thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-27 10:02:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into window_view_fix

Browse Source
This commit is contained in:
Suzy Wang 2023-02-06 10:06:04 -05:00 committed by GitHub
commit 6edbffa3cc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
437 changed files with 8184 additions and 3495 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
.github/workflows/backport_branches.yml vendored
View File

@ -512,6 +512,75 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (amd64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
InstallPackagesTestAarch64:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (arm64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################

69
.github/workflows/master.yml vendored
View File

@ -946,6 +946,75 @@ jobs:
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (amd64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
InstallPackagesTestAarch64:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (arm64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################

280
.github/workflows/pull_request.yml vendored
View File

@ -984,6 +984,75 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (amd64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
InstallPackagesTestAarch64:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (arm64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
@ -2813,6 +2882,217 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
# Parallel replicas
FunctionalStatefulTestDebugParallelReplicas:
needs: [BuilderDebDebug]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_debug
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (debug, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_debug/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
FunctionalStatefulTestUBsanParallelReplicas:
needs: [BuilderDebUBsan]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_ubsan
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (ubsan, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_ubsan/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
FunctionalStatefulTestMsanParallelReplicas:
needs: [BuilderDebMsan]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_msan
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (msan, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_msan/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
FunctionalStatefulTestTsanParallelReplicas:
needs: [BuilderDebTsan]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_tsan
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (tsan, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_tsan/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
FunctionalStatefulTestAsanParallelReplicas:
needs: [BuilderDebAsan]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_debug
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (asan, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_debug/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
FunctionalStatefulTestReleaseParallelReplicas:
needs: [BuilderDebRelease]
runs-on: [self-hosted, func-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/stateful_release
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Stateful tests (release, ParallelReplicas)
REPO_COPY=${{runner.temp}}/stateful_release/ClickHouse
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
##############################################################################################
######################################### STRESS TESTS #######################################
##############################################################################################

69
.github/workflows/release_branches.yml vendored
View File

@ -604,6 +604,75 @@ jobs:
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (amd64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
InstallPackagesTestAarch64:
needs: [BuilderDebRelease]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/test_install
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Install packages (arm64)
REPO_COPY=${{runner.temp}}/test_install/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Test packages installation
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################

3
.gitmodules vendored
View File

@ -257,6 +257,9 @@
[submodule "contrib/qpl"]
path = contrib/qpl
url = https://github.com/intel/qpl
[submodule "contrib/idxd-config"]
path = contrib/idxd-config
url = https://github.com/intel/idxd-config
[submodule "contrib/wyhash"]
path = contrib/wyhash
url = https://github.com/wangyi-fudan/wyhash

2
contrib/aws vendored

@ -1 +1 @@
Subproject commit 4a12641211d4dbc8e2fdb2dd0f1eea0927db9252
Subproject commit 06a6610e6fb3385e22ad85014a67aa307825ffb1

2
contrib/azure vendored

@ -1 +1 @@
Subproject commit ea8c3044f43f5afa7016d2d580ed201f495d7e94
Subproject commit e4fcdfc81e337e589ce231a452dcc280fcbb3f99

1
contrib/idxd-config vendored Submodule

@ -0,0 +1 @@
Subproject commit f6605c41a735e3fdfef2d2d18655a33af6490b99

2
contrib/qpl vendored

@ -1 +1 @@
Subproject commit becb7a1b15bdb4845ec3721a550707ffa51d029d
Subproject commit d75a29d95d8a548297fce3549d21020005364dc8

30
contrib/qpl-cmake/CMakeLists.txt
View File

@ -10,11 +10,30 @@ if (NOT ENABLE_QPL)
return()
endif()
## QPL has build dependency on libaccel-config. Here is to build libaccel-config which is required by QPL.
## libaccel-config is the utility library for controlling and configuring Intel® In-Memory Analytics Accelerator (Intel® IAA).
set (LIBACCEL_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/idxd-config")
set (UUID_DIR "${ClickHouse_SOURCE_DIR}/contrib/qpl-cmake")
set (LIBACCEL_HEADER_DIR "${ClickHouse_SOURCE_DIR}/contrib/qpl-cmake/idxd-header")
set (SRCS
"${LIBACCEL_SOURCE_DIR}/accfg/lib/libaccfg.c"
"${LIBACCEL_SOURCE_DIR}/util/log.c"
"${LIBACCEL_SOURCE_DIR}/util/sysfs.c"
)
add_library(accel-config ${SRCS})
target_compile_options(accel-config PRIVATE "-D_GNU_SOURCE")
target_include_directories(accel-config BEFORE
PRIVATE ${UUID_DIR}
PRIVATE ${LIBACCEL_HEADER_DIR}
PRIVATE ${LIBACCEL_SOURCE_DIR})
## QPL build start here.
set (QPL_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/qpl")
set (QPL_SRC_DIR "${ClickHouse_SOURCE_DIR}/contrib/qpl/sources")
set (QPL_BINARY_DIR "${ClickHouse_BINARY_DIR}/build/contrib/qpl")
set (UUID_DIR "${ClickHouse_SOURCE_DIR}/contrib/qpl-cmake")
set (EFFICIENT_WAIT OFF)
set (BLOCK_ON_FAULT ON)
set (LOG_HW_INIT OFF)
@ -315,13 +334,8 @@ target_compile_definitions(_qpl
PRIVATE -DQPL_BADARG_CHECK
PUBLIC -DENABLE_QPL_COMPRESSION)
find_library(LIBACCEL accel-config)
if(NOT LIBACCEL)
message(FATAL_ERROR "Please install QPL dependency library:libaccel-config from https://github.com/intel/idxd-config")
endif()
target_link_libraries(_qpl
PRIVATE ${LIBACCEL}
PRIVATE accel-config
PRIVATE ${CMAKE_DL_LIBS})
add_library (ch_contrib::qpl ALIAS _qpl)

159
contrib/qpl-cmake/idxd-header/config.h Normal file
View File

@ -0,0 +1,159 @@
/* config.h. Generated from config.h.in by configure. */
/* config.h.in. Generated from configure.ac by autoheader. */
/* Define if building universal (internal helper macro) */
/* #undef AC_APPLE_UNIVERSAL_BUILD */
/* Debug messages. */
/* #undef ENABLE_DEBUG */
/* Documentation / man pages. */
/* #define ENABLE_DOCS */
/* System logging. */
#define ENABLE_LOGGING 1
/* accfg test support */
/* #undef ENABLE_TEST */
/* Define to 1 if big-endian-arch */
/* #undef HAVE_BIG_ENDIAN */
/* Define to 1 if you have the <dlfcn.h> header file. */
#define HAVE_DLFCN_H 1
/* Define to 1 if you have the <inttypes.h> header file. */
#define HAVE_INTTYPES_H 1
/* Define to 1 if you have the <linux/version.h> header file. */
#define HAVE_LINUX_VERSION_H 1
/* Define to 1 if little-endian-arch */
#define HAVE_LITTLE_ENDIAN 1
/* Define to 1 if you have the <memory.h> header file. */
#define HAVE_MEMORY_H 1
/* Define to 1 if you have the `secure_getenv' function. */
#define HAVE_SECURE_GETENV 1
/* Define to 1 if you have statement expressions. */
#define HAVE_STATEMENT_EXPR 1
/* Define to 1 if you have the <stdint.h> header file. */
#define HAVE_STDINT_H 1
/* Define to 1 if you have the <stdlib.h> header file. */
#define HAVE_STDLIB_H 1
/* Define to 1 if you have the <strings.h> header file. */
#define HAVE_STRINGS_H 1
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
/* Define to 1 if you have the <sys/stat.h> header file. */
#define HAVE_SYS_STAT_H 1
/* Define to 1 if you have the <sys/types.h> header file. */
#define HAVE_SYS_TYPES_H 1
/* Define to 1 if typeof works with your compiler. */
#define HAVE_TYPEOF 1
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* Define to 1 if using libuuid */
#define HAVE_UUID 1
/* Define to 1 if you have the `__secure_getenv' function. */
/* #undef HAVE___SECURE_GETENV */
/* Define to the sub-directory where libtool stores uninstalled libraries. */
#define LT_OBJDIR ".libs/"
/* Name of package */
#define PACKAGE "accel-config"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT "linux-dsa@lists.01.org"
/* Define to the full name of this package. */
#define PACKAGE_NAME "accel-config"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "accel-config 3.5.2.gitf6605c41"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "accel-config"
/* Define to the home page for this package. */
#define PACKAGE_URL "https://github.com/xxx/accel-config"
/* Define to the version of this package. */
#define PACKAGE_VERSION "3.5.2.gitf6605c41"
/* Define to 1 if you have the ANSI C header files. */
#define STDC_HEADERS 1
/* Enable extensions on AIX 3, Interix. */
#ifndef _ALL_SOURCE
# define _ALL_SOURCE 1
#endif
/* Enable GNU extensions on systems that have them. */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE 1
#endif
/* Enable threading extensions on Solaris. */
#ifndef _POSIX_PTHREAD_SEMANTICS
# define _POSIX_PTHREAD_SEMANTICS 1
#endif
/* Enable extensions on HP NonStop. */
#ifndef _TANDEM_SOURCE
# define _TANDEM_SOURCE 1
#endif
/* Enable general extensions on Solaris. */
#ifndef __EXTENSIONS__
# define __EXTENSIONS__ 1
#endif
/* Version number of package */
#define VERSION "3.5.2.gitf6605c41"
/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most
significant byte first (like Motorola and SPARC, unlike Intel). */
#if defined AC_APPLE_UNIVERSAL_BUILD
# if defined __BIG_ENDIAN__
# define WORDS_BIGENDIAN 1
# endif
#else
# ifndef WORDS_BIGENDIAN
/* # undef WORDS_BIGENDIAN */
# endif
#endif
/* Enable large inode numbers on Mac OS X 10.5. */
#ifndef _DARWIN_USE_64_BIT_INODE
# define _DARWIN_USE_64_BIT_INODE 1
#endif
/* Number of bits in a file offset, on hosts where this is settable. */
/* #undef _FILE_OFFSET_BITS */
/* Define for large files, on AIX-style hosts. */
/* #undef _LARGE_FILES */
/* Define to 1 if on MINIX. */
/* #undef _MINIX */
/* Define to 2 if the system does not provide POSIX.1 features except with
this defined. */
/* #undef _POSIX_1_SOURCE */
/* Define to 1 if you need to in order for `stat' and other things to work. */
/* #undef _POSIX_SOURCE */
/* Define to __typeof__ if your compiler spells it that way. */
/* #undef typeof */

2
docker/docs/builder/Dockerfile
View File

@ -21,5 +21,3 @@ RUN yarn config set registry https://registry.npmjs.org \
COPY run.sh /run.sh
ENTRYPOINT ["/run.sh"]
CMD ["yarn", "build"]

3
docker/docs/builder/run.sh
View File

@ -25,7 +25,8 @@ done
sed -i '/onBrokenMarkdownLinks:/ s/ignore/error/g' docusaurus.config.js
if [[ $# -lt 1 ]] || [[ "$1" == "--"* ]]; then
export CI=true
export CI=true
yarn install
exec yarn build "$@"
fi

8
docker/images.json
View File

@ -134,6 +134,14 @@
"name": "clickhouse/keeper-jepsen-test",
"dependent": []
},
"docker/test/install/deb": {
"name": "clickhouse/install-deb-test",
"dependent": []
},
"docker/test/install/rpm": {
"name": "clickhouse/install-rpm-test",
"dependent": []
},
"docker/docs/builder": {
"name": "clickhouse/docs-builder",
"dependent": [

2
docker/server/Dockerfile.alpine
View File

@ -33,7 +33,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.1.2.9"
ARG VERSION="23.1.3.5"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# user/group precreated explicitly with fixed uid/gid on purpose.

2
docker/server/Dockerfile.ubuntu
View File

@ -21,7 +21,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="deb https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
ARG VERSION="23.1.2.9"
ARG VERSION="23.1.3.5"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# set non-empty deb_location_url url to create a docker image

1
docker/test/fasttest/run.sh
View File

@ -231,6 +231,7 @@ function run_tests
--hung-check
--fast-tests-only
--no-random-settings
--no-random-merge-tree-settings
--no-long
--testname
--shard

64
docker/test/install/deb/Dockerfile Normal file
View File

@ -0,0 +1,64 @@
FROM ubuntu:22.04
# The Dockerfile is nicely borrowed from
# https://github.com/lionelnicolas/docker-ubuntu-systemd/blob/83aa3249146f5df264fe45353f79fc76eb1e42d7/Dockerfile
ENV \
DEBIAN_FRONTEND=noninteractive \
LANG=C.UTF-8 \
container=docker \
init=/lib/systemd/systemd
# install systemd packages
RUN apt-get update && \
apt-get install -y --no-install-recommends \
systemd \
&& \
apt-get clean && \
rm -rf /var/lib/apt/lists
# configure systemd
# remove systemd 'wants' triggers
# remove everything except tmpfiles setup in sysinit target
# remove UTMP updater service
# disable /tmp mount
# fix missing BPF firewall support warning
# just for cosmetics, fix "not-found" entries while using "systemctl --all"
RUN \
find \
/etc/systemd/system/*.wants/* \
/lib/systemd/system/multi-user.target.wants/* \
/lib/systemd/system/sockets.target.wants/*initctl* \
! -type d \
-delete && \
find \
/lib/systemd/system/sysinit.target.wants \
! -type d \
! -name '*systemd-tmpfiles-setup*' \
-delete && \
find \
/lib/systemd \
-name systemd-update-utmp-runlevel.service \
-delete && \
rm -vf /usr/share/systemd/tmp.mount && \
sed -ri '/^IPAddressDeny/d' /lib/systemd/system/systemd-journald.service && \
for MATCH in \
plymouth-start.service \
plymouth-quit-wait.service \
syslog.socket \
syslog.service \
display-manager.service \
systemd-sysusers.service \
tmp.mount \
systemd-udevd.service \
; do \
grep -rn --binary-files=without-match ${MATCH} /lib/systemd/ | cut -d: -f1 | xargs sed -ri 's/(.*=.*)'${MATCH}'(.*)/\1\2/'; \
done && \
systemctl disable ondemand.service && \
systemctl set-default multi-user.target
VOLUME ["/run", "/run/lock"]
STOPSIGNAL SIGRTMIN+3
ENTRYPOINT ["/lib/systemd/systemd"]

55
docker/test/install/rpm/Dockerfile Normal file
View File

@ -0,0 +1,55 @@
FROM centos:8
# The Dockerfile is nicely borrowed from
# https://github.com/lionelnicolas/docker-ubuntu-systemd/blob/83aa3249146f5df264fe45353f79fc76eb1e42d7/Dockerfile
ENV \
LANG=C.UTF-8 \
container=docker \
init=/lib/systemd/systemd
# configure systemd
# remove systemd 'wants' triggers
# remove everything except tmpfiles setup in sysinit target
# remove UTMP updater service
# disable /tmp mount
# fix missing BPF firewall support warning
# just for cosmetics, fix "not-found" entries while using "systemctl --all"
RUN \
find \
/etc/systemd/system/*.wants/ \
/lib/systemd/system/multi-user.target.wants/ \
/lib/systemd/system/local-fs.target.wants/ \
/lib/systemd/system/sockets.target.wants/*initctl* \
! -type d \
-delete && \
find \
/lib/systemd/system/sysinit.target.wants \
! -type d \
! -name '*systemd-tmpfiles-setup*' \
-delete && \
find \
/lib/systemd \
-name systemd-update-utmp-runlevel.service \
-delete && \
rm -vf /usr/share/systemd/tmp.mount && \
sed -ri '/^IPAddressDeny/d' /lib/systemd/system/systemd-journald.service && \
for MATCH in \
plymouth-start.service \
plymouth-quit-wait.service \
syslog.socket \
syslog.service \
display-manager.service \
systemd-sysusers.service \
tmp.mount \
systemd-udevd.service \
; do \
grep -rn --binary-files=without-match ${MATCH} /lib/systemd/ | cut -d: -f1 | xargs sed -ri 's/(.*=.*)'${MATCH}'(.*)/\1\2/'; \
done && \
systemctl set-default multi-user.target
VOLUME ["/run", "/run/lock"]
STOPSIGNAL SIGRTMIN+3
ENTRYPOINT ["/lib/systemd/systemd"]

15
docker/test/stateful/run.sh
View File

@ -126,13 +126,16 @@ function run_tests()
fi
set +e
clickhouse-test -j 2 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --hung-check --print-time \
--skip 00168_parallel_processing_on_replicas "${ADDITIONAL_OPTIONS[@]}" \
if [[ -n "$USE_PARALLEL_REPLICAS" ]] && [[ "$USE_PARALLEL_REPLICAS" -eq 1 ]]; then
clickhouse-test --client="clickhouse-client --use_hedged_requests=0 --allow_experimental_parallel_reading_from_replicas=1 \
--max_parallel_replicas=100 --cluster_for_parallel_replicas='parallel_replicas'" \
-j 2 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --no-parallel-replicas --hung-check --print-time "${ADDITIONAL_OPTIONS[@]}" \
"$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt
clickhouse-test --timeout 1200 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --hung-check --print-time \
00168_parallel_processing_on_replicas "${ADDITIONAL_OPTIONS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a test_output/test_result.txt
else
clickhouse-test -j 2 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --hung-check --print-time "${ADDITIONAL_OPTIONS[@]}" \
"$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt
fi
set -e
}

6
docker/test/stateless/run.sh
View File

@ -134,9 +134,9 @@ function run_tests()
set +e
clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
--test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \
| tee -a test_output/test_result.txt
--test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \
| tee -a test_output/test_result.txt
set -e
}

44
docker/test/stress/run.sh
View File

@ -13,15 +13,28 @@ sysctl kernel.core_pattern='core.%e.%p-%P'
OK="\tOK\t\\N\t"
FAIL="\tFAIL\t\\N\t"
FAILURE_CONTEXT_LINES=50
FAILURE_CONTEXT_MAX_LINE_WIDTH=400
function escaped()
{
# That's the simplest way I found to escape a string in bash. Yep, bash is the most convenient programming language.
clickhouse local -S 's String' --input-format=LineAsString -q "select * from table format CustomSeparated settings format_custom_row_after_delimiter='\\\\\\\\n'"
# Also limit lines width just in case (too long lines are not really useful usually)
clickhouse local -S 's String' --input-format=LineAsString -q "select substr(s, 1, $FAILURE_CONTEXT_MAX_LINE_WIDTH)
from table format CustomSeparated settings format_custom_row_after_delimiter='\\\\\\\\n'"
}
function head_escaped()
{
head -50 $1 | escaped
head -n $FAILURE_CONTEXT_LINES $1 | escaped
}
function unts()
{
grep -Po "[0-9][0-9]:[0-9][0-9] \K.*"
}
function trim_server_logs()
{
head -n $FAILURE_CONTEXT_LINES "/test_output/$1" | grep -Eo " \[ [0-9]+ \] \{.*" | escaped
}
function install_packages()
@ -167,7 +180,7 @@ function start()
then
echo "Cannot start clickhouse-server"
rg --text "<Error>.*Application" /var/log/clickhouse-server/clickhouse-server.log > /test_output/application_errors.txt ||:
echo -e "Cannot start clickhouse-server$FAIL$(head_escaped /test_output/application_errors.txt)" >> /test_output/test_results.tsv
echo -e "Cannot start clickhouse-server$FAIL$(trim_server_logs application_errors.txt)" >> /test_output/test_results.tsv
cat /var/log/clickhouse-server/stdout.log
tail -n100 /var/log/clickhouse-server/stderr.log
tail -n100000 /var/log/clickhouse-server/clickhouse-server.log | rg -F -v -e '<Warning> RaftInstance:' -e '<Information> RaftInstance' | tail -n100
@ -389,7 +402,7 @@ start
# NOTE Hung check is implemented in docker/tests/stress/stress
rg -Fa "No queries hung" /test_output/test_results.tsv | grep -Fa "OK" \
|| echo -e "Hung check failed, possible deadlock found (see hung_check.log)$FAIL$(head_escaped /test_output/hung_check.log)"
|| echo -e "Hung check failed, possible deadlock found (see hung_check.log)$FAIL$(head_escaped /test_output/hung_check.log | unts)"
stop
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.stress.log
@ -402,7 +415,7 @@ start
clickhouse-client --query "SELECT 'Server successfully started', 'OK', NULL, ''" >> /test_output/test_results.tsv \
|| (rg --text "<Error>.*Application" /var/log/clickhouse-server/clickhouse-server.log > /test_output/application_errors.txt \
&& echo -e "Server failed to start (see application_errors.txt and clickhouse-server.clean.log)$FAIL$(head_escaped /test_output/application_errors.txt)" \
&& echo -e "Server failed to start (see application_errors.txt and clickhouse-server.clean.log)$FAIL$(trim_server_logs application_errors.txt)" \
>> /test_output/test_results.tsv)
stop
@ -435,7 +448,7 @@ rg -Fa "Code: 49. DB::Exception: " /var/log/clickhouse-server/clickhouse-server*
# No such key errors
rg --text "Code: 499.*The specified key does not exist" /var/log/clickhouse-server/clickhouse-server*.log > /test_output/no_such_key_errors.txt \
&& echo -e "S3_ERROR No such key thrown (see clickhouse-server.log or no_such_key_errors.txt)$FAIL$(head_escaped /test_output/no_such_key_errors.txt)" >> /test_output/test_results.tsv \
&& echo -e "S3_ERROR No such key thrown (see clickhouse-server.log or no_such_key_errors.txt)$FAIL$(trim_server_logs no_such_key_errors.txt)" >> /test_output/test_results.tsv \
|| echo -e "No lost s3 keys$OK" >> /test_output/test_results.tsv
# Remove file no_such_key_errors.txt if it's empty
@ -448,7 +461,7 @@ rg -Fa "########################################" /var/log/clickhouse-server/cli
# It also checks for crash without stacktrace (printed by watchdog)
rg -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server*.log > /test_output/fatal_messages.txt \
&& echo -e "Fatal message in clickhouse-server.log (see fatal_messages.txt)$FAIL$(head_escaped /test_output/fatal_messages.txt)" >> /test_output/test_results.tsv \
&& echo -e "Fatal message in clickhouse-server.log (see fatal_messages.txt)$FAIL$(trim_server_logs fatal_messages.txt)" >> /test_output/test_results.tsv \
|| echo -e "No fatal messages in clickhouse-server.log$OK" >> /test_output/test_results.tsv
# Remove file fatal_messages.txt if it's empty
@ -457,8 +470,13 @@ rg -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server*.log > /test_out
rg -Fa "########################################" /test_output/* > /dev/null \
&& echo -e "Killed by signal (output files)$FAIL" >> /test_output/test_results.tsv
function get_gdb_log_context()
{
rg -A50 -Fa " received signal " /test_output/gdb.log | head_escaped
}
rg -Fa " received signal " /test_output/gdb.log > /dev/null \
&& echo -e "Found signal in gdb.log$FAIL$(rg -A50 -Fa " received signal " /test_output/gdb.log | escaped)" >> /test_output/test_results.tsv
&& echo -e "Found signal in gdb.log$FAIL$(get_gdb_log_context)" >> /test_output/test_results.tsv
if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
echo -e "Backward compatibility check\n"
@ -579,7 +597,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
start 500
clickhouse-client --query "SELECT 'Backward compatibility check: Server successfully started', 'OK', NULL, ''" >> /test_output/test_results.tsv \
|| (rg --text "<Error>.*Application" /var/log/clickhouse-server/clickhouse-server.log >> /test_output/bc_check_application_errors.txt \
&& echo -e "Backward compatibility check: Server failed to start$FAIL$(head_escaped /test_output/bc_check_application_errors.txt)" >> /test_output/test_results.tsv)
&& echo -e "Backward compatibility check: Server failed to start$FAIL$(trim_server_logs bc_check_application_errors.txt)" >> /test_output/test_results.tsv)
clickhouse-client --query="SELECT 'Server version: ', version()"
@ -634,7 +652,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
-e "Session expired" \
-e "TOO_MANY_PARTS" \
/var/log/clickhouse-server/clickhouse-server.backward.dirty.log | rg -Fa "<Error>" > /test_output/bc_check_error_messages.txt \
&& echo -e "Backward compatibility check: Error message in clickhouse-server.log (see bc_check_error_messages.txt)$FAIL$(head_escaped /test_output/bc_check_error_messages.txt)" \
&& echo -e "Backward compatibility check: Error message in clickhouse-server.log (see bc_check_error_messages.txt)$FAIL$(trim_server_logs bc_check_error_messages.txt)" \
>> /test_output/test_results.tsv \
|| echo -e "Backward compatibility check: No Error messages in clickhouse-server.log$OK" >> /test_output/test_results.tsv
@ -657,7 +675,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
# Logical errors
echo "Check for Logical errors in server log:"
rg -Fa -A20 "Code: 49. DB::Exception:" /var/log/clickhouse-server/clickhouse-server.backward.*.log > /test_output/bc_check_logical_errors.txt \
&& echo -e "Backward compatibility check: Logical error thrown (see clickhouse-server.log or bc_check_logical_errors.txt)$FAIL$(head_escaped /test_output/bc_check_logical_errors.txt)" \
&& echo -e "Backward compatibility check: Logical error thrown (see clickhouse-server.log or bc_check_logical_errors.txt)$FAIL$(trim_server_logs bc_check_logical_errors.txt)" \
>> /test_output/test_results.tsv \
|| echo -e "Backward compatibility check: No logical errors$OK" >> /test_output/test_results.tsv
@ -672,7 +690,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
# It also checks for crash without stacktrace (printed by watchdog)
echo "Check for Fatal message in server log:"
rg -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server.backward.*.log > /test_output/bc_check_fatal_messages.txt \
&& echo -e "Backward compatibility check: Fatal message in clickhouse-server.log (see bc_check_fatal_messages.txt)$FAIL$(head_escaped /test_output/bc_check_fatal_messages.txt)" \
&& echo -e "Backward compatibility check: Fatal message in clickhouse-server.log (see bc_check_fatal_messages.txt)$FAIL$(trim_server_logs bc_check_fatal_messages.txt)" \
>> /test_output/test_results.tsv \
|| echo -e "Backward compatibility check: No fatal messages in clickhouse-server.log$OK" >> /test_output/test_results.tsv

10
docker/test/util/process_functional_tests_result.py
View File

@ -85,8 +85,16 @@ def process_test_log(log_path):
if DATABASE_SIGN in line:
test_end = True
# Python does not support TSV, so we have to escape '\t' and '\n' manually
# and hope that complex escape sequences will not break anything
test_results = [
(test[0], test[1], test[2], "".join(test[3])[:4096]) for test in test_results
(
test[0],
test[1],
test[2],
"".join(test[3])[:4096].replace("\t", "\\t").replace("\n", "\\n"),
)
for test in test_results
]
return (

17
docs/changelogs/v23.1.3.5-stable.md Normal file
View File

@ -0,0 +1,17 @@
---
sidebar_position: 1
sidebar_label: 2023
---
# 2023 Changelog
### ClickHouse release v23.1.3.5-stable (548b494bcce) FIXME as compared to v23.1.2.9-stable (8dfb1700858)
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Backported in [#45896](https://github.com/ClickHouse/ClickHouse/issues/45896): Bugfix IPv6 parser for mixed ip4 address with missed first octet (like `::.1.2.3`). [#45871](https://github.com/ClickHouse/ClickHouse/pull/45871) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Get rid of progress timestamps in release publishing [#45818](https://github.com/ClickHouse/ClickHouse/pull/45818) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).

5
docs/en/development/tests.md
View File

@ -16,6 +16,11 @@ Tests are located in `queries` directory. There are two subdirectories: `statele
Each test can be one of two types: `.sql` and `.sh`. `.sql` test is the simple SQL script that is piped to `clickhouse-client --multiquery`. `.sh` test is a script that is run by itself. SQL tests are generally preferable to `.sh` tests. You should use `.sh` tests only when you have to test some feature that cannot be exercised from pure SQL, such as piping some input data into `clickhouse-client` or testing `clickhouse-local`.
:::note
A common mistake when testing data types `DateTime` and `DateTime64` is assuming that the server uses a specific time zone (e.g. "UTC"). This is not the case, time zones in CI test runs
are deliberately randomized. The easiest workaround is to specify the time zone for test values explicitly, e.g. `toDateTime64(val, 3, 'Europe/Amsterdam')`.
:::
### Running a Test Locally {#functional-test-locally}
Start the ClickHouse server locally, listening on the default port (9000). To

5
docs/en/engines/table-engines/integrations/rabbitmq.md
View File

@ -77,9 +77,12 @@ Optional parameters:
- `rabbitmq_password` - RabbitMQ password.
- `rabbitmq_commit_on_select` - Commit messages when select query is made. Default: `false`.
- `rabbitmq_max_rows_per_message` — The maximum number of rows written in one RabbitMQ message for row-based formats. Default : `1`.
- `rabbitmq_empty_queue_backoff_start` — A start backoff point to reschedule read if the rabbitmq queue is empty.
- `rabbitmq_empty_queue_backoff_end` — An end backoff point to reschedule read if the rabbitmq queue is empty.
SSL connection:
* [ ] SSL connection:
Use either `rabbitmq_secure = 1` or `amqps` in connection address: `rabbitmq_address = 'amqps://guest:guest@localhost/vhost'`.
The default behaviour of the used library is not to check if the created TLS connection is sufficiently secure. Whether the certificate is expired, self-signed, missing or invalid: the connection is simply permitted. More strict checking of certificates can possibly be implemented in the future.

121
docs/en/engines/table-engines/mergetree-family/invertedindexes.md
View File

@ -2,10 +2,10 @@
slug: /en/engines/table-engines/mergetree-family/invertedindexes
sidebar_label: Inverted Indexes
description: Quickly find search terms in text.
keywords: [full-text search, text search]
keywords: [full-text search, text search, inverted, index, indices]
---
# Inverted indexes [experimental]
# Full-text Search using Inverted Indexes [experimental]
Inverted indexes are an experimental type of [secondary indexes](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#available-types-of-indices) which provide fast text search
capabilities for [String](/docs/en/sql-reference/data-types/string.md) or [FixedString](/docs/en/sql-reference/data-types/fixedstring.md)
@ -13,7 +13,7 @@ columns. The main idea of an inverted index is to store a mapping from "terms" t
tokenized cells of the string column. For example, the string cell "I will be a little late" is by default tokenized into six terms "I", "will",
"be", "a", "little" and "late". Another kind of tokenizer is n-grams. For example, the result of 3-gram tokenization will be 21 terms "I w",
" wi", "wil", "ill", "ll ", "l b", " be" etc. The more fine-granular the input strings are tokenized, the bigger but also the more
useful the resulting inverted index will be.
useful the resulting inverted index will be.
:::warning
Inverted indexes are experimental and should not be used in production environments yet. They may change in the future in backward-incompatible
@ -50,7 +50,7 @@ Being a type of skipping index, inverted indexes can be dropped or added to a co
``` sql
ALTER TABLE tab DROP INDEX inv_idx;
ALTER TABLE tab ADD INDEX inv_idx(s) TYPE inverted(2) GRANULARITY 1;
ALTER TABLE tab ADD INDEX inv_idx(s) TYPE inverted(2);
```
To use the index, no special functions or syntax are required. Typical string search predicates automatically leverage the index. As
@ -74,7 +74,120 @@ controls the amount of data read consumed from the underlying column before a ne
intermediate memory consumption for index construction but also improves lookup performance since fewer segments need to be checked on
average to evaluate a query.
## Full-text search of the Hacker News dataset
Let's look at the performance improvements of inverted indexes on a large dataset with lots of text. We will use 28.7M rows of comments on the popular Hacker News website. Here is the table without an inverted index:
```sql
CREATE TABLE hackernews (
id UInt64,
deleted UInt8,
type String,
author String,
timestamp DateTime,
comment String,
dead UInt8,
parent UInt64,
poll UInt64,
children Array(UInt32),
url String,
score UInt32,
title String,
parts Array(UInt32),
descendants UInt32
)
ENGINE = MergeTree
ORDER BY (type, author);
```
The 28.7M rows are in a Parquet file in S3 - let's insert them into the `hackernews` table:
```sql
INSERT INTO hackernews
SELECT * FROM s3Cluster(
'default',
'https://datasets-documentation.s3.eu-west-3.amazonaws.com/hackernews/hacknernews.parquet',
'Parquet',
'
id UInt64,
deleted UInt8,
type String,
by String,
time DateTime,
text String,
dead UInt8,
parent UInt64,
poll UInt64,
kids Array(UInt32),
url String,
score UInt32,
title String,
parts Array(UInt32),
descendants UInt32');
```
Consider the following simple search for the term `ClickHouse` (and its varied upper and lower cases) in the `comment` column:
```sql
SELECT count()
FROM hackernews
WHERE hasToken(lower(comment), 'clickhouse');
```
Notice it takes 3 seconds to execute the query:
```response
┌─count()─┐
│ 1145 │
└─────────┘
1 row in set. Elapsed: 3.001 sec. Processed 28.74 million rows, 9.75 GB (9.58 million rows/s., 3.25 GB/s.)
```
We will use `ALTER TABLE` and add an inverted index on the lowercase of the `comment` column, then materialize it (which can take a while - wait for it to materialize):
```sql
ALTER TABLE hackernews
ADD INDEX comment_lowercase(lower(comment)) TYPE inverted;
ALTER TABLE hackernews MATERIALIZE INDEX comment_lowercase;
```
We run the same query...
```sql
SELECT count()
FROM hackernews
WHERE hasToken(lower(comment), 'clickhouse')
```
...and notice the query executes 4x faster:
```response
┌─count()─┐
│ 1145 │
└─────────┘
1 row in set. Elapsed: 0.747 sec. Processed 4.49 million rows, 1.77 GB (6.01 million rows/s., 2.37 GB/s.)
```
We can also search for one or all of multiple terms, i.e., disjunctions or conjunctions:
```sql
-- multiple OR'ed terms
SELECT count(*)
FROM hackernews
WHERE multiSearchAny(lower(comment), ['oltp', 'olap']);
-- multiple AND'ed terms
SELECT count(*)
FROM hackernews
WHERE hasToken(lower(comment), 'avx') AND hasToken(lower(comment), 'sve');
```
:::note
Unlike other secondary indices, inverted indexes (for now) map to row numbers (row ids) instead of granule ids. The reason for this design
is performance. In practice, users often search for multiple terms at once. For example, filter predicate `WHERE s LIKE '%little%' OR s LIKE
'%big%'` can be evaluated directly using an inverted index by forming the union of the row id lists for terms "little" and "big". This also
means that the parameter `GRANULARITY` supplied to index creation has no meaning (it may be removed from the syntax in the future).
:::

6
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -1279,7 +1279,9 @@ The following settings are available:
- `size`: The maximum cache size in bytes. 0 means the query cache is disabled. Default value: `1073741824` (1 GiB).
- `max_entries`: The maximum number of `SELECT` query results stored in the cache. Default value: `1024`.
- `max_entry_size`: The maximum size in bytes `SELECT` query results may have to be saved in the cache. Default value: `1048576` (1 MiB).
- `max_entry_records`: The maximum number of records `SELECT` query results may have to be saved in the cache. Default value: `30000000` (30 mil).
- `max_entry_rows`: The maximum number of rows `SELECT` query results may have to be saved in the cache. Default value: `30000000` (30 mil).
Changed settings take effect immediately.
:::warning
Data for the query cache is allocated in DRAM. If memory is scarce, make sure to set a small value for `size` or disable the query cache altogether.
@ -1292,7 +1294,7 @@ Data for the query cache is allocated in DRAM. If memory is scarce, make sure to
<size>1073741824</size>
<max_entries>1024</max_entries>
<max_entry_size>1048576</max_entry_size>
<max_entry_records>30000000</max_entry_records>
<max_entry_rows>30000000</max_entry_rows>
</query_cache>
```

27
docs/en/sql-reference/aggregate-functions/reference/sparkbar.md
View File

@ -1,5 +1,5 @@
---
slug: /en/sql-reference/aggregate-functions/reference/sparkbar
slug: /en/sql-reference/aggregate-functions/reference/sparkbar
sidebar_position: 311
sidebar_label: sparkbar
---
@ -7,9 +7,11 @@ sidebar_label: sparkbar
# sparkbar
The function plots a frequency histogram for values `x` and the repetition rate `y` of these values over the interval `[min_x, max_x]`.
Repetitions for all `x` falling into the same bucket are averaged, so data should be pre-aggregated.
Negative repetitions are ignored.
If no interval is specified, then the minimum `x` is used as the interval start, and the maximum `x` — as the interval end.
If no interval is specified, then the minimum `x` is used as the interval start, and the maximum `x` — as the interval end.
Otherwise, values outside the interval are ignored.
**Syntax**
@ -37,29 +39,24 @@ sparkbar(width[, min_x, max_x])(x, y)
Query:
``` sql
CREATE TABLE spark_bar_data (`cnt` UInt64,`event_date` Date) ENGINE = MergeTree ORDER BY event_date SETTINGS index_granularity = 8192;
INSERT INTO spark_bar_data VALUES(1,'2020-01-01'),(4,'2020-01-02'),(5,'2020-01-03'),(2,'2020-01-04'),(3,'2020-01-05'),(7,'2020-01-06'),(6,'2020-01-07'),(8,'2020-01-08'),(2,'2020-01-11');
CREATE TABLE spark_bar_data (`value` Int64, `event_date` Date) ENGINE = MergeTree ORDER BY event_date;
SELECT sparkbar(9)(event_date,cnt) FROM spark_bar_data;
INSERT INTO spark_bar_data VALUES (1,'2020-01-01'), (3,'2020-01-02'), (4,'2020-01-02'), (-3,'2020-01-02'), (5,'2020-01-03'), (2,'2020-01-04'), (3,'2020-01-05'), (7,'2020-01-06'), (6,'2020-01-07'), (8,'2020-01-08'), (2,'2020-01-11');
SELECT sparkbar(9,toDate('2020-01-01'),toDate('2020-01-10'))(event_date,cnt) FROM spark_bar_data;
SELECT sparkbar(9)(event_date,cnt) FROM (SELECT sum(value) as cnt, event_date FROM spark_bar_data GROUP BY event_date);
SELECT sparkbar(9, toDate('2020-01-01'), toDate('2020-01-10'))(event_date,cnt) FROM (SELECT sum(value) as cnt, event_date FROM spark_bar_data GROUP BY event_date);
```
Result:
``` text
┌─sparkbar(9)(event_date, cnt)─┐
│ │
│ ▁▅▄▃██▅ ▁ │
│ │
│ ▂▅▂▃▆█ ▂ │
└──────────────────────────────┘
┌─sparkbar(9, toDate('2020-01-01'), toDate('2020-01-10'))(event_date, cnt)─┐
│ │
│▁▄▄▂▅▇█▁ │
│ │
│ ▂▅▂▃▇▆█ │
└──────────────────────────────────────────────────────────────────────────┘
```

12
docs/en/sql-reference/functions/comparison-functions.md
View File

@ -21,14 +21,14 @@ For example, you can’t compare a date with a string. You have to use a functio
Strings are compared by bytes. A shorter string is smaller than all strings that start with it and that contain at least one more character.
## equals, a = b and a == b operator
### equals, a `=` b and a `==` b operator
## notEquals, a != b and a \<\> b operator
### notEquals, a `!=` b and a `<>` b operator
## less, \< operator
### less, `<` operator
## greater, \> operator
### greater, `>` operator
## lessOrEquals, \<= operator
### lessOrEquals, `<=` operator
## greaterOrEquals, \>= operator
### greaterOrEquals, `>=` operator

40
docs/en/sql-reference/statements/delete.md
View File

@ -2,15 +2,16 @@
slug: /en/sql-reference/statements/delete
sidebar_position: 36
sidebar_label: DELETE
description: Lightweight deletes simplify the process of deleting data from the database.
keywords: [delete]
title: DELETE Statement
---
# DELETE Statement
``` sql
DELETE FROM [db.]table [ON CLUSTER cluster] [WHERE expr]
```
`DELETE FROM` removes rows from table `[db.]table` that match expression `expr`. The deleted rows are marked as deleted immediately and will be automatically filtered out of all subsequent queries. Cleanup of data happens asynchronously in background. This feature is only available for MergeTree table engine family.
`DELETE FROM` removes rows from the table `[db.]table` that match the expression `expr`. The deleted rows are marked as deleted immediately and will be automatically filtered out of all subsequent queries. Cleanup of data happens asynchronously in the background. This feature is only available for the MergeTree table engine family.
For example, the following query deletes all rows from the `hits` table where the `Title` column contains the text `hello`:
@ -32,7 +33,7 @@ SET allow_experimental_lightweight_delete = true;
An [alternative way to delete rows](./alter/delete.md) in ClickHouse is `ALTER TABLE ... DELETE`, which might be more efficient if you do bulk deletes only occasionally and don't need the operation to be applied instantly. In most use cases the new lightweight `DELETE FROM` behavior will be considerably faster.
:::warning
Even though deletes are becoming more lightweight in ClickHouse, they should still not be used as aggressively as on an OLTP system. Ligthweight deletes are currently efficient for wide parts, but for compact parts they can be a heavyweight operation, and it may be better to use `ALTER TABLE` for some scenarios.
Even though deletes are becoming more lightweight in ClickHouse, they should still not be used as aggressively as on an OLTP system. Lightweight deletes are currently efficient for wide parts, but for compact parts, they can be a heavyweight operation, and it may be better to use `ALTER TABLE` for some scenarios.
:::
:::note
@ -41,3 +42,34 @@ Even though deletes are becoming more lightweight in ClickHouse, they should sti
grant ALTER DELETE ON db.table to username;
```
:::
## Lightweight Delete Internals
The idea behind Lightweight Delete is that when a `DELETE FROM table ...` query is executed ClickHouse only saves a mask where each row is marked as either “existing” or as “deleted”. Those “deleted” rows become invisible for subsequent queries, but physically the rows are removed only later by subsequent merges. Writing this mask is usually much more lightweight than what is done by `ALTER table DELETE ...` query.
### How it is implemented
The mask is implemented as a hidden `_row_exists` system column that stores True for all visible rows and False for deleted ones. This column is only present in a part if some rows in this part were deleted. In other words, the column is not persisted when it has all values equal to True.
## SELECT query
When the column is present `SELECT ... FROM table WHERE condition` query internally is extended by an additional predicate on `_row_exists` and becomes similar to
```sql
SELECT ... FROM table PREWHERE _row_exists WHERE condition
```
At execution time the column `_row_exists` is read to figure out which rows are not visible and if there are many deleted rows it can figure out which granules can be fully skipped when reading the rest of the columns.
## DELETE query
`DELETE FROM table WHERE condition` is translated into `ALTER table UPDATE _row_exists = 0 WHERE condition` mutation. Internally this mutation is executed in 2 steps:
1. `SELECT count() FROM table WHERE condition` for each individual part to figure out if the part is affected.
2. Mutate affected parts, and make hardlinks for unaffected parts. Mutating a part in fact only writes `_row_exists` column and just hardlinks all other columns’ files in the case of Wide parts. But for Compact parts, all columns are rewritten because they all are stored together in one file.
So if we compare Lightweight Delete to `ALTER DELETE` in the first step they both do the same thing to figure out which parts are affected, but in the second step `ALTER DELETE` does much more work because it reads and rewrites all columns’ files for the affected parts.
With the described implementation now we can see what can negatively affect 'DELETE FROM' execution time:
- Heavy WHERE condition in DELETE query
- Mutations queue filled with other mutations, because all mutations on a table are executed sequentially
- Table having a very large number of data parts
- Having a lot of data in Compact parts—in a Compact part, all columns are stored in one file.
:::note
This implementation might change in the future.
:::

2
docs/en/sql-reference/statements/system.md
View File

@ -283,7 +283,7 @@ SYSTEM START REPLICATION QUEUES [[db.]replicated_merge_tree_family_table_name]
Wait until a `ReplicatedMergeTree` table will be synced with other replicas in a cluster. Will run until `receive_timeout` if fetches currently disabled for the table.
``` sql
SYSTEM SYNC REPLICA [db.]replicated_merge_tree_family_table_name
SYSTEM SYNC REPLICA [ON CLUSTER cluster_name] [db.]replicated_merge_tree_family_table_name
```
After running this statement the `[db.]replicated_merge_tree_family_table_name` fetches commands from the common replicated log into its own replication queue, and then the query waits till the replica processes all of the fetched commands.

18
docs/en/sql-reference/table-functions/s3.md
View File

@ -2,11 +2,12 @@
slug: /en/sql-reference/table-functions/s3
sidebar_position: 45
sidebar_label: s3
keywords: [s3, gcs, bucket]
---
# s3 Table Function
Provides table-like interface to select/insert files in [Amazon S3](https://aws.amazon.com/s3/). This table function is similar to [hdfs](../../sql-reference/table-functions/hdfs.md), but provides S3-specific features.
Provides a table-like interface to select/insert files in [Amazon S3](https://aws.amazon.com/s3/) and [Google Cloud Storage](https://cloud.google.com/storage/). This table function is similar to the [hdfs function](../../sql-reference/table-functions/hdfs.md), but provides S3-specific features.
**Syntax**
@ -14,9 +15,24 @@ Provides table-like interface to select/insert files in [Amazon S3](https://aws.
s3(path [,aws_access_key_id, aws_secret_access_key] [,format] [,structure] [,compression])
```
:::tip GCS
The S3 Table Function integrates with Google Cloud Storage by using the GCS XML API and HMAC keys. See the [Google interoperability docs]( https://cloud.google.com/storage/docs/interoperability) for more details about the endpoint and HMAC.
For GCS, substitute your HMAC key and HMAC secret where you see `aws_access_key_id` and `aws_secret_access_key`.
:::
**Arguments**
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [here](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
:::note GCS
The GCS path is in this format as the endpoint for the Google XML API is different than the JSON API:
```
https://storage.googleapis.com/<bucket>/<folder>/<filename(s)>
```
and not ~~https://storage.cloud.google.com~~.
:::
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
- `compression` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression by file extension.

25
docs/ru/sql-reference/aggregate-functions/reference/sparkbar.md
View File

@ -1,14 +1,15 @@
---
slug: /ru/sql-reference/aggregate-functions/reference/sparkbar
slug: /ru/sql-reference/aggregate-functions/reference/sparkbar
sidebar_position: 311
sidebar_label: sparkbar
---
# sparkbar {#sparkbar}
Функция строит гистограмму частот по заданным значениям `x` и частоте повторения этих значений `y` на интервале `[min_x, max_x]`.
Функция строит гистограмму частот по заданным значениям `x` и частоте повторения этих значений `y` на интервале `[min_x, max_x]`. Повторения для всех `x`, попавших в один бакет, усредняются, поэтому данные должны быть предварительно агрегированы. Отрицательные повторения игнорируются.
Если интервал для построения не указан, то в качестве нижней границы интервала будет взято минимальное значение `x`, а в качестве верхней границы — максимальное значение `x`.
Значения `x` вне указанного интервала игнорируются.
**Синтаксис**
@ -39,29 +40,23 @@ sparkbar(width[, min_x, max_x])(x, y)
Запрос:
``` sql
CREATE TABLE spark_bar_data (`cnt` UInt64,`event_date` Date) ENGINE = MergeTree ORDER BY event_date SETTINGS index_granularity = 8192;
INSERT INTO spark_bar_data VALUES(1,'2020-01-01'),(4,'2020-01-02'),(5,'2020-01-03'),(2,'2020-01-04'),(3,'2020-01-05'),(7,'2020-01-06'),(6,'2020-01-07'),(8,'2020-01-08'),(2,'2020-01-11');
CREATE TABLE spark_bar_data (`value` Int64, `event_date` Date) ENGINE = MergeTree ORDER BY event_date;
SELECT sparkbar(9)(event_date,cnt) FROM spark_bar_data;
INSERT INTO spark_bar_data VALUES (1,'2020-01-01'), (3,'2020-01-02'), (4,'2020-01-02'), (-3,'2020-01-02'), (5,'2020-01-03'), (2,'2020-01-04'), (3,'2020-01-05'), (7,'2020-01-06'), (6,'2020-01-07'), (8,'2020-01-08'), (2,'2020-01-11');
SELECT sparkbar(9,toDate('2020-01-01'),toDate('2020-01-10'))(event_date,cnt) FROM spark_bar_data;
SELECT sparkbar(9)(event_date,cnt) FROM (SELECT sum(value) as cnt, event_date FROM spark_bar_data GROUP BY event_date);
SELECT sparkbar(9, toDate('2020-01-01'), toDate('2020-01-10'))(event_date,cnt) FROM (SELECT sum(value) as cnt, event_date FROM spark_bar_data GROUP BY event_date);
```
Результат:
``` text
┌─sparkbar(9)(event_date, cnt)─┐
│ │
│ ▁▅▄▃██▅ ▁ │
│ │
│ ▂▅▂▃▆█ ▂ │
└──────────────────────────────┘
┌─sparkbar(9, toDate('2020-01-01'), toDate('2020-01-10'))(event_date, cnt)─┐
│ │
│▁▄▄▂▅▇█▁ │
│ │
│ ▂▅▂▃▇▆█ │
└──────────────────────────────────────────────────────────────────────────┘
```

3
packages/build
View File

@ -102,7 +102,8 @@ done
EOF
chmod +x "$PKG_PATH/install/doinst.sh"
if [ -f "$PKG_PATH/DEBIAN/postinst" ]; then
tail +2 "$PKG_PATH/DEBIAN/postinst" >> "$PKG_PATH/install/doinst.sh"
# we don't need debconf source in doinst in any case
tail +2 "$PKG_PATH/DEBIAN/postinst" | grep -v debconf/confmodule >> "$PKG_PATH/install/doinst.sh"
fi
rm -rf "$PKG_PATH/DEBIAN"
if [ -f "/usr/bin/pigz" ]; then

46
packages/clickhouse-keeper.postinstall Normal file
View File

@ -0,0 +1,46 @@
#!/bin/sh
set -e
# set -x
PROGRAM=clickhouse-keeper
KEEPER_USER=${KEEPER_USER:=clickhouse}
KEEPER_GROUP=${KEEPER_GROUP:=clickhouse}
# Please note that we don't support paths with whitespaces. This is rather ignorant.
KEEPER_CONFDIR=${KEEPER_CONFDIR:=/etc/$PROGRAM}
KEEPER_DATADIR=${KEEPER_DATADIR:=/var/lib/clickhouse}
KEEPER_LOGDIR=${KEEPER_LOGDIR:=/var/log/$PROGRAM}
[ -f /usr/share/debconf/confmodule ] && . /usr/share/debconf/confmodule
[ -f /etc/default/clickhouse-keeper ] && . /etc/default/clickhouse-keeper
if [ ! -f "/etc/debian_version" ]; then
not_deb_os=1
fi
if [ "$1" = configure ] || [ -n "$not_deb_os" ]; then
if ! getent group "${KEEPER_GROUP}" > /dev/null 2>&1 ; then
groupadd --system "${KEEPER_GROUP}"
fi
GID=$(getent group "${KEEPER_GROUP}" | cut -d: -f 3)
if ! id "${KEEPER_USER}" > /dev/null 2>&1 ; then
adduser --system --home /dev/null --no-create-home \
--gid "${GID}" --shell /bin/false \
"${KEEPER_USER}"
fi
chown -R "${KEEPER_USER}:${KEEPER_GROUP}" "${KEEPER_CONFDIR}"
chmod 0755 "${KEEPER_CONFDIR}"
if ! [ -d "${KEEPER_DATADIR}" ]; then
mkdir -p "${KEEPER_DATADIR}"
chown -R "${KEEPER_USER}:${KEEPER_GROUP}" "${KEEPER_DATADIR}"
chmod 0700 "${KEEPER_DATADIR}"
fi
if ! [ -d "${KEEPER_LOGDIR}" ]; then
mkdir -p "${KEEPER_LOGDIR}"
chown -R "${KEEPER_USER}:${KEEPER_GROUP}" "${KEEPER_LOGDIR}"
chmod 0770 "${KEEPER_LOGDIR}"
fi
fi
# vim: ts=4: sw=4: sts=4: expandtab

27
packages/clickhouse-keeper.service Normal file
View File

@ -0,0 +1,27 @@
[Unit]
Description=ClickHouse Keeper - zookeeper compatible distributed coordination server
Requires=network-online.target
# NOTE: that After/Wants=time-sync.target is not enough, you need to ensure
# that the time was adjusted already, if you use systemd-timesyncd you are
# safe, but if you use ntp or some other daemon, you should configure it
# additionaly.
After=time-sync.target network-online.target
Wants=time-sync.target
[Service]
Type=simple
User=clickhouse
Group=clickhouse
Restart=always
RestartSec=30
RuntimeDirectory=%p # %p is resolved to the systemd unit name
ExecStart=/usr/bin/clickhouse-keeper --config=/etc/clickhouse-keeper/keeper_config.xml --pid-file=%t/%p/%p.pid
# Minus means that this file is optional.
EnvironmentFile=-/etc/default/%p
LimitCORE=infinity
LimitNOFILE=500000
CapabilityBoundingSet=CAP_NET_ADMIN CAP_IPC_LOCK CAP_SYS_NICE CAP_NET_BIND_SERVICE
[Install]
# ClickHouse should not start from the rescue shell (rescue.target).
WantedBy=multi-user.target

5
packages/clickhouse-keeper.yaml
View File

@ -30,6 +30,8 @@ contents:
type: config|noreplace
- src: root/usr/bin/clickhouse-keeper
dst: /usr/bin/clickhouse-keeper
- src: clickhouse-keeper.service
dst: /lib/systemd/system/clickhouse-keeper.service
# docs
- src: ../AUTHORS
dst: /usr/share/doc/clickhouse-keeper/AUTHORS
@ -39,3 +41,6 @@ contents:
dst: /usr/share/doc/clickhouse-keeper/LICENSE
- src: ../README.md
dst: /usr/share/doc/clickhouse-keeper/README.md
scripts:
postinstall: ./clickhouse-keeper.postinstall

2
packages/clickhouse-server.postinstall
View File

@ -11,8 +11,6 @@ CLICKHOUSE_DATADIR=${CLICKHOUSE_DATADIR:=/var/lib/clickhouse}
CLICKHOUSE_LOGDIR=${CLICKHOUSE_LOGDIR:=/var/log/clickhouse-server}
CLICKHOUSE_BINDIR=${CLICKHOUSE_BINDIR:=/usr/bin}
CLICKHOUSE_GENERIC_PROGRAM=${CLICKHOUSE_GENERIC_PROGRAM:=clickhouse}
EXTRACT_FROM_CONFIG=${CLICKHOUSE_GENERIC_PROGRAM}-extract-from-config
CLICKHOUSE_CONFIG=$CLICKHOUSE_CONFDIR/config.xml
CLICKHOUSE_PIDDIR=/var/run/$PROGRAM
[ -f /usr/share/debconf/confmodule ] && . /usr/share/debconf/confmodule

6
packages/clickhouse-server.service
View File

@ -17,10 +17,10 @@ User=clickhouse
Group=clickhouse
Restart=always
RestartSec=30
RuntimeDirectory=clickhouse-server
ExecStart=/usr/bin/clickhouse-server --config=/etc/clickhouse-server/config.xml --pid-file=/run/clickhouse-server/clickhouse-server.pid
RuntimeDirectory=%p # %p is resolved to the systemd unit name
ExecStart=/usr/bin/clickhouse-server --config=/etc/clickhouse-server/config.xml --pid-file=%t/%p/%p.pid
# Minus means that this file is optional.
EnvironmentFile=-/etc/default/clickhouse
EnvironmentFile=-/etc/default/%p
LimitCORE=infinity
LimitNOFILE=500000
CapabilityBoundingSet=CAP_NET_ADMIN CAP_IPC_LOCK CAP_SYS_NICE CAP_NET_BIND_SERVICE

2
programs/benchmark/Benchmark.cpp
View File

@ -474,7 +474,7 @@ private:
executor.sendQuery(ClientInfo::QueryKind::INITIAL_QUERY);
ProfileInfo info;
while (Block block = executor.read())
while (Block block = executor.readBlock())
info.update(block);
executor.finish();

33
programs/client/Client.cpp
View File

@ -1,3 +1,4 @@
#include <boost/algorithm/string/join.hpp>
#include <cstdlib>
#include <fcntl.h>
#include <map>
@ -538,24 +539,28 @@ void Client::connect()
// Prints changed settings to stderr. Useful for debugging fuzzing failures.
void Client::printChangedSettings() const
{
const auto & changes = global_context->getSettingsRef().changes();
if (!changes.empty())
auto print_changes = [](const auto & changes, std::string_view settings_name)
{
fmt::print(stderr, "Changed settings: ");
for (size_t i = 0; i < changes.size(); ++i)
if (!changes.empty())
{
if (i)
fmt::print(stderr, "Changed {}: ", settings_name);
for (size_t i = 0; i < changes.size(); ++i)
{
fmt::print(stderr, ", ");
if (i)
fmt::print(stderr, ", ");
fmt::print(stderr, "{} = '{}'", changes[i].name, toString(changes[i].value));
}
fmt::print(stderr, "{} = '{}'", changes[i].name, toString(changes[i].value));
fmt::print(stderr, "\n");
}
fmt::print(stderr, "\n");
}
else
{
fmt::print(stderr, "No changed settings.\n");
}
else
{
fmt::print(stderr, "No changed {}.\n", settings_name);
}
};
print_changes(global_context->getSettingsRef().changes(), "settings");
print_changes(cmd_merge_tree_settings.changes(), "MergeTree settings");
}
@ -1352,6 +1357,8 @@ void Client::readArguments(
}
else if (arg == "--allow_repeated_settings")
allow_repeated_settings = true;
else if (arg == "--allow_merge_tree_settings")
allow_merge_tree_settings = true;
else
common_arguments.emplace_back(arg);
}

2
programs/copier/ClusterCopier.cpp
View File

@ -2040,7 +2040,7 @@ UInt64 ClusterCopier::executeQueryOnCluster(
while (true)
{
auto block = remote_query_executor->read();
auto block = remote_query_executor->readBlock();
if (!block)
break;
}

1
programs/keeper/Keeper.cpp
View File

@ -362,6 +362,7 @@ try
else
path = std::filesystem::path{KEEPER_DEFAULT_PATH};
std::filesystem::create_directories(path);
/// Check that the process user id matches the owner of the data.
const auto effective_user_id = geteuid();

3
programs/local/CMakeLists.txt
View File

@ -19,6 +19,9 @@ target_link_libraries(clickhouse-local-lib PRIVATE clickhouse-server-lib)
if (TARGET ch_rust::skim)
target_link_libraries(clickhouse-local-lib PRIVATE ch_rust::skim)
endif()
if (TARGET ch_contrib::azure_sdk)
target_link_libraries(clickhouse-local-lib PRIVATE ch_contrib::azure_sdk)
endif()
# Always use internal readpassphrase
target_link_libraries(clickhouse-local-lib PRIVATE readpassphrase)

12
programs/local/LocalServer.cpp
View File

@ -51,6 +51,10 @@
#include <Functions/getFuzzerData.h>
#endif
#if USE_AZURE_BLOB_STORAGE
# include <azure/storage/common/internal/xml_wrapper.hpp>
#endif
namespace fs = std::filesystem;
@ -115,6 +119,14 @@ void LocalServer::initialize(Poco::Util::Application & self)
config().getUInt("thread_pool_queue_size", 10000)
);
#if USE_AZURE_BLOB_STORAGE
/// See the explanation near the same line in Server.cpp
GlobalThreadPool::instance().addOnDestroyCallback([]
{
Azure::Storage::_internal::XmlGlobalDeinitialize();
});
#endif
IOThreadPool::initialize(
config().getUInt("max_io_thread_pool_size", 100),
config().getUInt("max_io_thread_pool_free_size", 0),

3
programs/server/CMakeLists.txt
View File

@ -27,6 +27,9 @@ set (CLICKHOUSE_SERVER_LINK
if (TARGET ch_contrib::jemalloc)
list(APPEND CLICKHOUSE_SERVER_LINK PRIVATE ch_contrib::jemalloc)
endif()
if (TARGET ch_contrib::azure_sdk)
list(APPEND CLICKHOUSE_SERVER_LINK PRIVATE ch_contrib::azure_sdk)
endif()
clickhouse_program_add(server)

32
programs/server/Server.cpp
View File

@ -82,9 +82,7 @@
#include <Common/ThreadFuzzer.h>
#include <Common/getHashOfLoadedBinary.h>
#include <Common/filesystemHelpers.h>
#if USE_BORINGSSL
#include <Compression/CompressionCodecEncrypted.h>
#endif
#include <Server/HTTP/HTTPServerConnectionFactory.h>
#include <Server/MySQLHandlerFactory.h>
#include <Server/PostgreSQLHandlerFactory.h>
@ -128,6 +126,10 @@
# include <jemalloc/jemalloc.h>
#endif
#if USE_AZURE_BLOB_STORAGE
# include <azure/storage/common/internal/xml_wrapper.hpp>
#endif
namespace CurrentMetrics
{
extern const Metric Revision;
@ -750,6 +752,19 @@ try
config().getUInt("max_thread_pool_free_size", 1000),
config().getUInt("thread_pool_queue_size", 10000));
#if USE_AZURE_BLOB_STORAGE
/// It makes sense to deinitialize libxml after joining of all threads
/// in global pool because libxml uses thread-local memory allocations via
/// 'pthread_key_create' and 'pthread_setspecific' which should be deallocated
/// at 'pthread_exit'. Deinitialization of libxml leads to call of 'pthread_key_delete'
/// and if it is done before joining of threads, allocated memory will not be freed
/// and there may be memory leaks in threads that used libxml.
GlobalThreadPool::instance().addOnDestroyCallback([]
{
Azure::Storage::_internal::XmlGlobalDeinitialize();
});
#endif
IOThreadPool::initialize(
config().getUInt("max_io_thread_pool_size", 100),
config().getUInt("max_io_thread_pool_free_size", 0),
@ -1331,9 +1346,8 @@ try
global_context->updateStorageConfiguration(*config);
global_context->updateInterserverCredentials(*config);
#if USE_BORINGSSL
global_context->updateQueryCacheConfiguration(*config);
CompressionCodecEncrypted::Configuration::instance().tryLoad(*config, "encryption_codecs");
#endif
#if USE_SSL
CertificateReloader::instance().tryLoad(*config);
#endif
@ -1517,13 +1531,7 @@ try
global_context->setMMappedFileCache(mmap_cache_size);
/// A cache for query results.
size_t query_cache_size = config().getUInt64("query_cache.size", 1_GiB);
if (query_cache_size)
global_context->setQueryCache(
query_cache_size,
config().getUInt64("query_cache.max_entries", 1024),
config().getUInt64("query_cache.max_entry_size", 1_MiB),
config().getUInt64("query_cache.max_entry_records", 30'000'000));
global_context->setQueryCache(config());
#if USE_EMBEDDED_COMPILER
/// 128 MB
@ -1547,10 +1555,8 @@ try
global_context->getMergeTreeSettings().sanityCheck(background_pool_tasks);
global_context->getReplicatedMergeTreeSettings().sanityCheck(background_pool_tasks);
}
#if USE_BORINGSSL
/// try set up encryption. There are some errors in config, error will be printed and server wouldn't start.
CompressionCodecEncrypted::Configuration::instance().load(config(), "encryption_codecs");
#endif
SCOPE_EXIT({
async_metrics.stop();

47
programs/server/config.xml
View File

@ -854,6 +854,51 @@
</replica>
</shard-->
</test_cluster_one_shard_three_replicas_localhost>
<parallel_replicas>
<shard>
<internal_replication>false</internal_replication>
<replica>
<host>127.0.0.1</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.2</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.3</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.4</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.5</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.6</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.7</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.8</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.9</host>
<port>9000</port>
</replica>
<replica>
<host>127.0.0.10</host>
<port>9000</port>
</replica>
</shard>
</parallel_replicas>
<test_cluster_two_shards_localhost>
<shard>
<replica>
@ -1471,7 +1516,7 @@
<!-- <size>1073741824</size> -->
<!-- <max_entries>1024</max_entries> -->
<!-- <max_entry_size>1048576</max_entry_size> -->
<!-- <max_entry_records>30000000</max_entry_records> -->
<!-- <max_entry_rows>30000000</max_entry_rows> -->
<!-- </query_cache> -->
<!-- Uncomment if enable merge tree metadata cache -->

42
rust/skim/src/lib.rs
View File

@ -10,11 +10,29 @@ mod ffi {
}
struct Item {
text: String,
text_no_newlines: String,
orig_text: String,
}
impl Item {
fn new(text: String) -> Self {
return Self{
// Text that will be printed by skim, and will be used for matching.
//
// Text that will be shown should not contains new lines since in this case skim may
// live some symbols on the screen, and this looks odd.
text_no_newlines: text.replace("\n", " "),
// This will be used when the match had been selected.
orig_text: text,
};
}
}
impl SkimItem for Item {
fn text(&self) -> Cow<str> {
return Cow::Borrowed(&self.text);
return Cow::Borrowed(&self.text_no_newlines);
}
fn output(&self) -> Cow<str> {
return Cow::Borrowed(&self.orig_text);
}
}
@ -29,12 +47,30 @@ fn skim(prefix: &CxxString, words: &CxxVector<CxxString>) -> Result<String, Stri
.query(Some(prefix.to_str().unwrap()))
.tac(true)
.tiebreak(Some("-score".to_string()))
// Exact mode performs better for SQL.
//
// Default fuzzy search is too smart for SQL, it even takes into account the case, which
// should not be accounted (you don't want to type "SELECT" instead of "select" to find the
// query).
//
// Exact matching seems better algorithm for SQL, it is not 100% exact, it splits by space,
// and apply separate matcher actually for each word.
// Note, that if you think that "space is not enough" as the delimiter, then you should
// first know that this is the delimiter only for the input query, so to match
// "system.query_log" you can use "sy qu log"
// Also it should be more common for users who did not know how to use fuzzy search.
// (also you can disable exact mode by prepending "'" char).
//
// Also it ignores the case correctly, i.e. it does not have penalty for case mismatch,
// like fuzzy algorithms (take a look at SkimScoreConfig::penalty_case_mismatch).
.exact(true)
.case(CaseMatching::Ignore)
.build()
.unwrap();
let (tx, rx): (SkimItemSender, SkimItemReceiver) = unbounded();
for word in words {
tx.send(Arc::new(Item{ text: word.to_string() })).unwrap();
tx.send(Arc::new(Item::new(word.to_string()))).unwrap();
}
// so that skim could know when to stop waiting for more items.
drop(tx);

1
src/Access/Common/AccessType.h
View File

@ -146,6 +146,7 @@ enum class AccessType
M(SYSTEM_DROP_COMPILED_EXPRESSION_CACHE, "SYSTEM DROP COMPILED EXPRESSION, DROP COMPILED EXPRESSION CACHE, DROP COMPILED EXPRESSIONS", GLOBAL, SYSTEM_DROP_CACHE) \
M(SYSTEM_DROP_FILESYSTEM_CACHE, "SYSTEM DROP FILESYSTEM CACHE, DROP FILESYSTEM CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
M(SYSTEM_DROP_SCHEMA_CACHE, "SYSTEM DROP SCHEMA CACHE, DROP SCHEMA CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
M(SYSTEM_DROP_S3_CLIENT_CACHE, "SYSTEM DROP S3 CLIENT, DROP S3 CLIENT CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
M(SYSTEM_DROP_CACHE, "DROP CACHE", GROUP, SYSTEM) \
M(SYSTEM_RELOAD_CONFIG, "RELOAD CONFIG", GLOBAL, SYSTEM_RELOAD) \
M(SYSTEM_RELOAD_USERS, "RELOAD USERS", GLOBAL, SYSTEM_RELOAD) \

34
src/AggregateFunctions/AggregateFunctionMLMethod.cpp
View File

@ -247,15 +247,8 @@ void Adam::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac)
if (adam_rhs.average_gradient.empty())
return;
if (average_gradient.empty())
{
if (!average_squared_gradient.empty() ||
adam_rhs.average_gradient.size() != adam_rhs.average_squared_gradient.size())
throw Exception(ErrorCodes::LOGICAL_ERROR, "Average_gradient and average_squared_gradient must have same size");
average_gradient.resize(adam_rhs.average_gradient.size(), Float64{0.0});
average_squared_gradient.resize(adam_rhs.average_squared_gradient.size(), Float64{0.0});
}
average_gradient.resize(adam_rhs.average_gradient.size(), Float64{0.0});
average_squared_gradient.resize(adam_rhs.average_squared_gradient.size(), Float64{0.0});
for (size_t i = 0; i < average_gradient.size(); ++i)
{
@ -268,14 +261,8 @@ void Adam::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac)
void Adam::update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient)
{
if (average_gradient.empty())
{
if (!average_squared_gradient.empty())
throw Exception(ErrorCodes::LOGICAL_ERROR, "Average_gradient and average_squared_gradient must have same size");
average_gradient.resize(batch_gradient.size(), Float64{0.0});
average_squared_gradient.resize(batch_gradient.size(), Float64{0.0});
}
average_gradient.resize(batch_gradient.size(), Float64{0.0});
average_squared_gradient.resize(batch_gradient.size(), Float64{0.0});
for (size_t i = 0; i != average_gradient.size(); ++i)
{
@ -328,8 +315,7 @@ void Nesterov::write(WriteBuffer & buf) const
void Nesterov::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac)
{
const auto & nesterov_rhs = static_cast<const Nesterov &>(rhs);
if (accumulated_gradient.empty())
accumulated_gradient.resize(nesterov_rhs.accumulated_gradient.size(), Float64{0.0});
accumulated_gradient.resize(nesterov_rhs.accumulated_gradient.size(), Float64{0.0});
for (size_t i = 0; i < accumulated_gradient.size(); ++i)
{
@ -339,10 +325,7 @@ void Nesterov::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac
void Nesterov::update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient)
{
if (accumulated_gradient.empty())
{
accumulated_gradient.resize(batch_gradient.size(), Float64{0.0});
}
accumulated_gradient.resize(batch_gradient.size(), Float64{0.0});
for (size_t i = 0; i < batch_gradient.size(); ++i)
{
@ -402,10 +385,7 @@ void Momentum::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac
void Momentum::update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient)
{
/// batch_size is already checked to be greater than 0
if (accumulated_gradient.empty())
{
accumulated_gradient.resize(batch_gradient.size(), Float64{0.0});
}
accumulated_gradient.resize(batch_gradient.size(), Float64{0.0});
for (size_t i = 0; i < batch_gradient.size(); ++i)
{

25
src/AggregateFunctions/AggregateFunctionMLMethod.h
View File

@ -149,9 +149,11 @@ public:
class Momentum : public IWeightsUpdater
{
public:
Momentum() = default;
explicit Momentum(Float64 alpha_) : alpha(alpha_) {}
explicit Momentum(size_t num_params, Float64 alpha_ = 0.1) : alpha(alpha_)
{
accumulated_gradient.resize(num_params + 1, 0);
}
void update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient) override;
@ -170,9 +172,10 @@ private:
class Nesterov : public IWeightsUpdater
{
public:
Nesterov() = default;
explicit Nesterov(Float64 alpha_) : alpha(alpha_) {}
explicit Nesterov(size_t num_params, Float64 alpha_ = 0.9) : alpha(alpha_)
{
accumulated_gradient.resize(num_params + 1, 0);
}
void addToBatch(
std::vector<Float64> & batch_gradient,
@ -201,10 +204,14 @@ private:
class Adam : public IWeightsUpdater
{
public:
Adam()
Adam(size_t num_params)
{
beta1_powered = beta1;
beta2_powered = beta2;
average_gradient.resize(num_params + 1, 0);
average_squared_gradient.resize(num_params + 1, 0);
}
void addToBatch(
@ -338,11 +345,11 @@ public:
if (weights_updater_name == "SGD")
new_weights_updater = std::make_shared<StochasticGradientDescent>();
else if (weights_updater_name == "Momentum")
new_weights_updater = std::make_shared<Momentum>();
new_weights_updater = std::make_shared<Momentum>(param_num);
else if (weights_updater_name == "Nesterov")
new_weights_updater = std::make_shared<Nesterov>();
new_weights_updater = std::make_shared<Nesterov>(param_num);
else if (weights_updater_name == "Adam")
new_weights_updater = std::make_shared<Adam>();
new_weights_updater = std::make_shared<Adam>(param_num);
else
throw Exception(ErrorCodes::LOGICAL_ERROR, "Illegal name of weights updater (should have been checked earlier)");

7
src/AggregateFunctions/AggregateFunctionSparkbar.cpp
View File

@ -50,11 +50,13 @@ AggregateFunctionPtr createAggregateFunctionSparkbar(const std::string & name, c
assertBinary(name, arguments);
if (params.size() != 1 && params.size() != 3)
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH, "The number of params does not match for aggregate function {}", name);
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
"The number of params does not match for aggregate function '{}', expected 1 or 3, got {}", name, params.size());
if (params.size() == 3)
{
if (params.at(1).getType() != arguments[0]->getDefault().getType() || params.at(2).getType() != arguments[0]->getDefault().getType())
if (params.at(1).getType() != arguments[0]->getDefault().getType() ||
params.at(2).getType() != arguments[0]->getDefault().getType())
{
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"The second and third parameters are not the same type as the first arguments for aggregate function {}", name);
@ -63,7 +65,6 @@ AggregateFunctionPtr createAggregateFunctionSparkbar(const std::string & name, c
return createAggregateFunctionSparkbarImpl(name, *arguments[0], *arguments[1], arguments, params);
}
}
void registerAggregateFunctionSparkbar(AggregateFunctionFactory & factory)

259
src/AggregateFunctions/AggregateFunctionSparkbar.h
View File

@ -18,10 +18,15 @@
namespace DB
{
namespace ErrorCodes
{
extern const int BAD_ARGUMENTS;
}
template<typename X, typename Y>
struct AggregateFunctionSparkbarData
{
/// TODO: calculate histogram instead of storing all points
using Points = HashMap<X, Y>;
Points points;
@ -31,20 +36,26 @@ struct AggregateFunctionSparkbarData
Y min_y = std::numeric_limits<Y>::max();
Y max_y = std::numeric_limits<Y>::lowest();
void insert(const X & x, const Y & y)
Y insert(const X & x, const Y & y)
{
auto result = points.insert({x, y});
if (!result.second)
result.first->getMapped() += y;
if (isNaN(y) || y <= 0)
return 0;
auto [it, inserted] = points.insert({x, y});
if (!inserted)
it->getMapped() += y;
return it->getMapped();
}
void add(X x, Y y)
{
insert(x, y);
auto new_y = insert(x, y);
min_x = std::min(x, min_x);
max_x = std::max(x, max_x);
min_y = std::min(y, min_y);
max_y = std::max(y, max_y);
max_y = std::max(new_y, max_y);
}
void merge(const AggregateFunctionSparkbarData & other)
@ -53,10 +64,14 @@ struct AggregateFunctionSparkbarData
return;
for (auto & point : other.points)
insert(point.getKey(), point.getMapped());
{
auto new_y = insert(point.getKey(), point.getMapped());
max_y = std::max(new_y, max_y);
}
min_x = std::min(other.min_x, min_x);
max_x = std::max(other.max_x, max_x);
min_y = std::min(other.min_y, min_y);
max_y = std::max(other.max_y, max_y);
}
@ -85,7 +100,6 @@ struct AggregateFunctionSparkbarData
size_t size;
readVarUInt(size, buf);
/// TODO Protection against huge size
X x;
Y y;
for (size_t i = 0; i < size; ++i)
@ -95,7 +109,6 @@ struct AggregateFunctionSparkbarData
insert(x, y);
}
}
};
template<typename X, typename Y>
@ -104,16 +117,17 @@ class AggregateFunctionSparkbar final
{
private:
size_t width;
X min_x;
X max_x;
bool specified_min_max_x;
const size_t width = 0;
template <class T>
size_t updateFrame(ColumnString::Chars & frame, const T value) const
/// Range for x specified in parameters.
const bool is_specified_range_x = false;
const X begin_x = std::numeric_limits<X>::min();
const X end_x = std::numeric_limits<X>::max();
size_t updateFrame(ColumnString::Chars & frame, Y value) const
{
static constexpr std::array<std::string_view, 9> bars{" ", "▁", "▂", "▃", "▄", "▅", "▆", "▇", "█"};
const auto & bar = (isNaN(value) || value > 8 || value < 1) ? bars[0] : bars[static_cast<UInt8>(value)];
const auto & bar = (isNaN(value) || value < 1 || 8 < value) ? bars[0] : bars[static_cast<UInt8>(value)];
frame.insert(bar.begin(), bar.end());
return bar.size();
}
@ -122,161 +136,108 @@ private:
* The minimum value of y is rendered as the lowest height "▁",
* the maximum value of y is rendered as the highest height "█", and the middle value will be rendered proportionally.
* If a bucket has no y value, it will be rendered as " ".
* If the actual number of buckets is greater than the specified bucket, it will be compressed by width.
* For example, there are actually 11 buckets, specify 10 buckets, and divide the 11 buckets as follows (11/10):
* 0.0-1.1, 1.1-2.2, 2.2-3.3, 3.3-4.4, 4.4-5.5, 5.5-6.6, 6.6-7.7, 7.7-8.8, 8.8-9.9, 9.9-11.
* The y value of the first bucket will be calculated as follows:
* the actual y value of the first position + the actual second position y*0.1, and the remaining y*0.9 is reserved for the next bucket.
* The next bucket will use the last y*0.9 + the actual third position y*0.2, and the remaining y*0.8 will be reserved for the next bucket. And so on.
*/
void render(ColumnString & to_column, const AggregateFunctionSparkbarData<X, Y> & data) const
{
size_t sz = 0;
auto & values = to_column.getChars();
auto & offsets = to_column.getOffsets();
auto update_column = [&] ()
if (data.points.empty())
{
values.push_back('\0');
offsets.push_back(offsets.empty() ? 1 : offsets.back() + 1);
return;
}
auto from_x = is_specified_range_x ? begin_x : data.min_x;
auto to_x = is_specified_range_x ? end_x : data.max_x;
if (from_x >= to_x)
{
size_t sz = updateFrame(values, 8);
values.push_back('\0');
offsets.push_back(offsets.empty() ? sz + 1 : offsets.back() + sz + 1);
};
if (data.points.empty() || !width)
return update_column();
size_t diff_x;
X min_x_local;
if (specified_min_max_x)
{
diff_x = max_x - min_x;
min_x_local = min_x;
}
else
{
diff_x = data.max_x - data.min_x;
min_x_local = data.min_x;
return;
}
if ((diff_x + 1) <= width)
{
Y min_y = data.min_y;
Y max_y = data.max_y;
Float64 diff_y = max_y - min_y;
PaddedPODArray<Y> histogram(width, 0);
PaddedPODArray<UInt64> fhistogram(width, 0);
if (diff_y != 0.0)
for (const auto & point : data.points)
{
if (point.getKey() < from_x || to_x < point.getKey())
continue;
X delta = to_x - from_x;
if (delta < std::numeric_limits<X>::max())
delta = delta + 1;
X value = point.getKey() - from_x;
Float64 w = histogram.size();
size_t index = std::min<size_t>(static_cast<size_t>(w / delta * value), histogram.size() - 1);
if (std::numeric_limits<Y>::max() - histogram[index] > point.getMapped())
{
for (size_t i = 0; i <= diff_x; ++i)
{
auto it = data.points.find(static_cast<X>(min_x_local + i));
bool found = it != data.points.end();
sz += updateFrame(values, found ? std::round(((it->getMapped() - min_y) / diff_y) * 7) + 1 : 0.0);
}
histogram[index] += point.getMapped();
fhistogram[index] += 1;
}
else
{
for (size_t i = 0; i <= diff_x; ++i)
sz += updateFrame(values, data.points.has(min_x_local + static_cast<X>(i)) ? 1 : 0);
/// In case of overflow, just saturate
histogram[index] = std::numeric_limits<Y>::max();
}
}
else
for (size_t i = 0; i < histogram.size(); ++i)
{
// begin reshapes to width buckets
Float64 multiple_d = (diff_x + 1) / static_cast<Float64>(width);
std::optional<Float64> min_y;
std::optional<Float64> max_y;
std::optional<Float64> new_y;
std::vector<std::optional<Float64>> new_points;
new_points.reserve(width);
std::pair<size_t, Float64> bound{0, 0.0};
size_t cur_bucket_num = 0;
// upper bound for bucket
auto upper_bound = [&](size_t bucket_num)
{
bound.second = (bucket_num + 1) * multiple_d;
bound.first = static_cast<size_t>(std::floor(bound.second));
};
upper_bound(cur_bucket_num);
for (size_t i = 0; i <= (diff_x + 1); ++i)
{
if (i == bound.first) // is bound
{
Float64 proportion = bound.second - bound.first;
auto it = data.points.find(min_x_local + static_cast<X>(i));
bool found = (it != data.points.end());
if (found && proportion > 0)
new_y = new_y.value_or(0) + it->getMapped() * proportion;
if (new_y)
{
Float64 avg_y = new_y.value() / multiple_d;
new_points.emplace_back(avg_y);
// If min_y has no value, or if the avg_y of the current bucket is less than min_y, update it.
if (!min_y || avg_y < min_y)
min_y = avg_y;
if (!max_y || avg_y > max_y)
max_y = avg_y;
}
else
{
new_points.emplace_back();
}
// next bucket
new_y = found ? ((1 - proportion) * it->getMapped()) : std::optional<Float64>();
upper_bound(++cur_bucket_num);
}
else
{
auto it = data.points.find(min_x_local + static_cast<X>(i));
if (it != data.points.end())
new_y = new_y.value_or(0) + it->getMapped();
}
}
if (!min_y || !max_y) // No value is set
return update_column();
Float64 diff_y = max_y.value() - min_y.value();
auto update_frame = [&] (const std::optional<Float64> & point_y)
{
sz += updateFrame(values, point_y ? std::round(((point_y.value() - min_y.value()) / diff_y) * 7) + 1 : 0);
};
auto update_frame_for_constant = [&] (const std::optional<Float64> & point_y)
{
sz += updateFrame(values, point_y ? 1 : 0);
};
if (diff_y != 0.0)
std::for_each(new_points.begin(), new_points.end(), update_frame);
else
std::for_each(new_points.begin(), new_points.end(), update_frame_for_constant);
if (fhistogram[i] > 0)
histogram[i] /= fhistogram[i];
}
update_column();
Y y_max = 0;
for (auto & y : histogram)
{
if (isNaN(y) || y <= 0)
continue;
y_max = std::max(y_max, y);
}
if (y_max == 0)
{
values.push_back('\0');
offsets.push_back(offsets.empty() ? 1 : offsets.back() + 1);
return;
}
for (auto & y : histogram)
{
if (isNaN(y) || y <= 0)
y = 0;
else
y = y * 7 / y_max + 1;
}
size_t sz = 0;
for (const auto & y : histogram)
sz += updateFrame(values, y);
values.push_back('\0');
offsets.push_back(offsets.empty() ? sz + 1 : offsets.back() + sz + 1);
}
public:
AggregateFunctionSparkbar(const DataTypes & arguments, const Array & params)
: IAggregateFunctionDataHelper<AggregateFunctionSparkbarData<X, Y>, AggregateFunctionSparkbar>(
arguments, params, std::make_shared<DataTypeString>())
: IAggregateFunctionDataHelper<AggregateFunctionSparkbarData<X, Y>, AggregateFunctionSparkbar>(arguments, params, std::make_shared<DataTypeString>())
, width(params.empty() ? 0 : params.at(0).safeGet<UInt64>())
, is_specified_range_x(params.size() >= 3)
, begin_x(is_specified_range_x ? static_cast<X>(params.at(1).safeGet<X>()) : std::numeric_limits<X>::min())
, end_x(is_specified_range_x ? static_cast<X>(params.at(2).safeGet<X>()) : std::numeric_limits<X>::max())
{
width = params.at(0).safeGet<UInt64>();
if (params.size() == 3)
{
specified_min_max_x = true;
min_x = static_cast<X>(params.at(1).safeGet<X>());
max_x = static_cast<X>(params.at(2).safeGet<X>());
}
else
{
specified_min_max_x = false;
min_x = std::numeric_limits<X>::min();
max_x = std::numeric_limits<X>::max();
}
if (width < 2 || 1024 < width)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter width must be in range [2, 1024]");
if (begin_x >= end_x)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter `min_x` must be less than `max_x`");
}
String getName() const override
@ -287,7 +248,7 @@ public:
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * /*arena*/) const override
{
X x = assert_cast<const ColumnVector<X> *>(columns[0])->getData()[row_num];
if (min_x <= x && x <= max_x)
if (begin_x <= x && x <= end_x)
{
Y y = assert_cast<const ColumnVector<Y> *>(columns[1])->getData()[row_num];
this->data(place).add(x, y);

40
src/AggregateFunctions/AggregateFunctionVarianceMatrix.cpp Normal file
View File

@ -0,0 +1,40 @@
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <AggregateFunctions/FactoryHelpers.h>
#include <AggregateFunctions/AggregateFunctionVarianceMatrix.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename FunctionTemplate>
AggregateFunctionPtr createAggregateFunctionVarianceMatrix(
const std::string & name, const DataTypes & argument_types, const Array & parameters, const Settings *)
{
assertNoParameters(name, parameters);
for (const auto & argument_type : argument_types)
if (!isNativeNumber(argument_type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} only supports numerical types", name);
return std::make_shared<FunctionTemplate>(argument_types);
}
}
void registerAggregateFunctionsVarianceMatrix(AggregateFunctionFactory & factory)
{
factory.registerFunction("covarSampMatrix", createAggregateFunctionVarianceMatrix<AggregateFunctionCovarSampMatrix>);
factory.registerFunction("covarPopMatrix", createAggregateFunctionVarianceMatrix<AggregateFunctionCovarPopMatrix>);
factory.registerFunction("corrMatrix", createAggregateFunctionVarianceMatrix<AggregateFunctionCorrMatrix>);
}
}

159
src/AggregateFunctions/AggregateFunctionVarianceMatrix.h Normal file
View File

@ -0,0 +1,159 @@
#pragma once
#include <Columns/ColumnArray.h>
#include <Columns/ColumnsNumber.h>
#include <Common/PODArray.h>
#include <Common/PODArray_fwd.h>
#include <DataTypes/DataTypeArray.h>
#include <AggregateFunctions/IAggregateFunction.h>
#include <AggregateFunctions/Moments.h>
#include <DataTypes/DataTypesNumber.h>
namespace DB
{
struct Settings;
enum class StatisticsMatrixFunctionKind
{
covarPopMatrix,
covarSampMatrix,
corrMatrix
};
template <StatisticsMatrixFunctionKind _kind>
struct AggregateFunctionVarianceMatrixData
{
using DataType = std::conditional_t<_kind == StatisticsMatrixFunctionKind::corrMatrix, CorrMoments<Float64>, CovarMoments<Float64>>;
AggregateFunctionVarianceMatrixData() = default;
explicit AggregateFunctionVarianceMatrixData(const size_t _num_args)
: num_args(_num_args)
{
data_matrix.resize_fill(num_args * (num_args + 1) / 2, DataType());
}
void add(const IColumn ** column, const size_t row_num)
{
for (size_t i = 0; i < num_args; ++i)
for (size_t j = 0; j <= i; ++j)
data_matrix[i * (i + 1) / 2 + j].add(column[i]->getFloat64(row_num), column[j]->getFloat64(row_num));
}
void merge(const AggregateFunctionVarianceMatrixData & other)
{
for (size_t i = 0; i < num_args; ++i)
for (size_t j = 0; j <= i; ++j)
data_matrix[i * (i + 1) / 2 + j].merge(other.data_matrix[i * (i + 1) / 2 + j]);
}
void serialize(WriteBuffer & buf) const
{
for (size_t i = 0; i < num_args; ++i)
for (size_t j = 0; j <= i; ++j)
data_matrix[i * (i + 1) / 2 + j].write(buf);
}
void deserialize(ReadBuffer & buf)
{
for (size_t i = 0; i < num_args; ++i)
for (size_t j = 0; j <= i; ++j)
data_matrix[i * (i + 1) / 2 + j].read(buf);
}
void insertResultInto(IColumn & to) const
{
auto & data_to = assert_cast<ColumnFloat64 &>(assert_cast<ColumnArray &>(assert_cast<ColumnArray &>(to).getData()).getData()).getData();
auto & root_offsets_to = assert_cast<ColumnArray &>(to).getOffsets();
auto & nested_offsets_to = assert_cast<ColumnArray &>(assert_cast<ColumnArray &>(to).getData()).getOffsets();
for (size_t i = 0; i < num_args; ++i)
{
for (size_t j = 0; j < num_args; ++j)
{
auto & data = i < j ? data_matrix[j * (j + 1) / 2 + i] : data_matrix[i * (i + 1) / 2 + j];
if constexpr (kind == StatisticsMatrixFunctionKind::covarPopMatrix)
data_to.push_back(data.getPopulation());
if constexpr (kind == StatisticsMatrixFunctionKind::covarSampMatrix)
data_to.push_back(data.getSample());
if constexpr (kind == StatisticsMatrixFunctionKind::corrMatrix)
data_to.push_back(data.get());
}
nested_offsets_to.push_back(nested_offsets_to.back() + num_args);
}
root_offsets_to.push_back(root_offsets_to.back() + num_args);
}
static constexpr StatisticsMatrixFunctionKind kind = _kind;
PaddedPODArray<DataType> data_matrix;
size_t num_args;
};
template <typename Data>
class AggregateFunctionVarianceMatrix final
: public IAggregateFunctionDataHelper<Data, AggregateFunctionVarianceMatrix<Data>>
{
public:
explicit AggregateFunctionVarianceMatrix(const DataTypes & argument_types_)
: IAggregateFunctionDataHelper<Data, AggregateFunctionVarianceMatrix<Data>>(argument_types_, {}, createResultType())
{}
AggregateFunctionVarianceMatrix(const IDataType &, const DataTypes & argument_types_)
: IAggregateFunctionDataHelper<Data, AggregateFunctionVarianceMatrix<Data>>(argument_types_, {}, createResultType())
{}
String getName() const override
{
if constexpr (Data::kind == StatisticsMatrixFunctionKind::covarPopMatrix)
return "covarPopMatrix";
if constexpr (Data::kind == StatisticsMatrixFunctionKind::covarSampMatrix)
return "covarSampMatrix";
if constexpr (Data::kind == StatisticsMatrixFunctionKind::corrMatrix)
return "corrMatrix";
UNREACHABLE();
}
void create(AggregateDataPtr __restrict place) const override
{
new (place) Data(this->argument_types.size());
}
static DataTypePtr createResultType()
{
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeArray>(std::make_shared<DataTypeFloat64>()));
}
bool allocatesMemoryInArena() const override { return false; }
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena *) const override
{
this->data(place).add(columns, row_num);
}
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena *) const override
{
this->data(place).merge(this->data(rhs));
}
void serialize(ConstAggregateDataPtr __restrict place, WriteBuffer & buf, std::optional<size_t> /* version */) const override
{
this->data(place).serialize(buf);
}
void deserialize(AggregateDataPtr __restrict place, ReadBuffer & buf, std::optional<size_t> /* version */, Arena *) const override
{
this->data(place).deserialize(buf);
}
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
{
this->data(place).insertResultInto(to);
}
};
using AggregateFunctionCovarPopMatrix = AggregateFunctionVarianceMatrix<AggregateFunctionVarianceMatrixData<StatisticsMatrixFunctionKind::covarPopMatrix>>;
using AggregateFunctionCovarSampMatrix = AggregateFunctionVarianceMatrix<AggregateFunctionVarianceMatrixData<StatisticsMatrixFunctionKind::covarSampMatrix>>;
using AggregateFunctionCorrMatrix = AggregateFunctionVarianceMatrix<AggregateFunctionVarianceMatrixData<StatisticsMatrixFunctionKind::corrMatrix>>;
}

2
src/AggregateFunctions/registerAggregateFunctions.cpp
View File

@ -40,6 +40,7 @@ void registerAggregateFunctionsMax(AggregateFunctionFactory &);
void registerAggregateFunctionsAny(AggregateFunctionFactory &);
void registerAggregateFunctionsStatisticsStable(AggregateFunctionFactory &);
void registerAggregateFunctionsStatisticsSimple(AggregateFunctionFactory &);
void registerAggregateFunctionsVarianceMatrix(AggregateFunctionFactory &);
void registerAggregateFunctionSum(AggregateFunctionFactory &);
void registerAggregateFunctionSumCount(AggregateFunctionFactory &);
void registerAggregateFunctionSumMap(AggregateFunctionFactory &);
@ -126,6 +127,7 @@ void registerAggregateFunctions()
registerAggregateFunctionsAny(factory);
registerAggregateFunctionsStatisticsStable(factory);
registerAggregateFunctionsStatisticsSimple(factory);
registerAggregateFunctionsVarianceMatrix(factory);
registerAggregateFunctionSum(factory);
registerAggregateFunctionSumCount(factory);
registerAggregateFunctionSumMap(factory);

17
src/Backups/BackupIO_S3.cpp
View File

@ -9,13 +9,12 @@
#include <IO/WriteBufferFromS3.h>
#include <IO/HTTPHeaderEntries.h>
#include <IO/S3/copyS3File.h>
#include <IO/S3/Client.h>
#include <Poco/Util/AbstractConfiguration.h>
#include <aws/core/auth/AWSCredentials.h>
#include <aws/s3/S3Client.h>
#include <aws/s3/model/DeleteObjectRequest.h>
#include <aws/s3/model/DeleteObjectsRequest.h>
#include <aws/s3/model/ListObjectsRequest.h>
#include <filesystem>
@ -31,7 +30,7 @@ namespace ErrorCodes
namespace
{
std::shared_ptr<Aws::S3::S3Client>
std::shared_ptr<S3::Client>
makeS3Client(const S3::URI & s3_uri, const String & access_key_id, const String & secret_access_key, const ContextPtr & context)
{
auto settings = context->getStorageS3Settings().getSettings(s3_uri.uri.toString());
@ -71,9 +70,9 @@ namespace
context->getConfigRef().getBool("s3.use_insecure_imds_request", false)));
}
Aws::Vector<Aws::S3::Model::Object> listObjects(Aws::S3::S3Client & client, const S3::URI & s3_uri, const String & file_name)
Aws::Vector<Aws::S3::Model::Object> listObjects(S3::Client & client, const S3::URI & s3_uri, const String & file_name)
{
Aws::S3::Model::ListObjectsRequest request;
S3::ListObjectsRequest request;
request.SetBucket(s3_uri.bucket);
request.SetPrefix(fs::path{s3_uri.key} / file_name);
request.SetMaxKeys(1);
@ -228,7 +227,7 @@ std::unique_ptr<WriteBuffer> BackupWriterS3::writeFile(const String & file_name)
void BackupWriterS3::removeFile(const String & file_name)
{
Aws::S3::Model::DeleteObjectRequest request;
S3::DeleteObjectRequest request;
request.SetBucket(s3_uri.bucket);
request.SetKey(fs::path(s3_uri.key) / file_name);
auto outcome = client->DeleteObject(request);
@ -285,7 +284,7 @@ void BackupWriterS3::removeFilesBatch(const Strings & file_names)
Aws::S3::Model::Delete delkeys;
delkeys.SetObjects(current_chunk);
Aws::S3::Model::DeleteObjectsRequest request;
S3::DeleteObjectsRequest request;
request.SetBucket(s3_uri.bucket);
request.SetDelete(delkeys);

5
src/Backups/BackupIO_S3.h
View File

@ -7,7 +7,6 @@
#include <IO/ReadSettings.h>
#include <IO/S3Common.h>
#include <Storages/StorageS3Settings.h>
#include <aws/s3/S3Client.h>
namespace DB
@ -27,7 +26,7 @@ public:
private:
S3::URI s3_uri;
std::shared_ptr<Aws::S3::S3Client> client;
std::shared_ptr<S3::Client> client;
ReadSettings read_settings;
S3Settings::RequestSettings request_settings;
};
@ -73,7 +72,7 @@ private:
void removeFilesBatch(const Strings & file_names);
S3::URI s3_uri;
std::shared_ptr<Aws::S3::S3Client> client;
std::shared_ptr<S3::Client> client;
ReadSettings read_settings;
S3Settings::RequestSettings request_settings;
Poco::Logger * log;

113
src/Backups/BackupImpl.cpp
View File

@ -271,16 +271,22 @@ size_t BackupImpl::getNumFiles() const
return num_files;
}
size_t BackupImpl::getNumProcessedFiles() const
UInt64 BackupImpl::getTotalSize() const
{
std::lock_guard lock{mutex};
return num_processed_files;
return total_size;
}
UInt64 BackupImpl::getProcessedFilesSize() const
size_t BackupImpl::getNumEntries() const
{
std::lock_guard lock{mutex};
return processed_files_size;
return num_entries;
}
UInt64 BackupImpl::getSizeOfEntries() const
{
std::lock_guard lock{mutex};
return size_of_entries;
}
UInt64 BackupImpl::getUncompressedSize() const
@ -295,6 +301,18 @@ UInt64 BackupImpl::getCompressedSize() const
return compressed_size;
}
size_t BackupImpl::getNumReadFiles() const
{
std::lock_guard lock{mutex};
return num_read_files;
}
UInt64 BackupImpl::getNumReadBytes() const
{
std::lock_guard lock{mutex};
return num_read_bytes;
}
void BackupImpl::writeBackupMetadata()
{
assert(!is_internal_backup);
@ -323,12 +341,18 @@ void BackupImpl::writeBackupMetadata()
}
}
size_t index = 0;
for (const auto & info : all_file_infos)
num_files = all_file_infos.size();
total_size = 0;
num_entries = 0;
size_of_entries = 0;
for (size_t i = 0; i != all_file_infos.size(); ++i)
{
String prefix = index ? "contents.file[" + std::to_string(index) + "]." : "contents.file.";
const auto & info = all_file_infos[i];
String prefix = i ? "contents.file[" + std::to_string(i) + "]." : "contents.file.";
config->setString(prefix + "name", info.file_name);
config->setUInt64(prefix + "size", info.size);
if (info.size)
{
config->setString(prefix + "checksum", hexChecksum(info.checksum));
@ -348,8 +372,14 @@ void BackupImpl::writeBackupMetadata()
if (info.pos_in_archive != static_cast<size_t>(-1))
config->setUInt64(prefix + "pos_in_archive", info.pos_in_archive);
}
increaseUncompressedSize(info);
++index;
total_size += info.size;
bool has_entry = !deduplicate_files || (info.size && (info.size != info.base_size) && (info.data_file_name.empty() || (info.data_file_name == info.file_name)));
if (has_entry)
{
++num_entries;
size_of_entries += info.size - info.base_size;
}
}
std::ostringstream stream; // STYLE_CHECK_ALLOW_STD_STRING_STREAM
@ -366,8 +396,7 @@ void BackupImpl::writeBackupMetadata()
out->write(str.data(), str.size());
out->finalize();
increaseUncompressedSize(str.size());
increaseProcessedSize(str.size());
uncompressed_size = size_of_entries + str.size();
}
@ -392,8 +421,6 @@ void BackupImpl::readBackupMetadata()
String str;
readStringUntilEOF(str, *in);
increaseUncompressedSize(str.size());
increaseProcessedSize(str.size());
Poco::XML::DOMParser dom_parser;
Poco::AutoPtr<Poco::XML::Document> config = dom_parser.parseMemory(str.data(), str.size());
const Poco::XML::Node * config_root = getRootNode(config);
@ -412,6 +439,11 @@ void BackupImpl::readBackupMetadata()
if (config_root->getNodeByPath("base_backup_uuid"))
base_backup_uuid = parse<UUID>(getString(config_root, "base_backup_uuid"));
num_files = 0;
total_size = 0;
num_entries = 0;
size_of_entries = 0;
const auto * contents = config_root->getNodeByPath("contents");
for (const Poco::XML::Node * child = contents->firstChild(); child; child = child->nextSibling())
{
@ -456,10 +488,20 @@ void BackupImpl::readBackupMetadata()
}
coordination->addFileInfo(info);
increaseUncompressedSize(info);
++num_files;
total_size += info.size;
bool has_entry = !deduplicate_files || (info.size && (info.size != info.base_size) && (info.data_file_name.empty() || (info.data_file_name == info.file_name)));
if (has_entry)
{
++num_entries;
size_of_entries += info.size - info.base_size;
}
}
}
uncompressed_size = size_of_entries + str.size();
compressed_size = uncompressed_size;
if (!use_archives)
setCompressedSize();
}
@ -612,7 +654,8 @@ BackupEntryPtr BackupImpl::readFile(const SizeAndChecksum & size_and_checksum) c
if (open_mode != OpenMode::READ)
throw Exception(ErrorCodes::LOGICAL_ERROR, "Backup is not opened for reading");
increaseProcessedSize(size_and_checksum.first);
++num_read_files;
num_read_bytes += size_and_checksum.first;
if (!size_and_checksum.first)
{
@ -780,7 +823,8 @@ void BackupImpl::writeFile(const String & file_name, BackupEntryPtr entry)
{
std::lock_guard lock{mutex};
increaseProcessedSize(info);
++num_files;
total_size += info.size;
}
/// Empty file, nothing to backup
@ -909,7 +953,12 @@ void BackupImpl::writeFile(const String & file_name, BackupEntryPtr entry)
{
LOG_TRACE(log, "Will copy file {}", adjusted_path);
if (!num_files_written)
bool has_entries = false;
{
std::lock_guard lock{mutex};
has_entries = num_entries > 0;
}
if (!has_entries)
checkLockFile(true);
if (use_archives)
@ -951,7 +1000,12 @@ void BackupImpl::writeFile(const String & file_name, BackupEntryPtr entry)
}
}
++num_files_written;
{
std::lock_guard lock{mutex};
++num_entries;
size_of_entries += info.size - info.base_size;
uncompressed_size += info.size - info.base_size;
}
}
@ -981,29 +1035,6 @@ void BackupImpl::finalizeWriting()
}
void BackupImpl::increaseUncompressedSize(UInt64 file_size)
{
uncompressed_size += file_size;
++num_files;
}
void BackupImpl::increaseUncompressedSize(const FileInfo & info)
{
if ((info.size > info.base_size) && (info.data_file_name.empty() || (info.data_file_name == info.file_name)))
increaseUncompressedSize(info.size - info.base_size);
}
void BackupImpl::increaseProcessedSize(UInt64 file_size) const
{
processed_files_size += file_size;
++num_processed_files;
}
void BackupImpl::increaseProcessedSize(const FileInfo & info)
{
increaseProcessedSize(info.size);
}
void BackupImpl::setCompressedSize()
{
if (use_archives)

25
src/Backups/BackupImpl.h
View File

@ -59,10 +59,13 @@ public:
time_t getTimestamp() const override { return timestamp; }
UUID getUUID() const override { return *uuid; }
size_t getNumFiles() const override;
size_t getNumProcessedFiles() const override;
UInt64 getProcessedFilesSize() const override;
UInt64 getTotalSize() const override;
size_t getNumEntries() const override;
UInt64 getSizeOfEntries() const override;
UInt64 getUncompressedSize() const override;
UInt64 getCompressedSize() const override;
size_t getNumReadFiles() const override;
UInt64 getNumReadBytes() const override;
Strings listFiles(const String & directory, bool recursive) const override;
bool hasFiles(const String & directory) const override;
bool fileExists(const String & file_name) const override;
@ -103,16 +106,6 @@ private:
std::shared_ptr<IArchiveReader> getArchiveReader(const String & suffix) const;
std::shared_ptr<IArchiveWriter> getArchiveWriter(const String & suffix);
/// Increases `uncompressed_size` by a specific value,
/// also increases `num_files` by 1.
void increaseUncompressedSize(UInt64 file_size);
void increaseUncompressedSize(const FileInfo & info);
/// Increases `num_processed_files` by a specific value,
/// also increases `num_processed_files` by 1.
void increaseProcessedSize(UInt64 file_size) const;
void increaseProcessedSize(const FileInfo & info);
/// Calculates and sets `compressed_size`.
void setCompressedSize();
@ -129,10 +122,13 @@ private:
std::optional<UUID> uuid;
time_t timestamp = 0;
size_t num_files = 0;
mutable size_t num_processed_files = 0;
mutable UInt64 processed_files_size = 0;
UInt64 total_size = 0;
size_t num_entries = 0;
UInt64 size_of_entries = 0;
UInt64 uncompressed_size = 0;
UInt64 compressed_size = 0;
mutable size_t num_read_files = 0;
mutable UInt64 num_read_bytes = 0;
int version;
std::optional<BackupInfo> base_backup_info;
std::shared_ptr<const IBackup> base_backup;
@ -141,7 +137,6 @@ private:
std::pair<String, std::shared_ptr<IArchiveWriter>> archive_writers[2];
String current_archive_suffix;
String lock_file_name;
std::atomic<size_t> num_files_written = 0;
bool writing_finalized = false;
bool deduplicate_files = true;
const Poco::Logger * log;

28
src/Backups/BackupsWorker.cpp
View File

@ -338,20 +338,20 @@ void BackupsWorker::doBackup(
}
size_t num_files = 0;
size_t num_processed_files = 0;
UInt64 total_size = 0;
size_t num_entries = 0;
UInt64 uncompressed_size = 0;
UInt64 compressed_size = 0;
UInt64 processed_files_size = 0;
/// Finalize backup (write its metadata).
if (!backup_settings.internal)
{
backup->finalizeWriting();
num_files = backup->getNumFiles();
num_processed_files = backup->getNumProcessedFiles();
total_size = backup->getTotalSize();
num_entries = backup->getNumEntries();
uncompressed_size = backup->getUncompressedSize();
compressed_size = backup->getCompressedSize();
processed_files_size = backup->getProcessedFilesSize();
}
/// Close the backup.
@ -359,7 +359,7 @@ void BackupsWorker::doBackup(
LOG_INFO(log, "{} {} was created successfully", (backup_settings.internal ? "Internal backup" : "Backup"), backup_name_for_logging);
setStatus(backup_id, BackupStatus::BACKUP_CREATED);
setNumFilesAndSize(backup_id, num_files, num_processed_files, processed_files_size, uncompressed_size, compressed_size);
setNumFilesAndSize(backup_id, num_files, total_size, num_entries, uncompressed_size, compressed_size, 0, 0);
}
catch (...)
{
@ -583,10 +583,12 @@ void BackupsWorker::doRestore(
setNumFilesAndSize(
restore_id,
backup->getNumFiles(),
backup->getNumProcessedFiles(),
backup->getProcessedFilesSize(),
backup->getTotalSize(),
backup->getNumEntries(),
backup->getUncompressedSize(),
backup->getCompressedSize());
backup->getCompressedSize(),
backup->getNumReadFiles(),
backup->getNumReadBytes());
}
catch (...)
{
@ -667,7 +669,9 @@ void BackupsWorker::setStatus(const String & id, BackupStatus status, bool throw
}
void BackupsWorker::setNumFilesAndSize(const String & id, size_t num_files, size_t num_processed_files, UInt64 processed_files_size, UInt64 uncompressed_size, UInt64 compressed_size)
void BackupsWorker::setNumFilesAndSize(const OperationID & id, size_t num_files, UInt64 total_size, size_t num_entries,
UInt64 uncompressed_size, UInt64 compressed_size, size_t num_read_files, UInt64 num_read_bytes)
{
std::lock_guard lock{infos_mutex};
auto it = infos.find(id);
@ -676,10 +680,12 @@ void BackupsWorker::setNumFilesAndSize(const String & id, size_t num_files, size
auto & info = it->second;
info.num_files = num_files;
info.num_processed_files = num_processed_files;
info.processed_files_size = processed_files_size;
info.total_size = total_size;
info.num_entries = num_entries;
info.uncompressed_size = uncompressed_size;
info.compressed_size = compressed_size;
info.num_read_files = num_read_files;
info.num_read_bytes = num_read_bytes;
}

26
src/Backups/BackupsWorker.h
View File

@ -53,23 +53,27 @@ public:
/// Status of backup or restore operation.
BackupStatus status;
/// Number of files in the backup (including backup's metadata; only unique files are counted).
/// The number of files stored in the backup.
size_t num_files = 0;
/// Number of processed files during backup or restore process
/// For restore it includes files from base backups
size_t num_processed_files = 0;
/// The total size of files stored in the backup.
UInt64 total_size = 0;
/// Size of processed files during backup or restore
/// For restore in includes sizes from base backups
UInt64 processed_files_size = 0;
/// The number of entries in the backup, i.e. the number of files inside the folder if the backup is stored as a folder.
size_t num_entries = 0;
/// Size of all files in the backup (including backup's metadata; only unique files are counted).
/// The uncompressed size of the backup.
UInt64 uncompressed_size = 0;
/// Size of the backup if it's stored as an archive; or the same as `uncompressed_size` if the backup is stored as a folder.
/// The compressed size of the backup.
UInt64 compressed_size = 0;
/// Returns the number of files read during RESTORE from this backup.
size_t num_read_files = 0;
// Returns the total size of files read during RESTORE from this backup.
UInt64 num_read_bytes = 0;
/// Set only if there was an error.
std::exception_ptr exception;
String error_message;
@ -110,7 +114,9 @@ private:
void addInfo(const OperationID & id, const String & name, bool internal, BackupStatus status);
void setStatus(const OperationID & id, BackupStatus status, bool throw_if_error = true);
void setStatusSafe(const String & id, BackupStatus status) { setStatus(id, status, false); }
void setNumFilesAndSize(const OperationID & id, size_t num_files, size_t num_processed_files, UInt64 processed_files_size, UInt64 uncompressed_size, UInt64 compressed_size);
void setNumFilesAndSize(const OperationID & id, size_t num_files, UInt64 total_size, size_t num_entries,
UInt64 uncompressed_size, UInt64 compressed_size, size_t num_read_files, UInt64 num_read_bytes);
std::vector<Info> getAllActiveBackupInfos() const;
std::vector<Info> getAllActiveRestoreInfos() const;
bool hasConcurrentBackups(const BackupSettings & backup_settings) const;

31
src/Backups/IBackup.h
View File

@ -37,21 +37,38 @@ public:
/// Returns UUID of the backup.
virtual UUID getUUID() const = 0;
/// Returns the number of unique files in the backup.
/// Returns the number of files stored in the backup. Compare with getNumEntries().
virtual size_t getNumFiles() const = 0;
/// Returns the number of files were processed for backup or restore
virtual size_t getNumProcessedFiles() const = 0;
/// Returns the total size of files stored in the backup. Compare with getTotalSizeOfEntries().
virtual UInt64 getTotalSize() const = 0;
// Returns the total size of processed files for backup or restore
virtual UInt64 getProcessedFilesSize() const = 0;
/// Returns the number of entries in the backup, i.e. the number of files inside the folder if the backup is stored as a folder or
/// the number of files inside the archive if the backup is stored as an archive.
/// It's not the same as getNumFiles() if it's an incremental backups or if it contains empty files or duplicates.
/// The following is always true: `getNumEntries() <= getNumFiles()`.
virtual size_t getNumEntries() const = 0;
/// Returns the total size of unique files in the backup.
/// Returns the size of entries in the backup, i.e. the total size of files inside the folder if the backup is stored as a folder or
/// the total size of files inside the archive if the backup is stored as an archive.
/// It's not the same as getTotalSize() because it doesn't include the size of duplicates and the size of files from the base backup.
/// The following is always true: `getSizeOfEntries() <= getTotalSize()`.
virtual UInt64 getSizeOfEntries() const = 0;
/// Returns the uncompressed size of the backup. It equals to `getSizeOfEntries() + size_of_backup_metadata (.backup)`
virtual UInt64 getUncompressedSize() const = 0;
/// Returns the compressed size of the backup. If the backup is not stored as an archive it returns the same as getUncompressedSize().
/// Returns the compressed size of the backup. If the backup is not stored as an archive it's the same as getUncompressedSize().
virtual UInt64 getCompressedSize() const = 0;
/// Returns the number of files read during RESTORE from this backup.
/// The following is always true: `getNumFilesRead() <= getNumFiles()`.
virtual size_t getNumReadFiles() const = 0;
// Returns the total size of files read during RESTORE from this backup.
/// The following is always true: `getNumReadBytes() <= getTotalSize()`.
virtual UInt64 getNumReadBytes() const = 0;
/// Returns names of entries stored in a specified directory in the backup.
/// If `directory` is empty or '/' the functions returns entries in the backup's root.
virtual Strings listFiles(const String & directory, bool recursive = false) const = 0;

2
src/BridgeHelper/CatBoostLibraryBridgeHelper.h
View File

@ -11,7 +11,7 @@
namespace DB
{
class CatBoostLibraryBridgeHelper : public LibraryBridgeHelper
class CatBoostLibraryBridgeHelper final : public LibraryBridgeHelper
{
public:
static constexpr inline auto PING_HANDLER = "/catboost_ping";

2
src/BridgeHelper/ExternalDictionaryLibraryBridgeHelper.h
View File

@ -14,7 +14,7 @@ namespace DB
class Pipe;
// Class to access the external dictionary part of the clickhouse-library-bridge.
class ExternalDictionaryLibraryBridgeHelper : public LibraryBridgeHelper
class ExternalDictionaryLibraryBridgeHelper final : public LibraryBridgeHelper
{
public:

12
src/CMakeLists.txt
View File

@ -226,13 +226,7 @@ add_object_library(clickhouse_access Access)
add_object_library(clickhouse_backups Backups)
add_object_library(clickhouse_core Core)
add_object_library(clickhouse_core_mysql Core/MySQL)
if (ENABLE_OPENSSL OR ENABLE_OPENSSL_DYNAMIC)
add_headers_and_sources(dbms Compression)
list(REMOVE_ITEM dbms_headers Compression/CompressionCodecEncrypted.h)
list(REMOVE_ITEM dbms_sources Compression/CompressionCodecEncrypted.cpp)
else ()
add_object_library(clickhouse_compression Compression)
endif ()
add_object_library(clickhouse_compression Compression)
add_object_library(clickhouse_querypipeline QueryPipeline)
add_object_library(clickhouse_datatypes DataTypes)
add_object_library(clickhouse_datatypes_serializations DataTypes/Serializations)
@ -343,8 +337,8 @@ set_source_files_properties(
PROPERTIES COMPILE_FLAGS "-mwaitpkg")
endif ()
target_link_libraries(clickhouse_common_io PUBLIC ch_contrib::re2_st)
target_link_libraries(clickhouse_common_io PUBLIC ch_contrib::re2)
target_link_libraries(common PUBLIC ch_contrib::re2_st)
target_link_libraries(common PUBLIC ch_contrib::re2)
target_link_libraries(clickhouse_common_io
PUBLIC

86
src/Client/ClientBase.cpp
View File

@ -41,6 +41,7 @@
#include <Parsers/ASTLiteral.h>
#include <Parsers/ASTIdentifier.h>
#include <Parsers/ASTColumnDeclaration.h>
#include <Parsers/ASTFunction.h>
#include <Parsers/Kusto/ParserKQLStatement.h>
#include <Processors/Formats/Impl/NullFormat.h>
@ -816,17 +817,15 @@ void ClientBase::processTextAsSingleQuery(const String & full_query)
void ClientBase::processOrdinaryQuery(const String & query_to_execute, ASTPtr parsed_query)
{
if (fake_drop)
{
if (parsed_query->as<ASTDropQuery>())
return;
}
if (fake_drop && parsed_query->as<ASTDropQuery>())
return;
auto query = query_to_execute;
/// Rewrite query only when we have query parameters.
/// Note that if query is rewritten, comments in query are lost.
/// But the user often wants to see comments in server logs, query log, processlist, etc.
/// For recent versions of the server query parameters will be transferred by network and applied on the server side.
auto query = query_to_execute;
if (!query_parameters.empty()
&& connection->getServerRevision(connection_parameters.timeouts) < DBMS_MIN_PROTOCOL_VERSION_WITH_PARAMETERS)
{
@ -838,6 +837,22 @@ void ClientBase::processOrdinaryQuery(const String & query_to_execute, ASTPtr pa
query = serializeAST(*parsed_query);
}
if (allow_merge_tree_settings && parsed_query->as<ASTCreateQuery>())
{
/// Rewrite query if new settings were added.
if (addMergeTreeSettings(*parsed_query->as<ASTCreateQuery>()))
{
/// Replace query parameters because AST cannot be serialized otherwise.
if (!query_parameters.empty())
{
ReplaceQueryParameterVisitor visitor(query_parameters);
visitor.visit(parsed_query);
}
query = serializeAST(*parsed_query);
}
}
int retries_left = 10;
while (retries_left)
{
@ -2065,6 +2080,41 @@ void ClientBase::initQueryIdFormats()
}
bool ClientBase::addMergeTreeSettings(ASTCreateQuery & ast_create)
{
if (ast_create.attach
|| !ast_create.storage
|| !ast_create.storage->isExtendedStorageDefinition()
|| !ast_create.storage->engine
|| ast_create.storage->engine->name.find("MergeTree") == std::string::npos)
return false;
auto all_changed = cmd_merge_tree_settings.allChanged();
if (all_changed.begin() == all_changed.end())
return false;
if (!ast_create.storage->settings)
{
auto settings_ast = std::make_shared<ASTSetQuery>();
settings_ast->is_standalone = false;
ast_create.storage->set(ast_create.storage->settings, settings_ast);
}
auto & storage_settings = *ast_create.storage->settings;
bool added_new_setting = false;
for (const auto & setting : all_changed)
{
if (!storage_settings.changes.tryGet(setting.getName()))
{
storage_settings.changes.emplace_back(setting.getName(), setting.getValue());
added_new_setting = true;
}
}
return added_new_setting;
}
void ClientBase::runInteractive()
{
if (config().has("query_id"))
@ -2302,6 +2352,30 @@ void ClientBase::parseAndCheckOptions(OptionsDescription & options_description,
cmd_settings.addProgramOptionsAsMultitokens(options_description.main_description.value());
else
cmd_settings.addProgramOptions(options_description.main_description.value());
if (allow_merge_tree_settings)
{
/// Add merge tree settings manually, because names of some settings
/// may clash. Query settings have higher priority and we just
/// skip ambiguous merge tree settings.
auto & main_options = options_description.main_description.value();
NameSet main_option_names;
for (const auto & option : main_options.options())
main_option_names.insert(option->long_name());
for (const auto & setting : cmd_merge_tree_settings.all())
{
if (main_option_names.contains(setting.getName()))
continue;
if (allow_repeated_settings)
cmd_merge_tree_settings.addProgramOptionAsMultitoken(main_options, setting);
else
cmd_merge_tree_settings.addProgramOption(main_options, setting);
}
}
/// Parse main commandline options.
auto parser = po::command_line_parser(arguments).options(options_description.main_description.value()).allow_unregistered();
po::parsed_options parsed = parser.run();

5
src/Client/ClientBase.h
View File

@ -1,6 +1,7 @@
#pragma once
#include "Common/NamePrompter.h"
#include <Parsers/ASTCreateQuery.h>
#include <Common/ProgressIndication.h>
#include <Common/InterruptListener.h>
#include <Common/ShellCommand.h>
@ -14,6 +15,7 @@
#include <boost/program_options.hpp>
#include <Storages/StorageFile.h>
#include <Storages/SelectQueryInfo.h>
#include <Storages/MergeTree/MergeTreeSettings.h>
namespace po = boost::program_options;
@ -164,6 +166,7 @@ private:
void updateSuggest(const ASTPtr & ast);
void initQueryIdFormats();
bool addMergeTreeSettings(ASTCreateQuery & ast_create);
protected:
static bool isSyncInsertWithData(const ASTInsertQuery & insert_query, const ContextPtr & context);
@ -212,6 +215,7 @@ protected:
/// Settings specified via command line args
Settings cmd_settings;
MergeTreeSettings cmd_merge_tree_settings;
/// thread status should be destructed before shared context because it relies on process list.
std::optional<ThreadStatus> thread_status;
@ -298,6 +302,7 @@ protected:
std::vector<HostAndPort> hosts_and_ports{};
bool allow_repeated_settings = false;
bool allow_merge_tree_settings = false;
bool cancelled = false;

19
src/Client/Connection.cpp
View File

@ -686,7 +686,7 @@ void Connection::sendReadTaskResponse(const String & response)
}
void Connection::sendMergeTreeReadTaskResponse(const PartitionReadResponse & response)
void Connection::sendMergeTreeReadTaskResponse(const ParallelReadResponse & response)
{
writeVarUInt(Protocol::Client::MergeTreeReadTaskResponse, *out);
response.serialize(*out);
@ -960,8 +960,12 @@ Packet Connection::receivePacket()
case Protocol::Server::ReadTaskRequest:
return res;
case Protocol::Server::MergeTreeAllRangesAnnounecement:
res.announcement = receiveInitialParallelReadAnnounecement();
return res;
case Protocol::Server::MergeTreeReadTaskRequest:
res.request = receivePartitionReadRequest();
res.request = receiveParallelReadRequest();
return res;
case Protocol::Server::ProfileEvents:
@ -1114,13 +1118,20 @@ ProfileInfo Connection::receiveProfileInfo() const
return profile_info;
}
PartitionReadRequest Connection::receivePartitionReadRequest() const
ParallelReadRequest Connection::receiveParallelReadRequest() const
{
PartitionReadRequest request;
ParallelReadRequest request;
request.deserialize(*in);
return request;
}
InitialAllRangesAnnouncement Connection::receiveInitialParallelReadAnnounecement() const
{
InitialAllRangesAnnouncement announcement;
announcement.deserialize(*in);
return announcement;
}
void Connection::throwUnexpectedPacket(UInt64 packet_type, const char * expected) const
{

5
src/Client/Connection.h
View File

@ -110,7 +110,7 @@ public:
void sendData(const Block & block, const String & name/* = "" */, bool scalar/* = false */) override;
void sendMergeTreeReadTaskResponse(const PartitionReadResponse & response) override;
void sendMergeTreeReadTaskResponse(const ParallelReadResponse & response) override;
void sendExternalTablesData(ExternalTablesData & data) override;
@ -265,7 +265,8 @@ private:
std::vector<String> receiveMultistringMessage(UInt64 msg_type) const;
std::unique_ptr<Exception> receiveException() const;
Progress receiveProgress() const;
PartitionReadRequest receivePartitionReadRequest() const;
ParallelReadRequest receiveParallelReadRequest() const;
InitialAllRangesAnnouncement receiveInitialParallelReadAnnounecement() const;
ProfileInfo receiveProfileInfo() const;
void initInputBuffers();

2
src/Client/HedgedConnections.h
View File

@ -94,7 +94,7 @@ public:
throw Exception(ErrorCodes::LOGICAL_ERROR, "sendReadTaskResponse in not supported with HedgedConnections");
}
void sendMergeTreeReadTaskResponse(PartitionReadResponse) override
void sendMergeTreeReadTaskResponse(const ParallelReadResponse &) override
{
throw Exception(ErrorCodes::LOGICAL_ERROR, "sendMergeTreeReadTaskResponse in not supported with HedgedConnections");
}

4
src/Client/IConnections.h
View File

@ -34,7 +34,7 @@ public:
bool with_pending_data) = 0;
virtual void sendReadTaskResponse(const String &) = 0;
virtual void sendMergeTreeReadTaskResponse(PartitionReadResponse response) = 0;
virtual void sendMergeTreeReadTaskResponse(const ParallelReadResponse & response) = 0;
/// Get packet from any replica.
virtual Packet receivePacket() = 0;
@ -60,9 +60,9 @@ public:
/// Get the replica addresses as a string.
virtual std::string dumpAddresses() const = 0;
struct ReplicaInfo
{
bool collaborate_with_initiator{false};
size_t all_replicas_count{0};
size_t number_of_current_replica{0};
};

8
src/Client/IServerConnection.h
View File

@ -33,8 +33,10 @@ struct Packet
Progress progress;
ProfileInfo profile_info;
std::vector<UUID> part_uuids;
PartitionReadRequest request;
PartitionReadResponse response;
InitialAllRangesAnnouncement announcement;
ParallelReadRequest request;
ParallelReadResponse response;
Packet() : type(Protocol::Server::Hello) {}
};
@ -104,7 +106,7 @@ public:
/// Send all contents of external (temporary) tables.
virtual void sendExternalTablesData(ExternalTablesData & data) = 0;
virtual void sendMergeTreeReadTaskResponse(const PartitionReadResponse & response) = 0;
virtual void sendMergeTreeReadTaskResponse(const ParallelReadResponse & response) = 0;
/// Check, if has data to read.
virtual bool poll(size_t timeout_microseconds) = 0;

2
src/Client/LocalConnection.cpp
View File

@ -508,7 +508,7 @@ void LocalConnection::sendExternalTablesData(ExternalTablesData &)
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Not implemented");
}
void LocalConnection::sendMergeTreeReadTaskResponse(const PartitionReadResponse &)
void LocalConnection::sendMergeTreeReadTaskResponse(const ParallelReadResponse &)
{
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Not implemented");
}

2
src/Client/LocalConnection.h
View File

@ -110,7 +110,7 @@ public:
void sendExternalTablesData(ExternalTablesData &) override;
void sendMergeTreeReadTaskResponse(const PartitionReadResponse & response) override;
void sendMergeTreeReadTaskResponse(const ParallelReadResponse & response) override;
bool poll(size_t timeout_microseconds/* = 0 */) override;

15
src/Client/MultiplexedConnections.cpp
View File

@ -133,16 +133,11 @@ void MultiplexedConnections::sendQuery(
modified_settings.group_by_two_level_threshold_bytes = 0;
}
bool parallel_reading_from_replicas = settings.max_parallel_replicas > 1
&& settings.allow_experimental_parallel_reading_from_replicas
/// To avoid trying to coordinate with clickhouse-benchmark,
/// since it uses the same code.
&& client_info.query_kind != ClientInfo::QueryKind::INITIAL_QUERY;
if (parallel_reading_from_replicas)
if (replica_info)
{
client_info.collaborate_with_initiator = true;
client_info.count_participating_replicas = replica_info.all_replicas_count;
client_info.number_of_current_replica = replica_info.number_of_current_replica;
client_info.count_participating_replicas = replica_info->all_replicas_count;
client_info.number_of_current_replica = replica_info->number_of_current_replica;
}
}
@ -199,7 +194,7 @@ void MultiplexedConnections::sendReadTaskResponse(const String & response)
}
void MultiplexedConnections::sendMergeTreeReadTaskResponse(PartitionReadResponse response)
void MultiplexedConnections::sendMergeTreeReadTaskResponse(const ParallelReadResponse & response)
{
std::lock_guard lock(cancel_mutex);
if (cancelled)
@ -263,6 +258,7 @@ Packet MultiplexedConnections::drain()
switch (packet.type)
{
case Protocol::Server::MergeTreeAllRangesAnnounecement:
case Protocol::Server::MergeTreeReadTaskRequest:
case Protocol::Server::ReadTaskRequest:
case Protocol::Server::PartUUIDs:
@ -343,6 +339,7 @@ Packet MultiplexedConnections::receivePacketUnlocked(AsyncCallback async_callbac
switch (packet.type)
{
case Protocol::Server::MergeTreeAllRangesAnnounecement:
case Protocol::Server::MergeTreeReadTaskRequest:
case Protocol::Server::ReadTaskRequest:
case Protocol::Server::PartUUIDs:

5
src/Client/MultiplexedConnections.h
View File

@ -42,7 +42,7 @@ public:
bool with_pending_data) override;
void sendReadTaskResponse(const String &) override;
void sendMergeTreeReadTaskResponse(PartitionReadResponse response) override;
void sendMergeTreeReadTaskResponse(const ParallelReadResponse & response) override;
Packet receivePacket() override;
@ -104,7 +104,8 @@ private:
bool sent_query = false;
bool cancelled = false;
ReplicaInfo replica_info;
/// std::nullopt if parallel reading from replicas is not used
std::optional<ReplicaInfo> replica_info;
/// A mutex for the sendCancel function to execute safely
/// in separate thread.

4
src/Client/ReplxxLineReader.cpp
View File

@ -417,6 +417,10 @@ ReplxxLineReader::ReplxxLineReader(
{
rx.print("skim failed: %s (consider using Ctrl-T for a regular non-fuzzy reverse search)\n", e.what());
}
/// REPAINT before to avoid prompt overlap by the query
rx.invoke(Replxx::ACTION::REPAINT, code);
if (!new_query.empty())
rx.set_state(replxx::Replxx::State(new_query.c_str(), static_cast<int>(new_query.size())));

126
src/Columns/ColumnArray.cpp
View File

@ -1,5 +1,6 @@
#include <Columns/ColumnArray.h>
#include <Columns/ColumnsNumber.h>
#include <Columns/ColumnDecimal.h>
#include <Columns/ColumnString.h>
#include <Columns/ColumnTuple.h>
#include <Columns/ColumnNullable.h>
@ -549,19 +550,48 @@ void ColumnArray::insertRangeFrom(const IColumn & src, size_t start, size_t leng
ColumnPtr ColumnArray::filter(const Filter & filt, ssize_t result_size_hint) const
{
if (typeid_cast<const ColumnUInt8 *>(data.get())) return filterNumber<UInt8>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt16 *>(data.get())) return filterNumber<UInt16>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt32 *>(data.get())) return filterNumber<UInt32>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt64 *>(data.get())) return filterNumber<UInt64>(filt, result_size_hint);
if (typeid_cast<const ColumnInt8 *>(data.get())) return filterNumber<Int8>(filt, result_size_hint);
if (typeid_cast<const ColumnInt16 *>(data.get())) return filterNumber<Int16>(filt, result_size_hint);
if (typeid_cast<const ColumnInt32 *>(data.get())) return filterNumber<Int32>(filt, result_size_hint);
if (typeid_cast<const ColumnInt64 *>(data.get())) return filterNumber<Int64>(filt, result_size_hint);
if (typeid_cast<const ColumnFloat32 *>(data.get())) return filterNumber<Float32>(filt, result_size_hint);
if (typeid_cast<const ColumnFloat64 *>(data.get())) return filterNumber<Float64>(filt, result_size_hint);
if (typeid_cast<const ColumnString *>(data.get())) return filterString(filt, result_size_hint);
if (typeid_cast<const ColumnTuple *>(data.get())) return filterTuple(filt, result_size_hint);
if (typeid_cast<const ColumnNullable *>(data.get())) return filterNullable(filt, result_size_hint);
if (typeid_cast<const ColumnUInt8 *>(data.get()))
return filterNumber<UInt8>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt16 *>(data.get()))
return filterNumber<UInt16>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt32 *>(data.get()))
return filterNumber<UInt32>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt64 *>(data.get()))
return filterNumber<UInt64>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt128 *>(data.get()))
return filterNumber<UInt128>(filt, result_size_hint);
if (typeid_cast<const ColumnUInt256 *>(data.get()))
return filterNumber<UInt256>(filt, result_size_hint);
if (typeid_cast<const ColumnInt8 *>(data.get()))
return filterNumber<Int8>(filt, result_size_hint);
if (typeid_cast<const ColumnInt16 *>(data.get()))
return filterNumber<Int16>(filt, result_size_hint);
if (typeid_cast<const ColumnInt32 *>(data.get()))
return filterNumber<Int32>(filt, result_size_hint);
if (typeid_cast<const ColumnInt64 *>(data.get()))
return filterNumber<Int64>(filt, result_size_hint);
if (typeid_cast<const ColumnInt128 *>(data.get()))
return filterNumber<Int128>(filt, result_size_hint);
if (typeid_cast<const ColumnInt256 *>(data.get()))
return filterNumber<Int256>(filt, result_size_hint);
if (typeid_cast<const ColumnFloat32 *>(data.get()))
return filterNumber<Float32>(filt, result_size_hint);
if (typeid_cast<const ColumnFloat64 *>(data.get()))
return filterNumber<Float64>(filt, result_size_hint);
if (typeid_cast<const ColumnDecimal<Decimal32> *>(data.get()))
return filterNumber<Decimal32>(filt, result_size_hint);
if (typeid_cast<const ColumnDecimal<Decimal64> *>(data.get()))
return filterNumber<Decimal64>(filt, result_size_hint);
if (typeid_cast<const ColumnDecimal<Decimal128> *>(data.get()))
return filterNumber<Decimal128>(filt, result_size_hint);
if (typeid_cast<const ColumnDecimal<Decimal256> *>(data.get()))
return filterNumber<Decimal256>(filt, result_size_hint);
if (typeid_cast<const ColumnString *>(data.get()))
return filterString(filt, result_size_hint);
if (typeid_cast<const ColumnTuple *>(data.get()))
return filterTuple(filt, result_size_hint);
if (typeid_cast<const ColumnNullable *>(data.get()))
return filterNullable(filt, result_size_hint);
return filterGeneric(filt, result_size_hint);
}
@ -597,15 +627,17 @@ void ColumnArray::expand(const IColumn::Filter & mask, bool inverted)
template <typename T>
ColumnPtr ColumnArray::filterNumber(const Filter & filt, ssize_t result_size_hint) const
{
using ColVecType = ColumnVectorOrDecimal<T>;
if (getOffsets().empty())
return ColumnArray::create(data);
auto res = ColumnArray::create(data->cloneEmpty());
auto & res_elems = assert_cast<ColumnVector<T> &>(res->getData()).getData();
auto & res_elems = assert_cast<ColVecType &>(res->getData()).getData();
Offsets & res_offsets = res->getOffsets();
filterArraysImpl<T>(assert_cast<const ColumnVector<T> &>(*data).getData(), getOffsets(), res_elems, res_offsets, filt, result_size_hint);
filterArraysImpl<T>(assert_cast<const ColVecType &>(*data).getData(), getOffsets(), res_elems, res_offsets, filt, result_size_hint);
return res;
}
@ -932,20 +964,50 @@ ColumnPtr ColumnArray::replicate(const Offsets & replicate_offsets) const
if (replicate_offsets.empty())
return cloneEmpty();
if (typeid_cast<const ColumnUInt8 *>(data.get())) return replicateNumber<UInt8>(replicate_offsets);
if (typeid_cast<const ColumnUInt16 *>(data.get())) return replicateNumber<UInt16>(replicate_offsets);
if (typeid_cast<const ColumnUInt32 *>(data.get())) return replicateNumber<UInt32>(replicate_offsets);
if (typeid_cast<const ColumnUInt64 *>(data.get())) return replicateNumber<UInt64>(replicate_offsets);
if (typeid_cast<const ColumnInt8 *>(data.get())) return replicateNumber<Int8>(replicate_offsets);
if (typeid_cast<const ColumnInt16 *>(data.get())) return replicateNumber<Int16>(replicate_offsets);
if (typeid_cast<const ColumnInt32 *>(data.get())) return replicateNumber<Int32>(replicate_offsets);
if (typeid_cast<const ColumnInt64 *>(data.get())) return replicateNumber<Int64>(replicate_offsets);
if (typeid_cast<const ColumnFloat32 *>(data.get())) return replicateNumber<Float32>(replicate_offsets);
if (typeid_cast<const ColumnFloat64 *>(data.get())) return replicateNumber<Float64>(replicate_offsets);
if (typeid_cast<const ColumnString *>(data.get())) return replicateString(replicate_offsets);
if (typeid_cast<const ColumnConst *>(data.get())) return replicateConst(replicate_offsets);
if (typeid_cast<const ColumnNullable *>(data.get())) return replicateNullable(replicate_offsets);
if (typeid_cast<const ColumnTuple *>(data.get())) return replicateTuple(replicate_offsets);
if (typeid_cast<const ColumnUInt8 *>(data.get()))
return replicateNumber<UInt8>(replicate_offsets);
if (typeid_cast<const ColumnUInt16 *>(data.get()))
return replicateNumber<UInt16>(replicate_offsets);
if (typeid_cast<const ColumnUInt32 *>(data.get()))
return replicateNumber<UInt32>(replicate_offsets);
if (typeid_cast<const ColumnUInt64 *>(data.get()))
return replicateNumber<UInt64>(replicate_offsets);
if (typeid_cast<const ColumnUInt128 *>(data.get()))
return replicateNumber<UInt128>(replicate_offsets);
if (typeid_cast<const ColumnUInt256 *>(data.get()))
return replicateNumber<UInt256>(replicate_offsets);
if (typeid_cast<const ColumnInt8 *>(data.get()))
return replicateNumber<Int8>(replicate_offsets);
if (typeid_cast<const ColumnInt16 *>(data.get()))
return replicateNumber<Int16>(replicate_offsets);
if (typeid_cast<const ColumnInt32 *>(data.get()))
return replicateNumber<Int32>(replicate_offsets);
if (typeid_cast<const ColumnInt64 *>(data.get()))
return replicateNumber<Int64>(replicate_offsets);
if (typeid_cast<const ColumnInt128 *>(data.get()))
return replicateNumber<Int128>(replicate_offsets);
if (typeid_cast<const ColumnInt256 *>(data.get()))
return replicateNumber<Int256>(replicate_offsets);
if (typeid_cast<const ColumnFloat32 *>(data.get()))
return replicateNumber<Float32>(replicate_offsets);
if (typeid_cast<const ColumnFloat64 *>(data.get()))
return replicateNumber<Float64>(replicate_offsets);
if (typeid_cast<const ColumnDecimal<Decimal32> *>(data.get()))
return replicateNumber<Decimal32>(replicate_offsets);
if (typeid_cast<const ColumnDecimal<Decimal64> *>(data.get()))
return replicateNumber<Decimal64>(replicate_offsets);
if (typeid_cast<const ColumnDecimal<Decimal128> *>(data.get()))
return replicateNumber<Decimal128>(replicate_offsets);
if (typeid_cast<const ColumnDecimal<Decimal256> *>(data.get()))
return replicateNumber<Decimal256>(replicate_offsets);
if (typeid_cast<const ColumnString *>(data.get()))
return replicateString(replicate_offsets);
if (typeid_cast<const ColumnConst *>(data.get()))
return replicateConst(replicate_offsets);
if (typeid_cast<const ColumnNullable *>(data.get()))
return replicateNullable(replicate_offsets);
if (typeid_cast<const ColumnTuple *>(data.get()))
return replicateTuple(replicate_offsets);
return replicateGeneric(replicate_offsets);
}
@ -953,6 +1015,8 @@ ColumnPtr ColumnArray::replicate(const Offsets & replicate_offsets) const
template <typename T>
ColumnPtr ColumnArray::replicateNumber(const Offsets & replicate_offsets) const
{
using ColVecType = ColumnVectorOrDecimal<T>;
size_t col_size = size();
if (col_size != replicate_offsets.size())
throw Exception(ErrorCodes::SIZES_OF_COLUMNS_DOESNT_MATCH, "Size of offsets doesn't match size of column.");
@ -964,10 +1028,10 @@ ColumnPtr ColumnArray::replicateNumber(const Offsets & replicate_offsets) const
ColumnArray & res_arr = typeid_cast<ColumnArray &>(*res);
const typename ColumnVector<T>::Container & src_data = typeid_cast<const ColumnVector<T> &>(*data).getData();
const typename ColVecType::Container & src_data = typeid_cast<const ColVecType &>(*data).getData();
const Offsets & src_offsets = getOffsets();
typename ColumnVector<T>::Container & res_data = typeid_cast<ColumnVector<T> &>(res_arr.getData()).getData();
typename ColVecType::Container & res_data = typeid_cast<ColVecType &>(res_arr.getData()).getData();
Offsets & res_offsets = res_arr.getOffsets();
res_data.reserve(data->size() / col_size * replicate_offsets.back());

5
src/Columns/ColumnDecimal.h
View File

@ -59,10 +59,7 @@ public:
void insertFrom(const IColumn & src, size_t n) override { data.push_back(static_cast<const Self &>(src).getData()[n]); }
void insertData(const char * src, size_t /*length*/) override;
void insertDefault() override { data.push_back(T()); }
virtual void insertManyDefaults(size_t length) override
{
data.resize_fill(data.size() + length);
}
void insertManyDefaults(size_t length) override { data.resize_fill(data.size() + length); }
void insert(const Field & x) override { data.push_back(x.get<T>()); }
void insertRangeFrom(const IColumn & src, size_t start, size_t length) override;

8
src/Columns/ColumnsCommon.cpp
View File

@ -320,12 +320,20 @@ INSTANTIATE(UInt8)
INSTANTIATE(UInt16)
INSTANTIATE(UInt32)
INSTANTIATE(UInt64)
INSTANTIATE(UInt128)
INSTANTIATE(UInt256)
INSTANTIATE(Int8)
INSTANTIATE(Int16)
INSTANTIATE(Int32)
INSTANTIATE(Int64)
INSTANTIATE(Int128)
INSTANTIATE(Int256)
INSTANTIATE(Float32)
INSTANTIATE(Float64)
INSTANTIATE(Decimal32)
INSTANTIATE(Decimal64)
INSTANTIATE(Decimal128)
INSTANTIATE(Decimal256)
#undef INSTANTIATE

4
src/Common/Exception.cpp
View File

@ -559,9 +559,9 @@ bool ExecutionStatus::tryDeserializeText(const std::string & data)
return true;
}
ExecutionStatus ExecutionStatus::fromCurrentException(const std::string & start_of_message)
ExecutionStatus ExecutionStatus::fromCurrentException(const std::string & start_of_message, bool with_stacktrace)
{
String msg = (start_of_message.empty() ? "" : (start_of_message + ": ")) + getCurrentExceptionMessage(false, true);
String msg = (start_of_message.empty() ? "" : (start_of_message + ": ")) + getCurrentExceptionMessage(with_stacktrace, true);
return ExecutionStatus(getCurrentExceptionCode(), msg);
}

2
src/Common/Exception.h
View File

@ -242,7 +242,7 @@ struct ExecutionStatus
explicit ExecutionStatus(int return_code, const std::string & exception_message = "")
: code(return_code), message(exception_message) {}
static ExecutionStatus fromCurrentException(const std::string & start_of_message = "");
static ExecutionStatus fromCurrentException(const std::string & start_of_message = "", bool with_stacktrace = false);
static ExecutionStatus fromText(const std::string & data);

11
src/Common/MultiVersion.h
View File

@ -1,5 +1,6 @@
#pragma once
#include <atomic>
#include <mutex>
#include <memory>
#include <base/defines.h>
@ -39,19 +40,15 @@ public:
/// Obtain current version for read-only usage. Returns shared_ptr, that manages lifetime of version.
Version get() const
{
/// NOTE: is it possible to lock-free replace of shared_ptr?
std::lock_guard lock(mutex);
return current_version;
return std::atomic_load(&current_version);
}
/// Update an object with new version.
void set(std::unique_ptr<const T> && value)
{
std::lock_guard lock(mutex);
current_version = std::move(value);
std::atomic_store(&current_version, Version{std::move(value)});
}
private:
Version current_version TSA_GUARDED_BY(mutex);
mutable std::mutex mutex;
Version current_version;
};

74
src/Common/OpenTelemetryTraceContext.cpp
View File

@ -14,76 +14,82 @@ namespace OpenTelemetry
thread_local TracingContextOnThread current_thread_trace_context;
void Span::addAttribute(std::string_view name, UInt64 value)
bool Span::addAttribute(std::string_view name, UInt64 value) noexcept
{
if (!this->isTraceEnabled() || name.empty())
return;
return false;
this->attributes.push_back(Tuple{name, toString(value)});
return addAttributeImpl(name, toString(value));
}
void Span::addAttributeIfNotZero(std::string_view name, UInt64 value)
bool Span::addAttributeIfNotZero(std::string_view name, UInt64 value) noexcept
{
if (value != 0)
addAttribute(name, value);
if (!this->isTraceEnabled() || name.empty() || value == 0)
return false;
return addAttributeImpl(name, toString(value));
}
void Span::addAttribute(std::string_view name, std::string_view value)
bool Span::addAttribute(std::string_view name, std::string_view value) noexcept
{
if (!this->isTraceEnabled() || name.empty())
return;
return false;
this->attributes.push_back(Tuple{name, value});
return addAttributeImpl(name, value);
}
void Span::addAttributeIfNotEmpty(std::string_view name, std::string_view value)
bool Span::addAttributeIfNotEmpty(std::string_view name, std::string_view value) noexcept
{
if (!this->isTraceEnabled() || name.empty() || value.empty())
return;
return false;
this->attributes.push_back(Tuple{name, value});
return addAttributeImpl(name, value);
}
void Span::addAttribute(std::string_view name, std::function<String()> value_supplier)
bool Span::addAttribute(std::string_view name, std::function<String()> value_supplier) noexcept
{
if (!this->isTraceEnabled() || !value_supplier)
return;
if (!this->isTraceEnabled() || name.empty() || !value_supplier)
return false;
String value = value_supplier();
if (value.empty())
return;
this->attributes.push_back(Tuple{name, value});
try
{
auto value = value_supplier();
return value.empty() ? false : addAttributeImpl(name, value);
}
catch (...)
{
/// Ignore exception raised by value_supplier
return false;
}
}
void Span::addAttribute(const Exception & e) noexcept
bool Span::addAttribute(const Exception & e) noexcept
{
if (!this->isTraceEnabled())
return;
return false;
try
{
this->attributes.push_back(Tuple{"clickhouse.exception", getExceptionMessage(e, false)});
}
catch (...)
{
/// Ignore exceptions
}
return addAttributeImpl("clickhouse.exception", getExceptionMessage(e, false));
}
void Span::addAttribute(std::exception_ptr e) noexcept
bool Span::addAttribute(std::exception_ptr e) noexcept
{
if (!this->isTraceEnabled() || e == nullptr)
return;
return false;
return addAttributeImpl("clickhouse.exception", getExceptionMessage(e, false));
}
bool Span::addAttributeImpl(std::string_view name, std::string_view value) noexcept
{
try
{
this->attributes.push_back(Tuple{"clickhouse.exception", getExceptionMessage(e, false)});
this->attributes.push_back(Tuple{name, value});
}
catch (...)
{
/// Ignore exceptions
return false;
}
return true;
}
SpanHolder::SpanHolder(std::string_view _operation_name)

23
src/Common/OpenTelemetryTraceContext.h
View File

@ -23,21 +23,24 @@ struct Span
UInt64 finish_time_us = 0;
Map attributes;
void addAttribute(std::string_view name, UInt64 value);
void addAttributeIfNotZero(std::string_view name, UInt64 value);
void addAttribute(std::string_view name, std::string_view value);
void addAttributeIfNotEmpty(std::string_view name, std::string_view value);
void addAttribute(std::string_view name, std::function<String()> value_supplier);
/// Following two methods are declared as noexcept to make sure they're exception safe
/// This is because they're usually called in exception handler
void addAttribute(const Exception & e) noexcept;
void addAttribute(std::exception_ptr e) noexcept;
/// Following methods are declared as noexcept to make sure they're exception safe.
/// This is because sometimes they will be called in exception handlers/dtor.
/// Returns true if attribute is successfully added and false otherwise.
bool addAttribute(std::string_view name, UInt64 value) noexcept;
bool addAttributeIfNotZero(std::string_view name, UInt64 value) noexcept;
bool addAttribute(std::string_view name, std::string_view value) noexcept;
bool addAttributeIfNotEmpty(std::string_view name, std::string_view value) noexcept;
bool addAttribute(std::string_view name, std::function<String()> value_supplier) noexcept;
bool addAttribute(const Exception & e) noexcept;
bool addAttribute(std::exception_ptr e) noexcept;
bool isTraceEnabled() const
{
return trace_id != UUID();
}
private:
bool addAttributeImpl(std::string_view name, std::string_view value) noexcept;
};
/// See https://www.w3.org/TR/trace-context/ for trace_flags definition

20
src/Common/ThreadPool.cpp
View File

@ -3,6 +3,7 @@
#include <Common/Exception.h>
#include <Common/getNumberOfPhysicalCPUCores.h>
#include <Common/OpenTelemetryTraceContext.h>
#include <Common/noexcept_scope.h>
#include <cassert>
#include <iostream>
@ -209,6 +210,7 @@ ThreadPoolImpl<Thread>::~ThreadPoolImpl()
/// and the destruction order of global variables is unspecified.
finalize();
onDestroy();
}
template <typename Thread>
@ -227,6 +229,24 @@ void ThreadPoolImpl<Thread>::finalize()
threads.clear();
}
template <typename Thread>
void ThreadPoolImpl<Thread>::addOnDestroyCallback(OnDestroyCallback && callback)
{
std::lock_guard lock(mutex);
on_destroy_callbacks.push(std::move(callback));
}
template <typename Thread>
void ThreadPoolImpl<Thread>::onDestroy()
{
while (!on_destroy_callbacks.empty())
{
auto callback = std::move(on_destroy_callbacks.top());
on_destroy_callbacks.pop();
NOEXCEPT_SCOPE({ callback(); });
}
}
template <typename Thread>
size_t ThreadPoolImpl<Thread>::active() const
{

16
src/Common/ThreadPool.h
View File

@ -9,6 +9,7 @@
#include <list>
#include <optional>
#include <atomic>
#include <stack>
#include <boost/heap/priority_queue.hpp>
@ -80,6 +81,16 @@ public:
void setQueueSize(size_t value);
size_t getMaxThreads() const;
/// Adds a callback which is called in destructor after
/// joining of all threads. The order of calling callbacks
/// is reversed to the order of their addition.
/// It may be useful for static thread pools to call
/// function after joining of threads because order
/// of destructors of global static objects and callbacks
/// added by atexit is undefined for different translation units.
using OnDestroyCallback = std::function<void()>;
void addOnDestroyCallback(OnDestroyCallback && callback);
private:
mutable std::mutex mutex;
std::condition_variable job_finished;
@ -111,6 +122,7 @@ private:
boost::heap::priority_queue<JobWithPriority> jobs;
std::list<Thread> threads;
std::exception_ptr first_exception;
std::stack<OnDestroyCallback> on_destroy_callbacks;
template <typename ReturnType>
ReturnType scheduleImpl(Job job, ssize_t priority, std::optional<uint64_t> wait_microseconds, bool propagate_opentelemetry_tracing_context = true);
@ -118,6 +130,7 @@ private:
void worker(typename std::list<Thread>::iterator thread_it);
void finalize();
void onDestroy();
};
@ -146,7 +159,8 @@ class GlobalThreadPool : public FreeThreadPool, private boost::noncopyable
size_t queue_size_, const bool shutdown_on_exception_)
: FreeThreadPool(max_threads_, max_free_threads_, queue_size_,
shutdown_on_exception_)
{}
{
}
public:
static void initialize(size_t max_threads = 10000, size_t max_free_threads = 1000, size_t queue_size = 10000);

2
src/Compression/CachedCompressedReadBuffer.h
View File

@ -17,7 +17,7 @@ namespace DB
* Disadvantages:
* - in case you need to read a lot of data in a row, but some of them only a part is cached, you have to do seek-and.
*/
class CachedCompressedReadBuffer : public CompressedReadBufferBase, public ReadBuffer
class CachedCompressedReadBuffer final : public CompressedReadBufferBase, public ReadBuffer
{
private:
std::function<std::unique_ptr<ReadBufferFromFileBase>()> file_in_creator;

2
src/Compression/CheckingCompressedReadBuffer.h
View File

@ -11,7 +11,7 @@ namespace DB
/** A buffer for reading from a compressed file with just checking checksums of
* the compressed blocks, without any decompression.
*/
class CheckingCompressedReadBuffer : public CompressedReadBufferBase, public ReadBuffer
class CheckingCompressedReadBuffer final : public CompressedReadBufferBase, public ReadBuffer
{
protected:
bool nextImpl() override;

2
src/Compression/CompressedReadBuffer.h
View File

@ -8,7 +8,7 @@
namespace DB
{
class CompressedReadBuffer : public CompressedReadBufferBase, public BufferWithOwnMemory<ReadBuffer>
class CompressedReadBuffer final : public CompressedReadBufferBase, public BufferWithOwnMemory<ReadBuffer>
{
private:
size_t size_compressed = 0;

2
src/Compression/CompressedReadBufferFromFile.h
View File

@ -14,7 +14,7 @@ class MMappedFileCache;
/// Unlike CompressedReadBuffer, it can do seek.
class CompressedReadBufferFromFile : public CompressedReadBufferBase, public BufferWithOwnMemory<ReadBuffer>
class CompressedReadBufferFromFile final : public CompressedReadBufferBase, public BufferWithOwnMemory<ReadBuffer>
{
private:
/** At any time, one of two things is true:

2
src/Compression/CompressedWriteBuffer.h
View File

@ -13,7 +13,7 @@
namespace DB
{
class CompressedWriteBuffer : public BufferWithOwnMemory<WriteBuffer>
class CompressedWriteBuffer final : public BufferWithOwnMemory<WriteBuffer>
{
public:
explicit CompressedWriteBuffer(

2
src/Compression/CompressionCodecDeflateQpl.h
View File

@ -87,7 +87,7 @@ private:
Poco::Logger * log;
};
class CompressionCodecDeflateQpl : public ICompressionCodec
class CompressionCodecDeflateQpl final : public ICompressionCodec
{
public:
CompressionCodecDeflateQpl();

201
src/Compression/CompressionCodecEncrypted.cpp
View File

@ -11,10 +11,14 @@
// This depends on BoringSSL-specific API, notably <openssl/aead.h>.
#if USE_SSL
#include <openssl/digest.h>
#include <openssl/err.h>
#include <boost/algorithm/hex.hpp>
#include <openssl/aead.h>
# include <openssl/err.h>
# include <boost/algorithm/hex.hpp>
# if USE_BORINGSSL
# include <openssl/digest.h>
# include <openssl/aead.h>
# else
# include <openssl/evp.h>
# endif
#endif
// Common part for both parts (with SSL and without)
@ -87,23 +91,6 @@ constexpr size_t nonce_max_size = 13; /// Nonce size and one byte to show i
constexpr size_t actual_nonce_size = 12; /// Nonce actual size
const String empty_nonce = {"\0\0\0\0\0\0\0\0\0\0\0\0", actual_nonce_size};
/// Get encryption/decryption algorithms.
auto getMethod(EncryptionMethod Method)
{
if (Method == AES_128_GCM_SIV)
{
return EVP_aead_aes_128_gcm_siv;
}
else if (Method == AES_256_GCM_SIV)
{
return EVP_aead_aes_256_gcm_siv;
}
else
{
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Wrong encryption Method. Got {}", getMethodName(Method));
}
}
/// Find out key size for each algorithm
UInt64 methodKeySize(EncryptionMethod Method)
{
@ -128,6 +115,24 @@ std::string lastErrorString()
return std::string(buffer.data());
}
#if USE_BORINGSSL
/// Get encryption/decryption algorithms.
auto getMethod(EncryptionMethod Method)
{
if (Method == AES_128_GCM_SIV)
{
return EVP_aead_aes_128_gcm_siv;
}
else if (Method == AES_256_GCM_SIV)
{
return EVP_aead_aes_256_gcm_siv;
}
else
{
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Wrong encryption Method. Got {}", getMethodName(Method));
}
}
/// Encrypt plaintext with particular algorithm and put result into ciphertext_and_tag.
/// This function get key and nonce and encrypt text with their help.
/// If something went wrong (can't init context or can't encrypt data) it throws exception.
@ -186,6 +191,160 @@ size_t decrypt(std::string_view ciphertext, char * plaintext, EncryptionMethod m
return out_len;
}
#else
/// Get encryption/decryption algorithms.
auto getMethod(EncryptionMethod Method)
{
if (Method == AES_128_GCM_SIV)
{
return EVP_aes_128_gcm;
}
else if (Method == AES_256_GCM_SIV)
{
return EVP_aes_256_gcm;
}
else
{
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Wrong encryption Method. Got {}", getMethodName(Method));
}
}
/// Encrypt plaintext with particular algorithm and put result into ciphertext_and_tag.
/// This function get key and nonce and encrypt text with their help.
/// If something went wrong (can't init context or can't encrypt data) it throws exception.
/// It returns length of encrypted text.
size_t encrypt(std::string_view plaintext, char * ciphertext_and_tag, EncryptionMethod method, const String & key, const String & nonce)
{
int out_len;
int ciphertext_len;
EVP_CIPHER_CTX *encrypt_ctx;
if (!(encrypt_ctx = EVP_CIPHER_CTX_new()))
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
try
{
const int ok_cryptinit = EVP_EncryptInit_ex(encrypt_ctx,
getMethod(method)(),
nullptr, nullptr, nullptr);
if (!ok_cryptinit)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_cipherctrl = EVP_CIPHER_CTX_ctrl(encrypt_ctx,
EVP_CTRL_GCM_SET_IVLEN,
static_cast<int32_t>(nonce.size()),
nullptr);
if (!ok_cipherctrl)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_nonceinit = EVP_EncryptInit_ex(encrypt_ctx, nullptr, nullptr,
reinterpret_cast<const uint8_t*>(key.data()),
reinterpret_cast<const uint8_t *>(nonce.data()));
if (!ok_nonceinit)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_encryptupdate = EVP_EncryptUpdate(encrypt_ctx,
reinterpret_cast<uint8_t *>(ciphertext_and_tag),
&out_len,
reinterpret_cast<const uint8_t *>(plaintext.data()),
static_cast<int32_t>(plaintext.size()));
ciphertext_len = out_len;
if (!ok_encryptupdate)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_encryptfinal = EVP_EncryptFinal_ex(encrypt_ctx,
reinterpret_cast<uint8_t *>(ciphertext_and_tag) + out_len,
reinterpret_cast<int32_t *>(&out_len));
ciphertext_len += out_len;
if (!ok_encryptfinal)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
/* Get the tag */
const int ok_tag = EVP_CIPHER_CTX_ctrl(encrypt_ctx,
EVP_CTRL_GCM_GET_TAG,
tag_size,
reinterpret_cast<uint8_t *>(ciphertext_and_tag) + plaintext.size());
if (!ok_tag)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
}
catch (...)
{
EVP_CIPHER_CTX_free(encrypt_ctx);
throw;
}
EVP_CIPHER_CTX_free(encrypt_ctx);
return ciphertext_len + tag_size;
}
/// Encrypt plaintext with particular algorithm and put result into ciphertext_and_tag.
/// This function get key and nonce and encrypt text with their help.
/// If something went wrong (can't init context or can't encrypt data) it throws exception.
/// It returns length of encrypted text.
size_t decrypt(std::string_view ciphertext, char * plaintext, EncryptionMethod method, const String & key, const String & nonce)
{
int out_len;
int plaintext_len;
EVP_CIPHER_CTX *decrypt_ctx;
if (!(decrypt_ctx = EVP_CIPHER_CTX_new()))
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
try
{
const int ok_cryptinit = EVP_DecryptInit_ex(decrypt_ctx,
getMethod(method)(),
nullptr, nullptr, nullptr);
if (!ok_cryptinit)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_cipherctrl = EVP_CIPHER_CTX_ctrl(decrypt_ctx,
EVP_CTRL_GCM_SET_IVLEN,
static_cast<int32_t>(nonce.size()), nullptr);
if (!ok_cipherctrl)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_nonceinit = EVP_DecryptInit_ex(decrypt_ctx, nullptr, nullptr,
reinterpret_cast<const uint8_t*>(key.data()),
reinterpret_cast<const uint8_t *>(nonce.data()));
if (!ok_nonceinit)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_decryptudpate = EVP_DecryptUpdate(decrypt_ctx,
reinterpret_cast<uint8_t *>(plaintext),
reinterpret_cast<int32_t *>(&out_len),
reinterpret_cast<const uint8_t *>(ciphertext.data()),
static_cast<int32_t>(ciphertext.size()) - tag_size);
plaintext_len = out_len;
if (!ok_decryptudpate)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_tag = EVP_CIPHER_CTX_ctrl(decrypt_ctx,
EVP_CTRL_GCM_SET_TAG,
tag_size,
reinterpret_cast<uint8_t *>(const_cast<char *>(ciphertext.data())) + ciphertext.size() - tag_size);
if (!ok_tag)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
const int ok_decryptfinal = EVP_DecryptFinal_ex(decrypt_ctx,
reinterpret_cast<uint8_t *>(plaintext) + out_len,
reinterpret_cast<int32_t *>(&out_len));
if (!ok_decryptfinal)
throw Exception::createDeprecated(lastErrorString(), ErrorCodes::OPENSSL_ERROR);
}
catch (...)
{
EVP_CIPHER_CTX_free(decrypt_ctx);
throw;
}
EVP_CIPHER_CTX_free(decrypt_ctx);
return plaintext_len + out_len;
}
#endif
/// Register codec in factory
void registerEncryptionCodec(CompressionCodecFactory & factory, EncryptionMethod Method)

2
src/Compression/CompressionCodecEncrypted.h
View File

@ -44,7 +44,7 @@ enum EncryptionMethod
* as otherwise our engines like ReplicatedMergeTree cannot
* deduplicate data blocks.
*/
class CompressionCodecEncrypted : public ICompressionCodec
class CompressionCodecEncrypted final : public ICompressionCodec
{
public:
/** If a key is available, the server is supposed to

2
src/Compression/CompressionCodecNone.h
View File

@ -8,7 +8,7 @@
namespace DB
{
class CompressionCodecNone : public ICompressionCodec
class CompressionCodecNone final : public ICompressionCodec
{
public:
CompressionCodecNone();

4
src/Compression/CompressionFactory.cpp
View File

@ -178,9 +178,7 @@ void registerCodecDelta(CompressionCodecFactory & factory);
void registerCodecT64(CompressionCodecFactory & factory);
void registerCodecDoubleDelta(CompressionCodecFactory & factory);
void registerCodecGorilla(CompressionCodecFactory & factory);
#if USE_BORINGSSL
void registerCodecEncrypted(CompressionCodecFactory & factory);
#endif
void registerCodecFPC(CompressionCodecFactory & factory);
#endif
@ -197,9 +195,7 @@ CompressionCodecFactory::CompressionCodecFactory()
registerCodecT64(*this);
registerCodecDoubleDelta(*this);
registerCodecGorilla(*this);
#if USE_BORINGSSL
registerCodecEncrypted(*this);
#endif
registerCodecFPC(*this);
#ifdef ENABLE_QPL_COMPRESSION
registerCodecDeflateQpl(*this);

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