_file("${ORC_INCLUDE_DIR}/orc/orc-config.hh.in" "${ORC_BUILD_INCLUDE_DI
configure_file("${ORC_SOURCE_SRC_DIR}/Adaptor.hh.in" "${ORC_BUILD_INCLUDE_DIR}/Adaptor.hh")
# ARROW_ORC + adapters/orc/CMakefiles
set(ORC_SRCS
"${ARROW_SRC_DIR}/arrow/adapters/orc/adapter.cc"
"${ARROW_SRC_DIR}/arrow/adapters/orc/adapter_util.cc"
@ -150,28 +171,8 @@ set(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src/arrow")
configure_file("${LIBRARY_DIR}/util/config.h.cmake" "${CMAKE_CURRENT_BINARY_DIR}/cpp/src/arrow/util/config.h")
# arrow/cpp/src/arrow/CMakeLists.txt
# arrow/cpp/src/arrow/CMakeLists.txt (ARROW_SRCS + ARROW_COMPUTE + ARROW_IPC)
set(ARROW_SRCS
"${LIBRARY_DIR}/buffer.cc"
"${LIBRARY_DIR}/builder.cc"
"${LIBRARY_DIR}/chunked_array.cc"
"${LIBRARY_DIR}/compare.cc"
"${LIBRARY_DIR}/datum.cc"
"${LIBRARY_DIR}/device.cc"
"${LIBRARY_DIR}/extension_type.cc"
"${LIBRARY_DIR}/memory_pool.cc"
"${LIBRARY_DIR}/pretty_print.cc"
"${LIBRARY_DIR}/record_batch.cc"
"${LIBRARY_DIR}/result.cc"
"${LIBRARY_DIR}/scalar.cc"
"${LIBRARY_DIR}/sparse_tensor.cc"
"${LIBRARY_DIR}/status.cc"
"${LIBRARY_DIR}/table_builder.cc"
"${LIBRARY_DIR}/table.cc"
"${LIBRARY_DIR}/tensor.cc"
"${LIBRARY_DIR}/type.cc"
"${LIBRARY_DIR}/visitor.cc"
"${LIBRARY_DIR}/array/array_base.cc"
"${LIBRARY_DIR}/array/array_binary.cc"
"${LIBRARY_DIR}/array/array_decimal.cc"
@ -191,25 +192,112 @@ set(ARROW_SRCS
"${LIBRARY_DIR}/array/diff.cc"
"${LIBRARY_DIR}/array/util.cc"
"${LIBRARY_DIR}/array/validate.cc"
"${LIBRARY_DIR}/builder.cc"
"${LIBRARY_DIR}/buffer.cc"
"${LIBRARY_DIR}/chunked_array.cc"
"${LIBRARY_DIR}/compare.cc"
"${LIBRARY_DIR}/config.cc"
"${LIBRARY_DIR}/datum.cc"
"${LIBRARY_DIR}/device.cc"
"${LIBRARY_DIR}/extension_type.cc"
"${LIBRARY_DIR}/memory_pool.cc"
"${LIBRARY_DIR}/pretty_print.cc"
"${LIBRARY_DIR}/record_batch.cc"
"${LIBRARY_DIR}/result.cc"
"${LIBRARY_DIR}/scalar.cc"
"${LIBRARY_DIR}/sparse_tensor.cc"
"${LIBRARY_DIR}/status.cc"
"${LIBRARY_DIR}/table.cc"
"${LIBRARY_DIR}/table_builder.cc"
"${LIBRARY_DIR}/tensor.cc"
"${LIBRARY_DIR}/tensor/coo_converter.cc"
"${LIBRARY_DIR}/tensor/csf_converter.cc"
"${LIBRARY_DIR}/tensor/csx_converter.cc"
"${LIBRARY_DIR}/type.cc"
"${LIBRARY_DIR}/visitor.cc"
"${LIBRARY_DIR}/c/bridge.cc"
"${LIBRARY_DIR}/io/buffered.cc"
"${LIBRARY_DIR}/io/caching.cc"
"${LIBRARY_DIR}/io/compressed.cc"
"${LIBRARY_DIR}/io/file.cc"
"${LIBRARY_DIR}/io/hdfs.cc"
"${LIBRARY_DIR}/io/hdfs_internal.cc"
"${LIBRARY_DIR}/io/interfaces.cc"
"${LIBRARY_DIR}/io/memory.cc"
"${LIBRARY_DIR}/io/slow.cc"
"${LIBRARY_DIR}/io/stdio.cc"
"${LIBRARY_DIR}/io/transform.cc"
"${LIBRARY_DIR}/util/async_util.cc"
"${LIBRARY_DIR}/util/basic_decimal.cc"
"${LIBRARY_DIR}/util/bit_block_counter.cc"
"${LIBRARY_DIR}/util/bit_run_reader.cc"
"${LIBRARY_DIR}/util/bit_util.cc"
"${LIBRARY_DIR}/util/bitmap.cc"
"${LIBRARY_DIR}/util/bitmap_builders.cc"
"${LIBRARY_DIR}/util/bitmap_ops.cc"
"${LIBRARY_DIR}/util/bpacking.cc"
"${LIBRARY_DIR}/util/cancel.cc"
"${LIBRARY_DIR}/util/compression.cc"
"${LIBRARY_DIR}/util/counting_semaphore.cc"
"${LIBRARY_DIR}/util/cpu_info.cc"
"${LIBRARY_DIR}/util/decimal.cc"
"${LIBRARY_DIR}/util/delimiting.cc"
"${LIBRARY_DIR}/util/formatting.cc"
"${LIBRARY_DIR}/util/future.cc"
"${LIBRARY_DIR}/util/int_util.cc"
"${LIBRARY_DIR}/util/io_util.cc"
"${LIBRARY_DIR}/util/logging.cc"
"${LIBRARY_DIR}/util/key_value_metadata.cc"
"${LIBRARY_DIR}/util/memory.cc"
"${LIBRARY_DIR}/util/mutex.cc"
"${LIBRARY_DIR}/util/string.cc"
"${LIBRARY_DIR}/util/string_builder.cc"
"${LIBRARY_DIR}/util/task_group.cc"
"${LIBRARY_DIR}/util/tdigest.cc"
"${LIBRARY_DIR}/util/thread_pool.cc"
"${LIBRARY_DIR}/util/time.cc"
"${LIBRARY_DIR}/util/trie.cc"
"${LIBRARY_DIR}/util/unreachable.cc"
"${LIBRARY_DIR}/util/uri.cc"
"${LIBRARY_DIR}/util/utf8.cc"
"${LIBRARY_DIR}/util/value_parsing.cc"
"${LIBRARY_DIR}/vendored/base64.cpp"
"${LIBRARY_DIR}/vendored/datetime/tz.cpp"
"${LIBRARY_DIR}/vendored/musl/strptime.c"
"${LIBRARY_DIR}/vendored/uriparser/UriCommon.c"
"${LIBRARY_DIR}/vendored/uriparser/UriCompare.c"
"${LIBRARY_DIR}/vendored/uriparser/UriEscape.c"
"${LIBRARY_DIR}/vendored/uriparser/UriFile.c"
"${LIBRARY_DIR}/vendored/uriparser/UriIp4Base.c"
"${LIBRARY_DIR}/vendored/uriparser/UriIp4.c"
"${LIBRARY_DIR}/vendored/uriparser/UriMemory.c"
"${LIBRARY_DIR}/vendored/uriparser/UriNormalizeBase.c"
"${LIBRARY_DIR}/vendored/uriparser/UriNormalize.c"
"${LIBRARY_DIR}/vendored/uriparser/UriParseBase.c"
"${LIBRARY_DIR}/vendored/uriparser/UriParse.c"
"${LIBRARY_DIR}/vendored/uriparser/UriQuery.c"
"${LIBRARY_DIR}/vendored/uriparser/UriRecompose.c"
"${LIBRARY_DIR}/vendored/uriparser/UriResolve.c"
"${LIBRARY_DIR}/vendored/uriparser/UriShorten.c"
"${LIBRARY_DIR}/compute/api_aggregate.cc"
"${LIBRARY_DIR}/compute/api_scalar.cc"
"${LIBRARY_DIR}/compute/api_vector.cc"
"${LIBRARY_DIR}/compute/cast.cc"
"${LIBRARY_DIR}/compute/exec.cc"
"${LIBRARY_DIR}/compute/exec/aggregate_node.cc"
"${LIBRARY_DIR}/compute/exec/exec_plan.cc"
"${LIBRARY_DIR}/compute/exec/expression.cc"
"${LIBRARY_DIR}/compute/exec/filter_node.cc"
"${LIBRARY_DIR}/compute/exec/project_node.cc"
"${LIBRARY_DIR}/compute/exec/source_node.cc"
"${LIBRARY_DIR}/compute/exec/sink_node.cc"
"${LIBRARY_DIR}/compute/exec/order_by_impl.cc"
"${LIBRARY_DIR}/compute/function.cc"
"${LIBRARY_DIR}/compute/function_internal.cc"
"${LIBRARY_DIR}/compute/kernel.cc"
"${LIBRARY_DIR}/compute/registry.cc"
"${LIBRARY_DIR}/compute/exec/exec_plan.cc"
"${LIBRARY_DIR}/compute/exec/expression.cc"
"${LIBRARY_DIR}/compute/exec/key_compare.cc"
"${LIBRARY_DIR}/compute/exec/key_encode.cc"
"${LIBRARY_DIR}/compute/exec/key_hash.cc"
"${LIBRARY_DIR}/compute/exec/key_map.cc"
"${LIBRARY_DIR}/compute/exec/util.cc"
"${LIBRARY_DIR}/compute/kernels/aggregate_basic.cc"
"${LIBRARY_DIR}/compute/kernels/aggregate_mode.cc"
"${LIBRARY_DIR}/compute/kernels/aggregate_quantile.cc"
@ -227,28 +315,31 @@ set(ARROW_SRCS
"${LIBRARY_DIR}/compute/kernels/scalar_cast_string.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_cast_temporal.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_compare.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_fill_null.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_if_else.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_nested.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_set_lookup.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_string.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_temporal.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_temporal_binary.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_temporal_unary.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_validity.cc"
"${LIBRARY_DIR}/compute/kernels/scalar_if_else.cc"
"${LIBRARY_DIR}/compute/kernels/util_internal.cc"
"${LIBRARY_DIR}/compute/kernels/vector_array_sort.cc"
"${LIBRARY_DIR}/compute/kernels/vector_hash.cc"
"${LIBRARY_DIR}/compute/kernels/vector_nested.cc"
"${LIBRARY_DIR}/compute/kernels/vector_replace.cc"
"${LIBRARY_DIR}/compute/kernels/vector_selection.cc"
"${LIBRARY_DIR}/compute/kernels/vector_sort.cc"
"${LIBRARY_DIR}/csv/chunker.cc"
"${LIBRARY_DIR}/csv/column_builder.cc"
"${LIBRARY_DIR}/csv/column_decoder.cc"
"${LIBRARY_DIR}/csv/converter.cc"
"${LIBRARY_DIR}/csv/options.cc"
"${LIBRARY_DIR}/csv/parser.cc"
"${LIBRARY_DIR}/csv/reader.cc"
"${LIBRARY_DIR}/csv/writer.cc"
"${LIBRARY_DIR}/compute/kernels/row_encoder.cc"
"${LIBRARY_DIR}/compute/exec/union_node.cc"
"${LIBRARY_DIR}/compute/exec/key_hash.cc"
"${LIBRARY_DIR}/compute/exec/key_map.cc"
"${LIBRARY_DIR}/compute/exec/key_compare.cc"
"${LIBRARY_DIR}/compute/exec/key_encode.cc"
"${LIBRARY_DIR}/compute/exec/util.cc"
"${LIBRARY_DIR}/compute/exec/hash_join_dict.cc"
"${LIBRARY_DIR}/compute/exec/hash_join.cc"
"${LIBRARY_DIR}/compute/exec/hash_join_node.cc"
"${LIBRARY_DIR}/compute/exec/task_util.cc"
"${LIBRARY_DIR}/ipc/dictionary.cc"
"${LIBRARY_DIR}/ipc/feather.cc"
@ -258,52 +349,6 @@ set(ARROW_SRCS
"${LIBRARY_DIR}/ipc/reader.cc"
"${LIBRARY_DIR}/ipc/writer.cc"
"${LIBRARY_DIR}/io/buffered.cc"
"${LIBRARY_DIR}/io/caching.cc"
"${LIBRARY_DIR}/io/compressed.cc"
"${LIBRARY_DIR}/io/file.cc"
"${LIBRARY_DIR}/io/interfaces.cc"
"${LIBRARY_DIR}/io/memory.cc"
"${LIBRARY_DIR}/io/slow.cc"
"${LIBRARY_DIR}/io/stdio.cc"
"${LIBRARY_DIR}/io/transform.cc"
"${LIBRARY_DIR}/tensor/coo_converter.cc"
"${LIBRARY_DIR}/tensor/csf_converter.cc"
"${LIBRARY_DIR}/tensor/csx_converter.cc"
"${LIBRARY_DIR}/util/basic_decimal.cc"
"${LIBRARY_DIR}/util/bit_block_counter.cc"
"${LIBRARY_DIR}/util/bit_run_reader.cc"
"${LIBRARY_DIR}/util/bit_util.cc"
"${LIBRARY_DIR}/util/bitmap_builders.cc"
"${LIBRARY_DIR}/util/bitmap_ops.cc"
"${LIBRARY_DIR}/util/bitmap.cc"
"${LIBRARY_DIR}/util/bpacking.cc"
"${LIBRARY_DIR}/util/cancel.cc"
"${LIBRARY_DIR}/util/compression.cc"
"${LIBRARY_DIR}/util/cpu_info.cc"
"${LIBRARY_DIR}/util/decimal.cc"
"${LIBRARY_DIR}/util/delimiting.cc"
"${LIBRARY_DIR}/util/formatting.cc"
"${LIBRARY_DIR}/util/future.cc"
"${LIBRARY_DIR}/util/int_util.cc"
"${LIBRARY_DIR}/util/io_util.cc"
"${LIBRARY_DIR}/util/key_value_metadata.cc"
"${LIBRARY_DIR}/util/logging.cc"
"${LIBRARY_DIR}/util/memory.cc"
"${LIBRARY_DIR}/util/mutex.cc"
"${LIBRARY_DIR}/util/string_builder.cc"
"${LIBRARY_DIR}/util/string.cc"
"${LIBRARY_DIR}/util/task_group.cc"
"${LIBRARY_DIR}/util/tdigest.cc"
"${LIBRARY_DIR}/util/thread_pool.cc"
"${LIBRARY_DIR}/util/time.cc"
"${LIBRARY_DIR}/util/trie.cc"
"${LIBRARY_DIR}/util/utf8.cc"
"${LIBRARY_DIR}/util/value_parsing.cc"
"${LIBRARY_DIR}/vendored/base64.cpp"
${ORC_SRCS}
)
@ -373,6 +418,7 @@ target_include_directories(${ARROW_LIBRARY} PRIVATE SYSTEM ${ORC_BUILD_INCLUDE_D
target_include_directories(${ARROW_LIBRARY} PRIVATE SYSTEM ${ORC_ADDITION_SOURCE_DIR})
target_include_directories(${ARROW_LIBRARY} PRIVATE SYSTEM ${ARROW_SRC_DIR})
target_include_directories(${ARROW_LIBRARY} PRIVATE SYSTEM ${FLATBUFFERS_INCLUDE_DIR})
target_include_directories(${ARROW_LIBRARY} PRIVATE SYSTEM ${HDFS_INCLUDE_DIR})
# === parquet
@ -446,7 +492,7 @@ set (HAVE_STRERROR_R 1)
set (HAVE_SCHED_GET_PRIORITY_MAX 1)
set (HAVE_SCHED_GET_PRIORITY_MIN 1)
if (OS_LINUX)
if (OS_LINUX AND NOT USE_MUSL)
set (STRERROR_R_CHAR_P 1)
endif ()

2
contrib/boost vendored

@ -1 +1 @@
Subproject commit fcb058e1459ac273ecfe7cdf72791cb1479115af
Subproject commit c0807e83f2824e8dd67a15b355496a9b784cdcd5

22
contrib/boost-cmake/CMakeLists.txt
View File

@ -1,9 +1,7 @@
option (USE_INTERNAL_BOOST_LIBRARY "Use internal Boost library" ON)
if (NOT USE_INTERNAL_BOOST_LIBRARY)
# 1.70 like in contrib/boost
# 1.71 on CI
set(BOOST_VERSION 1.71)
set(BOOST_VERSION 1.78)
find_package(Boost ${BOOST_VERSION} COMPONENTS
system
@ -66,9 +64,11 @@ if (NOT EXTERNAL_BOOST_FOUND)
set (SRCS_FILESYSTEM
"${LIBRARY_DIR}/libs/filesystem/src/codecvt_error_category.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/directory.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/exception.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/operations.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/path_traits.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/path.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/path_traits.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/portability.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/unique_path.cpp"
"${LIBRARY_DIR}/libs/filesystem/src/utf8_codecvt_facet.cpp"
@ -126,24 +126,11 @@ if (NOT EXTERNAL_BOOST_FOUND)
# regex
set (SRCS_REGEX
"${LIBRARY_DIR}/libs/regex/src/c_regex_traits.cpp"
"${LIBRARY_DIR}/libs/regex/src/cpp_regex_traits.cpp"
"${LIBRARY_DIR}/libs/regex/src/cregex.cpp"
"${LIBRARY_DIR}/libs/regex/src/fileiter.cpp"
"${LIBRARY_DIR}/libs/regex/src/icu.cpp"
"${LIBRARY_DIR}/libs/regex/src/instances.cpp"
"${LIBRARY_DIR}/libs/regex/src/internals.hpp"
"${LIBRARY_DIR}/libs/regex/src/posix_api.cpp"
"${LIBRARY_DIR}/libs/regex/src/regex_debug.cpp"
"${LIBRARY_DIR}/libs/regex/src/regex_raw_buffer.cpp"
"${LIBRARY_DIR}/libs/regex/src/regex_traits_defaults.cpp"
"${LIBRARY_DIR}/libs/regex/src/regex.cpp"
"${LIBRARY_DIR}/libs/regex/src/static_mutex.cpp"
"${LIBRARY_DIR}/libs/regex/src/usinstances.cpp"
"${LIBRARY_DIR}/libs/regex/src/w32_regex_traits.cpp"
"${LIBRARY_DIR}/libs/regex/src/wc_regex_traits.cpp"
"${LIBRARY_DIR}/libs/regex/src/wide_posix_api.cpp"
"${LIBRARY_DIR}/libs/regex/src/winstances.cpp"
)
add_library (_boost_regex ${SRCS_REGEX})
@ -166,7 +153,6 @@ if (NOT EXTERNAL_BOOST_FOUND)
set (SRCS_CONTEXT
"${LIBRARY_DIR}/libs/context/src/dummy.cpp"
"${LIBRARY_DIR}/libs/context/src/execution_context.cpp"
"${LIBRARY_DIR}/libs/context/src/posix/stack_traits.cpp"
)

2
contrib/cassandra vendored

@ -1 +1 @@
Subproject commit eb9b68dadbb4417a2c132ad4a1c2fa76e65e6fc1
Subproject commit f4a31e92a25c34c02c7291ff97c7813bc83b0e09

2
contrib/jemalloc vendored

@ -1 +1 @@
Subproject commit e6891d9746143bf2cf617493d880ba5a0b9a3efd
Subproject commit a1404807211b1612539f840b3dcb1bf38d1a269e

11
contrib/libuv-cmake/CMakeLists.txt
View File

@ -1,17 +1,8 @@
# This file is a modified version of contrib/libuv/CMakeLists.txt
include(CMakeDependentOption)
set (SOURCE_DIR "${CMAKE_SOURCE_DIR}/contrib/libuv")
set (BINARY_DIR "${CMAKE_BINARY_DIR}/contrib/libuv")
if(CMAKE_C_COMPILER_ID MATCHES "AppleClang|Clang|GNU")
list(APPEND uv_cflags -fvisibility=hidden --std=gnu89)
list(APPEND uv_cflags -Wall -Wextra -Wstrict-prototypes)
list(APPEND uv_cflags -Wno-unused-parameter)
endif()
set(uv_sources
src/fs-poll.c
src/idna.c
@ -76,7 +67,7 @@ endif()
if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
list(APPEND uv_defines _GNU_SOURCE _POSIX_C_SOURCE=200112)
list(APPEND uv_libraries dl rt)
list(APPEND uv_libraries rt)
list(APPEND uv_sources
src/unix/linux-core.c
src/unix/linux-inotify.c

5
contrib/mariadb-connector-c-cmake/CMakeLists.txt
View File

@ -236,8 +236,7 @@ set(LIBMARIADB_SOURCES ${LIBMARIADB_SOURCES} ${CC_SOURCE_DIR}/libmariadb/mariadb
add_library(mariadbclient STATIC ${LIBMARIADB_SOURCES})
target_link_libraries(mariadbclient ${SYSTEM_LIBS})
target_include_directories(mariadbclient
PRIVATE ${CC_BINARY_DIR}/include-private
PUBLIC ${CC_BINARY_DIR}/include-public ${CC_SOURCE_DIR}/include ${CC_SOURCE_DIR}/libmariadb)
target_include_directories(mariadbclient PRIVATE ${CC_BINARY_DIR}/include-private)
target_include_directories(mariadbclient SYSTEM PUBLIC ${CC_BINARY_DIR}/include-public ${CC_SOURCE_DIR}/include ${CC_SOURCE_DIR}/libmariadb)
set_target_properties(mariadbclient PROPERTIES IMPORTED_INTERFACE_LINK_LIBRARIES "${SYSTEM_LIBS}")

2
contrib/protobuf vendored

@ -1 +1 @@
Subproject commit c1c5d02026059f4c3cb51aaa08e82288d3e08b89
Subproject commit 6bb70196c5360268d9f021bb7936fb0b551724c2

2
contrib/s2geometry vendored

@ -1 +1 @@
Subproject commit 38b7a290f927cc372218c2094602b83e35b18c05
Subproject commit 471fe9dc931a4bb560333545186e9b5da168ac83

58
contrib/s2geometry-cmake/CMakeLists.txt
View File

@ -1,8 +1,12 @@
set(S2_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/s2geometry/src")
set(ABSL_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
if(NOT EXISTS "${ABSL_SOURCE_DIR}/CMakeLists.txt")
message(FATAL_ERROR " submodule contrib/abseil-cpp is missing. To fix try run: \n git submodule update --init --recursive")
endif()
set(S2_SRCS
"${S2_SOURCE_DIR}/s2/base/stringprintf.cc"
"${S2_SOURCE_DIR}/s2/base/strtoint.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2cell_id_vector.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2point_vector.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2shape_index.cc"
@ -14,11 +18,14 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s1chord_angle.cc"
"${S2_SOURCE_DIR}/s2/s1interval.cc"
"${S2_SOURCE_DIR}/s2/s2boolean_operation.cc"
"${S2_SOURCE_DIR}/s2/s2buffer_operation.cc"
"${S2_SOURCE_DIR}/s2/s2builder.cc"
"${S2_SOURCE_DIR}/s2/s2builder_graph.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_closed_set_normalizer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_find_polygon_degeneracies.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_get_snapped_winding_delta.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_lax_polygon_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_lax_polyline_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2point_vector_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2polygon_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2polyline_layer.cc"
@ -44,7 +51,6 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s2edge_crossings.cc"
"${S2_SOURCE_DIR}/s2/s2edge_distances.cc"
"${S2_SOURCE_DIR}/s2/s2edge_tessellator.cc"
"${S2_SOURCE_DIR}/s2/s2error.cc"
"${S2_SOURCE_DIR}/s2/s2furthest_edge_query.cc"
"${S2_SOURCE_DIR}/s2/s2latlng.cc"
"${S2_SOURCE_DIR}/s2/s2latlng_rect.cc"
@ -55,6 +61,7 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s2loop.cc"
"${S2_SOURCE_DIR}/s2/s2loop_measures.cc"
"${S2_SOURCE_DIR}/s2/s2measures.cc"
"${S2_SOURCE_DIR}/s2/s2memory_tracker.cc"
"${S2_SOURCE_DIR}/s2/s2metrics.cc"
"${S2_SOURCE_DIR}/s2/s2max_distance_targets.cc"
"${S2_SOURCE_DIR}/s2/s2min_distance_targets.cc"
@ -82,28 +89,15 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s2shapeutil_build_polygon_boundaries.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_coding.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_contains_brute_force.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_conversion.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_edge_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_get_reference_point.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_range_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_visit_crossing_edge_pairs.cc"
"${S2_SOURCE_DIR}/s2/s2text_format.cc"
"${S2_SOURCE_DIR}/s2/s2wedge_relations.cc"
"${S2_SOURCE_DIR}/s2/strings/ostringstream.cc"
"${S2_SOURCE_DIR}/s2/s2winding_operation.cc"
"${S2_SOURCE_DIR}/s2/strings/serialize.cc"
# ClickHouse doesn't use strings from abseil.
# So, there is no duplicate symbols.
"${S2_SOURCE_DIR}/s2/third_party/absl/base/dynamic_annotations.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/base/internal/raw_logging.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/base/internal/throw_delegate.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/numeric/int128.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/ascii.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/match.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/numbers.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/str_cat.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/str_split.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/string_view.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/strip.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/internal/memutil.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bit-interleave.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bits.cc"
"${S2_SOURCE_DIR}/s2/util/coding/coder.cc"
@ -111,17 +105,41 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/util/math/exactfloat/exactfloat.cc"
"${S2_SOURCE_DIR}/s2/util/math/mathutil.cc"
"${S2_SOURCE_DIR}/s2/util/units/length-units.cc"
)
add_library(s2 ${S2_SRCS})
set_property(TARGET s2 PROPERTY CXX_STANDARD 11)
set_property(TARGET s2 PROPERTY CXX_STANDARD 17)
if (OPENSSL_FOUND)
target_link_libraries(s2 PRIVATE ${OPENSSL_LIBRARIES})
endif()
# Copied from contrib/s2geometry/CMakeLists
target_link_libraries(s2 PRIVATE
absl::base
absl::btree
absl::config
absl::core_headers
absl::dynamic_annotations
absl::endian
absl::fixed_array
absl::flat_hash_map
absl::flat_hash_set
absl::hash
absl::inlined_vector
absl::int128
absl::log_severity
absl::memory
absl::span
absl::str_format
absl::strings
absl::type_traits
absl::utility
)
target_include_directories(s2 SYSTEM BEFORE PUBLIC "${S2_SOURCE_DIR}/")
target_include_directories(s2 SYSTEM PUBLIC "${ABSL_SOURCE_DIR}")
if(M_LIBRARY)
target_link_libraries(s2 PRIVATE ${M_LIBRARY})

5
docker/images.json
View File

@ -46,7 +46,6 @@
"name": "clickhouse/stateless-test",
"dependent": [
"docker/test/stateful",
"docker/test/coverage",
"docker/test/unit"
]
},
@ -56,10 +55,6 @@
"docker/test/stress"
]
},
"docker/test/coverage": {
"name": "clickhouse/test-coverage",
"dependent": []
},
"docker/test/unit": {
"name": "clickhouse/unit-test",
"dependent": []

2
docker/server/README.md
View File

@ -17,6 +17,8 @@ $ docker run -d --name some-clickhouse-server --ulimit nofile=262144:262144 clic
By default ClickHouse will be accessible only via docker network. See the [networking section below](#networking).
By default, starting above server instance will be run as default user without password.
### connect to it from a native client
```bash
$ docker run -it --rm --link some-clickhouse-server:clickhouse-server clickhouse/clickhouse-client --host clickhouse-server

6
docker/test/codebrowser/Dockerfile
View File

@ -6,7 +6,7 @@ FROM clickhouse/binary-builder
ARG apt_archive="http://archive.ubuntu.com"
RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
RUN apt-get update && apt-get --yes --allow-unauthenticated install clang-9 libllvm9 libclang-9-dev
RUN apt-get update && apt-get --yes --allow-unauthenticated install clang-13 libllvm13 libclang-13-dev
# repo versions doesn't work correctly with C++17
# also we push reports to s3, so we add index.html to subfolder urls
@ -23,12 +23,12 @@ ENV SOURCE_DIRECTORY=/repo_folder
ENV BUILD_DIRECTORY=/build
ENV HTML_RESULT_DIRECTORY=$BUILD_DIRECTORY/html_report
ENV SHA=nosha
ENV DATA="data"
ENV DATA="https://s3.amazonaws.com/clickhouse-test-reports/codebrowser/data"
CMD mkdir -p $BUILD_DIRECTORY && cd $BUILD_DIRECTORY && \
cmake $SOURCE_DIRECTORY -DCMAKE_CXX_COMPILER=/usr/bin/clang\+\+-13 -DCMAKE_C_COMPILER=/usr/bin/clang-13 -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DENABLE_EMBEDDED_COMPILER=0 -DENABLE_S3=0 && \
mkdir -p $HTML_RESULT_DIRECTORY && \
$CODEGEN -b $BUILD_DIRECTORY -a -o $HTML_RESULT_DIRECTORY -p ClickHouse:$SOURCE_DIRECTORY:$SHA -d $DATA | ts '%Y-%m-%d %H:%M:%S' && \
cp -r $STATIC_DATA $HTML_RESULT_DIRECTORY/ &&\
$CODEINDEX $HTML_RESULT_DIRECTORY -d $DATA | ts '%Y-%m-%d %H:%M:%S' && \
$CODEINDEX $HTML_RESULT_DIRECTORY -d "$DATA" | ts '%Y-%m-%d %H:%M:%S' && \
mv $HTML_RESULT_DIRECTORY /test_output

18
docker/test/coverage/Dockerfile
View File

@ -1,18 +0,0 @@
# docker build -t clickhouse/test-coverage .
FROM clickhouse/stateless-test
RUN apt-get update -y \
&& env DEBIAN_FRONTEND=noninteractive \
apt-get install --yes --no-install-recommends \
cmake
COPY s3downloader /s3downloader
COPY run.sh /run.sh
ENV DATASETS="hits visits"
ENV COVERAGE_DIR=/coverage_reports
ENV SOURCE_DIR=/build
ENV OUTPUT_DIR=/output
ENV IGNORE='.*contrib.*'
CMD ["/bin/bash", "/run.sh"]

112
docker/test/coverage/run.sh
View File

@ -1,112 +0,0 @@
#!/bin/bash
kill_clickhouse () {
echo "clickhouse pids $(pgrep -u clickhouse)" | ts '%Y-%m-%d %H:%M:%S'
pkill -f "clickhouse-server" 2>/dev/null
for _ in {1..120}
do
if ! pkill -0 -f "clickhouse-server" ; then break ; fi
echo "ClickHouse still alive" | ts '%Y-%m-%d %H:%M:%S'
sleep 1
done
if pkill -0 -f "clickhouse-server"
then
pstree -apgT
jobs
echo "Failed to kill the ClickHouse server" | ts '%Y-%m-%d %H:%M:%S'
return 1
fi
}
start_clickhouse () {
LLVM_PROFILE_FILE='server_%h_%p_%m.profraw' sudo -Eu clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml &
counter=0
until clickhouse-client --query "SELECT 1"
do
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
sleep 0.5
counter=$((counter + 1))
done
}
chmod 777 /
dpkg -i package_folder/clickhouse-common-static_*.deb; \
dpkg -i package_folder/clickhouse-common-static-dbg_*.deb; \
dpkg -i package_folder/clickhouse-server_*.deb; \
dpkg -i package_folder/clickhouse-client_*.deb; \
dpkg -i package_folder/clickhouse-test_*.deb
mkdir -p /var/lib/clickhouse
mkdir -p /var/log/clickhouse-server
chmod 777 -R /var/log/clickhouse-server/
# install test configs
/usr/share/clickhouse-test/config/install.sh
start_clickhouse
# shellcheck disable=SC2086 # No quotes because I want to split it into words.
if ! /s3downloader --dataset-names $DATASETS; then
echo "Cannot download datatsets"
exit 1
fi
chmod 777 -R /var/lib/clickhouse
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "SHOW DATABASES"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "ATTACH DATABASE datasets ENGINE = Ordinary"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "CREATE DATABASE test"
kill_clickhouse
start_clickhouse
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "SHOW TABLES FROM datasets"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "SHOW TABLES FROM test"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "RENAME TABLE datasets.hits_v1 TO test.hits"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "RENAME TABLE datasets.visits_v1 TO test.visits"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-client --query "SHOW TABLES FROM test"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-test -j 8 --testname --shard --zookeeper --print-time 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee /test_result.txt
readarray -t FAILED_TESTS < <(awk '/FAIL|TIMEOUT|ERROR/ { print substr($3, 1, length($3)-1) }' "/test_result.txt")
kill_clickhouse
sleep 3
if [[ -n "${FAILED_TESTS[*]}" ]]
then
# Clean the data so that there is no interference from the previous test run.
rm -rf /var/lib/clickhouse/{{meta,}data,user_files} ||:
start_clickhouse
echo "Going to run again: ${FAILED_TESTS[*]}"
LLVM_PROFILE_FILE='client_coverage_%5m.profraw' clickhouse-test --order=random --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a /test_result.txt
else
echo "No failed tests"
fi
mkdir -p "$COVERAGE_DIR"
mv /*.profraw "$COVERAGE_DIR"
mkdir -p "$SOURCE_DIR"/obj-x86_64-linux-gnu
cd "$SOURCE_DIR"/obj-x86_64-linux-gnu && CC=clang-11 CXX=clang++-11 cmake .. && cd /
llvm-profdata-11 merge -sparse "${COVERAGE_DIR}"/* -o clickhouse.profdata
llvm-cov-11 export /usr/bin/clickhouse -instr-profile=clickhouse.profdata -j=16 -format=lcov -skip-functions -ignore-filename-regex "$IGNORE" > output.lcov
genhtml output.lcov --ignore-errors source --output-directory "${OUTPUT_DIR}"

101
docker/test/coverage/s3downloader
View File

@ -1,101 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import os
import sys
import time
import tarfile
import logging
import argparse
import requests
import tempfile
DEFAULT_URL = 'https://clickhouse-datasets.s3.yandex.net'
AVAILABLE_DATASETS = {
'hits': 'hits_v1.tar',
'visits': 'visits_v1.tar',
}
RETRIES_COUNT = 5
def _get_temp_file_name():
return os.path.join(tempfile._get_default_tempdir(), next(tempfile._get_candidate_names()))
def build_url(base_url, dataset):
return os.path.join(base_url, dataset, 'partitions', AVAILABLE_DATASETS[dataset])
def dowload_with_progress(url, path):
logging.info("Downloading from %s to temp path %s", url, path)
for i in range(RETRIES_COUNT):
try:
with open(path, 'wb') as f:
response = requests.get(url, stream=True)
response.raise_for_status()
total_length = response.headers.get('content-length')
if total_length is None or int(total_length) == 0:
logging.info("No content-length, will download file without progress")
f.write(response.content)
else:
dl = 0
total_length = int(total_length)
logging.info("Content length is %ld bytes", total_length)
for data in response.iter_content(chunk_size=4096):
dl += len(data)
f.write(data)
if sys.stdout.isatty():
done = int(50 * dl / total_length)
percent = int(100 * float(dl) / total_length)
sys.stdout.write("\r[{}{}] {}%".format('=' * done, ' ' * (50-done), percent))
sys.stdout.flush()
break
except Exception as ex:
sys.stdout.write("\n")
time.sleep(3)
logging.info("Exception while downloading %s, retry %s", ex, i + 1)
if os.path.exists(path):
os.remove(path)
else:
raise Exception("Cannot download dataset from {}, all retries exceeded".format(url))
sys.stdout.write("\n")
logging.info("Downloading finished")
def unpack_to_clickhouse_directory(tar_path, clickhouse_path):
logging.info("Will unpack data from temp path %s to clickhouse db %s", tar_path, clickhouse_path)
with tarfile.open(tar_path, 'r') as comp_file:
comp_file.extractall(path=clickhouse_path)
logging.info("Unpack finished")
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
parser = argparse.ArgumentParser(
description="Simple tool for dowloading datasets for clickhouse from S3")
parser.add_argument('--dataset-names', required=True, nargs='+', choices=list(AVAILABLE_DATASETS.keys()))
parser.add_argument('--url-prefix', default=DEFAULT_URL)
parser.add_argument('--clickhouse-data-path', default='/var/lib/clickhouse/')
args = parser.parse_args()
datasets = args.dataset_names
logging.info("Will fetch following datasets: %s", ', '.join(datasets))
for dataset in datasets:
logging.info("Processing %s", dataset)
temp_archive_path = _get_temp_file_name()
try:
download_url_for_dataset = build_url(args.url_prefix, dataset)
dowload_with_progress(download_url_for_dataset, temp_archive_path)
unpack_to_clickhouse_directory(temp_archive_path, args.clickhouse_data_path)
except Exception as ex:
logging.info("Some exception occured %s", str(ex))
raise
finally:
logging.info("Will remove downloaded file %s from filesystem if it exists", temp_archive_path)
if os.path.exists(temp_archive_path):
os.remove(temp_archive_path)
logging.info("Processing of %s finished", dataset)
logging.info("Fetch finished, enjoy your tables!")

8
docker/test/fasttest/run.sh
View File

@ -257,7 +257,13 @@ function run_tests
start_server
set +e
time clickhouse-test --hung-check -j 8 --order=random \
local NPROC
NPROC=$(nproc)
NPROC=$((NPROC / 2))
if [[ $NPROC == 0 ]]; then
NPROC=1
fi
time clickhouse-test --hung-check -j "${NPROC}" --order=random \
--fast-tests-only --no-long --testname --shard --zookeeper --check-zookeeper-session \
-- "$FASTTEST_FOCUS" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \

18
docker/test/fuzzer/run-fuzzer.sh
View File

@ -52,9 +52,21 @@ function clone
}
function wget_with_retry
{
for _ in 1 2 3 4; do
if wget -nv -nd -c "$1";then
return 0
else
sleep 0.5
fi
done
return 1
}
function download
{
wget -nv -nd -c "$BINARY_URL_TO_DOWNLOAD"
wget_with_retry "$BINARY_URL_TO_DOWNLOAD"
chmod +x clickhouse
ln -s ./clickhouse ./clickhouse-server
@ -194,8 +206,8 @@ quit
time clickhouse-client --query "SELECT 'Connected to clickhouse-server after attaching gdb'" ||:
# Check connectivity after we attach gdb, because it might cause the server
# to freeze and the fuzzer will fail.
for _ in {1..60}
# to freeze and the fuzzer will fail. In debug build it can take a lot of time.
for _ in {1..180}
do
sleep 1
if clickhouse-client --query "select 1"

2
docker/test/pvs/Dockerfile
View File

@ -42,7 +42,7 @@ ENV CCACHE_DIR=/test_output/ccache
CMD echo "Running PVS version $PKG_VERSION" && mkdir -p $CCACHE_DIR && cd /repo_folder && pvs-studio-analyzer credentials $LICENCE_NAME $LICENCE_KEY -o ./licence.lic \
&& cmake . -D"ENABLE_EMBEDDED_COMPILER"=OFF -D"DISABLE_HERMETIC_BUILD"=ON -DCMAKE_C_COMPILER=clang-13 -DCMAKE_CXX_COMPILER=clang\+\+-13 \
&& ninja re2_st clickhouse_grpc_protos \
&& pvs-studio-analyzer analyze -o pvs-studio.log -e contrib -j 4 -l ./licence.lic; \
&& pvs-studio-analyzer analyze -o pvs-studio.log -e contrib -j "$(nproc)" -l ./licence.lic; \
cp /repo_folder/pvs-studio.log /test_output; \
plog-converter -a GA:1,2 -t fullhtml -o /test_output/pvs-studio-html-report pvs-studio.log; \
plog-converter -a GA:1,2 -t tasklist -o /test_output/pvs-studio-task-report.txt pvs-studio.log

75
docs/en/engines/database-engines/materialized-mysql.md
View File

@ -83,6 +83,7 @@ When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](
| VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) |
| BLOB | [String](../../sql-reference/data-types/string.md) |
| BINARY | [FixedString](../../sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](../../sql-reference/data-types/int-uint.md) |
[Nullable](../../sql-reference/data-types/nullable.md) is supported.
@ -150,20 +151,38 @@ Table overrides can be used to customize the ClickHouse DDL queries, allowing yo
application. This is especially useful for controlling partitioning, which is important for the overall performance of
MaterializedMySQL.
These are the schema conversion manipulations you can do with table overrides for MaterializedMySQL:
* Modify column type. Must be compatible with the original type, or replication will fail. For example,
you can modify a UInt32 column to UInt64, but you can not modify a String column to Array(String).
* Modify [column TTL](../table-engines/mergetree-family/mergetree/#mergetree-column-ttl).
* Modify [column compression codec](../../sql-reference/statements/create/table/#codecs).
* Add [ALIAS columns](../../sql-reference/statements/create/table/#alias).
* Add [skipping indexes](../table-engines/mergetree-family/mergetree/#table_engine-mergetree-data_skipping-indexes)
* Add [projections](../table-engines/mergetree-family/mergetree/#projections). Note that projection optimizations are
disabled when using `SELECT ... FINAL` (which MaterializedMySQL does by default), so their utility is limited here.
`INDEX ... TYPE hypothesis` as [described in the v21.12 blog post]](https://clickhouse.com/blog/en/2021/clickhouse-v21.12-released/)
may be more useful in this case.
* Modify [PARTITION BY](../table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Modify [PRIMARY KEY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [SAMPLE BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [table TTL](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
```sql
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)
[SETTINGS ...]
[TABLE OVERRIDE table_name (
[COLUMNS (
[name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1] [TTL expr1], ...]
[INDEX index_name1 expr1 TYPE type1(...) GRANULARITY value1, ...]
[PROJECTION projection_name_1 (SELECT <COLUMN LIST EXPR> [GROUP BY] [ORDER BY]), ...]
)]
[ORDER BY expr]
[PRIMARY KEY expr]
[PARTITION BY expr]
[SAMPLE BY expr]
[TTL expr]
[col_name [datatype] [ALIAS expr] [CODEC(...)] [TTL expr], ...]
[INDEX index_name expr TYPE indextype[(...)] GRANULARITY val, ...]
[PROJECTION projection_name (SELECT <COLUMN LIST EXPR> [GROUP BY] [ORDER BY]), ...]
)]
[ORDER BY expr]
[PRIMARY KEY expr]
[PARTITION BY expr]
[SAMPLE BY expr]
[TTL expr]
), ...]
```
@ -173,34 +192,34 @@ Example:
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)
TABLE OVERRIDE table1 (
COLUMNS (
userid UUID,
category LowCardinality(String),
timestamp DateTime CODEC(Delta, Default)
userid UUID,
category LowCardinality(String),
timestamp DateTime CODEC(Delta, Default)
)
PARTITION BY toYear(timestamp)
),
TABLE OVERRIDE table2 (
COLUMNS (
ip_hash UInt32 MATERIALIZED xxHash32(client_ip),
client_ip String TTL created + INTERVAL 72 HOUR
)
SAMPLE BY ip_hash
client_ip String TTL created + INTERVAL 72 HOUR
)
SAMPLE BY ip_hash
)
```
The `COLUMNS` list is sparse; it contains only modified or extra (MATERIALIZED or ALIAS) columns. Modified columns with
a different type must be assignable from the original type. There is currently no validation of this or similar issues
when the `CREATE DATABASE` query executes, so extra care needs to be taken.
The `COLUMNS` list is sparse; existing columns are modified as specified, extra ALIAS columns are added. It is not
possible to add ordinary or MATERIALIZED columns. Modified columns with a different type must be assignable from the
original type. There is currently no validation of this or similar issues when the `CREATE DATABASE` query executes, so
extra care needs to be taken.
You may specify overrides for tables that do not exist yet.
!!! note "Warning"
It is easy to break replication with TABLE OVERRIDEs if not used with care. For example:
!!! warning "Warning"
It is easy to break replication with table overrides if not used with care. For example:
* If a column is added with a table override, but then later added to the source MySQL table, the converted ALTER TABLE
query in ClickHouse will fail because the column already exists.
* If an ALIAS column is added with a table override, and a column with the same name is later added to the source
MySQL table, the converted ALTER TABLE query in ClickHouse will fail and replication stops.
* It is currently possible to add overrides that reference nullable columns where not-nullable are required, such as in
`ORDER BY` or `PARTITION BY`.
`ORDER BY` or `PARTITION BY`. This will cause CREATE TABLE queries that will fail, also causing replication to stop.
## Examples of Use {#examples-of-use}
@ -217,11 +236,9 @@ mysql> SELECT * FROM test;
```
```text
+---+------+------+
| a | b | c |
+---+------+------+
| 2 | 222 | Wow! |
+---+------+------+
┌─a─┬───b─┬─c────┐
│ 2 │ 222 │ Wow! │
└───┴─────┴──────┘
```
Database in ClickHouse, exchanging data with the MySQL server:

140
docs/en/engines/database-engines/materialized-postgresql.md
View File

@ -5,15 +5,15 @@ toc_title: MaterializedPostgreSQL
# [experimental] MaterializedPostgreSQL {#materialize-postgresql}
Creates ClickHouse database with an initial data dump of PostgreSQL database tables and starts replication process, i.e. executes background job to apply new changes as they happen on PostgreSQL database tables in the remote PostgreSQL database.
Creates a ClickHouse database with tables from PostgreSQL database. Firstly, database with engine `MaterializedPostgreSQL` creates a snapshot of PostgreSQL database and loads required tables. Required tables can include any subset of tables from any subset of schemas from specified database. Along with the snapshot database engine acquires LSN and once initial dump of tables is performed - it starts pulling updates from WAL. After database is created, newly added tables to PostgreSQL database are not automatically added to replication. They have to be added manually with `ATTACH TABLE db.table` query.
ClickHouse server works as PostgreSQL replica. It reads WAL and performs DML queries. DDL is not replicated, but can be handled (described below).
Replication is implemented with PostgreSQL Logical Replication Protocol, which does not allow to replicate DDL, but allows to know whether replication breaking changes happened (column type changes, adding/removing columns). Such changes are detected and according tables stop receiving updates. Such tables can be automatically reloaded in the background in case required setting is turned on. Safest way for now is to use `ATTACH`/ `DETACH` queries to reload table completely. If DDL does not break replication (for example, renaming a column) table will still receive updates (insertion is done by position).
## Creating a Database {#creating-a-database}
``` sql
CREATE DATABASE [IF NOT EXISTS] db_name [ON CLUSTER cluster]
ENGINE = MaterializedPostgreSQL('host:port', ['database' | database], 'user', 'password') [SETTINGS ...]
ENGINE = MaterializedPostgreSQL('host:port', 'database', 'user', 'password') [SETTINGS ...]
```
**Engine Parameters**
@ -23,51 +23,39 @@ ENGINE = MaterializedPostgreSQL('host:port', ['database' | database], 'user', 'p
- `user` — PostgreSQL user.
- `password` — User password.
## Example of Use {#example-of-use}
``` sql
CREATE DATABASE postgresql;
ENGINE = MaterializedPostgreSQL('postgres1:5432', 'postgres_database', 'postgres_user', 'postgres_password');
SHOW TABLES FROM postgres_db;
┌─name───┐
│ table1 │
└────────┘
SELECT * FROM postgresql_db.postgres_table;
```
## Dynamically adding new tables to replication {#dynamically-adding-table-to-replication}
After `MaterializedPostgreSQL` database is created, it does not automatically detect new tables in according PostgreSQL database. Such tables can be added manually:
``` sql
ATTACH TABLE postgres_database.new_table;
```
When specifying a specific list of tables in the database using the setting [materialized_postgresql_tables_list](../../operations/settings/settings.md#materialized-postgresql-tables-list), it will be updated to the current state, taking into account the tables which were added by the `ATTACH TABLE` query.
Warning: before version 21.13 adding table to replication left unremoved temprorary replication slot (named `{db_name}_ch_replication_slot_tmp`). If attaching tables in clickhouse version before 21.13, make sure to delete it manually (`SELECT pg_drop_replication_slot('{db_name}_ch_replication_slot_tmp')`). Otherwise disk usage will grow. Issue is fixed in 21.13.
## Dynamically removing tables from replication {#dynamically-removing-table-from-replication}
It is possible to remove specific tables from replication:
``` sql
DETACH TABLE postgres_database.table_to_remove;
```
## Settings {#settings}
- [materialized_postgresql_tables_list](../../operations/settings/settings.md#materialized-postgresql-tables-list)
- [materialized_postgresql_schema](../../operations/settings/settings.md#materialized-postgresql-schema)
- [materialized_postgresql_schema_list](../../operations/settings/settings.md#materialized-postgresql-schema-list)
- [materialized_postgresql_allow_automatic_update](../../operations/settings/settings.md#materialized-postgresql-allow-automatic-update)
- [materialized_postgresql_max_block_size](../../operations/settings/settings.md#materialized-postgresql-max-block-size)
- [materialized_postgresql_replication_slot](../../operations/settings/settings.md#materialized-postgresql-replication-slot)
- [materialized_postgresql_snapshot](../../operations/settings/settings.md#materialized-postgresql-snapshot)
``` sql
CREATE DATABASE database1
ENGINE = MaterializedPostgreSQL('postgres1:5432', 'postgres_database', 'postgres_user', 'postgres_password')
SETTINGS materialized_postgresql_tables_list = 'table1,table2,table3';
SELECT * FROM database1.table1;
```
The settings can be changed, if necessary, using a DDL query. But it is impossible to change the setting `materialized_postgresql_tables_list`. To update the list of tables in this setting use the `ATTACH TABLE` query.
``` sql
ALTER DATABASE postgres_database MODIFY SETTING materialized_postgresql_max_block_size = <new_size>;
```
## PostgreSQL schema {#schema}
PostgreSQL [schema](https://www.postgresql.org/docs/9.1/ddl-schemas.html) can be configured in 3 ways (starting from version 21.12).
@ -150,13 +138,63 @@ WHERE oid = 'postgres_table'::regclass;
!!! warning "Warning"
Replication of [**TOAST**](https://www.postgresql.org/docs/9.5/storage-toast.html) values is not supported. The default value for the data type will be used.
## Example of Use {#example-of-use}
## Settings {#settings}
1. materialized_postgresql_tables_list {#materialized-postgresql-tables-list}
Sets a comma-separated list of PostgreSQL database tables, which will be replicated via [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md) database engine.
Default value: empty list — means whole PostgreSQL database will be replicated.
2. materialized_postgresql_schema {#materialized-postgresql-schema}
Default value: empty string. (Default schema is used)
3. materialized_postgresql_schema_list {#materialized-postgresql-schema-list}
Default value: empty list. (Default schema is used)
4. materialized_postgresql_allow_automatic_update {#materialized-postgresql-allow-automatic-update}
Allows reloading table in the background, when schema changes are detected. DDL queries on the PostgreSQL side are not replicated via ClickHouse [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md) engine, because it is not allowed with PostgreSQL logical replication protocol, but the fact of DDL changes is detected transactionally. In this case, the default behaviour is to stop replicating those tables once DDL is detected. However, if this setting is enabled, then, instead of stopping the replication of those tables, they will be reloaded in the background via database snapshot without data losses and replication will continue for them.
Possible values:
- 0 — The table is not automatically updated in the background, when schema changes are detected.
- 1 — The table is automatically updated in the background, when schema changes are detected.
Default value: `0`.
5. materialized_postgresql_max_block_size {#materialized-postgresql-max-block-size}
Sets the number of rows collected in memory before flushing data into PostgreSQL database table.
Possible values:
- Positive integer.
Default value: `65536`.
6. materialized_postgresql_replication_slot {#materialized-postgresql-replication-slot}
A user-created replication slot. Must be used together with `materialized_postgresql_snapshot`.
7. materialized_postgresql_snapshot {#materialized-postgresql-snapshot}
A text string identifying a snapshot, from which [initial dump of PostgreSQL tables](../../engines/database-engines/materialized-postgresql.md) will be performed. Must be used together with `materialized_postgresql_replication_slot`.
``` sql
CREATE DATABASE postgresql_db
ENGINE = MaterializedPostgreSQL('postgres1:5432', 'postgres_database', 'postgres_user', 'postgres_password');
CREATE DATABASE database1
ENGINE = MaterializedPostgreSQL('postgres1:5432', 'postgres_database', 'postgres_user', 'postgres_password')
SETTINGS materialized_postgresql_tables_list = 'table1,table2,table3';
SELECT * FROM postgresql_db.postgres_table;
SELECT * FROM database1.table1;
```
The settings can be changed, if necessary, using a DDL query. But it is impossible to change the setting `materialized_postgresql_tables_list`. To update the list of tables in this setting use the `ATTACH TABLE` query.
``` sql
ALTER DATABASE postgres_database MODIFY SETTING materialized_postgresql_max_block_size = <new_size>;
```
## Notes {#notes}
@ -165,11 +203,11 @@ SELECT * FROM postgresql_db.postgres_table;
Logical Replication Slots which exist on the primary are not available on standby replicas.
So if there is a failover, new primary (the old physical standby) won’t be aware of any slots which were existing with old primary. This will lead to a broken replication from PostgreSQL.
A solution to this is to manage replication slots yourself and define a permanent replication slot (some information can be found [here](https://patroni.readthedocs.io/en/latest/SETTINGS.html)). You'll need to pass slot name via [materialized_postgresql_replication_slot](../../operations/settings/settings.md#materialized-postgresql-replication-slot) setting, and it has to be exported with `EXPORT SNAPSHOT` option. The snapshot identifier needs to be passed via [materialized_postgresql_snapshot](../../operations/settings/settings.md#materialized-postgresql-snapshot) setting.
A solution to this is to manage replication slots yourself and define a permanent replication slot (some information can be found [here](https://patroni.readthedocs.io/en/latest/SETTINGS.html)). You'll need to pass slot name via `materialized_postgresql_replication_slot` setting, and it has to be exported with `EXPORT SNAPSHOT` option. The snapshot identifier needs to be passed via `materialized_postgresql_snapshot` setting.
Please note that this should be used only if it is actually needed. If there is no real need for that or full understanding why, then it is better to allow the table engine to create and manage its own replication slot.
**Example (from [@bchrobot](https://github.com/bchrobot))**
**Example (from [@bchrobot](https://github.com/bchrobot))**
1. Configure replication slot in PostgreSQL.
@ -214,3 +252,23 @@ SETTINGS
```bash
kubectl exec acid-demo-cluster-0 -c postgres -- su postgres -c 'patronictl failover --candidate acid-demo-cluster-1 --force'
```
### Required permissions
1. [CREATE PUBLICATION](https://postgrespro.ru/docs/postgresql/14/sql-createpublication) -- create query privilege.
2. [CREATE_REPLICATION_SLOT](https://postgrespro.ru/docs/postgrespro/10/protocol-replication#PROTOCOL-REPLICATION-CREATE-SLOT) -- replication privelege.
3. [pg_drop_replication_slot](https://postgrespro.ru/docs/postgrespro/9.5/functions-admin#functions-replication) -- replication privilege or superuser.
4. [DROP PUBLICATION](https://postgrespro.ru/docs/postgresql/10/sql-droppublication) -- owner of publication (`username` in MaterializedPostgreSQL engine itself).
It is possible to avoid executing `2` and `3` commands and having those permissions. Use settings `materialized_postgresql_replication_slot` and `materialized_postgresql_snapshot`. But with much care.
Access to tables:
1. pg_publication
2. pg_replication_slots
3. pg_publication_tables

2
docs/en/engines/table-engines/integrations/hdfs.md
View File

@ -189,7 +189,7 @@ Similar to GraphiteMergeTree, the HDFS engine supports extended configuration us
|libhdfs3\_conf | "" |
### Limitations {#limitations}
* `hadoop_security_kerberos_ticket_cache_path` and `libhdfs3_conf` can be global only, not user specific
* `hadoop_security_kerberos_ticket_cache_path` and `libhdfs3_conf` can be global only, not user specific
## Kerberos support {#kerberos-support}

4
docs/en/engines/table-engines/integrations/materialized-postgresql.md
View File

@ -7,7 +7,7 @@ toc_title: MaterializedPostgreSQL
Creates ClickHouse table with an initial data dump of PostgreSQL table and starts replication process, i.e. executes background job to apply new changes as they happen on PostgreSQL table in the remote PostgreSQL database.
If more than one table is required, it is highly recommended to use the [MaterializedPostgreSQL](../../../engines/database-engines/materialized-postgresql.md) database engine instead of the table engine and use the [materialized_postgresql_tables_list](../../../operations/settings/settings.md#materialized-postgresql-tables-list) setting, which specifies the tables to be replicated. It will be much better in terms of CPU, fewer connections and fewer replication slots inside the remote PostgreSQL database.
If more than one table is required, it is highly recommended to use the [MaterializedPostgreSQL](../../../engines/database-engines/materialized-postgresql.md) database engine instead of the table engine and use the `materialized_postgresql_tables_list` setting, which specifies the tables to be replicated (will also be possible to add database `schema`). It will be much better in terms of CPU, fewer connections and fewer replication slots inside the remote PostgreSQL database.
## Creating a Table {#creating-a-table}
@ -38,7 +38,7 @@ PRIMARY KEY key;
- `_version` — Transaction counter. Type: [UInt64](../../../sql-reference/data-types/int-uint.md).
- `_sign` — Deletion mark. Type: [Int8](../../../sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `1` — Row is not deleted,
- `-1` — Row is deleted.
These columns do not need to be added when a table is created. They are always accessible in `SELECT` query.

25
docs/en/engines/table-engines/integrations/postgresql.md
View File

@ -36,6 +36,31 @@ The table structure can differ from the original PostgreSQL table structure:
- `schema` — Non-default table schema. Optional.
- `on conflict ...` — example: `ON CONFLICT DO NOTHING`. Optional. Note: adding this option will make insertion less efficient.
or via config (since version 21.11):
```
<named_collections>
<postgres1>
<host></host>
<port></port>
<username></username>
<password></password>
<table></table>
</postgres1>
<postgres2>
<host></host>
<port></port>
<username></username>
<password></password>
</postgres2>
</named_collections>
```
Some parameters can be overriden by key value arguments:
``` sql
SELECT * FROM postgresql(postgres1, schema='schema1', table='table1');
```
## Implementation Details {#implementation-details}
`SELECT` queries on PostgreSQL side run as `COPY (SELECT ...) TO STDOUT` inside read-only PostgreSQL transaction with commit after each `SELECT` query.

15
docs/en/faq/general/how-do-i-contribute-code-to-clickhouse.md Normal file
View File

@ -0,0 +1,15 @@
---
title: How do I contribute code to ClickHouse?
toc_hidden: true
toc_priority: 120
---
# How do I contribute code to ClickHouse? {#how-do-i-contribute-code-to-clickhouse}
ClickHouse is an open-source project [developed on GitHub](https://github.com/ClickHouse/ClickHouse).
As customary, contribution instructions are published in [CONTRIBUTING.md](https://github.com/ClickHouse/ClickHouse/blob/master/CONTRIBUTING.md) file in the root of the source code repository.
If you want to suggest a substantial change to ClickHouse, consider [opening a GitHub issue](https://github.com/ClickHouse/ClickHouse/issues/new/choose) explaining what you want to do, to discuss it with maintainers and community first. [Examples of such RFC issues](https://github.com/ClickHouse/ClickHouse/issues?q=is%3Aissue+is%3Aopen+rfc).
If your contributions are security related, please check out [our security policy](https://github.com/ClickHouse/ClickHouse/security/policy/) too.

1
docs/en/faq/general/index.md
View File

@ -17,6 +17,7 @@ Questions:
- [What is OLAP?](../../faq/general/olap.md)
- [What is a columnar database?](../../faq/general/columnar-database.md)
- [Why not use something like MapReduce?](../../faq/general/mapreduce.md)
- [How do I contribute code to ClickHouse?](../../faq/general/how-do-i-contribute-code-to-clickhouse.md)
!!! info "Don’t see what you were looking for?"
Check out [other F.A.Q. categories](../../faq/index.md) or browse around main documentation articles found in the left sidebar.

1
docs/en/faq/operations/index.md
View File

@ -11,6 +11,7 @@ Questions:
- [Which ClickHouse version to use in production?](../../faq/operations/production.md)
- [Is it possible to delete old records from a ClickHouse table?](../../faq/operations/delete-old-data.md)
- [Does ClickHouse support multi-region replication?](../../faq/operations/multi-region-replication.md)
!!! info "Don’t see what you were looking for?"
Check out [other F.A.Q. categories](../../faq/index.md) or browse around main documentation articles found in the left sidebar.

13
docs/en/faq/operations/multi-region-replication.md Normal file
View File

@ -0,0 +1,13 @@
---
title: Does ClickHouse support multi-region replication?
toc_hidden: true
toc_priority: 30
---
# Does ClickHouse support multi-region replication? {#does-clickhouse-support-multi-region-replication}
The short answer is "yes". However, we recommend keeping latency between all regions/datacenters in two-digit range, otherwise write performance will suffer as it goes through distributed consensus protocol. For example, replication between US coasts will likely work fine, but between the US and Europe won't.
Configuration-wise there's no difference compared to single-region replication, simply use hosts that are located in different locations for replicas.
For more information, see [full article on data replication](../../engines/table-engines/mergetree-family/replication.md).

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

@ -142,6 +142,12 @@ On Gentoo, you can just use `emerge clickhouse` to install ClickHouse from sourc
To start the server as a daemon, run:
``` bash
$ sudo clickhouse start
```
There are also another ways to run ClickHouse:
``` bash
$ sudo service clickhouse-server start
```
@ -152,6 +158,12 @@ If you do not have `service` command, run as
$ sudo /etc/init.d/clickhouse-server start
```
If you have `systemctl` command, run as
``` bash
$ sudo systemctl start clickhouse-server.service
```
See the logs in the `/var/log/clickhouse-server/` directory.
If the server does not start, check the configurations in the file `/etc/clickhouse-server/config.xml`.

18
docs/en/interfaces/http.md
View File

@ -424,7 +424,10 @@ Next are the configuration methods for different `type`.
`query` value is a predefined query of `predefined_query_handler`, which is executed by ClickHouse when an HTTP request is matched and the result of the query is returned. It is a must configuration.
The following example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_alter_threads` settings, then queries the system table to check whether these settings were set successfully.
The following example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_final_threads` settings, then queries the system table to check whether these settings were set successfully.
!!! note "Warning"
To keep the default `handlers` such as` query`, `play`,` ping`, use the `<defaults/>` rule.
Example:
@ -443,13 +446,14 @@ Example:
<query>SELECT name, value FROM system.settings WHERE name = {name_2:String}</query>
</handler>
</rule>
<defaults/>
</http_handlers>
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_alter_threads?max_threads=1&max_alter_threads=2'
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_final_threads?max_threads=1&max_final_threads=2'
1
max_alter_threads 2
max_final_threads 2
```
!!! note "caution"
@ -461,7 +465,7 @@ In `dynamic_query_handler`, the query is written in the form of param of the HTT
ClickHouse extracts and executes the value corresponding to the `query_param_name` value in the URL of the HTTP request. The default value of `query_param_name` is `/query` . It is an optional configuration. If there is no definition in the configuration file, the param is not passed in.
To experiment with this functionality, the example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_alter_threads` and `queries` whether the settings were set successfully.
To experiment with this functionality, the example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_final_threads` and `queries` whether the settings were set successfully.
Example:
@ -475,13 +479,14 @@ Example:
<query_param_name>query_param</query_param_name>
</handler>
</rule>
<defaults/>
</http_handlers>
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_alter_threads=2&param_name_1=max_threads&param_name_2=max_alter_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_final_threads=2&param_name_1=max_threads&param_name_2=max_final_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
max_threads 1
max_alter_threads 2
max_final_threads 2
```
### static {#static}
@ -505,6 +510,7 @@ Return a message.
<response_content>Say Hi!</response_content>
</handler>
</rule>
<defaults/>
</http_handlers>
```

2
docs/en/interfaces/third-party/client-libraries.md vendored
View File

@ -6,7 +6,7 @@ toc_title: Client Libraries
# Client Libraries from Third-party Developers {#client-libraries-from-third-party-developers}
!!! warning "Disclaimer"
Yandex does **not** maintain the libraries listed below and hasn’t done any extensive testing to ensure their quality.
ClickHouse Inc does **not** maintain the libraries listed below and hasn’t done any extensive testing to ensure their quality.
- Python
- [infi.clickhouse_orm](https://github.com/Infinidat/infi.clickhouse_orm)

20
docs/en/interfaces/third-party/gui.md vendored
View File

@ -220,4 +220,24 @@ SeekTable is [free](https://www.seektable.com/help/cloud-pricing) for personal/i
[Chadmin](https://github.com/bun4uk/chadmin) is a simple UI where you can visualize your currently running queries on your ClickHouse cluster and info about them and kill them if you want.
### TABLUM.IO {#tablum_io}
[TABLUM.IO](https://tablum.io/) — an online query and analytics tool for ETL and visualization. It allows connecting to ClickHouse, query data via a versatile SQL console as well as to load data from static files and 3rd party services. TABLUM.IO can visualize data results as charts and tables.
Features:
- ETL: data loading from popular databases, local and remote files, API invocations.
- Versatile SQL console with syntax highlight and visual query builder.
- Data visualization as charts and tables.
- Data materialization and sub-queries.
- Data reporting to Slack, Telegram or email.
- Data pipelining via proprietary API.
- Data export in JSON, CSV, SQL, HTML formats.
- Web-based interface.
TABLUM.IO can be run as a self-hosted solution (as a docker image) or in the cloud.
License: [commercial](https://tablum.io/pricing) product with 3-month free period.
Try it out for free [in the cloud](https://tablum.io/try).
Learn more about the product at [TABLUM.IO](https://tablum.io/)
[Original article](https://clickhouse.com/docs/en/interfaces/third-party/gui/) <!--hide-->

2
docs/en/introduction/adopters.md
View File

@ -87,7 +87,7 @@ toc_title: Adopters
| <a href="https://kontur.ru" class="favicon">Kontur</a> | Software Development | Metrics | — | — | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY) |
| <a href="https://www.kuaishou.com/" class="favicon">Kuaishou</a> | Video | — | — | — | [ClickHouse Meetup, October 2018](https://clickhouse.com/blog/en/2018/clickhouse-community-meetup-in-beijing-on-october-28-2018/) |
| <a href="https://www.kgk-global.com/en/" class="favicon">KGK Global</a> | Vehicle monitoring | — | — | — | [Press release, June 2021](https://zoom.cnews.ru/news/item/530921) |
| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a> | Research | Traffic analysis | 1 server | 11.8 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) |
| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a> | Research | Traffic analysis | 5 servers | 55 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) |
| <a href="https://lifestreet.com/" class="favicon">LifeStreet</a> | Ad network | Main product | 75 servers (3 replicas) | 5.27 PiB | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/) |
| <a href="https://mcs.mail.ru/" class="favicon">Mail.ru Cloud Solutions</a> | Cloud services | Main product | — | — | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#) |
| <a href="https://maxilect.com/" class="favicon">MAXILECT</a> | Ad Tech, Blockchain, ML, AI | — | — | — | [Job advertisement, 2021](https://www.linkedin.com/feed/update/urn:li:activity:6780842017229430784/) |

13
docs/en/operations/clickhouse-keeper.md
View File

@ -3,14 +3,14 @@ toc_priority: 66
toc_title: ClickHouse Keeper
---
# [pre-production] ClickHouse Keeper
# [pre-production] ClickHouse Keeper {#clickHouse-keeper}
ClickHouse server uses [ZooKeeper](https://zookeeper.apache.org/) coordination system for data [replication](../engines/table-engines/mergetree-family/replication.md) and [distributed DDL](../sql-reference/distributed-ddl.md) queries execution. ClickHouse Keeper is an alternative coordination system compatible with ZooKeeper.
!!! warning "Warning"
This feature is currently in the pre-production stage. We test it in our CI and on small internal installations.
## Implementation details
## Implementation details {#implementation-details}
ZooKeeper is one of the first well-known open-source coordination systems. It's implemented in Java, has quite a simple and powerful data model. ZooKeeper's coordination algorithm called ZAB (ZooKeeper Atomic Broadcast) doesn't provide linearizability guarantees for reads, because each ZooKeeper node serves reads locally. Unlike ZooKeeper ClickHouse Keeper is written in C++ and uses [RAFT algorithm](https://raft.github.io/) [implementation](https://github.com/eBay/NuRaft). This algorithm allows to have linearizability for reads and writes, has several open-source implementations in different languages.
@ -21,7 +21,7 @@ ClickHouse Keeper supports Access Control List (ACL) the same way as [ZooKeeper]
!!! info "Note"
External integrations are not supported.
## Configuration
## Configuration {#configuration}
ClickHouse Keeper can be used as a standalone replacement for ZooKeeper or as an internal part of the ClickHouse server, but in both cases configuration is almost the same `.xml` file. The main ClickHouse Keeper configuration tag is `<keeper_server>`. Keeper configuration has the following parameters:
@ -102,7 +102,7 @@ Examples of configuration for quorum with three nodes can be found in [integrati
</keeper_server>
```
## How to run
## How to run {#how-to-run}
ClickHouse Keeper is bundled into the ClickHouse server package, just add configuration of `<keeper_server>` and start ClickHouse server as always. If you want to run standalone ClickHouse Keeper you can start it in a similar way with:
@ -110,13 +110,14 @@ ClickHouse Keeper is bundled into the ClickHouse server package, just add config
clickhouse-keeper --config /etc/your_path_to_config/config.xml --daemon
```
## Four Letter Word Commands
## Four Letter Word Commands {#four-letter-word-commands}
ClickHouse Keeper also provides 4lw commands which are almost the same with Zookeeper. Each command is composed of four letters such as `mntr`, `stat` etc. There are some more interesting commands: `stat` gives some general information about the server and connected clients, while `srvr` and `cons` give extended details on server and connections respectively.
The 4lw commands has a white list configuration `four_letter_word_white_list` which has default value "conf,cons,crst,envi,ruok,srst,srvr,stat,wchc,wchs,dirs,mntr,isro".
You can issue the commands to ClickHouse Keeper via telnet or nc, at the client port.
```
echo mntr | nc localhost 9181
```
@ -296,7 +297,7 @@ Sessions with Ephemerals (1):
/clickhouse/task_queue/ddl
```
## [experimental] Migration from ZooKeeper
## [experimental] Migration from ZooKeeper {#migration-from-zookeeper}
Seamlessly migration from ZooKeeper to ClickHouse Keeper is impossible you have to stop your ZooKeeper cluster, convert data and start ClickHouse Keeper. `clickhouse-keeper-converter` tool allows converting ZooKeeper logs and snapshots to ClickHouse Keeper snapshot. It works only with ZooKeeper > 3.4. Steps for migration:

6
docs/en/operations/external-authenticators/kerberos.md
View File

@ -14,11 +14,11 @@ To enable Kerberos, one should include `kerberos` section in `config.xml`. This
#### Parameters:
- `principal` - canonical service principal name that will be acquired and used when accepting security contexts.
- This parameter is optional, if omitted, the default principal will be used.
- This parameter is optional, if omitted, the default principal will be used.
- `realm` - a realm, that will be used to restrict authentication to only those requests whose initiator's realm matches it.
- This parameter is optional, if omitted, no additional filtering by realm will be applied.
- This parameter is optional, if omitted, no additional filtering by realm will be applied.
Example (goes into `config.xml`):
@ -75,7 +75,7 @@ In order to enable Kerberos authentication for the user, specify `kerberos` sect
Parameters:
- `realm` - a realm that will be used to restrict authentication to only those requests whose initiator's realm matches it.
- This parameter is optional, if omitted, no additional filtering by realm will be applied.
- This parameter is optional, if omitted, no additional filtering by realm will be applied.
Example (goes into `users.xml`):

85
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -435,26 +435,58 @@ Similar to `interserver_http_host`, except that this hostname can be used by oth
## interserver_http_credentials {#server-settings-interserver-http-credentials}
The username and password used to authenticate during [replication](../../engines/table-engines/mergetree-family/replication.md) with the Replicated\* engines. These credentials are used only for communication between replicas and are unrelated to credentials for ClickHouse clients. The server is checking these credentials for connecting replicas and use the same credentials when connecting to other replicas. So, these credentials should be set the same for all replicas in a cluster.
By default, the authentication is not used.
A username and a password used to connect to other servers during [replication](../../engines/table-engines/mergetree-family/replication.md). Also the server authenticates other replicas using these credentials. So, `interserver_http_credentials` must be the same for all replicas in a cluster.
By default, if `interserver_http_credentials` section is omitted, authentication is not used during replication.
!!! note "Note"
These credentials are common for replication through `HTTP` and `HTTPS`.
`interserver_http_credentials` settings do not relate to a ClickHouse client credentials [configuration](../../interfaces/cli.md#configuration_files).
This section contains the following parameters:
!!! note "Note"
These credentials are common for replication via `HTTP` and `HTTPS`.
- `user` — username.
- `password` — password.
The section contains the following parameters:
**Example**
- `user` — Username.
- `password` — Password.
- `allow_empty` — If `true`, then other replicas are allowed to connect without authentication even if credentials are set. If `false`, then connections without authentication are refused. Default value: `false`.
- `old` — Contains old `user` and `password` used during credential rotation. Several `old` sections can be specified.
**Credentials Rotation**
ClickHouse supports dynamic interserver credentials rotation without stopping all replicas at the same time to update their configuration. Credentials can be changed in several steps.
To enable authentication, set `interserver_http_credentials.allow_empty` to `true` and add credentials. This allows connections with authentication and without it.
``` xml
<interserver_http_credentials>
<user>admin</user>
<password>111</password>
<allow_empty>true</allow_empty>
</interserver_http_credentials>
```
After configuring all replicas set `allow_empty` to `false` or remove this setting. It makes authentication with new credentials mandatory.
To change existing credentials, move the username and the password to `interserver_http_credentials.old` section and update `user` and `password` with new values. At this point the server uses new credentials to connect to other replicas and accepts connections with either new or old credentials.
``` xml
<interserver_http_credentials>
<user>admin</user>
<password>222</password>
<old>
<user>admin</user>
<password>111</password>
</old>
<old>
<user>temp</user>
<password>000</password>
</old>
</interserver_http_credentials>
```
When new credentials are applied to all replicas, old credentials may be removed.
## keep_alive_timeout {#keep-alive-timeout}
The number of seconds that ClickHouse waits for incoming requests before closing the connection. Defaults to 10 seconds.
@ -640,7 +672,8 @@ On hosts with low RAM and swap, you possibly need setting `max_server_memory_usa
## max_concurrent_queries {#max-concurrent-queries}
The maximum number of simultaneously processed queries related to MergeTree table. Queries may be limited by other settings: [max_concurrent_queries_for_user](#max-concurrent-queries-for-user), [max_concurrent_queries_for_all_users](#max-concurrent-queries-for-all-users), [min_marks_to_honor_max_concurrent_queries](#min-marks-to-honor-max-concurrent-queries).
The maximum number of simultaneously processed queries related to MergeTree table.
Queries may be limited by other settings: [max_concurrent_insert_queries](#max-concurrent-insert-queries), [max_concurrent_select_queries](#max-concurrent-select-queries), [max_concurrent_queries_for_user](#max-concurrent-queries-for-user), [max_concurrent_queries_for_all_users](#max-concurrent-queries-for-all-users), [min_marks_to_honor_max_concurrent_queries](#min-marks-to-honor-max-concurrent-queries).
!!! info "Note"
These settings can be modified at runtime and will take effect immediately. Queries that are already running will remain unchanged.
@ -656,6 +689,42 @@ Possible values:
<max_concurrent_queries>100</max_concurrent_queries>
```
## max_concurrent_insert_queries {#max-concurrent-insert-queries}
The maximum number of simultaneously processed insert queries.
!!! info "Note"
These settings can be modified at runtime and will take effect immediately. Queries that are already running will remain unchanged.
Possible values:
- Positive integer.
- 0 — Disabled.
**Example**
``` xml
<max_concurrent_insert_queries>100</max_concurrent_insert_queries>
```
## max_concurrent_select_queries {#max-concurrent-select-queries}
The maximum number of simultaneously processed select queries.
!!! info "Note"
These settings can be modified at runtime and will take effect immediately. Queries that are already running will remain unchanged.
Possible values:
- Positive integer.
- 0 — Disabled.
**Example**
``` xml
<max_concurrent_select_queries>100</max_concurrent_select_queries>
```
## max_concurrent_queries_for_user {#max-concurrent-queries-for-user}
The maximum number of simultaneously processed queries related to MergeTree table per user.

87
docs/en/operations/settings/settings.md
View File

@ -817,9 +817,19 @@ If the number of rows to be read from a file of a [MergeTree](../../engines/tabl
Possible values:
- Any positive integer.
- Positive integer.
Default value: 163840.
Default value: `163840`.
## merge_tree_min_rows_for_concurrent_read_for_remote_filesystem {#merge-tree-min-rows-for-concurrent-read-for-remote-filesystem}
The minimum number of lines to read from one file before [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) engine can parallelize reading, when reading from remote filesystem.
Possible values:
- Positive integer.
Default value: `163840`.
## merge_tree_min_bytes_for_concurrent_read {#setting-merge-tree-min-bytes-for-concurrent-read}
@ -827,9 +837,19 @@ If the number of bytes to read from one file of a [MergeTree](../../engines/tabl
Possible value:
- Any positive integer.
- Positive integer.
Default value: 251658240.
Default value: `251658240`.
## merge_tree_min_bytes_for_concurrent_read_for_remote_filesystem {#merge-tree-min-bytes-for-concurrent-read-for-remote-filesystem}
The minimum number of bytes to read from one file before [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) engine can parallelize reading, when reading from remote filesystem.
Possible values:
- Positive integer.
Default value: `251658240`.
## merge_tree_min_rows_for_seek {#setting-merge-tree-min-rows-for-seek}
@ -1469,7 +1489,7 @@ Possible values:
Default value: `1`.
**See Also**
**See Also**
- [min_count_to_compile_aggregate_expression](#min_count_to_compile_aggregate_expression)
@ -2095,7 +2115,7 @@ Possible values:
- 0 — Optimization disabled.
- 1 — Optimization enabled.
Default value: `1`.
See also:
@ -3134,6 +3154,12 @@ Possible values:
Default value: `0`.
!!! warning "Warning"
Nullable primary key usually indicates bad design. It is forbidden in almost all main stream DBMS. The feature is mainly for [AggregatingMergeTree](../../engines/table-engines/mergetree-family/aggregatingmergetree.md) and is not heavily tested. Use with care.
!!! warning "Warning"
Do not enable this feature in version `<= 21.8`. It's not properly implemented and may lead to server crash.
## aggregate_functions_null_for_empty {#aggregate_functions_null_for_empty}
Enables or disables rewriting all aggregate functions in a query, adding [-OrNull](../../sql-reference/aggregate-functions/combinators.md#agg-functions-combinator-ornull) suffix to them. Enable it for SQL standard compatibility.
@ -3682,49 +3708,6 @@ Possible values:
Default value: `0`.
## materialized_postgresql_max_block_size {#materialized-postgresql-max-block-size}
Sets the number of rows collected in memory before flushing data into PostgreSQL database table.
Possible values:
- Positive integer.
Default value: `65536`.
## materialized_postgresql_tables_list {#materialized-postgresql-tables-list}
Sets a comma-separated list of PostgreSQL database tables, which will be replicated via [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md) database engine.
Default value: empty list — means whole PostgreSQL database will be replicated.
## materialized_postgresql_schema {#materialized-postgresql-schema}
Default value: empty string. (Default schema is used)
## materialized_postgresql_schema_list {#materialized-postgresql-schema-list}
Default value: empty list. (Default schema is used)
## materialized_postgresql_allow_automatic_update {#materialized-postgresql-allow-automatic-update}
Allows reloading table in the background, when schema changes are detected. DDL queries on the PostgreSQL side are not replicated via ClickHouse [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md) engine, because it is not allowed with PostgreSQL logical replication protocol, but the fact of DDL changes is detected transactionally. In this case, the default behaviour is to stop replicating those tables once DDL is detected. However, if this setting is enabled, then, instead of stopping the replication of those tables, they will be reloaded in the background via database snapshot without data losses and replication will continue for them.
Possible values:
- 0 — The table is not automatically updated in the background, when schema changes are detected.
- 1 — The table is automatically updated in the background, when schema changes are detected.
Default value: `0`.
## materialized_postgresql_replication_slot {#materialized-postgresql-replication-slot}
A user-created replication slot. Must be used together with [materialized_postgresql_snapshot](#materialized-postgresql-snapshot).
## materialized_postgresql_snapshot {#materialized-postgresql-snapshot}
A text string identifying a snapshot, from which [initial dump of PostgreSQL tables](../../engines/database-engines/materialized-postgresql.md) will be performed. Must be used together with [materialized_postgresql_replication_slot](#materialized-postgresql-replication-slot).
## allow_experimental_projection_optimization {#allow-experimental-projection-optimization}
Enables or disables [projection](../../engines/table-engines/mergetree-family/mergetree.md#projections) optimization when processing `SELECT` queries.
@ -3993,8 +3976,8 @@ If [wait_for_async_insert](#wait-for-async-insert) is enabled, every client will
Possible values:
- 0 — Insertions are made synchronously, one after another.
- 1 — Multiple asynchronous insertions enabled.
- 0 — Insertions are made synchronously, one after another.
- 1 — Multiple asynchronous insertions enabled.
Default value: `0`.
@ -4066,7 +4049,7 @@ Default value: `0`.
## alter_partition_verbose_result {#alter-partition-verbose-result}
Enables or disables the display of information about the parts to which the manipulation operations with partitions and parts have been successfully applied.
Enables or disables the display of information about the parts to which the manipulation operations with partitions and parts have been successfully applied.
Applicable to [ATTACH PARTITION|PART](../../sql-reference/statements/alter/partition.md#alter_attach-partition) and to [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md#alter_freeze-partition).
Possible values:

19
docs/en/operations/system-tables/columns.md
View File

@ -6,7 +6,7 @@ You can use this table to get information similar to the [DESCRIBE TABLE](../../
Columns from [temporary tables](../../sql-reference/statements/create/table.md#temporary-tables) are visible in the `system.columns` only in those session where they have been created. They are shown with the empty `database` field.
Columns:
The `system.columns` table contains the following columns (the column type is shown in brackets):
- `database` ([String](../../sql-reference/data-types/string.md)) — Database name.
- `table` ([String](../../sql-reference/data-types/string.md)) — Table name.
@ -86,21 +86,4 @@ numeric_scale: ᴺᵁᴸᴸ
datetime_precision: ᴺᵁᴸᴸ
```
The `system.columns` table contains the following columns (the column type is shown in brackets):
- `database` (String) — Database name.
- `table` (String) — Table name.
- `name` (String) — Column name.
- `type` (String) — Column type.
- `default_kind` (String) — Expression type (`DEFAULT`, `MATERIALIZED`, `ALIAS`) for the default value, or an empty string if it is not defined.
- `default_expression` (String) — Expression for the default value, or an empty string if it is not defined.
- `data_compressed_bytes` (UInt64) — The size of compressed data, in bytes.
- `data_uncompressed_bytes` (UInt64) — The size of decompressed data, in bytes.
- `marks_bytes` (UInt64) — The size of marks, in bytes.
- `comment` (String) — Comment on the column, or an empty string if it is not defined.
- `is_in_partition_key` (UInt8) — Flag that indicates whether the column is in the partition expression.
- `is_in_sorting_key` (UInt8) — Flag that indicates whether the column is in the sorting key expression.
- `is_in_primary_key` (UInt8) — Flag that indicates whether the column is in the primary key expression.
- `is_in_sampling_key` (UInt8) — Flag that indicates whether the column is in the sampling key expression.
[Original article](https://clickhouse.com/docs/en/operations/system-tables/columns) <!--hide-->

2
docs/en/operations/system-tables/metrics.md
View File

@ -35,7 +35,7 @@ SELECT * FROM system.metrics LIMIT 10
- [system.asynchronous_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.
- [system.events](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that occurred.
- [system.metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` и `system.events`.
- [system.metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` and `system.events`.
- [Monitoring](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.
[Original article](https://clickhouse.com/docs/en/operations/system-tables/metrics) <!--hide-->

4
docs/en/sql-reference/aggregate-functions/reference/uniq.md
View File

@ -24,9 +24,7 @@ Function:
- Calculates a hash for all parameters in the aggregate, then uses it in calculations.
- Uses an adaptive sampling algorithm. For the calculation state, the function uses a sample of element hash values up to 65536.
This algorithm is very accurate and very efficient on the CPU. When the query contains several of these functions, using `uniq` is almost as fast as using other aggregate functions.
- Uses an adaptive sampling algorithm. For the calculation state, the function uses a sample of element hash values up to 65536. This algorithm is very accurate and very efficient on the CPU. When the query contains several of these functions, using `uniq` is almost as fast as using other aggregate functions.
- Provides the result deterministically (it does not depend on the query processing order).

4
docs/en/sql-reference/data-types/aggregatefunction.md
View File

@ -11,9 +11,7 @@ Aggregate functions can have an implementation-defined intermediate state that c
**Parameters**
- Name of the aggregate function.
If the function is parametric, specify its parameters too.
- Name of the aggregate function. If the function is parametric, specify its parameters too.
- Types of the aggregate function arguments.

13
docs/en/sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md
View File

@ -122,7 +122,12 @@ Setting fields:
- `command` — The absolute path to the executable file, or the file name (if the program directory is written to `PATH`).
- `format` — The file format. All the formats described in [Formats](../../../interfaces/formats.md#formats) are supported.
- `command_termination_timeout` — executable script should contain main read-write loop. After dictionary is destroyed, pipe is closed, and executable file will have `command_termination_timeout` seconds to shutdown, before ClickHouse will send SIGTERM signal to child process. Specified in seconds. Default value is 10. Optional parameter.
- `command_read_timeout` - timeout for reading data from command stdout in milliseconds. Default value 10000. Optional parameter.
- `command_read_timeout` - timeout for writing data to command stdin in milliseconds. Default value 10000. Optional parameter.
- `implicit_key` — The executable source file can return only values, and the correspondence to the requested keys is determined implicitly — by the order of rows in the result. Default value is false.
- `execute_direct` - Executable source file will be searched inside `user_scripts` folder and executed directly. Arguments are passed using spaces. Example: `test_script arg_1 arg_2`. Default value is false. Optional parameter.
- `send_chunk_header` - controls whether to send row count before sending a chunk of data to process. Optional. Default value is `false`.
That dictionary source can be configured only via XML configuration. Creating dictionaries with executable source via DDL is disabled, otherwise, the DB user would be able to execute arbitrary binary on ClickHouse node.
@ -150,10 +155,14 @@ Setting fields:
- `command` — The absolute path to the executable file, or the file name (if the program directory is written to `PATH`).
- `format` — The file format. All the formats described in “[Formats](../../../interfaces/formats.md#formats)” are supported.
- `pool_size` — Size of pool. If 0 is specified as `pool_size` then there is no pool size restrictions.
- `command_termination_timeout` — Executable pool script should contain main read-write loop. After dictionary is destroyed, pipe is closed, and executable file will have `command_termination_timeout` seconds to shutdown, before ClickHouse will send SIGTERM signal to child process. Specified in seconds. Default value is 10. Optional parameter.
- `pool_size` — Size of pool. If 0 is specified as `pool_size` then there is no pool size restrictions. Default value is `16`.
- `command_termination_timeout` — executable script should contain main read-write loop. After dictionary is destroyed, pipe is closed, and executable file will have `command_termination_timeout` seconds to shutdown, before ClickHouse will send SIGTERM signal to child process. Specified in seconds. Default value is 10. Optional parameter.
- `max_command_execution_time` — Maximum executable script command execution time for processing block of data. Specified in seconds. Default value is 10. Optional parameter.
- `command_read_timeout` - timeout for reading data from command stdout in milliseconds. Default value 10000. Optional parameter.
- `command_read_timeout` - timeout for writing data to command stdin in milliseconds. Default value 10000. Optional parameter.
- `implicit_key` — The executable source file can return only values, and the correspondence to the requested keys is determined implicitly — by the order of rows in the result. Default value is false. Optional parameter.
- `execute_direct` - Executable source file will be searched inside `user_scripts` folder and executed directly. Additional arguments can be specified. Example: `test_script arg_1 arg_2`. Default value is false. Optional parameter.
- `send_chunk_header` - controls whether to send row count before sending a chunk of data to process. Optional. Default value is `false`.
That dictionary source can be configured only via XML configuration. Creating dictionaries with executable source via DDL is disabled, otherwise, the DB user would be able to execute arbitrary binary on ClickHouse node.

10
docs/en/sql-reference/functions/index.md
View File

@ -73,16 +73,19 @@ User defined function configurations are searched relative to the path specified
A function configuration contains the following settings:
- `name` - a function name.
- `command` - a command or a script to execute.
- `command` - script name to execute or command if `execute_direct` is false.
- `argument` - argument description with the `type` of an argument. Each argument is described in a separate setting.
- `format` - a [format](../../interfaces/formats.md) in which arguments are passed to the command.
- `return_type` - the type of a returned value.
- `type` - an executable type. If `type` is set to `executable` then single command is started. If it is set to `executable_pool` then a pool of commands is created.
- `max_command_execution_time` - maximum execution time in seconds for processing block of data. This setting is valid for `executable_pool` commands only. Optional. Default value is `10`.
- `command_termination_timeout` - time in seconds during which a command should finish after its pipe is closed. After that time `SIGTERM` is sent to the process executing the command. This setting is valid for `executable_pool` commands only. Optional. Default value is `10`.
- `command_termination_timeout` - time in seconds during which a command should finish after its pipe is closed. After that time `SIGTERM` is sent to the process executing the command. Optional. Default value is `10`.
- `command_read_timeout` - timeout for reading data from command stdout in milliseconds. Default value 10000. Optional parameter.
- `command_read_timeout` - timeout for writing data to command stdin in milliseconds. Default value 10000. Optional parameter.
- `pool_size` - the size of a command pool. Optional. Default value is `16`.
- `lifetime` - the reload interval of a function in seconds. If it is set to `0` then the function is not reloaded.
- `send_chunk_header` - controls whether to send row count before sending a chunk of data to process. Optional. Default value is `false`.
- `execute_direct` - Executable source file will be searched inside `user_scripts` folder and executed directly. Additional arguments can be specified. Example: `test_script arg_1 arg_2`. Default value is true. Optional parameter.
- `lifetime` - the reload interval of a function in seconds. If it is set to `0` then the function is not reloaded. Default value is `0`. Optional parameter.
The command must read arguments from `STDIN` and must output the result to `STDOUT`. The command must process arguments iteratively. That is after processing a chunk of arguments it must wait for the next chunk.
@ -102,7 +105,6 @@ Creating `test_function` using XML configuration:
</argument>
<format>TabSeparated</format>
<command>cd /; clickhouse-local --input-format TabSeparated --output-format TabSeparated --structure 'x UInt64, y UInt64' --query "SELECT x + y FROM table"</command>
<lifetime>0</lifetime>
</function>
</functions>
```

4
docs/en/sql-reference/statements/grant.md
View File

@ -21,7 +21,7 @@ GRANT [ON CLUSTER cluster_name] privilege[(column_name [,...])] [,...] ON {db.ta
- `user` — ClickHouse user account.
The `WITH GRANT OPTION` clause grants `user` or `role` with permission to execute the `GRANT` query. Users can grant privileges of the same scope they have and less.
The `WITH REPLACE OPTION` clause replace old privileges by new privileges for the `user` or `role`, if not specified it is append privileges.
The `WITH REPLACE OPTION` clause replace old privileges by new privileges for the `user` or `role`, if is not specified it appends privileges.
## Assigning Role Syntax {#assign-role-syntax}
@ -33,7 +33,7 @@ GRANT [ON CLUSTER cluster_name] role [,...] TO {user | another_role | CURRENT_US
- `user` — ClickHouse user account.
The `WITH ADMIN OPTION` clause grants [ADMIN OPTION](#admin-option-privilege) privilege to `user` or `role`.
The `WITH REPLACE OPTION` clause replace old roles by new role for the `user` or `role`, if not specified it is append roles.
The `WITH REPLACE OPTION` clause replace old roles by new role for the `user` or `role`, if is not specified it appends roles.
## Usage {#grant-usage}

48
docs/en/sql-reference/statements/select/join.md
View File

@ -55,13 +55,13 @@ The behavior of ClickHouse server for `ANY JOIN` operations depends on the [any_
- [join_on_disk_max_files_to_merge](../../../operations/settings/settings.md#join_on_disk_max_files_to_merge)
- [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys)
## ON Section Conditions {on-section-conditions}
## ON Section Conditions {#on-section-conditions}
An `ON` section can contain several conditions combined using the `AND` and `OR` operators. Conditions specifying join keys must refer both left and right tables and must use the equality operator. Other conditions may use other logical operators but they must refer either the left or the right table of a query.
An `ON` section can contain several conditions combined using the `AND` operator. Conditions specifying join keys must refer both left and right tables and must use the equality operator. Other conditions may use other logical operators but they must refer either the left or the right table of a query.
Rows are joined if the whole complex condition is met. If the conditions are not met, still rows may be included in the result depending on the `JOIN` type. Note that if the same conditions are placed in a `WHERE` section and they are not met, then rows are always filtered out from the result.
!!! note "Note"
The `OR` operator inside an `ON` section is not supported yet.
The `OR` operator inside the `ON` clause works using the hash join algorithm — for each `OR` argument with join keys for `JOIN`, a separate hash table is created, so memory consumption and query execution time grow linearly with an increase in the number of expressions `OR` of the `ON` clause.
!!! note "Note"
If a condition refers columns from different tables, then only the equality operator (`=`) is supported so far.
@ -109,7 +109,47 @@ Result:
│ B │ Text B │ 15 │
└──────┴────────┴────────┘
```
Query with `INNER` type of a join and condition with `OR`:
``` sql
CREATE TABLE t1 (`a` Int64, `b` Int64) ENGINE = MergeTree() ORDER BY a;
CREATE TABLE t2 (`key` Int32, `val` Int64) ENGINE = MergeTree() ORDER BY key;
INSERT INTO t1 SELECT number as a, -a as b from numbers(5);
INSERT INTO t2 SELECT if(number % 2 == 0, toInt64(number), -number) as key, number as val from numbers(5);
SELECT a, b, val FROM t1 INNER JOIN t2 ON t1.a = t2.key OR t1.b = t2.key;
```
Result:
```
┌─a─┬──b─┬─val─┐
│ 0 │ 0 │ 0 │
│ 1 │ -1 │ 1 │
│ 2 │ -2 │ 2 │
│ 3 │ -3 │ 3 │
│ 4 │ -4 │ 4 │
└───┴────┴─────┘
```
Query with `INNER` type of a join and conditions with `OR` and `AND`:
``` sql
SELECT a, b, val FROM t1 INNER JOIN t2 ON t1.a = t2.key OR t1.b = t2.key AND t2.val > 3;
```
Result:
```
┌─a─┬──b─┬─val─┐
│ 0 │ 0 │ 0 │
│ 2 │ -2 │ 2 │
│ 4 │ -4 │ 4 │
└───┴────┴─────┘
```
## ASOF JOIN Usage {#asof-join-usage}
`ASOF JOIN` is useful when you need to join records that have no exact match.

58
docs/en/sql-reference/table-functions/hdfsCluster.md Normal file
View File

@ -0,0 +1,58 @@
---
toc_priority: 55
toc_title: hdfsCluster
---
# hdfsCluster Table Function {#hdfsCluster-table-function}
Allows processing files from HDFS in parallel from many nodes in a specified cluster. On initiator it creates a connection to all nodes in the cluster, discloses asterics in HDFS file path, and dispatches each file dynamically. On the worker node it asks the initiator about the next task to process and processes it. This is repeated until all tasks are finished.
**Syntax**
``` sql
hdfsCluster(cluster_name, URI, format, structure)
```
**Arguments**
- `cluster_name` — Name of a cluster that is used to build a set of addresses and connection parameters to remote and local servers.
- `URI` — URI to a file or a bunch of files. Supports following wildcards in readonly mode: `*`, `?`, `{'abc','def'}` and `{N..M}` where `N`, `M` — numbers, `abc`, `def` — strings. For more information see [Wildcards In Path](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
**Returned value**
A table with the specified structure for reading data in the specified file.
**Examples**
1. Suppose that we have a ClickHouse cluster named `cluster_simple`, and several files with following URIs on HDFS:
- ‘hdfs://hdfs1:9000/some_dir/some_file_1’
- ‘hdfs://hdfs1:9000/some_dir/some_file_2’
- ‘hdfs://hdfs1:9000/some_dir/some_file_3’
- ‘hdfs://hdfs1:9000/another_dir/some_file_1’
- ‘hdfs://hdfs1:9000/another_dir/some_file_2’
- ‘hdfs://hdfs1:9000/another_dir/some_file_3’
2. Query the amount of rows in these files:
``` sql
SELECT count(*)
FROM hdfsCluster('cluster_simple', 'hdfs://hdfs1:9000/{some,another}_dir/some_file_{1..3}', 'TSV', 'name String, value UInt32')
```
3. Query the amount of rows in all files of these two directories:
``` sql
SELECT count(*)
FROM hdfsCluster('cluster_simple', 'hdfs://hdfs1:9000/{some,another}_dir/*', 'TSV', 'name String, value UInt32')
```
!!! warning "Warning"
If your listing of files contains number ranges with leading zeros, use the construction with braces for each digit separately or use `?`.
**See Also**
- [HDFS engine](../../engines/table-engines/integrations/hdfs.md)
- [HDFS table function](../../sql-reference/table-functions/hdfs.md)

1
docs/ja/faq/general/how-do-i-contribute-code-to-clickhouse.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/general/how-do-i-contribute-code-to-clickhouse.md

1
docs/ja/faq/operations/multi-region-replication.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/operations/multi-region-replication.md

10
docs/ja/getting-started/example-datasets/ontime.md
View File

@ -15,13 +15,7 @@ toc_title: OnTime
データのダウンロード:
``` bash
for s in `seq 1987 2018`
do
for m in `seq 1 12`
do
wget https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_${s}_${m}.zip
done
done
wget --no-check-certificate --continue https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_{1987..2021}_{1..12}.zip
```
（https://github.com/Percona-Lab/ontime-airline-performance/blob/master/download.sh より)
@ -40,7 +34,7 @@ CREATE TABLE `ontime`
`Reporting_Airline` String,
`DOT_ID_Reporting_Airline` Int32,
`IATA_CODE_Reporting_Airline` String,
`Tail_Number` Int32,
`Tail_Number` String,
`Flight_Number_Reporting_Airline` String,
`OriginAirportID` Int32,
`OriginAirportSeqID` Int32,

12
docs/ja/interfaces/http.md
View File

@ -397,7 +397,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
`<query>` 値は以下の定義済みクエリです `<predefined_query_handler>` これは、Http要求が一致し、クエリの結果が返されたときにClickHouseによって実行されます。 これは必須構成です。
次の例では、次の値を定義します `max_threads` と `max_alter_threads` 設定、そしてクエリのテーブルから設定設定します。
次の例では、次の値を定義します `max_threads` と `max_final_threads` 設定、そしてクエリのテーブルから設定設定します。
例:
@ -420,9 +420,9 @@ $ curl -v 'http://localhost:8123/predefined_query'
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_alter_threads?max_threads=1&max_alter_threads=2'
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_final_threads?max_threads=1&max_final_threads=2'
1
max_alter_threads 2
max_final_threads 2
```
!!! note "注意"
@ -434,7 +434,7 @@ max_alter_threads 2
クリックハウスは、 `<query_param_name>` HTTP要求のurlの値。 のデフォルト値 `<query_param_name>` は `/query` . これはオプションの構成です。 設定ファイルに定義がない場合、paramは渡されません。
この機能を試すために、この例ではmax_threadsとmax_alter_threadsの値を定義し、設定が正常に設定されたかどうかを照会します。
この機能を試すために、この例ではmax_threadsとmax_final_threadsの値を定義し、設定が正常に設定されたかどうかを照会します。
例:
@ -452,9 +452,9 @@ max_alter_threads 2
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_alter_threads=2&param_name_1=max_threads&param_name_2=max_alter_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_final_threads=2&param_name_1=max_threads&param_name_2=max_final_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
max_threads 1
max_alter_threads 2
max_final_threads 2
```
## 静的 {#static}

2
docs/ru/development/developer-instruction.md
View File

@ -40,7 +40,7 @@ ClickHouse не работает и не собирается на 32-битны
Выполните в терминале:
git clone git@github.com:ClickHouse/ClickHouse.git
git clone git@github.com:your_github_username/ClickHouse.git
cd ClickHouse
Замените первое вхождение слова `ClickHouse` в команде для git на имя вашего аккаунта на GitHub.

34
docs/ru/engines/table-engines/integrations/hdfs.md
View File

@ -5,7 +5,7 @@ toc_title: HDFS
# HDFS {#table_engines-hdfs}
Управляет данными в HDFS. Данный движок похож на движки [File](../special/file.md#table_engines-file) и [URL](../special/url.md#table_engines-url).
Этот движок обеспечивает интеграцию с экосистемой [Apache Hadoop](https://ru.wikipedia.org/wiki/Hadoop), позволяя управлять данными в HDFS посредством ClickHouse. Данный движок похож на движки [File](../special/file.md#table_engines-file) и [URL](../special/url.md#table_engines-url), но предоставляет возможности, характерные для Hadoop.
## Использование движка {#usage}
@ -13,9 +13,11 @@ toc_title: HDFS
ENGINE = HDFS(URI, format)
```
В параметр `URI` нужно передавать полный URI файла в HDFS.
**Параметры движка**
В параметр `URI` нужно передавать полный URI файла в HDFS. Часть URI с путем файла может содержать шаблоны. В этом случае таблица может использоваться только для чтения.
Параметр `format` должен быть таким, который ClickHouse может использовать и в запросах `INSERT`, и в запросах `SELECT`. Полный список поддерживаемых форматов смотрите в разделе [Форматы](../../../interfaces/formats.md#formats).
Часть URI с путем файла может содержать шаблоны. В этом случае таблица может использоваться только для чтения.
**Пример:**
@ -67,12 +69,12 @@ SELECT * FROM hdfs_engine_table LIMIT 2
1. Предположим, у нас есть несколько файлов со следующими URI в HDFS:
- 'hdfs://hdfs1:9000/some_dir/some_file_1'
- 'hdfs://hdfs1:9000/some_dir/some_file_2'
- 'hdfs://hdfs1:9000/some_dir/some_file_3'
- 'hdfs://hdfs1:9000/another_dir/some_file_1'
- 'hdfs://hdfs1:9000/another_dir/some_file_2'
- 'hdfs://hdfs1:9000/another_dir/some_file_3'
- 'hdfs://hdfs1:9000/some_dir/some_file_1'
- 'hdfs://hdfs1:9000/some_dir/some_file_2'
- 'hdfs://hdfs1:9000/some_dir/some_file_3'
- 'hdfs://hdfs1:9000/another_dir/some_file_1'
- 'hdfs://hdfs1:9000/another_dir/some_file_2'
- 'hdfs://hdfs1:9000/another_dir/some_file_3'
1. Есть несколько возможностей создать таблицу, состояющую из этих шести файлов:
@ -128,6 +130,7 @@ CREATE TABLE big_table (name String, value UInt32) ENGINE = HDFS('hdfs://hdfs1:9
| **параметр** | **по умолчанию** |
| - | - |
| rpc\_client\_connect\_tcpnodelay | true |
| dfs\_client\_read\_shortcircuit | true |
| output\_replace-datanode-on-failure | true |
@ -177,22 +180,23 @@ CREATE TABLE big_table (name String, value UInt32) ENGINE = HDFS('hdfs://hdfs1:9
#### Расширенные параметры для ClickHouse {#clickhouse-extras}
| **параметр** | **по умолчанию** |
| - | - |
|hadoop\_kerberos\_keytab | "" |
|hadoop\_kerberos\_principal | "" |
|hadoop\_kerberos\_kinit\_command | kinit |
### Ограничения {#limitations}
* hadoop\_security\_kerberos\_ticket\_cache\_path могут быть определены только на глобальном уровне
* `hadoop_security_kerberos_ticket_cache_path` и `libhdfs3_conf` могут быть определены только на глобальном, а не на пользовательском уровне
## Поддержка Kerberos {#kerberos-support}
Если hadoop\_security\_authentication параметр имеет значение 'kerberos', ClickHouse аутентифицируется с помощью Kerberos.
[Расширенные параметры](#clickhouse-extras) и hadoop\_security\_kerberos\_ticket\_cache\_path помогают сделать это.
Если параметр `hadoop_security_authentication` имеет значение `kerberos`, ClickHouse аутентифицируется с помощью Kerberos.
[Расширенные параметры](#clickhouse-extras) и `hadoop_security_kerberos_ticket_cache_path` помогают сделать это.
Обратите внимание что из-за ограничений libhdfs3 поддерживается только устаревший метод аутентификации,
коммуникация с узлами данных не защищена SASL (HADOOP\_SECURE\_DN\_USER надежный показатель такого
подхода к безопасности). Используйте tests/integration/test\_storage\_kerberized\_hdfs/hdfs_configs/bootstrap.sh для примера настроек.
коммуникация с узлами данных не защищена SASL (`HADOOP_SECURE_DN_USER` надежный показатель такого
подхода к безопасности). Используйте `tests/integration/test_storage_kerberized_hdfs/hdfs_configs/bootstrap.sh` для примера настроек.
Если hadoop\_kerberos\_keytab, hadoop\_kerberos\_principal или hadoop\_kerberos\_kinit\_command указаны в настройках, kinit будет вызван. hadoop\_kerberos\_keytab и hadoop\_kerberos\_principal обязательны в этом случае. Необходимо также будет установить kinit и файлы конфигурации krb5.
Если `hadoop_kerberos_keytab`, `hadoop_kerberos_principal` или `hadoop_kerberos_kinit_command` указаны в настройках, `kinit` будет вызван. `hadoop_kerberos_keytab` и `hadoop_kerberos_principal` обязательны в этом случае. Необходимо также будет установить `kinit` и файлы конфигурации krb5.
## Виртуальные столбцы {#virtual-columns}

2
docs/ru/engines/table-engines/integrations/kafka.md
View File

@ -191,5 +191,5 @@ ClickHouse может поддерживать учетные данные Kerbe
**Смотрите также**
- [Виртуальные столбцы](index.md#table_engines-virtual_columns)
- [background_schedule_pool_size](../../../operations/settings/settings.md#background_schedule_pool_size)
- [background_message_broker_schedule_pool_size](../../../operations/settings/settings.md#background_message_broker_schedule_pool_size)

1
docs/ru/faq/general/how-do-i-contribute-code-to-clickhouse.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/general/how-do-i-contribute-code-to-clickhouse.md

1
docs/ru/faq/operations/multi-region-replication.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/operations/multi-region-replication.md

10
docs/ru/getting-started/example-datasets/ontime.md
View File

@ -15,13 +15,7 @@ toc_title: OnTime
Скачивание данных (из `https://github.com/Percona-Lab/ontime-airline-performance/blob/master/download.sh`):
``` bash
for s in `seq 1987 2018`
do
for m in `seq 1 12`
do
wget https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_${s}_${m}.zip
done
done
wget --no-check-certificate --continue https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_{1987..2021}_{1..12}.zip
```
Создание таблицы:
@ -38,7 +32,7 @@ CREATE TABLE `ontime`
`Reporting_Airline` String,
`DOT_ID_Reporting_Airline` Int32,
`IATA_CODE_Reporting_Airline` String,
`Tail_Number` Int32,
`Tail_Number` String,
`Flight_Number_Reporting_Airline` String,
`OriginAirportID` Int32,
`OriginAirportSeqID` Int32,

4
docs/ru/interfaces/cli.md
View File

@ -114,7 +114,7 @@ $ clickhouse-client --param_tbl="numbers" --param_db="system" --param_col="numbe
Параметры в конфигурационных файлах переопределяют значения по умолчанию.
### Параметры командной строки {#parametry-komandnoi-stroki}
### Параметры командной строки {#command-line-options}
- `--host, -h` — имя сервера, по умолчанию — ‘localhost’. Вы можете использовать как имя, так и IPv4 или IPv6 адрес.
- `--port` — порт для подключения, по умолчанию — 9000. Обратите внимание: для HTTP-интерфейса и нативного интерфейса используются разные порты.
@ -136,7 +136,7 @@ $ clickhouse-client --param_tbl="numbers" --param_db="system" --param_col="numbe
Начиная с версии 20.5, в `clickhouse-client` есть автоматическая подсветка синтаксиса (включена всегда).
### Конфигурационные файлы {#konfiguratsionnye-faily}
### Конфигурационные файлы {#configuration_files}
`clickhouse—client` использует первый существующий файл из:

18
docs/ru/interfaces/http.md
View File

@ -422,7 +422,10 @@ $ curl -v 'http://localhost:8123/predefined_query'
Значение `query` — это предопределенный запрос `predefined_query_handler`, который выполняется ClickHouse при совпадении HTTP-запроса и возврате результата запроса. Это обязательная настройка.
В следующем примере определяются настройки [max_threads](../operations/settings/settings.md#settings-max_threads) и `max_alter_threads`, а затем запрашивается системная таблица, чтобы проверить, были ли эти параметры успешно установлены.
В следующем примере определяются настройки [max_threads](../operations/settings/settings.md#settings-max_threads) и `max_final_threads`, а затем запрашивается системная таблица, чтобы проверить, были ли эти параметры успешно установлены.
!!! note "Предупреждение"
Чтобы сохранить стандартные `handlers` такие как `query`, `play`, `ping`, используйте правило `<defaults/>`.
Пример:
@ -441,13 +444,14 @@ $ curl -v 'http://localhost:8123/predefined_query'
<query>SELECT name, value FROM system.settings WHERE name = {name_2:String}</query>
</handler>
</rule>
<defaults/>
</http_handlers>
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_alter_threads?max_threads=1&max_alter_threads=2'
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_final_threads?max_threads=1&max_final_threads=2'
1
max_alter_threads 2
max_final_threads 2
```
!!! note "Предупреждение"
@ -459,7 +463,7 @@ max_alter_threads 2
ClickHouse извлекает и выполняет значение, соответствующее значению `query_param_name` URL-адресе HTTP-запроса. Значение по умолчанию `query_param_name` — это `/query` . Это необязательная настройка. Если в файле конфигурации нет определения, параметр не передается.
Чтобы поэкспериментировать с этой функциональностью, в примере определяются значения [max_threads](../operations/settings/settings.md#settings-max_threads) и `max_alter_threads` и запрашивается, успешно ли были установлены настройки.
Чтобы поэкспериментировать с этой функциональностью, в примере определяются значения [max_threads](../operations/settings/settings.md#settings-max_threads) и `max_final_threads` и запрашивается, успешно ли были установлены настройки.
Пример:
@ -473,13 +477,14 @@ ClickHouse извлекает и выполняет значение, соотв
<query_param_name>query_param</query_param_name>
</handler>
</rule>
<defaults/>
</http_handlers>
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_alter_threads=2&param_name_1=max_threads&param_name_2=max_alter_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_final_threads=2&param_name_1=max_threads&param_name_2=max_final_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
max_threads 1
max_alter_threads 2
max_final_threads 2
```
### static {#static}
@ -503,6 +508,7 @@ max_alter_threads 2
<response_content>Say Hi!</response_content>
</handler>
</rule>
<defaults/>
</http_handlers>
```

21
docs/ru/interfaces/third-party/gui.md vendored
View File

@ -227,4 +227,25 @@ SeekTable [бесплатен](https://www.seektable.com/help/cloud-pricing) д
[Chadmin](https://github.com/bun4uk/chadmin) — простой графический интерфейс для визуализации запущенных запросов на вашем кластере ClickHouse. Он отображает информацию о запросах и дает возможность их завершать.
### TABLUM.IO {#tablum_io}
[TABLUM.IO](https://tablum.io/) — онлайн инструмент для загрузки и визуализации данных. Позволяет подключаться к БД ClickHouse, работать с базами и таблицами через многофункциональную SQL консоль, загружать данные из таблиц, объединять их с данными из других источников (файлов, сторонних сервисов) и визуализировать результаты в виде таблиц и графиков.
Основные возможности:
- Многофункциональный ETL: загрузка данных из популярных баз данных, локальных и удаленных файлов, загрузка результатов вызова REST API.
- Универсальная SQL консоль с подсветкой синтаксиса и визуальным генератором SQL запросов.
- Визуализация загруженных данных в виде графиков и таблиц.
- Материализация данных и подзапросы к загруженным данным.
- Отправка результатов визуализации в Slack, Telegram или на email.
- Организация потоков данных (data pipeline) через собственный API.
- Экспорт данных в форматах JSON, CSV, SQL, HTML.
- Веб-интерфейс.
Поддерживается установка TABLUM.IO на собственный сервер (в виде Docker образа) или работа с сервисом в облаке.
Лицензия: [коммерческий](https://tablum.io/pricing) продукт с периодом бесплатного тестирования 3 месяца.
Протестировать TABLUM.IO без разворачивания на собственном сервере можно [здесь](https://tablum.io/try).
Подробно о продукте смотрите на [TABLUM.IO](https://tablum.io/)
[Original article](https://clickhouse.com/docs/en/interfaces/third-party/gui/) <!--hide-->

199
docs/ru/operations/clickhouse-keeper.md
View File

@ -3,14 +3,14 @@ toc_priority: 66
toc_title: ClickHouse Keeper
---
# [пре-продакшн] ClickHouse Keeper
# [пре-продакшн] ClickHouse Keeper {#clickHouse-keeper}
Сервер ClickHouse использует сервис координации [ZooKeeper](https://zookeeper.apache.org/) для [репликации](../engines/table-engines/mergetree-family/replication.md) данных и выполнения [распределенных DDL запросов](../sql-reference/distributed-ddl.md). ClickHouse Keeper — это альтернативный сервис координации, совместимый с ZooKeeper.
!!! warning "Предупреждение"
ClickHouse Keeper находится в стадии пре-продакшн и тестируется в CI ClickHouse и на нескольких внутренних инсталляциях.
## Детали реализации
## Детали реализации {#implementation-details}
ZooKeeper — один из первых широко известных сервисов координации с открытым исходным кодом. Он реализован на языке программирования Java, имеет достаточно простую и мощную модель данных. Алгоритм координации Zookeeper называется ZAB (ZooKeeper Atomic Broadcast). Он не гарантирует линеаризуемость операций чтения, поскольку каждый узел ZooKeeper обслуживает чтения локально. В отличие от ZooKeeper, ClickHouse Keeper реализован на C++ и использует алгоритм [RAFT](https://raft.github.io/), [реализация](https://github.com/eBay/NuRaft). Этот алгоритм позволяет достичь линеаризуемости чтения и записи, имеет несколько реализаций с открытым исходным кодом на разных языках.
@ -21,7 +21,7 @@ ZooKeeper — один из первых широко известных сер
!!! info "Примечание"
Внешние интеграции не поддерживаются.
## Конфигурация
## Конфигурация {#configuration}
ClickHouse Keeper может использоваться как равноценная замена ZooKeeper или как внутренняя часть сервера ClickHouse, но в обоих случаях конфигурация представлена файлом `.xml`. Главный тег конфигурации ClickHouse Keeper — это `<keeper_server>`. Параметры конфигурации:
@ -54,6 +54,7 @@ ClickHouse Keeper может использоваться как равноце
- `auto_forwarding` — разрешить пересылку запросов на запись от последователей лидеру (по умолчанию: true).
- `shutdown_timeout` — время ожидания завершения внутренних подключений и выключения, в миллисекундах (по умолчанию: 5000).
- `startup_timeout` — время отключения сервера, если он не подключается к другим участникам кворума, в миллисекундах (по умолчанию: 30000).
- `four_letter_word_white_list` — список разрешенных 4-х буквенных команд (по умолчанию: "conf,cons,crst,envi,ruok,srst,srvr,stat,wchc,wchs,dirs,mntr,isro").
Конфигурация кворума находится в `<keeper_server>.<raft_configuration>` и содержит описание серверов.
@ -101,7 +102,7 @@ ClickHouse Keeper может использоваться как равноце
</keeper_server>
```
## Как запустить
## Как запустить {#how-to-run}
ClickHouse Keeper входит в пакет `clickhouse-server`, просто добавьте кофигурацию `<keeper_server>` и запустите сервер ClickHouse как обычно. Если вы хотите запустить ClickHouse Keeper автономно, сделайте это аналогичным способом:
@ -109,7 +110,195 @@ ClickHouse Keeper входит в пакет `clickhouse-server`, просто
clickhouse-keeper --config /etc/your_path_to_config/config.xml --daemon
```
## [экспериментально] Переход с ZooKeeper
## 4-х буквенные команды {#four-letter-word-commands}
ClickHouse Keeper также поддерживает 4-х буквенные команды, почти такие же, как у Zookeeper. Каждая команда состоит из 4-х символов, например, `mntr`, `stat` и т. д. Несколько интересных команд: `stat` предоставляет общую информацию о сервере и подключенных клиентах, а `srvr` и `cons` предоставляют расширенные сведения о сервере и подключениях соответственно.
У 4-х буквенных команд есть параметр для настройки разрешенного списка `four_letter_word_white_list`, который имеет значение по умолчанию "conf,cons,crst,envi,ruok,srst,srvr,stat, wchc,wchs,dirs,mntr,isro".
Вы можете отправлять команды в ClickHouse Keeper через telnet или nc на порт для клиента.
```
echo mntr | nc localhost 9181
```
Ниже приведен подробный список 4-х буквенных команд:
- `ruok`: Проверяет, что сервер запущен без ошибок. В этом случае сервер ответит `imok`. В противном случае он не ответит. Ответ `imok` не обязательно означает, что сервер присоединился к кворуму, а указывает, что процесс сервера активен и привязан к указанному клиентскому порту. Используйте команду `stat` для получения подробной информации о состоянии кворума и клиентском подключении.
```
imok
```
- `mntr`: Выводит список переменных, которые используются для мониторинга работоспособности кластера.
```
zk_version v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
zk_avg_latency 0
zk_max_latency 0
zk_min_latency 0
zk_packets_received 68
zk_packets_sent 68
zk_num_alive_connections 1
zk_outstanding_requests 0
zk_server_state leader
zk_znode_count 4
zk_watch_count 1
zk_ephemerals_count 0
zk_approximate_data_size 723
zk_open_file_descriptor_count 310
zk_max_file_descriptor_count 10240
zk_followers 0
zk_synced_followers 0
```
- `srvr`: Выводит информацию о сервере: его версию, роль участника кворума и т.п.
```
ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
Latency min/avg/max: 0/0/0
Received: 2
Sent : 2
Connections: 1
Outstanding: 0
Zxid: 34
Mode: leader
Node count: 4
```
- `stat`: Выводит краткие сведения о сервере и подключенных клиентах.
```
ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
Clients:
192.168.1.1:52852(recved=0,sent=0)
192.168.1.1:52042(recved=24,sent=48)
Latency min/avg/max: 0/0/0
Received: 4
Sent : 4
Connections: 1
Outstanding: 0
Zxid: 36
Mode: leader
Node count: 4
```
- `srst`: Сбрасывает статистику сервера. Команда влияет на результат вывода `srvr`, `mntr` и `stat`.
```
Server stats reset.
```
- `conf`: Выводит подробную информацию о серверной конфигурации.
```
server_id=1
tcp_port=2181
four_letter_word_white_list=*
log_storage_path=./coordination/logs
snapshot_storage_path=./coordination/snapshots
max_requests_batch_size=100
session_timeout_ms=30000
operation_timeout_ms=10000
dead_session_check_period_ms=500
heart_beat_interval_ms=500
election_timeout_lower_bound_ms=1000
election_timeout_upper_bound_ms=2000
reserved_log_items=1000000000000000
snapshot_distance=10000
auto_forwarding=true
shutdown_timeout=5000
startup_timeout=240000
raft_logs_level=information
snapshots_to_keep=3
rotate_log_storage_interval=100000
stale_log_gap=10000
fresh_log_gap=200
max_requests_batch_size=100
quorum_reads=false
force_sync=false
compress_logs=true
compress_snapshots_with_zstd_format=true
configuration_change_tries_count=20
```
- `cons`: Выводит полную информацию о подключениях/сессиях для всех клиентов, подключенных к этому серверу. Включает информацию о количестве принятых/отправленных пакетов, идентификаторе сессии, задержках операций, последней выполненной операции и т. д.
```
192.168.1.1:52163(recved=0,sent=0,sid=0xffffffffffffffff,lop=NA,est=1636454787393,to=30000,lzxid=0xffffffffffffffff,lresp=0,llat=0,minlat=0,avglat=0,maxlat=0)
192.168.1.1:52042(recved=9,sent=18,sid=0x0000000000000001,lop=List,est=1636454739887,to=30000,lcxid=0x0000000000000005,lzxid=0x0000000000000005,lresp=1636454739892,llat=0,minlat=0,avglat=0,maxlat=0)
```
- `crst`: Сбрасывает статистику подключений/сессий для всех подключений.
```
Connection stats reset.
```
- `envi`: Выводит подробную информацию о серверном окружении.
```
Environment:
clickhouse.keeper.version=v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
host.name=ZBMAC-C02D4054M.local
os.name=Darwin
os.arch=x86_64
os.version=19.6.0
cpu.count=12
user.name=root
user.home=/Users/JackyWoo/
user.dir=/Users/JackyWoo/project/jd/clickhouse/cmake-build-debug/programs/
user.tmp=/var/folders/b4/smbq5mfj7578f2jzwn602tt40000gn/T/
```
- `dirs`: Показывает общий размер файлов снэпшотов и журналов в байтах.
```
snapshot_dir_size: 0
log_dir_size: 3875
```
- `isro`: Проверяет, что сервер работает в режиме только для чтения. Сервер ответит `ro`, если он находится в режиме только для чтения, или `rw`, если нет.
```
rw
```
- `wchs`: Показывает краткую информацию о количестве отслеживаемых путей (watches) на сервере.
```
1 connections watching 1 paths
Total watches:1
```
- `wchc`: Показывает подробную информацию об отслеживаемых путях (watches) на сервере в разбивке по сессиям. При этом выводится список сессий (подключений) с соответствующими отслеживаемыми путями. Обратите внимание, что в зависимости от количества отслеживаемых путей эта операция может быть дорогостоящей (т. е. повлиять на производительность сервера), используйте ее осторожно.
```
0x0000000000000001
/clickhouse/task_queue/ddl
```
- `wchp`: Показывает подробную информацию об отслеживаемых путях (watches) на сервере в разбивке по пути. При этом выводится список путей (узлов) с соответствующими сессиями. Обратите внимание, что в зависимости от количества отселживаемых путей (watches) эта операция может быть дорогостоящей (т. е. повлиять на производительность сервера), используйте ее осторожно.
```
/clickhouse/task_queue/ddl
0x0000000000000001
```
- `dump`: Выводит список незавершенных сеансов и эфемерных узлов. Команда работает только на лидере.
```
Sessions dump (2):
0x0000000000000001
0x0000000000000002
Sessions with Ephemerals (1):
0x0000000000000001
/clickhouse/task_queue/ddl
```
## [экспериментально] Переход с ZooKeeper {#migration-from-zookeeper}
Плавный переход с ZooKeeper на ClickHouse Keeper невозможен, необходимо остановить кластер ZooKeeper, преобразовать данные и запустить ClickHouse Keeper. Утилита `clickhouse-keeper-converter` конвертирует журналы и снэпшоты ZooKeeper в снэпшот ClickHouse Keeper. Работа утилиты проверена только для версий ZooKeeper выше 3.4. Для миграции необходимо выполнить следующие шаги:

40
docs/ru/operations/server-configuration-parameters/settings.md
View File

@ -436,26 +436,58 @@ ClickHouse проверяет условия для `min_part_size` и `min_part
## interserver_http_credentials {#server-settings-interserver-http-credentials}
Имя пользователя и пароль, использующиеся для аутентификации при [репликации](../../operations/server-configuration-parameters/settings.md) движками Replicated\*. Это имя пользователя и пароль используются только для взаимодействия между репликами кластера и никак не связаны с аутентификацией клиентов ClickHouse. Сервер проверяет совпадение имени и пароля для соединяющихся с ним реплик, а также использует это же имя и пароль для соединения с другими репликами. Соответственно, эти имя и пароль должны быть прописаны одинаковыми для всех реплик кластера.
По умолчанию аутентификация не используется.
Имя пользователя и пароль, использующиеся для подключения к другим серверам при [репликации](../../engines/table-engines/mergetree-family/replication.md) движками Replicated\*. Сервер использует эти же учетные данные при аутентификации других реплик. Поэтому настройки `interserver_http_credentials` должны быть заданы одинаковыми для всех реплик кластера.
По умолчанию, если секция `interserver_http_credentials` не задана в конфигурации, аутентификация при репликации не используется.
!!! note "Примечание"
Эти учетные данные являются общими для обмена данными по протоколам `HTTP` и `HTTPS`.
Настройки `interserver_http_credentials` не относятся к [конфигурации](../../interfaces/cli.md#configuration_files) учетных данных клиента ClickHouse.
!!! note "Примечание"
Учетные данные в `interserver_http_credentials` являются общими для репликации по `HTTP` и `HTTPS`.
Раздел содержит следующие параметры:
- `user` — имя пользователя.
- `password` — пароль.
- `allow_empty` — если `true`, то другие реплики могут подключаться без аутентификации, даже если учетные данные заданы. Если `false`, то подключение без аутентификации не допускается. Значение по умолчанию: `false`.
- `old` — секция содержит старые значения `user` и `password`, которые используются в процессе изменения учетных данных. Можно указывать несколько секций `old`.
**Пример конфигурации**
**Изменение учетных данных**
ClickHouse поддерживает динамическое изменение учетных данных. При этом не требуется одновременно останавливать все реплики, чтобы обновить конфигурацию. Изменение учетных данных выполняется за несколько шагов.
Чтобы включить аутентификацию, установите `interserver_http_credentials.allow_empty` в значение `true` и задайте учетные данные. С такой конфигурацией разрешены подключения как с аутентификацией, так и без нее.
``` xml
<interserver_http_credentials>
<user>admin</user>
<password>111</password>
<allow_empty>true</allow_empty>
</interserver_http_credentials>
```
После конфигурации всех реплик установите `allow_empty` в значение `false` или удалите эту настройку. Это сделает аутентификацию с новыми учетными данными обязательной.
Чтобы изменить учетные данные, перенесите имя пользователя и пароль в секцию `interserver_http_credentials.old` и укажите новые значения для `user` и `password`. Сервер будет использовать новые учетные данные при подключении к другим репликам и при этом будет разрешать подключения как с новыми, так и со старыми учетными данными.
``` xml
<interserver_http_credentials>
<user>admin</user>
<password>222</password>
<old>
<user>admin</user>
<password>111</password>
</old>
<old>
<user>temp</user>
<password>000</password>
</old>
</interserver_http_credentials>
```
Когда новые учетные данные обновятся на всех репликах, старые учетные данные можно удалить из конфигурации.
## keep_alive_timeout {#keep-alive-timeout}
Время в секундах, в течение которого ClickHouse ожидает входящих запросов прежде чем закрыть соединение. Значение по умолчанию: 10 секунд.

59
docs/ru/operations/settings/settings.md
View File

@ -761,9 +761,20 @@ ClickHouse может парсить только базовый формат `Y
Возможные значения:
- Любое положительное целое число.
- Положительное целое число.
Значение по умолчанию: 163840.
Значение по умолчанию: `163840`.
## merge_tree_min_rows_for_concurrent_read_for_remote_filesystem {#merge-tree-min-rows-for-concurrent-read-for-remote-filesystem}
Минимальное количество строк для чтения из одного файла, прежде чем движок [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) может выполнять параллельное чтение из удаленной файловой системы.
Возможные значения:
- Положительное целое число.
Значение по умолчанию: `163840`.
## merge_tree_min_bytes_for_concurrent_read {#setting-merge-tree-min-bytes-for-concurrent-read}
@ -773,7 +784,17 @@ ClickHouse может парсить только базовый формат `Y
- Положительное целое число.
Значение по умолчанию: 251658240.
Значение по умолчанию: `251658240`.
## merge_tree_min_bytes_for_concurrent_read_for_remote_filesystem {#merge-tree-min-bytes-for-concurrent-read-for-remote-filesystem}
Минимальное количество байтов для чтения из одного файла, прежде чем движок [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) может выполнять параллельное чтение из удаленной файловой системы.
Возможное значение:
- Положительное целое число.
Значение по умолчанию: `251658240`.
## merge_tree_min_rows_for_seek {#setting-merge-tree-min-rows-for-seek}
@ -1620,18 +1641,19 @@ SELECT * FROM table_with_enum_column_for_csv_insert;
`INSERT` завершается успешно только в том случае, когда ClickHouse смог без ошибки записать данные в `insert_quorum` реплик за время `insert_quorum_timeout`. Если по любой причине количество реплик с успешной записью не достигнет `insert_quorum`, то запись считается не состоявшейся и ClickHouse удалит вставленный блок из всех реплик, куда уже успел записать данные.
Все реплики в кворуме консистентны, т.е. содержат данные всех более ранних запросов `INSERT`. Последовательность `INSERT` линеаризуется.
Когда `insert_quorum_parallel` выключена, все реплики кворума консистентны, то есть содержат данные всех предыдущих запросов `INSERT` (последовательность `INSERT` линеаризуется). При чтении с диска данных, записанных с помощью `insert_quorum` и при выключенной `insert_quorum_parallel`, можно включить последовательную консистентность для запросов `SELECT` с помощью [select_sequential_consistency](#settings-select_sequential_consistency).
При чтении данных, записанных с `insert_quorum` можно использовать настройку [select_sequential_consistency](#settings-select_sequential_consistency).
ClickHouse генерирует исключение
ClickHouse генерирует исключение:
- Если количество доступных реплик на момент запроса меньше `insert_quorum`.
- При попытке записать данные в момент, когда предыдущий блок ещё не вставлен в `insert_quorum` реплик. Эта ситуация может возникнуть, если пользователь вызвал `INSERT` прежде, чем завершился предыдущий с `insert_quorum`.
- При выключенной `insert_quorum_parallel` и при попытке записать данные в момент, когда предыдущий блок еще не вставлен в `insert_quorum` реплик (несколько параллельных `INSERT`-запросов). Эта ситуация может возникнуть при попытке пользователя выполнить очередной запрос `INSERT` к той же таблице, прежде чем завершится предыдущий с `insert_quorum`.
См. также:
- [insert_quorum_timeout](#settings-insert_quorum_timeout)
- [insert_quorum_parallel](#settings-insert_quorum_parallel)
- [select_sequential_consistency](#settings-select_sequential_consistency)
## insert_quorum_timeout {#settings-insert_quorum_timeout}
@ -1643,11 +1665,29 @@ ClickHouse генерирует исключение
См. также:
- [insert_quorum](#settings-insert_quorum)
- [insert_quorum_parallel](#settings-insert_quorum_parallel)
- [select_sequential_consistency](#settings-select_sequential_consistency)
## insert_quorum_parallel {#settings-insert_quorum_parallel}
Включает и выключает параллелизм для кворумных вставок (`INSERT`-запросы). Когда опция включена, возможно выполнять несколько кворумных `INSERT`-запросов одновременно, при этом запросы не дожидаются окончания друг друга . Когда опция выключена, одновременные записи с кворумом в одну и ту же таблицу будут отклонены (будет выполнена только одна из них).
Возможные значения:
- 0 — Выключена.
- 1 — Включена.
Значение по умолчанию: 1.
См. также:
- [insert_quorum](#settings-insert_quorum)
- [insert_quorum_timeout](#settings-insert_quorum_timeout)
- [select_sequential_consistency](#settings-select_sequential_consistency)
## select_sequential_consistency {#settings-select_sequential_consistency}
Включает или выключает последовательную консистентность для запросов `SELECT`.
Включает или выключает последовательную консистентность для запросов `SELECT`. Необходимо, чтобы `insert_quorum_parallel` была выключена (по умолчанию включена), а опция `insert_quorum` включена.
Возможные значения:
@ -1660,10 +1700,13 @@ ClickHouse генерирует исключение
Когда последовательная консистентность включена, то ClickHouse позволит клиенту выполнить запрос `SELECT` только к тем репликам, которые содержат данные всех предыдущих запросов `INSERT`, выполненных с `insert_quorum`. Если клиент обратится к неполной реплике, то ClickHouse сгенерирует исключение. В запросе SELECT не будут участвовать данные, которые ещё не были записаны на кворум реплик.
Если `insert_quorum_parallel` включена (по умолчанию это так), тогда `select_sequential_consistency` не будет работать. Причина в том, что параллельные запросы `INSERT` можно записать в разные наборы реплик кворума, поэтому нет гарантии того, что в отдельно взятую реплику будут сделаны все записи.
См. также:
- [insert_quorum](#settings-insert_quorum)
- [insert_quorum_timeout](#settings-insert_quorum_timeout)
- [insert_quorum_parallel](#settings-insert_quorum_parallel)
## insert_deduplicate {#settings-insert-deduplicate}

4
docs/ru/sql-reference/statements/grant.md
View File

@ -21,7 +21,7 @@ GRANT [ON CLUSTER cluster_name] privilege[(column_name [,...])] [,...] ON {db.ta
- `user` — Пользователь ClickHouse.
`WITH GRANT OPTION` разрешает пользователю или роли выполнять запрос `GRANT`. Пользователь может выдавать только те привилегии, которые есть у него, той же или меньшей области действий.
`WITH REPLACE OPTION` заменяет все старые привилегии новыми привилегиями для `user` или `role`, Если не указано, добавьте новые привилегии для старых.
`WITH REPLACE OPTION` заменяет все старые привилегии новыми привилегиями для `user` или `role`, если не указано, добавляет новые привилегии.
## Синтаксис назначения ролей {#assign-role-syntax}
@ -34,7 +34,7 @@ GRANT [ON CLUSTER cluster_name] role [,...] TO {user | another_role | CURRENT_US
- `user` — Пользователь ClickHouse.
`WITH ADMIN OPTION` присваивает привилегию [ADMIN OPTION](#admin-option-privilege) пользователю или роли.
`WITH REPLACE OPTION` заменяет все старые роли новыми ролями для пользователя `user` или `role`, Если не указано, добавьте новые роли в старые.
`WITH REPLACE OPTION` заменяет все старые роли новыми ролями для пользователя `user` или `role`, если не указано, добавляет новые новые роли.
## Использование {#grant-usage}

49
docs/ru/sql-reference/statements/select/join.md
View File

@ -55,13 +55,13 @@ FROM <left_table>
- [join_on_disk_max_files_to_merge](../../../operations/settings/settings.md#join_on_disk_max_files_to_merge)
- [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys)
## Условия в секции ON {on-section-conditions}
## Условия в секции ON {#on-section-conditions}
Секция `ON` может содержать несколько условий, связанных операторами `AND` и `OR`. Условия, задающие ключи соединения, должны содержать столбцы левой и правой таблицы и должны использовать оператор равенства. Прочие условия могут использовать другие логические операторы, но в отдельном условии могут использоваться столбцы либо только левой, либо только правой таблицы.
Секция `ON` может содержать несколько условий, связанных оператором `AND`. Условия, задающие ключи соединения, должны содержать столбцы левой и правой таблицы и должны использовать оператор равенства. Прочие условия могут использовать другие логические операторы, но в отдельном условии могут использоваться столбцы либо только левой, либо только правой таблицы.
Строки объединяются только тогда, когда всё составное условие выполнено. Если оно не выполнено, то строки могут попасть в результат в зависимости от типа `JOIN`. Обратите внимание, что если то же самое условие поместить в секцию `WHERE`, то строки, для которых оно не выполняется, никогда не попаду в результат.
!!! note "Примечание"
Оператор `OR` внутри секции `ON` пока не поддерживается.
Оператор `OR` внутри секции `ON` работает, используя алгоритм хеш-соединения — на каждый агрумент `OR` с ключами соединений для `JOIN` создается отдельная хеш-таблица, поэтому потребление памяти и время выполнения запроса растет линейно при увеличении количества выражений `OR` секции `ON`.
!!! note "Примечание"
Если в условии использованы столбцы из разных таблиц, то пока поддерживается только оператор равенства (`=`).
@ -110,6 +110,47 @@ SELECT name, text, scores FROM table_1 INNER JOIN table_2
└──────┴────────┴────────┘
```
Запрос с типом соединения `INNER` и условием с оператором `OR`:
``` sql
CREATE TABLE t1 (`a` Int64, `b` Int64) ENGINE = MergeTree() ORDER BY a;
CREATE TABLE t2 (`key` Int32, `val` Int64) ENGINE = MergeTree() ORDER BY key;
INSERT INTO t1 SELECT number as a, -a as b from numbers(5);
INSERT INTO t2 SELECT if(number % 2 == 0, toInt64(number), -number) as key, number as val from numbers(5);
SELECT a, b, val FROM t1 INNER JOIN t2 ON t1.a = t2.key OR t1.b = t2.key;
```
Результат:
```
┌─a─┬──b─┬─val─┐
│ 0 │ 0 │ 0 │
│ 1 │ -1 │ 1 │
│ 2 │ -2 │ 2 │
│ 3 │ -3 │ 3 │
│ 4 │ -4 │ 4 │
└───┴────┴─────┘
```
Запрос с типом соединения `INNER` и условиями с операторами `OR` и `AND`:
``` sql
SELECT a, b, val FROM t1 INNER JOIN t2 ON t1.a = t2.key OR t1.b = t2.key AND t2.val > 3;
```
Результат:
```
┌─a─┬──b─┬─val─┐
│ 0 │ 0 │ 0 │
│ 2 │ -2 │ 2 │
│ 4 │ -4 │ 4 │
└───┴────┴─────┘
```
## Использование ASOF JOIN {#asof-join-usage}
`ASOF JOIN` применим в том случае, когда необходимо объединять записи, которые не имеют точного совпадения.

1
docs/zh/faq/general/how-do-i-contribute-code-to-clickhouse.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/general/how-do-i-contribute-code-to-clickhouse.md

1
docs/zh/faq/operations/multi-region-replication.md Symbolic link
View File

@ -0,0 +1 @@
../../../en/faq/operations/multi-region-replication.md

12
docs/zh/getting-started/example-datasets/ontime.md
View File

@ -15,17 +15,9 @@ toc_title: OnTime
下载数据：
``` bash
for s in `seq 1987 2018`
do
for m in `seq 1 12`
do
wget https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_${s}_${m}.zip
done
done
wget --no-check-certificate --continue https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_{1987..2021}_{1..12}.zip
```
(参考 https://github.com/Percona-Lab/ontime-airline-performance/blob/master/download.sh )
创建表结构：
``` sql
@ -40,7 +32,7 @@ CREATE TABLE `ontime`
`Reporting_Airline` String,
`DOT_ID_Reporting_Airline` Int32,
`IATA_CODE_Reporting_Airline` String,
`Tail_Number` Int32,
`Tail_Number` String,
`Flight_Number_Reporting_Airline` String,
`OriginAirportID` Int32,
`OriginAirportSeqID` Int32,

12
docs/zh/interfaces/http.md
View File

@ -407,7 +407,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
`query` 是一个预定义的`predefined_query_handler`查询，它由ClickHouse在匹配HTTP请求并返回查询结果时执行。这是一个必须的配置。
以下是定义的[max_threads](../operations/settings/settings.md#settings-max_threads)和`max_alter_threads`设置， 然后查询系统表以检查这些设置是否设置成功。
以下是定义的[max_threads](../operations/settings/settings.md#settings-max_threads)和`max_final_threads`设置， 然后查询系统表以检查这些设置是否设置成功。
示例:
@ -430,9 +430,9 @@ $ curl -v 'http://localhost:8123/predefined_query'
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_alter_threads?max_threads=1&max_alter_threads=2'
$ curl -H 'XXX:TEST_HEADER_VALUE' -H 'PARAMS_XXX:max_threads' 'http://localhost:8123/query_param_with_url/1/max_threads/max_final_threads?max_threads=1&max_final_threads=2'
1
max_alter_threads 2
max_final_threads 2
```
!!! note "警告"
@ -444,7 +444,7 @@ max_alter_threads 2
ClickHouse提取并执行与HTTP请求URL中的`query_param_name`值对应的值。`query_param_name`的默认值是`/query`。这是一个可选的配置。如果配置文件中没有定义，则不会传入参数。
为了试验这个功能，示例定义了[max_threads](../operations/settings/settings.md#settings-max_threads)和`max_alter_threads`，`queries`设置是否成功的值。
为了试验这个功能，示例定义了[max_threads](../operations/settings/settings.md#settings-max_threads)和`max_final_threads`，`queries`设置是否成功的值。
示例:
@ -462,9 +462,9 @@ ClickHouse提取并执行与HTTP请求URL中的`query_param_name`值对应的值
```
``` bash
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_alter_threads=2&param_name_1=max_threads&param_name_2=max_alter_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
$ curl -H 'XXX:TEST_HEADER_VALUE_DYNAMIC' 'http://localhost:8123/own?max_threads=1&max_final_threads=2&param_name_1=max_threads&param_name_2=max_final_threads&query_param=SELECT%20name,value%20FROM%20system.settings%20where%20name%20=%20%7Bname_1:String%7D%20OR%20name%20=%20%7Bname_2:String%7D'
max_threads 1
max_alter_threads 2
max_final_threads 2
```
### static {#static}

104
docs/zh/operations/system-tables/columns.md
View File

@ -1,29 +1,89 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.columns {#system-columns}
# 系统。列 {#system-columns}
此系统表包含所有表中列的信息。
包含有关所有表中列的信息。
你可以使用这个表来获得类似于 [DESCRIBE TABLE](../../sql-reference/statements/misc.md#misc-describe-table) 查询的信息，但是可以同时获得多个表的信息。
您可以使用此表获取类似于以下内容的信息 [DESCRIBE TABLE](../../sql-reference/statements/misc.md#misc-describe-table) 查询，但对于多个表一次。
[临时表](../../sql-reference/statements/create/table.md#temporary-tables)中的列只在创建它们的会话中的 `system.columns` 中才可见，并且它们的 `database` 字段显示为空。
该 `system.columns` 表包含以下列（列类型显示在括号中):
`system.columns` 表包含以下列 (括号中显示的是列类型):
- `database` (String) — Database name.
- `table` (String) — Table name.
- `name` (String) — Column name.
- `type` (String) — Column type.
- `default_kind` (String) — Expression type (`DEFAULT`, `MATERIALIZED`, `ALIAS`)为默认值，如果没有定义，则为空字符串。
- `default_expression` (String) — Expression for the default value, or an empty string if it is not defined.
- `data_compressed_bytes` (UInt64) — The size of compressed data, in bytes.
- `data_uncompressed_bytes` (UInt64) — The size of decompressed data, in bytes.
- `marks_bytes` (UInt64) — The size of marks, in bytes.
- `comment` (String) — Comment on the column, or an empty string if it is not defined.
- `is_in_partition_key` (UInt8) — Flag that indicates whether the column is in the partition expression.
- `is_in_sorting_key` (UInt8) — Flag that indicates whether the column is in the sorting key expression.
- `is_in_primary_key` (UInt8) — Flag that indicates whether the column is in the primary key expression.
- `is_in_sampling_key` (UInt8) — Flag that indicates whether the column is in the sampling key expression.
- `database` ([String](../../sql-reference/data-types/string.md)) — 数据库名称。
- `table` ([String](../../sql-reference/data-types/string.md)) — 表名。
- `name` ([String](../../sql-reference/data-types/string.md)) — 列名。
- `type` ([String](../../sql-reference/data-types/string.md)) — 列类型。
- `position` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 列在表中的顺序位置，从1开始。
- `default_kind` ([String](../../sql-reference/data-types/string.md)) — 默认值的表达式类型(`DEFAULT`, `MATERIALIZED`, `ALIAS`) ，如果没有定义，则为空字符串。
- `default_expression` ([String](../../sql-reference/data-types/string.md)) — 默认值的表达式，如果未定义则为空字符串。
- `data_compressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 压缩数据的大小，以字节为单位。
- `data_uncompressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 解压后的数据的大小，以字节为单位。
- `marks_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 标记的大小，以字节为单位。
- `comment` ([String](../../sql-reference/data-types/string.md)) — 列注释，如果没有定义，则为空字符串。
- `is_in_partition_key` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 列是否在分区表达式中的标志。
- `is_in_sorting_key` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 列是否在排序键表达式中的标志。
- `is_in_primary_key` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 列是否在主键表达式中的标志。
- `is_in_sampling_key` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 列是否在采样键表达式中的标志。
- `compression_codec` ([String](../../sql-reference/data-types/string.md)) — 压缩编码的名称。
- `character_octet_length` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — 二进制数据、字符数据或文本数据和图像的最大长度(以字节为单位)。在 ClickHouse 中只对 `FixedString` 数据类型有意义。否则，将返回 `NULL` 值。
- `numeric_precision` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — 近似数字型数据、精确数字型数据、整数型数据或货币数据的精度。在 ClickHouse 中，对于整数类型是比特率(bitness)，对于 `Decimal` 类型是十进制精度。否则，将返回 `NULL` 值。
- `numeric_precision_radix` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — 数字系统的基数是近似数字型数据、精确数字型数据、整数型数据或货币数据的精度。在 ClickHouse 中，对于整数类型是2，对于 `Decimal` 类型是10。否则，将返回 `NULL` 值。
- `numeric_scale` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — 近似数字型数据、精确数字型数据、整数型数据或货币数据的比例。在 ClickHouse 中只对 `Decimal` 类型有意义。否则，将返回 `NULL` 值。
- `datetime_precision` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — `DateTime64` 数据类型的小数精度。对于其他数据类型，将返回 `NULL` 值。
**示例**
```sql
SELECT * FROM system.columns LIMIT 2 FORMAT Vertical;
```
```text
Row 1:
──────
database: INFORMATION_SCHEMA
table: COLUMNS
name: table_catalog
type: String
position: 1
default_kind:
default_expression:
data_compressed_bytes: 0
data_uncompressed_bytes: 0
marks_bytes: 0
comment:
is_in_partition_key: 0
is_in_sorting_key: 0
is_in_primary_key: 0
is_in_sampling_key: 0
compression_codec:
character_octet_length: ᴺᵁᴸᴸ
numeric_precision: ᴺᵁᴸᴸ
numeric_precision_radix: ᴺᵁᴸᴸ
numeric_scale: ᴺᵁᴸᴸ
datetime_precision: ᴺᵁᴸᴸ
Row 2:
──────
database: INFORMATION_SCHEMA
table: COLUMNS
name: table_schema
type: String
position: 2
default_kind:
default_expression:
data_compressed_bytes: 0
data_uncompressed_bytes: 0
marks_bytes: 0
comment:
is_in_partition_key: 0
is_in_sorting_key: 0
is_in_primary_key: 0
is_in_sampling_key: 0
compression_codec:
character_octet_length: ᴺᵁᴸᴸ
numeric_precision: ᴺᵁᴸᴸ
numeric_precision_radix: ᴺᵁᴸᴸ
numeric_scale: ᴺᵁᴸᴸ
datetime_precision: ᴺᵁᴸᴸ
```
[原文](https://clickhouse.com/docs/zh/operations/system-tables/columns) <!--hide-->

15
docs/zh/operations/system-tables/contributors.md
View File

@ -1,15 +1,10 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.contributors {#system-contributors}
# 系统。贡献者 {#system-contributors}
包含有关贡献者的信息。 该顺序在查询执行时是随机的。
此系统表包含有关贡献者的信息。排列顺序是在查询执行时随机生成的。
列:
- `name` (String) — Contributor (author) name from git log.
- `name` (String) — git 日志中的贡献者 (作者) 名字。
**示例**
@ -32,7 +27,7 @@ SELECT * FROM system.contributors LIMIT 10
└──────────────────┘
```
要在表中找出自己，请使用查询:
要在表中找到你自己，请这样查询:
``` sql
SELECT * FROM system.contributors WHERE name = 'Olga Khvostikova'
@ -43,3 +38,5 @@ SELECT * FROM system.contributors WHERE name = 'Olga Khvostikova'
│ Olga Khvostikova │
└──────────────────┘
```
[原文](https://clickhouse.com/docs/zh/operations/system-tables/contributors) <!--hide-->

43
docs/zh/operations/system-tables/databases.md
View File

@ -1,12 +1,39 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.databases {#system-databases}
# 系统。数据库 {#system-databases}
包含当前用户可用的数据库的相关信息。
此表包含一个名为"字符串"的列 ‘name’ – the name of a database.
列:
服务器知道的每个数据库在表中都有相应的条目。
- `name` ([String](../../sql-reference/data-types/string.md)) — 数据库的名称。
- `engine` ([String](../../sql-reference/data-types/string.md)) — [数据库的引擎](../../engines/database-engines/index.md)。
- `data_path` ([String](../../sql-reference/data-types/string.md)) — 数据的路径。
- `metadata_path` ([String](../../sql-reference/data-types/enum.md)) — 元数据的路径。
- `uuid` ([UUID](../../sql-reference/data-types/uuid.md)) — 数据库的 UUID。
- `comment` ([String](../../sql-reference/data-types/enum.md)) — 数据库的注释。
该系统表用于实现 `SHOW DATABASES` 查询。
这个系统表的 `name` 列被用于实现 `SHOW DATABASES` 查询。
**示例**
创建一个数据库。
``` sql
CREATE DATABASE test;
```
查询此用户所有可用的数据库。
``` sql
SELECT * FROM system.databases;
```
``` text
┌─name───────────────┬─engine─┬─data_path──────────────────┬─metadata_path───────────────────────────────────────────────────────┬─uuid─────────────────────────────────┬─comment─┐
│ INFORMATION_SCHEMA │ Memory │ /var/lib/clickhouse/ │ │ 00000000-0000-0000-0000-000000000000 │ │
│ default │ Atomic │ /var/lib/clickhouse/store/ │ /var/lib/clickhouse/store/d31/d317b4bd-3595-4386-81ee-c2334694128a/ │ 24363899-31d7-42a0-a436-389931d752a0 │ │
│ information_schema │ Memory │ /var/lib/clickhouse/ │ │ 00000000-0000-0000-0000-000000000000 │ │
│ system │ Atomic │ /var/lib/clickhouse/store/ │ /var/lib/clickhouse/store/1d1/1d1c869d-e465-4b1b-a51f-be033436ebf9/ │ 03e9f3d1-cc88-4a49-83e9-f3d1cc881a49 │ │
└────────────────────┴────────┴────────────────────────────┴─────────────────────────────────────────────────────────────────────┴──────────────────────────────────────┴─────────┘
```
[原文](https://clickhouse.com/docs/zh/operations/system-tables/databases) <!--hide-->

15
docs/zh/operations/system-tables/detached_parts.md
View File

@ -1,14 +1,11 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.detached_parts {#system_tables-detached_parts}
# 系统。detached_parts {#system_tables-detached_parts}
包含关于 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 表的分离分区的信息。`reason` 列详细说明了该分区被分离的原因。
包含有关分离部分的信息 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 桌子 该 `reason` 列指定分离部件的原因。
对于用户分离的分区，原因是空的。你可以通过 [ALTER TABLE ATTACH PARTITION\|PART](../../sql-reference/statements/alter/partition.md#alter_attach-partition) 命令添加这些分区。
对于用户分离的部件，原因是空的。 这些部件可以附加 [ALTER TABLE ATTACH PARTITION\|PART](../../sql-reference/statements/alter.md#alter_attach-partition) 指挥部
关于其他列的描述，请参见 [system.parts](../../operations/system-tables/parts.md#system_tables-parts)。
有关其他列的说明，请参阅 [系统。零件](../../operations/system-tables/parts.md#system_tables-parts).
如果分区名称无效，一些列的值可能是`NULL`。你可以通过[ALTER TABLE DROP DETACHED PART](../../sql-reference/statements/alter/partition.md#alter_drop-detached)来删除这些分区。
如果部件名称无效，某些列的值可能为 `NULL`. 这些部分可以删除 [ALTER TABLE DROP DETACHED PART](../../sql-reference/statements/alter.md#alter_drop-detached).
[原文](https://clickhouse.com/docs/zh/operations/system-tables/detached_parts) <!--hide-->

40
docs/zh/operations/system-tables/disks.md
View File

@ -1,31 +1,27 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.disks {#system_tables-disks}
# 系统。磁盘 {#system_tables-disks}
包含有关在定义的磁盘信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
包含在 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure) 中定义的磁盘信息.
列:
- `name` ([字符串](../../sql-reference/data-types/string.md)) — Name of a disk in the server configuration.
- `path` ([字符串](../../sql-reference/data-types/string.md)) — Path to the mount point in the file system.
- `free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Free space on disk in bytes.
- `total_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Disk volume in bytes.
- `keep_free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Amount of disk space that should stay free on disk in bytes. Defined in the `keep_free_space_bytes` 磁盘配置参数。
- `name` ([字符串](../../sql-reference/data-types/string.md)) — 服务器配置中的磁盘名称.
- `path` ([字符串](../../sql-reference/data-types/string.md)) — 文件系统中挂载点的路径.
- `free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 磁盘上的可用空间，以字节为单位.
- `total_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 磁盘容量，以字节为单位。
- `keep_free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 在磁盘上应保持空闲的磁盘空间的数量，以字节为单位。在磁盘配置的 `keep_free_space_bytes` 参数中定义。
## 系统。storage_policies {#system_tables-storage_policies}
**示例**
包含有关存储策略和卷中定义的信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
```sql
:) SELECT * FROM system.disks;
```
列:
```text
┌─name────┬─path─────────────────┬───free_space─┬──total_space─┬─keep_free_space─┐
│ default │ /var/lib/clickhouse/ │ 276392587264 │ 490652508160 │ 0 │
└─────────┴──────────────────────┴──────────────┴──────────────┴─────────────────┘
- `policy_name` ([字符串](../../sql-reference/data-types/string.md)) — Name of the storage policy.
- `volume_name` ([字符串](../../sql-reference/data-types/string.md)) — Volume name defined in the storage policy.
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Volume order number in the configuration.
- `disks` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Disk names, defined in the storage policy.
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
1 rows in set. Elapsed: 0.001 sec.
```
如果存储策略包含多个卷，则每个卷的信息将存储在表的单独行中。
[原文](https://clickhouse.com/docs/zh/operations/system-tables/disks) <!--hide-->

25
docs/zh/operations/system-tables/metrics.md
View File

@ -1,19 +1,14 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.metrics {#system_tables-metrics}
# 系统。指标 {#system_tables-metrics}
包含可以立即计算或具有当前值的指标。 例如，同时处理的查询的数量或当前副本的延迟。 此表始终是最新的。
此系统表包含可以即时计算或具有当前值的指标。例如，同时处理的查询数量或当前的复制延迟。这个表始终是最新的。
列:
- `metric` ([字符串](../../sql-reference/data-types/string.md)) — Metric name.
- `value` ([Int64](../../sql-reference/data-types/int-uint.md)) — Metric value.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — Metric description.
- `metric` ([字符串](../../sql-reference/data-types/string.md)) — 指标名称.
- `value` ([Int64](../../sql-reference/data-types/int-uint.md)) — 指标的值.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — 指标的描述.
支持的指标列表，您可以在 [src/Common/CurrentMetrics.cpp](https://github.com/ClickHouse/ClickHouse/blob/master/src/Common/CurrentMetrics.cpp) ClickHouse的源文件。
对于支持的指标列表，您可以查看 [src/Common/CurrentMetrics.cpp](https://github.com/ClickHouse/ClickHouse/blob/master/src/Common/CurrentMetrics.cpp) ClickHouse 的源文件。
**示例**
@ -38,7 +33,7 @@ SELECT * FROM system.metrics LIMIT 10
**另请参阅**
- [系统。asynchronous_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.
- [系统。活动](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that occurred.
- [系统。metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — Contains a history of metrics values from tables `system.metrics` и `system.events`.
- [监测](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring.
- [system.asynchronous_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — 包含周期性的计算指标。
- [system.events](../../operations/system-tables/events.md#system_tables-events) — 包含发生的一些事件。
- [system.metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log) — 包含`system.metrics`表和`system.events`表的历史指标值。
- [监控](../../operations/monitoring.md) — ClickHouse 监控的基本概念。

36
docs/zh/operations/system-tables/numbers.md
View File

@ -1,12 +1,32 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.numbers {#system-numbers}
# 系统。数字 {#system-numbers}
这个表有一个名为 `number` 的 UInt64 列，包含了几乎所有从 0 开始的自然数。
此表包含一个名为UInt64的列 `number` 它包含几乎所有从零开始的自然数。
你可以用这个表进行测试，或者如果你需要进行暴力搜索。
您可以使用此表进行测试，或者如果您需要进行暴力搜索。
从该表的读取是不并行的。
从此表中读取的内容不是并行的。
**示例**
```sql
:) SELECT * FROM system.numbers LIMIT 10;
```
```text
┌─number─┐
│ 0 │
│ 1 │
│ 2 │
│ 3 │
│ 4 │
│ 5 │
│ 6 │
│ 7 │
│ 8 │
│ 9 │
└────────┘
10 rows in set. Elapsed: 0.001 sec.
```
[原文](https://clickhouse.com/docs/zh/operations/system-tables/numbers) <!--hide-->

27
docs/zh/operations/system-tables/one.md
View File

@ -1,12 +1,23 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.one {#system-one}
# 系统。一 {#system-one}
此表包含一行只有一个值为 0 的 `dummy` UInt8 列的数据。
此表包含一行，其中包含一行 `dummy` UInt8列包含值0。
如果 `SELECT` 查询没有指定 `FROM` 子句，就会使用这个表来查询。
如果使用此表 `SELECT` 查询不指定 `FROM` 条款
这个表类似于其他数据库管理系统(DMBS)中的 `DUAL` 表。
这类似于 `DUAL` 表在其他Dbms中找到。
**示例**
```sql
:) SELECT * FROM system.one LIMIT 10;
```
```text
┌─dummy─┐
│ 0 │
└───────┘
1 rows in set. Elapsed: 0.001 sec.
```
[原文](https://clickhouse.com/docs/zh/operations/system-tables/one) <!--hide-->

168
docs/zh/operations/system-tables/parts.md
View File

@ -1,85 +1,167 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.parts {#system_tables-parts}
# 系统。零件 {#system_tables-parts}
此系统表包含 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 表分区的相关信息。
包含有关的部分信息 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 桌子
每行描述一个数据部分。
每一行描述一个数据分区。
列:
- `partition` (String) – The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter.md#query_language_queries_alter) 查询。
- `partition` ([String](../../sql-reference/data-types/string.md)) – 分区名称。请参阅 [ALTER](../../sql-reference/statements/alter/index.md#query_language_queries_alter) 查询的说明，来了解什么是分区。
格式:
- `YYYYMM` 用于按月自动分区。
- `any_string` 手动分区时。
- `any_string` 手动分区时，是其他格式的字符串。
- `name` (`String`) – Name of the data part.
- `name` ([String](../../sql-reference/data-types/string.md)) – 数据分区的名称。
- `active` (`UInt8`) – Flag that indicates whether the data part is active. If a data part is active, it's used in a table. Otherwise, it's deleted. Inactive data parts remain after merging.
- `part_type` ([String](../../sql-reference/data-types/string.md)) — 数据分区的存储格式。
- `marks` (`UInt64`) – The number of marks. To get the approximate number of rows in a data part, multiply `marks` 通过索引粒度（通常为8192）（此提示不适用于自适应粒度）。
可能的值:
- `rows` (`UInt64`) – The number of rows.
- `Wide` — 每一列在文件系统中的一个单独文件中存储。
- `Compact` — 所有列在文件系统中的一个文件中存储。
- `bytes_on_disk` (`UInt64`) – Total size of all the data part files in bytes.
数据存储格式由 [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 表的 `min_bytes_for_wide_part` 和 `min_rows_for_wide_part` 控制。
- `data_compressed_bytes` (`UInt64`) – Total size of compressed data in the data part. All the auxiliary files (for example, files with marks) are not included.
- `active` ([UInt8](../../sql-reference/data-types/int-uint.md)) – 指示数据分区是否处于活动状态的标志。如果数据分区处于活动状态，则此数据正在被表使用。反之，则不活跃(deleted)。合并后仍会保留非活跃的数据分区。
- `data_uncompressed_bytes` (`UInt64`) – Total size of uncompressed data in the data part. All the auxiliary files (for example, files with marks) are not included.
- `marks` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 标记数。要获得数据分区中的大致行数：使用`marks`(标记数)乘以索引粒度(通常为 8192)。不适用于自适应颗粒度。
- `marks_bytes` (`UInt64`) – The size of the file with marks.
- `rows` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 行数.
- `modification_time` (`DateTime`) – The time the directory with the data part was modified. This usually corresponds to the time of data part creation.\|
- `bytes_on_disk` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 数据总大小（以字节为单位）。
- `remove_time` (`DateTime`) – The time when the data part became inactive.
- `data_compressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 数据分区中压缩数据的总大小。不包括所有辅助文件（例如，带有标记的文件）。
- `refcount` (`UInt32`) – The number of places where the data part is used. A value greater than 2 indicates that the data part is used in queries or merges.
- `data_uncompressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 数据分区中未压缩数据的总大小。不包括所有辅助文件（例如，带有标记的文件）。
- `min_date` (`Date`) – The minimum value of the date key in the data part.
- `marks_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 带有标记的文件的大小。
- `max_date` (`Date`) – The maximum value of the date key in the data part.
- `secondary_indices_compressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 数据分区中二级索引的压缩数据总大小。所有的辅助文件（例如，带有标记的文件）都不包括在内。
- `min_time` (`DateTime`) – The minimum value of the date and time key in the data part.
- `secondary_indices_uncompressed_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 数据分区中二级索引的未压缩数据的总大小。所有的辅助文件（例如，带有标记的文件）都不包括在内。
- `max_time`(`DateTime`) – The maximum value of the date and time key in the data part.
- `secondary_indices_marks_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 带标记的二级索引的文件大小。
- `partition_id` (`String`) – ID of the partition.
- `modification_time` ([DateTime](../../sql-reference/data-types/datetime.md)) – 包含数据分区的目录被修改的时间。这通常对应于数据部分创建的时间。
- `min_block_number` (`UInt64`) – The minimum number of data parts that make up the current part after merging.
- `remove_time` ([DateTime](../../sql-reference/data-types/datetime.md)) – 数据分区变为非活动状态的时间。
- `max_block_number` (`UInt64`) – The maximum number of data parts that make up the current part after merging.
- `refcount` ([UInt32](../../sql-reference/data-types/int-uint.md)) – 使用数据部分的位置数。大于 2 的值表示数据部分用于查询或是用于合并。
- `level` (`UInt32`) – Depth of the merge tree. Zero means that the current part was created by insert rather than by merging other parts.
- `min_date` ([Date](../../sql-reference/data-types/date.md)) – 数据部分中日期键的最小值。
- `data_version` (`UInt64`) – Number that is used to determine which mutations should be applied to the data part (mutations with a version higher than `data_version`).
- `max_date` ([Date](../../sql-reference/data-types/date.md)) – 数据部分中日期键的最大值。
- `primary_key_bytes_in_memory` (`UInt64`) – The amount of memory (in bytes) used by primary key values.
- `min_time` ([DateTime](../../sql-reference/data-types/datetime.md)) – 数据部分中日期和时间键的最小值。
- `primary_key_bytes_in_memory_allocated` (`UInt64`) – The amount of memory (in bytes) reserved for primary key values.
- `max_time`([DateTime](../../sql-reference/data-types/datetime.md)) – 数据部分中日期和时间键的最大值。
- `is_frozen` (`UInt8`) – Flag that shows that a partition data backup exists. 1, the backup exists. 0, the backup doesn't exist. For more details, see [FREEZE PARTITION](../../sql-reference/statements/alter.md#alter_freeze-partition)
- `partition_id` ([String](../../sql-reference/data-types/string.md)) – 分区的 ID。
- `database` (`String`) – Name of the database.
- `min_block_number` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 合并后构成当前部分的最小数据部分数量。
- `table` (`String`) – Name of the table.
- `max_block_number` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 合并后构成当前部分的最大数据部分数量。
- `engine` (`String`) – Name of the table engine without parameters.
- `level` ([UInt32](../../sql-reference/data-types/int-uint.md)) – 合并树的深度。值为 0 表示该分区是通过插入创建的，而不是通过合并创建的。
- `path` (`String`) – Absolute path to the folder with data part files.
- `data_version` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 用于确定应将哪些订正(mutations)应用于数据部分（版本高于 `data_version` 的订正(mutations)）的数字。
- `disk` (`String`) – Name of a disk that stores the data part.
- `primary_key_bytes_in_memory` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 主键值使用的内存量（以字节为单位）。
- `hash_of_all_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 的压缩文件。
- `primary_key_bytes_in_memory_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md)) – 为主键值保留的内存量（以字节为单位）。
- `hash_of_uncompressed_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 未压缩的文件（带标记的文件，索引文件等。).
- `is_frozen` ([UInt8](../../sql-reference/data-types/int-uint.md)) – 显示分区数据备份存在的标志。1，备份存在。0，备份不存在。更多细节，见 [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md#alter_freeze-partition)。
- `uncompressed_hash_of_compressed_files` (`String`) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) 压缩文件中的数据，就好像它们是未压缩的。
- `database` ([String](../../sql-reference/data-types/string.md)) – 数据库的名称。
- `bytes` (`UInt64`) – Alias for `bytes_on_disk`.
- `table` ([String](../../sql-reference/data-types/string.md)) – 表的名称。
- `marks_size` (`UInt64`) – Alias for `marks_bytes`.
- `engine` ([String](../../sql-reference/data-types/string.md)) – 不带参数的表引擎名称。
- `path` ([String](../../sql-reference/data-types/string.md)) – 包含数据部分文件的文件夹的绝对路径。
- `disk` ([String](../../sql-reference/data-types/string.md)) – 存储数据部分的磁盘的名称。
- `hash_of_all_files` ([String](../../sql-reference/data-types/string.md)) – 压缩文件的 [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128)。
- `hash_of_uncompressed_files` ([String](../../sql-reference/data-types/string.md)) – 未压缩文件(带有标记的文件、索引文件等)的 [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128)。
- `uncompressed_hash_of_compressed_files` ([String](../../sql-reference/data-types/string.md)) – 压缩文件中的数据(没有压缩时)的 [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128)。
- `delete_ttl_info_min` ([DateTime](../../sql-reference/data-types/datetime.md)) — [TTL DELETE 规则](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl) 的日期和时间键的最小值。
- `delete_ttl_info_max` ([DateTime](../../sql-reference/data-types/datetime.md)) — [TTL DELETE 规则](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl) 的日期和时间键的最大值。
- `move_ttl_info.expression` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — 表达式的数组。 每个表达式定义一个 [TTL MOVE 规则](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
!!! note "警告"
保留 `move_ttl_info.expression` 数组主要是为了向后兼容，现在检查 `TTL MOVE` 规则最简单的方法是使用 `move_ttl_info.min` 和 `move_ttl_info.max` 字段。
- `move_ttl_info.min` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — 日期值和时间值的数组。数组中的每个元素都描述了一个 [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl) 的最小键值。
- `move_ttl_info.max` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — 日期值和时间值的数组。数组中的每个元素都描述了一个 [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl) 的最大键值。
- `bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – `bytes_on_disk`的别名。
- `marks_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) – `marks_bytes`的别名。
**示例**
``` sql
SELECT * FROM system.parts LIMIT 1 FORMAT Vertical;
```
``` text
Row 1:
──────
partition: tuple()
name: all_1_4_1_6
part_type: Wide
active: 1
marks: 2
rows: 6
bytes_on_disk: 310
data_compressed_bytes: 157
data_uncompressed_bytes: 91
secondary_indices_compressed_bytes: 58
secondary_indices_uncompressed_bytes: 6
secondary_indices_marks_bytes: 48
marks_bytes: 144
modification_time: 2020-06-18 13:01:49
remove_time: 1970-01-01 00:00:00
refcount: 1
min_date: 1970-01-01
max_date: 1970-01-01
min_time: 1970-01-01 00:00:00
max_time: 1970-01-01 00:00:00
partition_id: all
min_block_number: 1
max_block_number: 4
level: 1
data_version: 6
primary_key_bytes_in_memory: 8
primary_key_bytes_in_memory_allocated: 64
is_frozen: 0
database: default
table: months
engine: MergeTree
disk_name: default
path: /var/lib/clickhouse/data/default/months/all_1_4_1_6/
hash_of_all_files: 2d0657a16d9430824d35e327fcbd87bf
hash_of_uncompressed_files: 84950cc30ba867c77a408ae21332ba29
uncompressed_hash_of_compressed_files: 1ad78f1c6843bbfb99a2c931abe7df7d
delete_ttl_info_min: 1970-01-01 00:00:00
delete_ttl_info_max: 1970-01-01 00:00:00
move_ttl_info.expression: []
move_ttl_info.min: []
move_ttl_info.max: []
```
**另请参阅**
- [MergeTree(合并树)家族](../../engines/table-engines/mergetree-family/mergetree.md)
- [列和表的 TTL](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl)
[原文](https://clickhouse.com/docs/zh/operations/system-tables/parts) <!--hide-->

39
docs/zh/operations/system-tables/settings.md
View File

@ -1,27 +1,22 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.settings {#system-tables-system-settings}
# 系统。设置 {#system-tables-system-settings}
包含有关当前用户的会话设置的信息。
包含当前用户会话设置的相关信息。
列:
- `name` ([字符串](../../sql-reference/data-types/string.md)) — Setting name.
- `value` ([字符串](../../sql-reference/data-types/string.md)) — Setting value.
- `changed` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Shows whether a setting is changed from its default value.
- `description` ([字符串](../../sql-reference/data-types/string.md)) — Short setting description.
- `min` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — Minimum value of the setting, if any is set via [制约因素](../../operations/settings/constraints-on-settings.md#constraints-on-settings). 如果设置没有最小值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `max` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — Maximum value of the setting, if any is set via [制约因素](../../operations/settings/constraints-on-settings.md#constraints-on-settings). 如果设置没有最大值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `readonly` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Shows whether the current user can change the setting:
- `0` — Current user can change the setting.
- `1` — Current user can't change the setting.
- `name` ([字符串](../../sql-reference/data-types/string.md)) — 设置名称。
- `value` ([字符串](../../sql-reference/data-types/string.md)) — 设置的值。
- `changed` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — 显示该设置是否从其默认值修改。
- `description` ([字符串](../../sql-reference/data-types/string.md)) — 该设置的简要描述。
- `min` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — 该设置的最小值，如果有最小值，则是通过[约束](../../operations/settings/constraints-on-settings.md#constraints-on-settings)设置的。如果该设置没有最小值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `max` ([可为空](../../sql-reference/data-types/nullable.md)([字符串](../../sql-reference/data-types/string.md))) — 该设置的最大值, 如果有最大值，则是通过[约束](../../operations/settings/constraints-on-settings.md#constraints-on-settings)设置的。如果该设置没有最大值，则包含 [NULL](../../sql-reference/syntax.md#null-literal).
- `readonly` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — 当前用户是否可以修改该设置:
- `0` — 当前用户可以修改此设置.
- `1` — 当前用户不能修改此设置.
**示例**
下面的示例演示如何获取有关名称包含的设置的信息 `min_i`.
下面的例子显示了如何获得设置名称中包含`min_i`的设置信息。
``` sql
SELECT *
@ -37,10 +32,10 @@ WHERE name LIKE '%min_i%'
└─────────────────────────────────────────────┴───────────┴─────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┴──────┴──────┴──────────┘
```
使用 `WHERE changed` 可以是有用的，例如，当你想检查:
比如，当你想要检查以下情况时，使用 `WHERE changed` 会很有用:
- 配置文件中的设置是否正确加载并正在使用。
- 在当前会话中更改的设置。
- 配置文件中的设置是否正确加载，并正在使用。
- 在当前会话中更改过的设置。
<!-- -->
@ -52,4 +47,6 @@ SELECT * FROM system.settings WHERE changed AND name='load_balancing'
- [设置](../../operations/settings/index.md#session-settings-intro)
- [查询权限](../../operations/settings/permissions-for-queries.md#settings_readonly)
- [对设置的限制](../../operations/settings/constraints-on-settings.md)
- [对设置的约束](../../operations/settings/constraints-on-settings.md)
[原文](https://clickhouse.com/docs/zh/operations/system-tables/settings) <!--hide-->

26
docs/zh/operations/system-tables/storage_policies.md
View File

@ -1,19 +1,17 @@
---
machine_translated: true
machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3
---
# system.storage_policies {#system_tables-storage_policies}
# 系统。storage_policies {#system_tables-storage_policies}
包含有关存储策略和卷中定义的信息 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure).
包含有关 [服务器配置](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes_configure) 中定义的存储策略和卷信息。
列:
- `policy_name` ([字符串](../../sql-reference/data-types/string.md)) — Name of the storage policy.
- `volume_name` ([字符串](../../sql-reference/data-types/string.md)) — Volume name defined in the storage policy.
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Volume order number in the configuration.
- `disks` ([数组（字符串)](../../sql-reference/data-types/array.md)) — Disk names, defined in the storage policy.
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
- `policy_name` ([String](../../sql-reference/data-types/string.md)) — 存储策略的名称。
- `volume_name` ([String](../../sql-reference/data-types/string.md)) — 存储策略中定义的卷名称。
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 配置中的卷顺序号，数据根据这个优先级填充卷，比如插入和合并期间的数据将被写入优先级较低的卷 (还需考虑其他规则: TTL, `max_data_part_size`, `move_factor`)。
- `disks` ([Array(String)](../../sql-reference/data-types/array.md)) — 存储策略中定义的磁盘名。
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — 可以存储在卷磁盘上数据部分的最大大小 (0 - 不限制)。
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — 磁盘空闲的比率。当比率超过配置的值，ClickHouse 将把数据向下一个卷移动。
- `prefer_not_to_merge` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 设置中 `prefer_not_to_merge` 的值. 当这个设置启用时，不允许在此卷上合并数据。这将允许控制 ClickHouse 如何与运行速度较慢的磁盘一起工作。
如果存储策略包含多个卷，则每个卷的信息将存储在表的单独行中。
如果存储策略包含多个卷，则每个卷的信息将在表中作为单独一行存储。
[原文](https://clickhouse.com/docs/zh/operations/system-tables/storage_policies) <!--hide-->

2
programs/copier/ClusterCopier.cpp
View File

@ -46,7 +46,7 @@ void ClusterCopier::init()
reloadTaskDescription();
task_cluster->loadTasks(*task_cluster_current_config);
getContext()->setClustersConfig(task_cluster_current_config, task_cluster->clusters_prefix);
getContext()->setClustersConfig(task_cluster_current_config, false, task_cluster->clusters_prefix);
/// Set up shards and their priority
task_cluster->random_engine.seed(task_cluster->random_device());

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