thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-10 01:25:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into HEAD

Browse Source
This commit is contained in:
Anton Popov 2022-12-02 12:06:45 +00:00
commit 5d9077cdb6
1775 changed files with 49498 additions and 15886 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/ISSUE_TEMPLATE/85_bug-report.md vendored
View File

@ -13,6 +13,8 @@ assignees: ''
> A clear and concise description of what works not as it is supposed to.
> A link to reproducer in [https://fiddle.clickhouse.com/](https://fiddle.clickhouse.com/).
**Does it reproduce on recent release?**
[The list of releases](https://github.com/ClickHouse/ClickHouse/blob/master/utils/list-versions/version_date.tsv)

2
.github/ISSUE_TEMPLATE/96_installation-issues.md vendored
View File

@ -7,6 +7,8 @@ assignees: ''
---
**I have tried the following solutions**: https://clickhouse.com/docs/en/faq/troubleshooting/#troubleshooting-installation-errors
**Installation type**
Packages, docker, single binary, curl?

28
.github/workflows/backport_branches.yml vendored
View File

@ -145,8 +145,8 @@ jobs:
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -190,8 +190,8 @@ jobs:
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -233,8 +233,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -276,8 +276,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -319,8 +319,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -364,8 +364,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -409,8 +409,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"

2
.github/workflows/cancel.yml vendored
View File

@ -6,7 +6,7 @@ env:
on: # yamllint disable-line rule:truthy
workflow_run:
workflows: ["PullRequestCI", "ReleaseCI", "DocsCheck", "BackportPR"]
workflows: ["PullRequestCI", "ReleaseBranchCI", "DocsCheck", "BackportPR"]
types:
- requested
jobs:

2
.github/workflows/debug.yml vendored
View File

@ -2,7 +2,7 @@
name: Debug
'on':
[push, pull_request, release, workflow_dispatch]
[push, pull_request, release, workflow_dispatch, workflow_call]
jobs:
DebugInfo:

33
.github/workflows/jepsen.yml vendored
View File

@ -32,10 +32,41 @@ jobs:
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 keeper_jepsen_check.py
python3 jepsen_check.py keeper
- 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"
# ServerJepsenRelease:
# runs-on: [self-hosted, style-checker]
# if: ${{ always() }}
# needs: [KeeperJepsenRelease]
# steps:
# - name: Set envs
# run: |
# cat >> "$GITHUB_ENV" << 'EOF'
# TEMP_PATH=${{runner.temp}}/server_jepsen
# REPO_COPY=${{runner.temp}}/server_jepsen/ClickHouse
# EOF
# - name: Clear repository
# run: |
# sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
# - name: Check out repository code
# uses: actions/checkout@v2
# with:
# fetch-depth: 0
# - name: Jepsen Test
# run: |
# sudo rm -fr "$TEMP_PATH"
# mkdir -p "$TEMP_PATH"
# cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
# cd "$REPO_COPY/tests/ci"
# python3 jepsen_check.py server
# - name: Cleanup
# if: always()
# run: |
# docker ps --quiet | xargs --no-run-if-empty docker kill ||:
# docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
# sudo rm -fr "$TEMP_PATH"

304
.github/workflows/master.yml vendored
View File

@ -209,8 +209,8 @@ jobs:
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -251,8 +251,8 @@ jobs:
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -295,8 +295,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -338,8 +338,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -381,8 +381,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -424,8 +424,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -467,8 +467,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -510,8 +510,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -556,8 +556,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -599,8 +599,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -644,8 +644,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -689,8 +689,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -734,8 +734,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -779,8 +779,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -824,8 +824,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -869,8 +869,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -914,8 +914,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -1056,6 +1056,23 @@ 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 "$TEMP_PATH"
MarkReleaseReady:
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Mark Commit Release Ready
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
@ -2994,10 +3011,227 @@ 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 "$TEMP_PATH"
PerformanceComparisonAarch-0:
needs: [BuilderDebAarch64]
runs-on: [self-hosted, func-tester-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/performance_comparison
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Performance Comparison Aarch64
REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
RUN_BY_HASH_NUM=0
RUN_BY_HASH_TOTAL=4
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Performance Comparison
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 performance_comparison_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"
PerformanceComparisonAarch-1:
needs: [BuilderDebAarch64]
runs-on: [self-hosted, func-tester-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/performance_comparison
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Performance Comparison Aarch64
REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
RUN_BY_HASH_NUM=1
RUN_BY_HASH_TOTAL=4
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Performance Comparison
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 performance_comparison_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"
PerformanceComparisonAarch-2:
needs: [BuilderDebAarch64]
runs-on: [self-hosted, func-tester-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/performance_comparison
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Performance Comparison Aarch64
REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
RUN_BY_HASH_NUM=2
RUN_BY_HASH_TOTAL=4
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Performance Comparison
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 performance_comparison_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"
PerformanceComparisonAarch-3:
needs: [BuilderDebAarch64]
runs-on: [self-hosted, func-tester-aarch64]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/performance_comparison
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Performance Comparison Aarch64
REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
RUN_BY_HASH_NUM=3
RUN_BY_HASH_TOTAL=4
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Performance Comparison
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 performance_comparison_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"
##############################################################################################
###################################### SQLANCER FUZZERS ######################################
##############################################################################################
SQLancerTestRelease:
needs: [BuilderDebRelease]
runs-on: [self-hosted, fuzzer-unit-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/sqlancer_release
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=SQLancer (release)
REPO_COPY=${{runner.temp}}/sqlancer_release/ClickHouse
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: SQLancer
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 sqlancer_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"
SQLancerTestDebug:
needs: [BuilderDebDebug]
runs-on: [self-hosted, fuzzer-unit-tester]
steps:
- name: Set envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/sqlancer_debug
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=SQLancer (debug)
REPO_COPY=${{runner.temp}}/sqlancer_debug/ClickHouse
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 "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: SQLancer
run: |
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 sqlancer_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"
FinishCheck:
needs:
- DockerHubPush
- BuilderReport
- BuilderSpecialReport
- MarkReleaseReady
- FunctionalStatelessTestDebug0
- FunctionalStatelessTestDebug1
- FunctionalStatelessTestDebug2
@ -3053,6 +3287,8 @@ jobs:
- UnitTestsUBsan
- UnitTestsReleaseClang
- SharedBuildSmokeTest
- SQLancerTestRelease
- SQLancerTestDebug
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository

60
.github/workflows/nightly.yml vendored
View File

@ -10,6 +10,9 @@ env:
workflow_dispatch:
jobs:
Debug:
# The task for having a preserved ENV and event.json for later investigation
uses: ./.github/workflows/debug.yml
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
@ -102,7 +105,7 @@ jobs:
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -122,3 +125,58 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
SonarCloud:
runs-on: [self-hosted, builder]
env:
SONAR_SCANNER_VERSION: 4.7.0.2747
SONAR_SERVER_URL: "https://sonarcloud.io"
BUILD_WRAPPER_OUT_DIR: build_wrapper_output_directory # Directory where build-wrapper output will be placed
CC: clang-15
CXX: clang++-15
steps:
- uses: actions/checkout@v2
with:
fetch-depth: 0 # Shallow clones should be disabled for a better relevancy of analysis
submodules: true
- name: Set up JDK 11
uses: actions/setup-java@v1
with:
java-version: 11
- name: Download and set up sonar-scanner
env:
SONAR_SCANNER_DOWNLOAD_URL: https://binaries.sonarsource.com/Distribution/sonar-scanner-cli/sonar-scanner-cli-${{ env.SONAR_SCANNER_VERSION }}-linux.zip
run: |
mkdir -p "$HOME/.sonar"
curl -sSLo "$HOME/.sonar/sonar-scanner.zip" "${{ env.SONAR_SCANNER_DOWNLOAD_URL }}"
unzip -o "$HOME/.sonar/sonar-scanner.zip" -d "$HOME/.sonar/"
echo "$HOME/.sonar/sonar-scanner-${{ env.SONAR_SCANNER_VERSION }}-linux/bin" >> "$GITHUB_PATH"
- name: Download and set up build-wrapper
env:
BUILD_WRAPPER_DOWNLOAD_URL: ${{ env.SONAR_SERVER_URL }}/static/cpp/build-wrapper-linux-x86.zip
run: |
curl -sSLo "$HOME/.sonar/build-wrapper-linux-x86.zip" "${{ env.BUILD_WRAPPER_DOWNLOAD_URL }}"
unzip -o "$HOME/.sonar/build-wrapper-linux-x86.zip" -d "$HOME/.sonar/"
echo "$HOME/.sonar/build-wrapper-linux-x86" >> "$GITHUB_PATH"
- name: Set Up Build Tools
run: |
sudo apt-get update
sudo apt-get install -yq git cmake ccache python3 ninja-build
sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"
- name: Run build-wrapper
run: |
mkdir build
cd build
cmake ..
cd ..
build-wrapper-linux-x86-64 --out-dir ${{ env.BUILD_WRAPPER_OUT_DIR }} cmake --build build/
- name: Run sonar-scanner
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
run: |
sonar-scanner \
--define sonar.host.url="${{ env.SONAR_SERVER_URL }}" \
--define sonar.cfamily.build-wrapper-output="${{ env.BUILD_WRAPPER_OUT_DIR }}" \
--define sonar.projectKey="ClickHouse_ClickHouse" \
--define sonar.organization="clickhouse-java" \
--define sonar.exclusions="**/*.java,**/*.ts,**/*.js,**/*.css,**/*.sql"

1158
.github/workflows/pull_request.yml vendored
View File

File diff suppressed because it is too large Load Diff

54
.github/workflows/release_branches.yml vendored
View File

@ -136,8 +136,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -178,8 +178,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -220,8 +220,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -263,8 +263,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -306,8 +306,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -349,8 +349,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -392,8 +392,8 @@ jobs:
uses: actions/checkout@v2
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -437,8 +437,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -482,8 +482,8 @@ jobs:
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$GITHUB_WORKSPACE" submodule sync --recursive
git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --recursive --init --jobs=10
git -C "$GITHUB_WORKSPACE" submodule sync
git -C "$GITHUB_WORKSPACE" submodule update --single-branch --depth=1 --init --jobs=10
sudo rm -fr "$TEMP_PATH"
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -615,6 +615,23 @@ 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 "$TEMP_PATH"
MarkReleaseReady:
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Mark Commit Release Ready
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
@ -1888,6 +1905,7 @@ jobs:
- DockerServerImages
- BuilderReport
- BuilderSpecialReport
- MarkReleaseReady
- FunctionalStatelessTestDebug0
- FunctionalStatelessTestDebug1
- FunctionalStatelessTestDebug2

3
.github/workflows/tags_stable.yml vendored
View File

@ -38,7 +38,7 @@ jobs:
with:
ref: master
fetch-depth: 0
- name: Generate versions
- name: Update versions, docker version, changelog, security
env:
GITHUB_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
run: |
@ -51,6 +51,7 @@ jobs:
--gh-user-or-token="$GITHUB_TOKEN" --jobs=5 \
--output="/ClickHouse/docs/changelogs/${GITHUB_TAG}.md" "${GITHUB_TAG}"
git add "./docs/changelogs/${GITHUB_TAG}.md"
python ./utils/security-generator/generate_security.py > SECURITY.md
git diff HEAD
- name: Create Pull Request
uses: peter-evans/create-pull-request@v3

3
.gitignore vendored
View File

@ -154,3 +154,6 @@ website/package-lock.json
/programs/server/metadata
/programs/server/store
# temporary test files
tests/queries/0_stateless/test_*
tests/queries/0_stateless/*.binary

9
.gitmodules vendored
View File

@ -65,12 +65,6 @@
[submodule "contrib/libgsasl"]
path = contrib/libgsasl
url = https://github.com/ClickHouse/libgsasl.git
[submodule "contrib/libcxx"]
path = contrib/libcxx
url = https://github.com/ClickHouse/libcxx.git
[submodule "contrib/libcxxabi"]
path = contrib/libcxxabi
url = https://github.com/ClickHouse/libcxxabi.git
[submodule "contrib/snappy"]
path = contrib/snappy
url = https://github.com/ClickHouse/snappy.git
@ -290,3 +284,6 @@
[submodule "contrib/morton-nd"]
path = contrib/morton-nd
url = https://github.com/morton-nd/morton-nd
[submodule "contrib/xxHash"]
path = contrib/xxHash
url = https://github.com/Cyan4973/xxHash.git

4
.snyk Normal file
View File

@ -0,0 +1,4 @@
# Snyk (https://snyk.io) policy file
exclude:
global:
- tests/**

110
CHANGELOG.md
View File

@ -1,4 +1,5 @@
### Table of Contents
**[ClickHouse release v22.11, 2022-11-17](#2211)**<br/>
**[ClickHouse release v22.10, 2022-10-25](#2210)**<br/>
**[ClickHouse release v22.9, 2022-09-22](#229)**<br/>
**[ClickHouse release v22.8-lts, 2022-08-18](#228)**<br/>
@ -11,6 +12,109 @@
**[ClickHouse release v22.1, 2022-01-18](#221)**<br/>
**[Changelog for 2021](https://clickhouse.com/docs/en/whats-new/changelog/2021/)**<br/>
### <a id="2211"></a> ClickHouse release 22.11, 2022-11-17
#### Backward Incompatible Change
* `JSONExtract` family of functions will now attempt to coerce to the requested type. [#41502](https://github.com/ClickHouse/ClickHouse/pull/41502) ([Márcio Martins](https://github.com/marcioapm)).
#### New Feature
* Adds support for retries during INSERTs into ReplicatedMergeTree when a session with ClickHouse Keeper is lost. Apart from fault tolerance, it aims to provide better user experience, - avoid returning a user an error during insert if keeper is restarted (for example, due to upgrade). This is controlled by the `insert_keeper_max_retries` setting, which is disabled by default. [#42607](https://github.com/ClickHouse/ClickHouse/pull/42607) ([Igor Nikonov](https://github.com/devcrafter)).
* Add `Hudi` and `DeltaLake` table engines, read-only, only for tables on S3. [#41054](https://github.com/ClickHouse/ClickHouse/pull/41054) ([Daniil Rubin](https://github.com/rubin-do), [Kseniia Sumarokova](https://github.com/kssenii)).
* Add table function `hudi` and `deltaLake`. [#43080](https://github.com/ClickHouse/ClickHouse/pull/43080) ([flynn](https://github.com/ucasfl)).
* Support for composite time intervals. 1. Add, subtract and negate operations are now available on Intervals. In the case where the types of Intervals are different, they will be transformed into the Tuple of those types. 2. A tuple of intervals can be added to or subtracted from a Date/DateTime field. 3. Added parsing of Intervals with different types, for example: `INTERVAL '1 HOUR 1 MINUTE 1 SECOND'`. [#42195](https://github.com/ClickHouse/ClickHouse/pull/42195) ([Nikolay Degterinsky](https://github.com/evillique)).
* Added `**` glob support for recursive directory traversal of the filesystem and S3. Resolves [#36316](https://github.com/ClickHouse/ClickHouse/issues/36316). [#42376](https://github.com/ClickHouse/ClickHouse/pull/42376) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Introduce `s3_plain` disk type for write-once-read-many operations. Implement `ATTACH` of `MergeTree` table for `s3_plain` disk. [#42628](https://github.com/ClickHouse/ClickHouse/pull/42628) ([Azat Khuzhin](https://github.com/azat)).
* Added applied row-level policies to `system.query_log`. [#39819](https://github.com/ClickHouse/ClickHouse/pull/39819) ([Vladimir Chebotaryov](https://github.com/quickhouse)).
* Add four-letter command `csnp` for manually creating snapshots in ClickHouse Keeper. Additionally, `lgif` was added to get Raft information for a specific node (e.g. index of last created snapshot, last committed log index). [#41766](https://github.com/ClickHouse/ClickHouse/pull/41766) ([JackyWoo](https://github.com/JackyWoo)).
* Add function `ascii` like in Apache Spark: https://spark.apache.org/docs/latest/api/sql/#ascii. [#42670](https://github.com/ClickHouse/ClickHouse/pull/42670) ([李扬](https://github.com/taiyang-li)).
* Add function `positive_modulo` (`pmod`) which returns non-negative result based on modulo. [#42755](https://github.com/ClickHouse/ClickHouse/pull/42755) ([李扬](https://github.com/taiyang-li)).
* Add function `formatReadableDecimalSize`. [#42774](https://github.com/ClickHouse/ClickHouse/pull/42774) ([Alejandro](https://github.com/alexon1234)).
* Add function `randCanonical`, which is similar to the `rand` function in Apache Spark or Impala. The function generates pseudo random results with independent and identically distributed uniformly distributed values in [0, 1). [#43124](https://github.com/ClickHouse/ClickHouse/pull/43124) ([李扬](https://github.com/taiyang-li)).
* Add function `displayName`, closes [#36770](https://github.com/ClickHouse/ClickHouse/issues/36770). [#37681](https://github.com/ClickHouse/ClickHouse/pull/37681) ([hongbin](https://github.com/xlwh)).
* Add `min_age_to_force_merge_on_partition_only` setting to optimize old parts for the entire partition only. [#42659](https://github.com/ClickHouse/ClickHouse/pull/42659) ([Antonio Andelic](https://github.com/antonio2368)).
* Add generic implementation for arbitrary structured named collections, access type and `system.named_collections`. [#43147](https://github.com/ClickHouse/ClickHouse/pull/43147) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Performance Improvement
* Parallelized merging of `uniqExact` states for aggregation without key, i.e. queries like `SELECT uniqExact(number) FROM table`. The improvement becomes noticeable when the number of unique keys approaches 10^6. Also `uniq` performance is slightly optimized. [#43072](https://github.com/ClickHouse/ClickHouse/pull/43072) ([Nikita Taranov](https://github.com/nickitat)).
* `match` function can use the index if it's a condition on string prefix. This closes [#37333](https://github.com/ClickHouse/ClickHouse/issues/37333). [#42458](https://github.com/ClickHouse/ClickHouse/pull/42458) ([clarkcaoliu](https://github.com/Clark0)).
* Speed up AND and OR operators when they are sequenced. [#42214](https://github.com/ClickHouse/ClickHouse/pull/42214) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* Support parallel parsing for `LineAsString` input format. This improves performance just slightly. This closes [#42502](https://github.com/ClickHouse/ClickHouse/issues/42502). [#42780](https://github.com/ClickHouse/ClickHouse/pull/42780) ([Kruglov Pavel](https://github.com/Avogar)).
* ClickHouse Keeper performance improvement: improve commit performance for cases when many different nodes have uncommitted states. This should help with cases when a follower node can't sync fast enough. [#42926](https://github.com/ClickHouse/ClickHouse/pull/42926) ([Antonio Andelic](https://github.com/antonio2368)).
* A condition like `NOT LIKE 'prefix%'` can use the primary index. [#42209](https://github.com/ClickHouse/ClickHouse/pull/42209) ([Duc Canh Le](https://github.com/canhld94)).
#### Experimental Feature
* Support type `Object` inside other types, e.g. `Array(JSON)`. [#36969](https://github.com/ClickHouse/ClickHouse/pull/36969) ([Anton Popov](https://github.com/CurtizJ)).
* Ignore MySQL binlog SAVEPOINT event for MaterializedMySQL. [#42931](https://github.com/ClickHouse/ClickHouse/pull/42931) ([zzsmdfj](https://github.com/zzsmdfj)). Handle (ignore) SAVEPOINT queries in MaterializedMySQL. [#43086](https://github.com/ClickHouse/ClickHouse/pull/43086) ([Stig Bakken](https://github.com/stigsb)).
#### Improvement
* Trivial queries with small LIMIT will properly determine the number of estimated rows to read, so that the threshold will be checked properly. Closes [#7071](https://github.com/ClickHouse/ClickHouse/issues/7071). [#42580](https://github.com/ClickHouse/ClickHouse/pull/42580) ([Han Fei](https://github.com/hanfei1991)).
* Add support for interactive parameters in INSERT VALUES queries. [#43077](https://github.com/ClickHouse/ClickHouse/pull/43077) ([Nikolay Degterinsky](https://github.com/evillique)).
* Added new field `allow_readonly` in `system.table_functions` to allow using table functions in readonly mode. Resolves [#42414](https://github.com/ClickHouse/ClickHouse/issues/42414) Implementation: * Added a new field allow_readonly to table system.table_functions. * Updated to use new field allow_readonly to allow using table functions in readonly mode. Testing: * Added a test for filesystem tests/queries/0_stateless/02473_functions_in_readonly_mode.sh Documentation: * Updated the english documentation for Table Functions. [#42708](https://github.com/ClickHouse/ClickHouse/pull/42708) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* The `system.asynchronous_metrics` gets embedded documentation. This documentation is also exported to Prometheus. Fixed an error with the metrics about `cache` disks - they were calculated only for one arbitrary cache disk instead all of them. This closes [#7644](https://github.com/ClickHouse/ClickHouse/issues/7644). [#43194](https://github.com/ClickHouse/ClickHouse/pull/43194) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Throttling algorithm changed to token bucket. [#42665](https://github.com/ClickHouse/ClickHouse/pull/42665) ([Sergei Trifonov](https://github.com/serxa)).
* Mask passwords and secret keys both in `system.query_log` and `/var/log/clickhouse-server/*.log` and also in error messages. [#42484](https://github.com/ClickHouse/ClickHouse/pull/42484) ([Vitaly Baranov](https://github.com/vitlibar)).
* Remove covered parts for fetched part (to avoid possible replication delay grows). [#39737](https://github.com/ClickHouse/ClickHouse/pull/39737) ([Azat Khuzhin](https://github.com/azat)).
* If `/dev/tty` is available, the progress in clickhouse-client and clickhouse-local will be rendered directly to the terminal, without writing to STDERR. It allows getting progress even if STDERR is redirected to a file, and the file will not be polluted by terminal escape sequences. The progress can be disabled by `--progress false`. This closes [#32238](https://github.com/ClickHouse/ClickHouse/issues/32238). [#42003](https://github.com/ClickHouse/ClickHouse/pull/42003) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add support for `FixedString` input to base64 coding functions. [#42285](https://github.com/ClickHouse/ClickHouse/pull/42285) ([ltrk2](https://github.com/ltrk2)).
* Add columns `bytes_on_disk` and `path` to `system.detached_parts`. Closes [#42264](https://github.com/ClickHouse/ClickHouse/issues/42264). [#42303](https://github.com/ClickHouse/ClickHouse/pull/42303) ([chen](https://github.com/xiedeyantu)).
* Improve using structure from insertion table in table functions, now setting `use_structure_from_insertion_table_in_table_functions` has new possible value - `2` that means that ClickHouse will try to determine if we can use structure from insertion table or not automatically. Closes [#40028](https://github.com/ClickHouse/ClickHouse/issues/40028). [#42320](https://github.com/ClickHouse/ClickHouse/pull/42320) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix no progress indication on INSERT FROM INFILE. Closes [#42548](https://github.com/ClickHouse/ClickHouse/issues/42548). [#42634](https://github.com/ClickHouse/ClickHouse/pull/42634) ([chen](https://github.com/xiedeyantu)).
* Refactor function `tokens` to enable max tokens returned for related functions (disabled by default). [#42673](https://github.com/ClickHouse/ClickHouse/pull/42673) ([李扬](https://github.com/taiyang-li)).
* Allow to use `Date32` arguments for `formatDateTime` and `FROM_UNIXTIME` functions. [#42737](https://github.com/ClickHouse/ClickHouse/pull/42737) ([Roman Vasin](https://github.com/rvasin)).
* Update tzdata to 2022f. Mexico will no longer observe DST except near the US border: https://www.timeanddate.com/news/time/mexico-abolishes-dst-2022.html. Chihuahua moves to year-round UTC-6 on 2022-10-30. Fiji no longer observes DST. See https://github.com/google/cctz/pull/235 and https://bugs.launchpad.net/ubuntu/+source/tzdata/+bug/1995209. [#42796](https://github.com/ClickHouse/ClickHouse/pull/42796) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add `FailedAsyncInsertQuery` event metric for async inserts. [#42814](https://github.com/ClickHouse/ClickHouse/pull/42814) ([Krzysztof Góralski](https://github.com/kgoralski)).
* Implement `read-in-order` optimization on top of query plan. It is enabled by default. Set `query_plan_read_in_order = 0` to use previous AST-based version. [#42829](https://github.com/ClickHouse/ClickHouse/pull/42829) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Increase the size of upload part exponentially for backup to S3 to avoid errors about max 10 000 parts limit of the multipart upload to s3. [#42833](https://github.com/ClickHouse/ClickHouse/pull/42833) ([Vitaly Baranov](https://github.com/vitlibar)).
* When the merge task is continuously busy and the disk space is insufficient, the completely expired parts cannot be selected and dropped, resulting in insufficient disk space. My idea is that when the entire Part expires, there is no need for additional disk space to guarantee, ensure the normal execution of TTL. [#42869](https://github.com/ClickHouse/ClickHouse/pull/42869) ([zhongyuankai](https://github.com/zhongyuankai)).
* Add `oss` function and `OSS` table engine (this is convenient for users). oss is fully compatible with s3. [#43155](https://github.com/ClickHouse/ClickHouse/pull/43155) ([zzsmdfj](https://github.com/zzsmdfj)).
* Improve error reporting in the collection of OS-related info for the `system.asynchronous_metrics` table. [#43192](https://github.com/ClickHouse/ClickHouse/pull/43192) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Modify the `INFORMATION_SCHEMA` tables in a way so that ClickHouse can connect to itself using the MySQL compatibility protocol. Add columns instead of aliases (related to [#9769](https://github.com/ClickHouse/ClickHouse/issues/9769)). It will improve the compatibility with various MySQL clients. [#43198](https://github.com/ClickHouse/ClickHouse/pull/43198) ([Filatenkov Artur](https://github.com/FArthur-cmd)).
* Add some functions for compatibility with PowerBI, when it connects using MySQL protocol [#42612](https://github.com/ClickHouse/ClickHouse/pull/42612) ([Filatenkov Artur](https://github.com/FArthur-cmd)).
* Better usability for Dashboard on changes [#42872](https://github.com/ClickHouse/ClickHouse/pull/42872) ([Vladimir C](https://github.com/vdimir)).
#### Build/Testing/Packaging Improvement
* Run SQLancer for each pull request and commit to master. [SQLancer](https://github.com/sqlancer/sqlancer) is an OpenSource fuzzer that focuses on automatic detection of logical bugs. [#42397](https://github.com/ClickHouse/ClickHouse/pull/42397) ([Ilya Yatsishin](https://github.com/qoega)).
* Update to latest zlib-ng. [#42463](https://github.com/ClickHouse/ClickHouse/pull/42463) ([Boris Kuschel](https://github.com/bkuschel)).
* Add support for testing ClickHouse server with Jepsen. By the way, we already have support for testing ClickHouse Keeper with Jepsen. This pull request extends it to Replicated tables. [#42619](https://github.com/ClickHouse/ClickHouse/pull/42619) ([Antonio Andelic](https://github.com/antonio2368)).
* Use https://github.com/matus-chochlik/ctcache for clang-tidy results caching. [#42913](https://github.com/ClickHouse/ClickHouse/pull/42913) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Before the fix, the user-defined config was preserved by RPM in `$file.rpmsave`. The PR fixes it and won't replace the user's files from packages. [#42936](https://github.com/ClickHouse/ClickHouse/pull/42936) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Remove some libraries from Ubuntu Docker image. [#42622](https://github.com/ClickHouse/ClickHouse/pull/42622) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Updated normaliser to clone the alias ast. Resolves [#42452](https://github.com/ClickHouse/ClickHouse/issues/42452) Implementation: * Updated QueryNormalizer to clone alias ast, when its replaced. Previously just assigning the same leads to exception in LogicalExpressinsOptimizer as it would be the same parent being inserted again. * This bug is not seen with new analyser (allow_experimental_analyzer), so no changes for it. I added a test for the same. [#42827](https://github.com/ClickHouse/ClickHouse/pull/42827) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix race for backup of tables in `Lazy` databases. [#43104](https://github.com/ClickHouse/ClickHouse/pull/43104) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fix for `skip_unavailable_shards`: it did not work with the `s3Cluster` table function. [#43131](https://github.com/ClickHouse/ClickHouse/pull/43131) ([chen](https://github.com/xiedeyantu)).
* Fix schema inference in `s3Cluster` and improvement in `hdfsCluster`. [#41979](https://github.com/ClickHouse/ClickHouse/pull/41979) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix retries while reading from URL table engines / table function. (retriable errors could be retries more times than needed, non-retriable errors resulted in failed assertion in code). [#42224](https://github.com/ClickHouse/ClickHouse/pull/42224) ([Kseniia Sumarokova](https://github.com/kssenii)).
* A segmentation fault related to DNS & c-ares has been reported and fixed. [#42234](https://github.com/ClickHouse/ClickHouse/pull/42234) ([Arthur Passos](https://github.com/arthurpassos)).
* Fix `LOGICAL_ERROR` `Arguments of 'plus' have incorrect data types` which may happen in PK analysis (monotonicity check). Fix invalid PK analysis for monotonic binary functions with first constant argument. [#42410](https://github.com/ClickHouse/ClickHouse/pull/42410) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix incorrect key analysis when key types cannot be inside Nullable. This fixes [#42456](https://github.com/ClickHouse/ClickHouse/issues/42456). [#42469](https://github.com/ClickHouse/ClickHouse/pull/42469) ([Amos Bird](https://github.com/amosbird)).
* Fix typo in a setting name that led to bad usage of schema inference cache while using setting `input_format_csv_use_best_effort_in_schema_inference`. Closes [#41735](https://github.com/ClickHouse/ClickHouse/issues/41735). [#42536](https://github.com/ClickHouse/ClickHouse/pull/42536) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix creating a Set with wrong header when data type is LowCardinality. Closes [#42460](https://github.com/ClickHouse/ClickHouse/issues/42460). [#42579](https://github.com/ClickHouse/ClickHouse/pull/42579) ([flynn](https://github.com/ucasfl)).
* `(U)Int128` and `(U)Int256` values were correctly checked in `PREWHERE`. [#42605](https://github.com/ClickHouse/ClickHouse/pull/42605) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix a bug in functions parser that could have led to a segmentation fault. [#42724](https://github.com/ClickHouse/ClickHouse/pull/42724) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix the locking in `truncate table`. [#42728](https://github.com/ClickHouse/ClickHouse/pull/42728) ([flynn](https://github.com/ucasfl)).
* Fix possible crash in `web` disks when file does not exist (or `OPTIMIZE TABLE FINAL`, that also can got the same error eventually). [#42767](https://github.com/ClickHouse/ClickHouse/pull/42767) ([Azat Khuzhin](https://github.com/azat)).
* Fix `auth_type` mapping in `system.session_log`, by including `SSL_CERTIFICATE` for the enum values. [#42782](https://github.com/ClickHouse/ClickHouse/pull/42782) ([Miel Donkers](https://github.com/mdonkers)).
* Fix stack-use-after-return under ASAN build in the Create User query parser. [#42804](https://github.com/ClickHouse/ClickHouse/pull/42804) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix `lowerUTF8`/`upperUTF8` in case of symbol was in between 16-byte boundary (very frequent case of you have strings > 16 bytes long). [#42812](https://github.com/ClickHouse/ClickHouse/pull/42812) ([Azat Khuzhin](https://github.com/azat)).
* Additional bound check was added to LZ4 decompression routine to fix misbehaviour in case of malformed input. [#42868](https://github.com/ClickHouse/ClickHouse/pull/42868) ([Nikita Taranov](https://github.com/nickitat)).
* Fix rare possible hang on query cancellation. [#42874](https://github.com/ClickHouse/ClickHouse/pull/42874) ([Azat Khuzhin](https://github.com/azat)).
* Fix incorrect behavior with multiple disjuncts in hash join, close [#42832](https://github.com/ClickHouse/ClickHouse/issues/42832). [#42876](https://github.com/ClickHouse/ClickHouse/pull/42876) ([Vladimir C](https://github.com/vdimir)).
* A null pointer will be generated when select if as from ‘three table join’ , For example, this SQL query: [#42883](https://github.com/ClickHouse/ClickHouse/pull/42883) ([zzsmdfj](https://github.com/zzsmdfj)).
* Fix memory sanitizer report in Cluster Discovery, close [#42763](https://github.com/ClickHouse/ClickHouse/issues/42763). [#42905](https://github.com/ClickHouse/ClickHouse/pull/42905) ([Vladimir C](https://github.com/vdimir)).
* Improve DateTime schema inference in case of empty string. [#42911](https://github.com/ClickHouse/ClickHouse/pull/42911) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix rare NOT_FOUND_COLUMN_IN_BLOCK error when projection is possible to use but there is no projection available. This fixes [#42771](https://github.com/ClickHouse/ClickHouse/issues/42771) . The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/25563. [#42938](https://github.com/ClickHouse/ClickHouse/pull/42938) ([Amos Bird](https://github.com/amosbird)).
* Fix ATTACH TABLE in `PostgreSQL` database engine if the table contains DATETIME data type. Closes [#42817](https://github.com/ClickHouse/ClickHouse/issues/42817). [#42960](https://github.com/ClickHouse/ClickHouse/pull/42960) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix lambda parsing. Closes [#41848](https://github.com/ClickHouse/ClickHouse/issues/41848). [#42979](https://github.com/ClickHouse/ClickHouse/pull/42979) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix incorrect key analysis when nullable keys appear in the middle of a hyperrectangle. This fixes [#43111](https://github.com/ClickHouse/ClickHouse/issues/43111) . [#43133](https://github.com/ClickHouse/ClickHouse/pull/43133) ([Amos Bird](https://github.com/amosbird)).
* Fix several buffer over-reads in deserialization of carefully crafted aggregate function states. [#43159](https://github.com/ClickHouse/ClickHouse/pull/43159) ([Raúl Marín](https://github.com/Algunenano)).
* Fix function `if` in case of NULL and const Nullable arguments. Closes [#43069](https://github.com/ClickHouse/ClickHouse/issues/43069). [#43178](https://github.com/ClickHouse/ClickHouse/pull/43178) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix decimal math overflow in parsing DateTime with the 'best effort' algorithm. Closes [#43061](https://github.com/ClickHouse/ClickHouse/issues/43061). [#43180](https://github.com/ClickHouse/ClickHouse/pull/43180) ([Kruglov Pavel](https://github.com/Avogar)).
* The `indent` field produced by the `git-import` tool was miscalculated. See https://clickhouse.com/docs/en/getting-started/example-datasets/github/. [#43191](https://github.com/ClickHouse/ClickHouse/pull/43191) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fixed unexpected behaviour of `Interval` types with subquery and casting. [#43193](https://github.com/ClickHouse/ClickHouse/pull/43193) ([jh0x](https://github.com/jh0x)).
### <a id="2210"></a> ClickHouse release 22.10, 2022-10-26
#### Backward Incompatible Change
@ -570,7 +674,7 @@
* Support SQL standard CREATE INDEX and DROP INDEX syntax. [#35166](https://github.com/ClickHouse/ClickHouse/pull/35166) ([Jianmei Zhang](https://github.com/zhangjmruc)).
* Send profile events for INSERT queries (previously only SELECT was supported). [#37391](https://github.com/ClickHouse/ClickHouse/pull/37391) ([Azat Khuzhin](https://github.com/azat)).
* Implement in order aggregation (`optimize_aggregation_in_order`) for fully materialized projections. [#37469](https://github.com/ClickHouse/ClickHouse/pull/37469) ([Azat Khuzhin](https://github.com/azat)).
* Remove subprocess run for kerberos initialization. Added new integration test. Closes [#27651](https://github.com/ClickHouse/ClickHouse/issues/27651). [#38105](https://github.com/ClickHouse/ClickHouse/pull/38105) ([Roman Vasin](https://github.com/rvasin)).
* Remove subprocess run for Kerberos initialization. Added new integration test. Closes [#27651](https://github.com/ClickHouse/ClickHouse/issues/27651). [#38105](https://github.com/ClickHouse/ClickHouse/pull/38105) ([Roman Vasin](https://github.com/rvasin)).
* * Add setting `multiple_joins_try_to_keep_original_names` to not rewrite identifier name on multiple JOINs rewrite, close [#34697](https://github.com/ClickHouse/ClickHouse/issues/34697). [#38149](https://github.com/ClickHouse/ClickHouse/pull/38149) ([Vladimir C](https://github.com/vdimir)).
* Improved trace-visualizer UX. [#38169](https://github.com/ClickHouse/ClickHouse/pull/38169) ([Sergei Trifonov](https://github.com/serxa)).
* Enable stack trace collection and query profiler for AArch64. [#38181](https://github.com/ClickHouse/ClickHouse/pull/38181) ([Maksim Kita](https://github.com/kitaisreal)).
@ -850,8 +954,8 @@
#### Upgrade Notes
* Now, background merges, mutations and `OPTIMIZE` will not increment `SelectedRows` and `SelectedBytes` metrics. They (still) will increment `MergedRows` and `MergedUncompressedBytes` as it was before. This only affects the metric values, and makes them better. This change does not introduce any incompatibility, but you may wonder about the changes of metrics, so we put in this category. [#37040](https://github.com/ClickHouse/ClickHouse/pull/37040) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Updated the BoringSSL module to the official FIPS compliant version. This makes ClickHouse FIPS compliant. [#35914](https://github.com/ClickHouse/ClickHouse/pull/35914) ([Meena-Renganathan](https://github.com/Meena-Renganathan)). The ciphers `aes-192-cfb128` and `aes-256-cfb128` were removed, because they are not included in the FIPS certified version of BoringSSL.
* Now, background merges, mutations, and `OPTIMIZE` will not increment `SelectedRows` and `SelectedBytes` metrics. They (still) will increment `MergedRows` and `MergedUncompressedBytes` as it was before. This only affects the metric values and makes them better. This change does not introduce any incompatibility, but you may wonder about the changes to the metrics, so we put in this category. [#37040](https://github.com/ClickHouse/ClickHouse/pull/37040) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Updated the BoringSSL module to the official FIPS compliant version. This makes ClickHouse FIPS compliant in this area. [#35914](https://github.com/ClickHouse/ClickHouse/pull/35914) ([Meena-Renganathan](https://github.com/Meena-Renganathan)). The ciphers `aes-192-cfb128` and `aes-256-cfb128` were removed, because they are not included in the FIPS certified version of BoringSSL.
* `max_memory_usage` setting is removed from the default user profile in `users.xml`. This enables flexible memory limits for queries instead of the old rigid limit of 10 GB.
* Disable `log_query_threads` setting by default. It controls the logging of statistics about every thread participating in query execution. After supporting asynchronous reads, the total number of distinct thread ids became too large, and logging into the `query_thread_log` has become too heavy. [#37077](https://github.com/ClickHouse/ClickHouse/pull/37077) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove function `groupArraySorted` which has a bug. [#36822](https://github.com/ClickHouse/ClickHouse/pull/36822) ([Alexey Milovidov](https://github.com/alexey-milovidov)).

9
CMakeLists.txt
View File

@ -202,7 +202,7 @@ option(ADD_GDB_INDEX_FOR_GOLD "Add .gdb-index to resulting binaries for gold lin
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# Can be lld or ld-lld or lld-13 or /path/to/lld.
if (LINKER_NAME MATCHES "lld")
if (LINKER_NAME MATCHES "lld" AND OS_LINUX)
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,--gdb-index")
message (STATUS "Adding .gdb-index via --gdb-index linker option.")
@ -248,7 +248,7 @@ endif ()
# Create BuildID when using lld. For other linkers it is created by default.
# (NOTE: LINKER_NAME can be either path or name, and in different variants)
if (LINKER_NAME MATCHES "lld")
if (LINKER_NAME MATCHES "lld" AND OS_LINUX)
# SHA1 is not cryptographically secure but it is the best what lld is offering.
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--build-id=sha1")
endif ()
@ -442,8 +442,9 @@ elseif (OS_DARWIN)
include(cmake/darwin/default_libs.cmake)
elseif (OS_FREEBSD)
include(cmake/freebsd/default_libs.cmake)
else()
link_libraries(global-group)
endif ()
link_libraries(global-group)
if (NOT (OS_LINUX OR OS_DARWIN))
# Using system libs can cause a lot of warnings in includes (on macro expansion).
@ -592,7 +593,7 @@ add_subdirectory (programs)
add_subdirectory (tests)
add_subdirectory (utils)
include (cmake/sanitize_target_link_libraries.cmake)
include (cmake/sanitize_targets.cmake)
# Build native targets if necessary
get_property(NATIVE_BUILD_TARGETS GLOBAL PROPERTY NATIVE_BUILD_TARGETS)

9
README.md
View File

@ -5,7 +5,7 @@ ClickHouse® is an open-source column-oriented database management system that a
## Useful Links
* [Official website](https://clickhouse.com/) has a quick high-level overview of ClickHouse on the main page.
* [ClickHouse Cloud](https://clickhouse.com/cloud) ClickHouse as a service, built by the creators and maintainers.
* [ClickHouse Cloud](https://clickhouse.cloud) ClickHouse as a service, built by the creators and maintainers.
* [Tutorial](https://clickhouse.com/docs/en/getting_started/tutorial/) shows how to set up and query a small ClickHouse cluster.
* [Documentation](https://clickhouse.com/docs/en/) provides more in-depth information.
* [YouTube channel](https://www.youtube.com/c/ClickHouseDB) has a lot of content about ClickHouse in video format.
@ -16,5 +16,8 @@ ClickHouse® is an open-source column-oriented database management system that a
* [Contacts](https://clickhouse.com/company/contact) can help to get your questions answered if there are any.
## Upcoming events
* [**v22.10 Release Webinar**](https://clickhouse.com/company/events/v22-10-release-webinar) Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release, provide live demos, and share vision into what is coming in the roadmap.
* [**Introducing ClickHouse Cloud**](https://clickhouse.com/company/events/cloud-beta) Introducing ClickHouse as a service, built by creators and maintainers of the fastest OLAP database on earth. Join Tanya Bragin for a detailed walkthrough of ClickHouse Cloud capabilities, as well as a peek behind the curtain to understand the unique architecture that makes our service tick.
* [**v22.11 Release Webinar**](https://clickhouse.com/company/events/v22-11-release-webinar) Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release, provide live demos, and share vision into what is coming in the roadmap.
* [**ClickHosue Meetup at the RELEX Solutions office in Stockholm**](https://www.meetup.com/clickhouse-stockholm-user-group/events/289492084/) - Dec 1 - Formulate by RELEX is a Swedish promotion planning and analytics company. They will share why they chose ClickHouse for their real time analytics and forecasting solution. The ClickHouse team will then present how ClickHouse is used for real time financial data analytics, including tick data, trade analytics and risk management.
* [**ClickHouse Meetup at the Deutsche Bank office in Berlin**](https://www.meetup.com/clickhouse-berlin-user-group/events/289311596/) - Dec 5 - Hear from Deutsche Bank on why they chose ClickHouse for big sensitive data in a regulated environment. The ClickHouse team will then present how ClickHouse is used for real time financial data analytics, including tick data, trade analytics and risk management.
* [**ClickHouse Meetup at the Rokt offices in Manhattan**](https://www.meetup.com/clickhouse-new-york-user-group/events/289403909/) - Dec 6 - We are very excited to be holding our next in-person ClickHouse meetup at the Rokt offices in Manhattan. Featuring talks from Bloomberg, Disney Streaming, Prequel, Rokt, and ClickHouse

6
SECURITY.md
View File

@ -1,3 +1,6 @@
<!--
the file is autogenerated by utils/security-generator/generate_security.py
-->
# Security Policy
@ -10,6 +13,7 @@ The following versions of ClickHouse server are currently being supported with s
| Version | Supported |
|:-|:-|
| 22.11 | ✔️ |
| 22.10 | ✔️ |
| 22.9 | ✔️ |
| 22.8 | ✔️ |
@ -61,5 +65,5 @@ As the security issue moves from triage, to identified fix, to release planning
## Public Disclosure Timing
A public disclosure date is negotiated by the ClickHouse maintainers and the bug submitter. We prefer to fully disclose the bug as soon as possible once a user mitigation is available. It is reasonable to delay disclosure when the bug or the fix is not yet fully understood, the solution is not well-tested, or for vendor coordination. The timeframe for disclosure is from immediate (especially if it's already publicly known) to 90 days. For a vulnerability with a straightforward mitigation, we expect the report date to disclosure date to be on the order of 7 days.
A public disclosure date is negotiated by the ClickHouse maintainers and the bug submitter. We prefer to fully disclose the bug as soon as possible once a user mitigation is available. It is reasonable to delay disclosure when the bug or the fix is not yet fully understood, the solution is not well-tested, or for vendor coordination. The timeframe for disclosure is from immediate (especially if it's already publicly known) to 90 days. For a vulnerability with a straightforward mitigation, we expect the report date to disclosure date to be on the order of 7 days.

16
base/base/bit_cast.h
View File

@ -12,7 +12,21 @@
template <typename To, typename From>
std::decay_t<To> bit_cast(const From & from)
{
/**
* Assume the source value is 0xAABBCCDD (i.e. sizeof(from) == 4).
* Its BE representation is 0xAABBCCDD, the LE representation is 0xDDCCBBAA.
* Further assume, sizeof(res) == 8 and that res is initially zeroed out.
* With LE, the result after bit_cast will be 0xDDCCBBAA00000000 --> input value == output value.
* With BE, the result after bit_cast will be 0x00000000AABBCCDD --> input value == output value.
*/
To res {};
memcpy(static_cast<void*>(&res), &from, std::min(sizeof(res), sizeof(from)));
if constexpr (std::endian::native == std::endian::little)
memcpy(static_cast<void*>(&res), &from, std::min(sizeof(res), sizeof(from)));
else
{
uint32_t offset_to = (sizeof(res) > sizeof(from)) ? (sizeof(res) - sizeof(from)) : 0;
uint32_t offset_from = (sizeof(from) > sizeof(res)) ? (sizeof(from) - sizeof(res)) : 0;
memcpy(reinterpret_cast<char *>(&res) + offset_to, reinterpret_cast<const char *>(&from) + offset_from, std::min(sizeof(res), sizeof(from)));
}
return res;
}

2
base/base/safeExit.cpp
View File

@ -1,8 +1,10 @@
#if defined(OS_LINUX)
# include <sys/syscall.h>
#endif
#include <cstdlib>
#include <unistd.h>
#include <base/safeExit.h>
#include <base/defines.h> /// for THREAD_SANITIZER
[[noreturn]] void safeExit(int code)
{

2
base/glibc-compatibility/glibc-compatibility.c
View File

@ -220,13 +220,13 @@ struct statx {
uint32_t stx_dev_minor;
uint64_t spare[14];
};
#endif
int statx(int fd, const char *restrict path, int flag,
unsigned int mask, struct statx *restrict statxbuf)
{
return syscall(SYS_statx, fd, path, flag, mask, statxbuf);
}
#endif
#include <syscall.h>

17
base/glibc-compatibility/musl/getauxval.c
View File

@ -8,6 +8,14 @@
#include <link.h> // ElfW
#include <errno.h>
#include "syscall.h"
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#include <sanitizer/msan_interface.h>
#endif
#endif
#define ARRAY_SIZE(a) sizeof((a))/sizeof((a[0]))
/// Suppress TSan since it is possible for this code to be called from multiple threads,
@ -39,7 +47,9 @@ ssize_t __retry_read(int fd, void * buf, size_t count)
{
for (;;)
{
ssize_t ret = read(fd, buf, count);
// We cannot use the read syscall as it will be intercept by sanitizers, which aren't
// initialized yet. Emit syscall directly.
ssize_t ret = __syscall_ret(__syscall(SYS_read, fd, buf, count));
if (ret == -1)
{
if (errno == EINTR)
@ -90,6 +100,11 @@ static unsigned long NO_SANITIZE_THREAD __auxv_init_procfs(unsigned long type)
_Static_assert(sizeof(aux) < 4096, "Unexpected sizeof(aux)");
while (__retry_read(fd, &aux, sizeof(aux)) == sizeof(aux))
{
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
__msan_unpoison(&aux, sizeof(aux));
#endif
#endif
if (aux.a_type == AT_NULL)
{
break;

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54468)
SET(VERSION_REVISION 54469)
SET(VERSION_MAJOR 22)
SET(VERSION_MINOR 11)
SET(VERSION_MINOR 12)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 98ab5a3c189232ea2a3dddb9d2be7196ae8b3434)
SET(VERSION_DESCRIBE v22.11.1.1-testing)
SET(VERSION_STRING 22.11.1.1)
SET(VERSION_GITHASH 0d211ed19849fe44b0e43fdebe2c15d76d560a77)
SET(VERSION_DESCRIBE v22.12.1.1-testing)
SET(VERSION_STRING 22.12.1.1)
# end of autochange

24
cmake/clang_tidy.cmake
View File

@ -3,10 +3,20 @@ option (ENABLE_CLANG_TIDY "Use clang-tidy static analyzer" OFF)
if (ENABLE_CLANG_TIDY)
find_program (CLANG_TIDY_PATH NAMES "clang-tidy" "clang-tidy-15" "clang-tidy-14" "clang-tidy-13" "clang-tidy-12")
find_program (CLANG_TIDY_CACHE_PATH NAMES "clang-tidy-cache")
if (CLANG_TIDY_CACHE_PATH)
find_program (_CLANG_TIDY_PATH NAMES "clang-tidy" "clang-tidy-15" "clang-tidy-14" "clang-tidy-13" "clang-tidy-12")
# Why do we use ';' here?
# It's a cmake black magic: https://cmake.org/cmake/help/latest/prop_tgt/LANG_CLANG_TIDY.html#prop_tgt:%3CLANG%3E_CLANG_TIDY
# The CLANG_TIDY_PATH is passed to CMAKE_CXX_CLANG_TIDY, which follows CXX_CLANG_TIDY syntax.
set (CLANG_TIDY_PATH "${CLANG_TIDY_CACHE_PATH};${_CLANG_TIDY_PATH}" CACHE STRING "A combined command to run clang-tidy with caching wrapper")
else ()
find_program (CLANG_TIDY_PATH NAMES "clang-tidy" "clang-tidy-15" "clang-tidy-14" "clang-tidy-13" "clang-tidy-12")
endif ()
if (CLANG_TIDY_PATH)
message(STATUS
message (STATUS
"Using clang-tidy: ${CLANG_TIDY_PATH}.
The checks will be run during build process.
See the .clang-tidy file at the root directory to configure the checks.")
@ -15,11 +25,15 @@ if (ENABLE_CLANG_TIDY)
# clang-tidy requires assertions to guide the analysis
# Note that NDEBUG is set implicitly by CMake for non-debug builds
set(COMPILER_FLAGS "${COMPILER_FLAGS} -UNDEBUG")
set (COMPILER_FLAGS "${COMPILER_FLAGS} -UNDEBUG")
# The variable CMAKE_CXX_CLANG_TIDY will be set inside src and base directories with non third-party code.
# The variable CMAKE_CXX_CLANG_TIDY will be set inside the following directories with non third-party code.
# - base
# - programs
# - src
# - utils
# set (CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_PATH}")
else ()
message(${RECONFIGURE_MESSAGE_LEVEL} "clang-tidy is not found")
message (${RECONFIGURE_MESSAGE_LEVEL} "clang-tidy is not found")
endif ()
endif ()

1
cmake/darwin/default_libs.cmake
View File

@ -23,6 +23,7 @@ set(THREADS_PREFER_PTHREAD_FLAG ON)
find_package(Threads REQUIRED)
include (cmake/cxx.cmake)
link_libraries(global-group)
target_link_libraries(global-group INTERFACE
$<TARGET_PROPERTY:global-libs,INTERFACE_LINK_LIBRARIES>

1
cmake/freebsd/default_libs.cmake
View File

@ -24,6 +24,7 @@ find_package(Threads REQUIRED)
include (cmake/unwind.cmake)
include (cmake/cxx.cmake)
link_libraries(global-group)
target_link_libraries(global-group INTERFACE
$<TARGET_PROPERTY:global-libs,INTERFACE_LINK_LIBRARIES>

10
cmake/linux/default_libs.cmake
View File

@ -34,6 +34,13 @@ set(CMAKE_C_STANDARD_LIBRARIES ${DEFAULT_LIBS})
set(THREADS_PREFER_PTHREAD_FLAG ON)
find_package(Threads REQUIRED)
include (cmake/unwind.cmake)
include (cmake/cxx.cmake)
# Delay the call to link the global interface after the libc++ libraries are included to avoid circular dependencies
# which are ok with static libraries but not with dynamic ones
link_libraries(global-group)
if (NOT OS_ANDROID)
if (NOT USE_MUSL)
# Our compatibility layer doesn't build under Android, many errors in musl.
@ -42,9 +49,6 @@ if (NOT OS_ANDROID)
add_subdirectory(base/harmful)
endif ()
include (cmake/unwind.cmake)
include (cmake/cxx.cmake)
target_link_libraries(global-group INTERFACE
-Wl,--start-group
$<TARGET_PROPERTY:global-libs,INTERFACE_LINK_LIBRARIES>

4
cmake/sanitize.cmake
View File

@ -16,7 +16,9 @@ endmacro()
if (SANITIZE)
if (SANITIZE STREQUAL "address")
set (ASAN_FLAGS "-fsanitize=address -fsanitize-address-use-after-scope")
# LLVM-15 has a bug in Address Sanitizer, preventing the usage of 'sanitize-address-use-after-scope',
# see https://github.com/llvm/llvm-project/issues/58633
set (ASAN_FLAGS "-fsanitize=address -fno-sanitize-address-use-after-scope")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_FLAGS} ${ASAN_FLAGS}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_FLAGS} ${ASAN_FLAGS}")

53
cmake/sanitize_target_link_libraries.cmake → cmake/sanitize_targets.cmake
View File

@ -1,3 +1,13 @@
# https://stackoverflow.com/a/62311397/328260
macro (get_all_targets_recursive targets dir)
get_property (subdirectories DIRECTORY ${dir} PROPERTY SUBDIRECTORIES)
foreach (subdir ${subdirectories})
get_all_targets_recursive (${targets} ${subdir})
endforeach ()
get_property (current_targets DIRECTORY ${dir} PROPERTY BUILDSYSTEM_TARGETS)
list (APPEND ${targets} ${current_targets})
endmacro ()
# When you will try to link target with the directory (that exists), cmake will
# skip this without an error, only the following warning will be reported:
#
@ -18,23 +28,12 @@
# -- but cannot be used with link_libraries()
# - use BUILDSYSTEM_TARGETS property to get list of all targets and sanitize
# -- this will work.
# https://stackoverflow.com/a/62311397/328260
function (get_all_targets var)
set (targets)
get_all_targets_recursive (targets ${CMAKE_CURRENT_SOURCE_DIR})
set (${var} ${targets} PARENT_SCOPE)
endfunction()
macro (get_all_targets_recursive targets dir)
get_property (subdirectories DIRECTORY ${dir} PROPERTY SUBDIRECTORIES)
foreach (subdir ${subdirectories})
get_all_targets_recursive (${targets} ${subdir})
endforeach ()
get_property (current_targets DIRECTORY ${dir} PROPERTY BUILDSYSTEM_TARGETS)
list (APPEND ${targets} ${current_targets})
endmacro ()
macro (sanitize_link_libraries target)
function (sanitize_link_libraries target)
get_target_property(target_type ${target} TYPE)
if (${target_type} STREQUAL "INTERFACE_LIBRARY")
get_property(linked_libraries TARGET ${target} PROPERTY INTERFACE_LINK_LIBRARIES)
@ -48,9 +47,35 @@ macro (sanitize_link_libraries target)
message(FATAL_ERROR "${target} requested to link with directory: ${linked_library}")
endif()
endforeach()
endmacro()
endfunction()
get_all_targets (all_targets)
foreach (target ${all_targets})
sanitize_link_libraries(${target})
endforeach()
#
# Do not allow to define -W* from contrib publically (INTERFACE/PUBLIC).
#
function (get_contrib_targets var)
set (targets)
get_all_targets_recursive (targets ${CMAKE_CURRENT_SOURCE_DIR}/contrib)
set (${var} ${targets} PARENT_SCOPE)
endfunction()
function (sanitize_interface_flags target)
get_target_property(target_type ${target} TYPE)
get_property(compile_definitions TARGET ${target} PROPERTY INTERFACE_COMPILE_DEFINITIONS)
get_property(compile_options TARGET ${target} PROPERTY INTERFACE_COMPILE_OPTIONS)
if (NOT "${compile_options}" STREQUAL "")
message(FATAL_ERROR "${target} set INTERFACE_COMPILE_OPTIONS to ${compile_options}. This is forbidden.")
endif()
if ("${compile_definitions}" MATCHES "-Wl,")
# linker option - OK
elseif ("${compile_definitions}" MATCHES "-W")
message(FATAL_ERROR "${target} contains ${compile_definitions} flags in INTERFACE_COMPILE_DEFINITIONS. This is forbidden.")
endif()
endfunction()
get_contrib_targets (contrib_targets)
foreach (contrib_target ${contrib_targets})
sanitize_interface_flags(${contrib_target})
endforeach()

12
cmake/tools.cmake
View File

@ -58,13 +58,19 @@ if (NOT LINKER_NAME)
find_program (LLD_PATH NAMES "ld.lld")
find_program (GOLD_PATH NAMES "ld.gold")
elseif (COMPILER_CLANG)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "lld-${COMPILER_VERSION_MAJOR}" "ld.lld" "lld")
# llvm lld is a generic driver.
# Invoke ld.lld (Unix), ld64.lld (macOS), lld-link (Windows), wasm-ld (WebAssembly) instead
if (OS_LINUX)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
elseif (OS_DARWIN)
find_program (LLD_PATH NAMES "ld64.lld-${COMPILER_VERSION_MAJOR}" "ld64.lld")
endif ()
find_program (GOLD_PATH NAMES "ld.gold" "gold")
endif ()
endif()
if (OS_LINUX AND NOT LINKER_NAME)
# prefer lld linker over gold or ld on linux
if ((OS_LINUX OR OS_DARWIN) AND NOT LINKER_NAME)
# prefer lld linker over gold or ld on linux and macos
if (LLD_PATH)
if (COMPILER_GCC)
# GCC driver requires one of supported linker names like "lld".

4
contrib/CMakeLists.txt vendored
View File

@ -167,7 +167,9 @@ add_contrib (c-ares-cmake c-ares)
add_contrib (qpl-cmake qpl)
add_contrib (morton-nd-cmake morton-nd)
add_contrib(annoy-cmake annoy)
add_contrib (annoy-cmake annoy)
add_contrib (xxHash-cmake xxHash)
# Put all targets defined here and in subdirectories under "contrib/<immediate-subdir>" folders in GUI-based IDEs.
# Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they would not appear

2
contrib/NuRaft vendored

@ -1 +1 @@
Subproject commit 1be805e7cb2494aa8170015493474379b0362dfc
Subproject commit e4e746a24eb56861a86f3672771e3308d8c40722

2
contrib/cctz vendored

@ -1 +1 @@
Subproject commit 7a454c25c7d16053bcd327cdd16329212a08fa4a
Subproject commit 5c8528fb35e89ee0b3a7157490423fba0d4dd7b5

1
contrib/libcxx vendored

@ -1 +0,0 @@
Subproject commit 4db7f838afd3139eb3761694b04d31275df45d2d

4
contrib/libcxx-cmake/CMakeLists.txt
View File

@ -1,6 +1,6 @@
include(CheckCXXCompilerFlag)
set(LIBCXX_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/libcxx")
set(LIBCXX_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/llvm-project/libcxx")
set(SRCS
"${LIBCXX_SOURCE_DIR}/src/algorithm.cpp"
@ -57,7 +57,7 @@ add_library(cxx ${SRCS})
set_target_properties(cxx PROPERTIES FOLDER "contrib/libcxx-cmake")
target_include_directories(cxx SYSTEM BEFORE PRIVATE $<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}/src>)
target_include_directories(cxx SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}/include>)
target_include_directories(cxx SYSTEM BEFORE PUBLIC $<$<COMPILE_LANGUAGE:CXX>:$<BUILD_INTERFACE:${LIBCXX_SOURCE_DIR}/include>>)
target_compile_definitions(cxx PRIVATE -D_LIBCPP_BUILDING_LIBRARY -DLIBCXX_BUILDING_LIBCXXABI)
# Enable capturing stack traces for all exceptions.

1
contrib/libcxxabi vendored

@ -1 +0,0 @@
Subproject commit a736a6b3c6a7b8aae2ebad629ca21b2c55b4820e

2
contrib/libcxxabi-cmake/CMakeLists.txt
View File

@ -1,4 +1,4 @@
set(LIBCXXABI_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/libcxxabi")
set(LIBCXXABI_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/llvm-project/libcxxabi")
set(SRCS
"${LIBCXXABI_SOURCE_DIR}/src/abort_message.cpp"

2
contrib/llvm-project vendored

@ -1 +1 @@
Subproject commit 3a39038345a400e7e767811b142a94355d511215
Subproject commit e61a81aa6fc529b469e2a54b7ce788606e138b5d

3
contrib/llvm-project-cmake/CMakeLists.txt
View File

@ -21,6 +21,9 @@ set (LLVM_INCLUDE_DIRS
"${ClickHouse_BINARY_DIR}/contrib/llvm-project/llvm/include"
)
set (LLVM_LIBRARY_DIRS "${ClickHouse_BINARY_DIR}/contrib/llvm-project/llvm")
# NOTE: You should not remove this line since otherwise it will use default 20,
# and llvm cannot be compiled with bundled libcxx and 20 standard.
set (CMAKE_CXX_STANDARD 14)
# This list was generated by listing all LLVM libraries, compiling the binary and removing all libraries while it still compiles.
set (REQUIRED_LLVM_LIBRARIES

2
contrib/poco vendored

@ -1 +1 @@
Subproject commit 76746b35d0e254eaaba71dc3b79e46cba8cbb144
Subproject commit 799234226187c0ae0b8c90f23465b25ed7956e56

1
contrib/xxHash vendored Submodule

@ -0,0 +1 @@
Subproject commit 3078dc6039f8c0bffcb1904f81cfe6b2c3209435

13
contrib/xxHash-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,13 @@
set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/xxHash")
set (SRCS
"${LIBRARY_DIR}/xxhash.c"
)
add_library(xxHash ${SRCS})
target_include_directories(xxHash SYSTEM BEFORE INTERFACE "${LIBRARY_DIR}")
# XXH_INLINE_ALL - Make all functions inline, with implementations being directly included within xxhash.h. Inlining functions is beneficial for speed on small keys.
# https://github.com/Cyan4973/xxHash/tree/v0.8.1#build-modifiers
target_compile_definitions(xxHash PUBLIC XXH_INLINE_ALL)
add_library(ch_contrib::xxHash ALIAS xxHash)

1
docker/docs/builder/run.sh
View File

@ -25,6 +25,7 @@ done
sed -i '/onBrokenMarkdownLinks:/ s/ignore/error/g' docusaurus.config.js
if [[ $# -lt 1 ]] || [[ "$1" == "--"* ]]; then
export CI=true
exec yarn build "$@"
fi

32
docker/packager/binary/Dockerfile
View File

@ -6,29 +6,24 @@ FROM clickhouse/test-util:$FROM_TAG
# Rust toolchain and libraries
ENV RUSTUP_HOME=/rust/rustup
ENV CARGO_HOME=/rust/cargo
RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
RUN chmod 777 -R /rust
ENV PATH="/rust/cargo/env:${PATH}"
ENV PATH="/rust/cargo/bin:${PATH}"
RUN rustup target add aarch64-unknown-linux-gnu && \
rustup target add x86_64-apple-darwin && \
rustup target add x86_64-unknown-freebsd && \
rustup target add aarch64-apple-darwin && \
rustup target add powerpc64le-unknown-linux-gnu
RUN apt-get install \
RUN curl https://sh.rustup.rs -sSf | bash -s -- -y && \
chmod 777 -R /rust && \
rustup target add aarch64-unknown-linux-gnu && \
rustup target add x86_64-apple-darwin && \
rustup target add x86_64-unknown-freebsd && \
rustup target add aarch64-apple-darwin && \
rustup target add powerpc64le-unknown-linux-gnu
RUN apt-get update && \
apt-get install --yes \
gcc-aarch64-linux-gnu \
build-essential \
libc6 \
libc6-dev \
libc6-dev-arm64-cross \
--yes
# Install CMake 3.20+ for Rust compilation
# Used https://askubuntu.com/a/1157132 as reference
RUN apt purge cmake --yes
RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /etc/apt/trusted.gpg.d/kitware.gpg >/dev/null
RUN apt-add-repository 'deb https://apt.kitware.com/ubuntu/ focal main'
RUN apt update && apt install cmake --yes
libc6-dev-arm64-cross && \
apt-get clean
ENV CC=clang-${LLVM_VERSION}
ENV CXX=clang++-${LLVM_VERSION}
@ -91,6 +86,9 @@ ENV PATH="$PATH:/usr/local/go/bin"
ENV GOPATH=/workdir/go
ENV GOCACHE=/workdir/
RUN curl https://raw.githubusercontent.com/matus-chochlik/ctcache/7fd516e91c17779cbc6fc18bd119313d9532dd90/clang-tidy-cache -Lo /usr/bin/clang-tidy-cache \
&& chmod +x /usr/bin/clang-tidy-cache
RUN mkdir /workdir && chmod 777 /workdir
WORKDIR /workdir

8
docker/packager/packager
View File

@ -258,6 +258,10 @@ def parse_env_variables(
if clang_tidy:
# 15G is not enough for tidy build
cache_maxsize = "25G"
# `CTCACHE_DIR` has the same purpose as the `CCACHE_DIR` above.
# It's there to have the clang-tidy cache embedded into our standard `CCACHE_DIR`
result.append("CTCACHE_DIR=/ccache/clang-tidy-cache")
result.append(f"CCACHE_MAXSIZE={cache_maxsize}")
if distcc_hosts:
@ -282,9 +286,7 @@ def parse_env_variables(
cmake_flags.append("-DENABLE_TESTS=1")
if shared_libraries:
cmake_flags.append(
"-DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1"
)
cmake_flags.append("-DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1")
# We can't always build utils because it requires too much space, but
# we have to build them at least in some way in CI. The shared library
# build is probably the least heavy disk-wise.

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="22.10.1.1877"
ARG VERSION="22.11.1.1360"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# user/group precreated explicitly with fixed uid/gid on purpose.

12
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 ${REPO_CHANNEL} main"
ARG VERSION="22.10.1.1877"
ARG VERSION="22.11.1.1360"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# set non-empty deb_location_url url to create a docker image
@ -80,6 +80,16 @@ RUN arch=${TARGETARCH:-amd64} \
&& mkdir -p /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client \
&& chmod ugo+Xrw -R /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client
# Remove as much of Ubuntu as possible.
# ClickHouse does not need Ubuntu. It can run on top of Linux kernel without any OS distribution.
# ClickHouse does not need Docker at all. ClickHouse is above all that.
# It does not care about Ubuntu, Docker, or other cruft and you should neither.
# The fact that this Docker image is based on Ubuntu is just a misconception.
# Some vulnerability scanners are arguing about Ubuntu, which is not relevant to ClickHouse at all.
# ClickHouse does not care when you report false vulnerabilities by running some Docker scanners.
RUN apt-get remove --purge -y libksba8 && apt-get autoremove -y
# we need to allow "others" access to clickhouse folder, because docker container
# can be started with arbitrary uid (openshift usecase)

4
docker/test/fasttest/run.sh
View File

@ -117,8 +117,7 @@ function clone_submodules
contrib/cctz
contrib/libcpuid
contrib/double-conversion
contrib/libcxx
contrib/libcxxabi
contrib/llvm-project
contrib/lz4
contrib/zstd
contrib/fastops
@ -137,6 +136,7 @@ function clone_submodules
contrib/hashidsxx
contrib/c-ares
contrib/morton-nd
contrib/xxHash
)
git submodule sync

2
docker/test/fuzzer/Dockerfile
View File

@ -38,7 +38,7 @@ COPY * /
SHELL ["/bin/bash", "-c"]
CMD set -o pipefail \
&& cd /workspace \
&& /run-fuzzer.sh 2>&1 | ts "$(printf '%%Y-%%m-%%d %%H:%%M:%%S\t')" | tee main.log
&& timeout -s 9 1h /run-fuzzer.sh 2>&1 | ts "$(printf '%%Y-%%m-%%d %%H:%%M:%%S\t')" | tee main.log
# docker run --network=host --volume <workspace>:/workspace -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/fuzzer

54
docker/test/fuzzer/run-fuzzer.sh
View File

@ -1,5 +1,5 @@
#!/bin/bash
# shellcheck disable=SC2086,SC2001,SC2046,SC2030,SC2031
# shellcheck disable=SC2086,SC2001,SC2046,SC2030,SC2031,SC2010,SC2015
set -x
@ -10,11 +10,6 @@ set -e
set -u
set -o pipefail
trap "exit" INT TERM
# The watchdog is in the separate process group, so we have to kill it separately
# if the script terminates earlier.
trap 'kill $(jobs -pr) ${watchdog_pid:-} ||:' EXIT
stage=${stage:-}
script_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
echo "$script_dir"
@ -110,26 +105,6 @@ function configure
EOL
}
function watchdog
{
sleep 1800
echo "Fuzzing run has timed out"
for _ in {1..10}
do
# Only kill by pid the particular client that runs the fuzzing, or else
# we can kill some clickhouse-client processes this script starts later,
# e.g. for checking server liveness.
if ! kill $fuzzer_pid
then
break
fi
sleep 1
done
kill -9 -- $fuzzer_pid ||:
}
function filter_exists_and_template
{
local path
@ -175,10 +150,8 @@ function fuzz
mkdir -p /var/run/clickhouse-server
# interferes with gdb
export CLICKHOUSE_WATCHDOG_ENABLE=0
# NOTE: we use process substitution here to preserve keep $! as a pid of clickhouse-server
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db > >(tail -100000 > server.log) 2>&1 &
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db 2>&1 | pigz > server.log.gz &
server_pid=$!
kill -0 $server_pid
@ -214,7 +187,7 @@ detach
quit
" > script.gdb
gdb -batch -command script.gdb -p $server_pid &
gdb -batch -command script.gdb -p "$(cat /var/run/clickhouse-server/clickhouse-server.pid)" &
sleep 5
# gdb will send SIGSTOP, spend some time loading debug info and then send SIGCONT, wait for it (up to send_timeout, 300s)
time clickhouse-client --query "SELECT 'Connected to clickhouse-server after attaching gdb'" ||:
@ -236,7 +209,7 @@ quit
# SC2012: Use find instead of ls to better handle non-alphanumeric filenames. They are all alphanumeric.
# SC2046: Quote this to prevent word splitting. Actually I need word splitting.
# shellcheck disable=SC2012,SC2046
clickhouse-client \
timeout -s TERM --preserve-status 30m clickhouse-client \
--receive_timeout=10 \
--receive_data_timeout_ms=10000 \
--stacktrace \
@ -249,16 +222,6 @@ quit
fuzzer_pid=$!
echo "Fuzzer pid is $fuzzer_pid"
# Start a watchdog that should kill the fuzzer on timeout.
# The shell won't kill the child sleep when we kill it, so we have to put it
# into a separate process group so that we can kill them all.
set -m
watchdog &
watchdog_pid=$!
set +m
# Check that the watchdog has started.
kill -0 $watchdog_pid
# Wait for the fuzzer to complete.
# Note that the 'wait || ...' thing is required so that the script doesn't
# exit because of 'set -e' when 'wait' returns nonzero code.
@ -266,8 +229,6 @@ quit
wait "$fuzzer_pid" || fuzzer_exit_code=$?
echo "Fuzzer exit code is $fuzzer_exit_code"
kill -- -$watchdog_pid ||:
# If the server dies, most often the fuzzer returns code 210: connetion
# refused, and sometimes also code 32: attempt to read after eof. For
# simplicity, check again whether the server is accepting connections, using
@ -297,7 +258,7 @@ quit
# The server has died.
task_exit_code=210
echo "failure" > status.txt
if ! grep --text -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: AddressSanitizer:.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*\|.*_LIBCPP_ASSERT.*" server.log > description.txt
if ! zgrep --text -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: AddressSanitizer:.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*\|.*_LIBCPP_ASSERT.*" server.log.gz > description.txt
then
echo "Lost connection to server. See the logs." > description.txt
fi
@ -333,6 +294,8 @@ quit
pigz core.*
mv core.*.gz core.gz
fi
dmesg -T | grep -q -F -e 'Out of memory: Killed process' -e 'oom_reaper: reaped process' -e 'oom-kill:constraint=CONSTRAINT_NONE' && echo "OOM in dmesg" ||:
}
case "$stage" in
@ -391,8 +354,9 @@ th { cursor: pointer; }
<h1>AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST}</h1>
<p class="links">
<a href="runlog.log">runlog.log</a>
<a href="fuzzer.log">fuzzer.log</a>
<a href="server.log">server.log</a>
<a href="server.log.gz">server.log.gz</a>
<a href="main.log">main.log</a>
${CORE_LINK}
</p>

4
docker/test/keeper-jepsen/run.sh
View File

@ -15,8 +15,8 @@ if [ -z "$CLICKHOUSE_REPO_PATH" ]; then
ls -lath ||:
fi
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse-keeper"
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse"
(lein run test-all --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --snapshot-distance 100 --stale-log-gap 100 --reserved-log-items 10 --lightweight-run --clickhouse-source "$CLICKHOUSE_PACKAGE" -q --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
(lein run keeper test-all --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --snapshot-distance 100 --stale-log-gap 100 --reserved-log-items 10 --lightweight-run --clickhouse-source "$CLICKHOUSE_PACKAGE" -q --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
mv store "$TEST_OUTPUT/"

3
docker/test/performance-comparison/perf.py
View File

@ -295,6 +295,9 @@ if not args.use_existing_tables:
reportStageEnd("create")
# Let's sync the data to avoid writeback affects performance
os.system("sync")
# By default, test all queries.
queries_to_run = range(0, len(test_queries))

43
docker/test/server-jepsen/Dockerfile Normal file
View File

@ -0,0 +1,43 @@
# rebuild in #33610
# docker build -t clickhouse/server-jepsen-test .
ARG FROM_TAG=latest
FROM clickhouse/test-base:$FROM_TAG
ENV DEBIAN_FRONTEND=noninteractive
ENV CLOJURE_VERSION=1.10.3.814
# arguments
ENV PR_TO_TEST=""
ENV SHA_TO_TEST=""
ENV NODES_USERNAME="root"
ENV NODES_PASSWORD=""
ENV TESTS_TO_RUN="8"
ENV TIME_LIMIT="30"
ENV KEEPER_NODE=""
# volumes
ENV NODES_FILE_PATH="/nodes.txt"
ENV TEST_OUTPUT="/test_output"
RUN mkdir "/root/.ssh"
RUN touch "/root/.ssh/known_hosts"
# install java
RUN apt-get update && apt-get install default-jre default-jdk libjna-java libjna-jni ssh gnuplot graphviz --yes --no-install-recommends
# install clojure
RUN curl -O "https://download.clojure.org/install/linux-install-${CLOJURE_VERSION}.sh" && \
chmod +x "linux-install-${CLOJURE_VERSION}.sh" && \
bash "./linux-install-${CLOJURE_VERSION}.sh"
# install leiningen
RUN curl -O "https://raw.githubusercontent.com/technomancy/leiningen/stable/bin/lein" && \
chmod +x ./lein && \
mv ./lein /usr/bin
COPY run.sh /
CMD ["/bin/bash", "/run.sh"]

22
docker/test/server-jepsen/run.sh Normal file
View File

@ -0,0 +1,22 @@
#!/usr/bin/env bash
set -euo pipefail
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-15_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}
if [ -z "$CLICKHOUSE_REPO_PATH" ]; then
CLICKHOUSE_REPO_PATH=ch
rm -rf ch ||:
mkdir ch ||:
wget -nv -nd -c "https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/repo/clickhouse_no_subs.tar.gz"
tar -C ch --strip-components=1 -xf clickhouse_no_subs.tar.gz
ls -lath ||:
fi
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse"
(lein run server test-all --keeper "$KEEPER_NODE" --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --clickhouse-source "$CLICKHOUSE_PACKAGE" --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
mv store "$TEST_OUTPUT/"

2
docker/test/sqlancer/Dockerfile
View File

@ -1,5 +1,5 @@
# docker build -t clickhouse/sqlancer-test .
FROM ubuntu:20.04
FROM ubuntu:22.04
# ARG for quick switch to a given ubuntu mirror
ARG apt_archive="http://archive.ubuntu.com"

46
docker/test/sqlancer/process_sqlancer_result.py
View File

@ -11,13 +11,15 @@ def process_result(result_folder):
summary = []
paths = []
tests = [
"TLPWhere",
"TLPAggregate",
"TLPDistinct",
"TLPGroupBy",
"TLPHaving",
"TLPWhere",
"TLPWhereGroupBy",
"TLPDistinct",
"TLPAggregate",
"NoREC",
]
failed_tests = []
for test in tests:
err_path = "{}/{}.err".format(result_folder, test)
@ -33,15 +35,11 @@ def process_result(result_folder):
with open(err_path, "r") as f:
if "AssertionError" in f.read():
summary.append((test, "FAIL"))
failed_tests.append(test)
status = "failure"
else:
summary.append((test, "OK"))
logs_path = "{}/logs.tar.gz".format(result_folder)
if not os.path.exists(logs_path):
logging.info("No logs tar on path %s", logs_path)
else:
paths.append(logs_path)
stdout_path = "{}/stdout.log".format(result_folder)
if not os.path.exists(stdout_path):
logging.info("No stdout log on path %s", stdout_path)
@ -53,18 +51,23 @@ def process_result(result_folder):
else:
paths.append(stderr_path)
description = "SQLancer test run. See report"
description = "SQLancer run successfully"
if status == "failure":
description = f"Failed oracles: {failed_tests}"
return status, description, summary, paths
def write_results(results_file, status_file, results, status):
def write_results(
results_file, status_file, description_file, results, status, description
):
with open(results_file, "w") as f:
out = csv.writer(f, delimiter="\t")
out.writerows(results)
with open(status_file, "w") as f:
out = csv.writer(f, delimiter="\t")
out.writerow(status)
f.write(status + "\n")
with open(description_file, "w") as f:
f.write(description + "\n")
if __name__ == "__main__":
@ -72,13 +75,20 @@ if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="ClickHouse script for parsing results of sqlancer test"
)
parser.add_argument("--in-results-dir", default="/test_output/")
parser.add_argument("--out-results-file", default="/test_output/test_results.tsv")
parser.add_argument("--out-status-file", default="/test_output/check_status.tsv")
parser.add_argument("--in-results-dir", default="/workspace/")
parser.add_argument("--out-results-file", default="/workspace/summary.tsv")
parser.add_argument("--out-description-file", default="/workspace/description.txt")
parser.add_argument("--out-status-file", default="/workspace/status.txt")
args = parser.parse_args()
state, description, test_results, logs = process_result(args.in_results_dir)
status, description, summary, logs = process_result(args.in_results_dir)
logging.info("Result parsed")
status = (state, description)
write_results(args.out_results_file, args.out_status_file, test_results, status)
write_results(
args.out_results_file,
args.out_status_file,
args.out_description_file,
summary,
status,
description,
)
logging.info("Result written")

73
docker/test/sqlancer/run.sh
View File

@ -1,33 +1,62 @@
#!/bin/bash
set -exu
trap "exit" INT TERM
set -e -x
function wget_with_retry
{
for _ in 1 2 3 4; do
if wget -nv -nd -c "$1";then
return 0
else
sleep 0.5
fi
done
return 1
}
dpkg -i package_folder/clickhouse-common-static_*.deb
dpkg -i package_folder/clickhouse-common-static-dbg_*.deb
dpkg -i package_folder/clickhouse-server_*.deb
dpkg -i package_folder/clickhouse-client_*.deb
if [ -z ${BINARY_URL_TO_DOWNLOAD+x} ]
then
echo "No BINARY_URL_TO_DOWNLOAD provided."
else
wget_with_retry "$BINARY_URL_TO_DOWNLOAD"
chmod +x /clickhouse
fi
service clickhouse-server start && sleep 5
if [[ -f "/clickhouse" ]]; then
echo "/clickhouse exists"
else
exit 1
fi
cd /workspace
/clickhouse server -P /workspace/clickhouse-server.pid -L /workspace/clickhouse-server.log -E /workspace/clickhouse-server.log.err --daemon
for _ in $(seq 1 60); do if [[ $(wget -q 'localhost:8123' -O-) == 'Ok.' ]]; then break ; else sleep 1; fi ; done
cd /sqlancer/sqlancer-master
export TIMEOUT=300
export NUM_QUERIES=1000
TIMEOUT=300
NUM_QUERIES=1000
NUM_THREADS=10
TESTS=( "TLPGroupBy" "TLPHaving" "TLPWhere" "TLPDistinct" "TLPAggregate" "NoREC" )
echo "${TESTS[@]}"
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere | tee /test_output/TLPWhere.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhere.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPGroupBy | tee /test_output/TLPGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPGroupBy.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPHaving | tee /test_output/TLPHaving.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPHaving.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere --oracle TLPGroupBy | tee /test_output/TLPWhereGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhereGroupBy.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPDistinct | tee /test_output/TLPDistinct.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPDistinct.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPAggregate | tee /test_output/TLPAggregate.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPAggregate.err
for TEST in "${TESTS[@]}"; do
echo "$TEST"
if [[ $(wget -q 'localhost:8123' -O-) == 'Ok.' ]]
then
echo "Server is OK"
( java -jar target/sqlancer-*.jar --log-each-select true --print-failed false --num-threads "$NUM_THREADS" --timeout-seconds "$TIMEOUT" --num-queries "$NUM_QUERIES" --username default --password "" clickhouse --oracle "$TEST" | tee "/workspace/$TEST.out" ) 3>&1 1>&2 2>&3 | tee "/workspace/$TEST.err"
else
touch "/workspace/$TEST.err" "/workspace/$TEST.out"
echo "Server is not responding" | tee /workspace/server_crashed.log
fi
done
service clickhouse stop
ls /workspace
pkill -F /workspace/clickhouse-server.pid || true
ls /var/log/clickhouse-server/
tar czf /test_output/logs.tar.gz -C /var/log/clickhouse-server/ .
tail -n 1000 /var/log/clickhouse-server/stderr.log > /test_output/stderr.log
tail -n 1000 /var/log/clickhouse-server/stdout.log > /test_output/stdout.log
tail -n 1000 /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log
for _ in $(seq 1 60); do if [[ $(wget -q 'localhost:8123' -O-) == 'Ok.' ]]; then sleep 1 ; else break; fi ; done
/process_sqlancer_result.py || echo -e "failure\tCannot parse results" > /test_output/check_status.tsv
ls /test_output
/process_sqlancer_result.py || echo -e "failure\tCannot parse results" > /workspace/check_status.tsv
ls /workspace

22
docker/test/stress/run.sh
View File

@ -131,7 +131,14 @@ function stop()
# Preserve the pid, since the server can hung after the PID will be deleted.
pid="$(cat /var/run/clickhouse-server/clickhouse-server.pid)"
clickhouse stop --do-not-kill && return
# --max-tries is supported only since 22.12
if dpkg --compare-versions "$(clickhouse local -q 'select version()')" ge "22.12"; then
# Increase default waiting timeout for sanitizers and debug builds
clickhouse stop --max-tries 180 --do-not-kill && return
else
clickhouse stop --do-not-kill && return
fi
# We failed to stop the server with SIGTERM. Maybe it hang, let's collect stacktraces.
kill -TERM "$(pidof gdb)" ||:
sleep 5
@ -254,7 +261,7 @@ sudo chgrp clickhouse /etc/clickhouse-server/config.d/s3_storage_policy_by_defau
start
./stress --hung-check --drop-databases --output-folder test_output --skip-func-tests "$SKIP_TESTS_OPTION" \
./stress --hung-check --drop-databases --output-folder test_output --skip-func-tests "$SKIP_TESTS_OPTION" --global-time-limit 1200 \
&& echo -e 'Test script exit code\tOK' >> /test_output/test_results.tsv \
|| echo -e 'Test script failed\tFAIL' >> /test_output/test_results.tsv
@ -388,6 +395,11 @@ else
rm -f /etc/clickhouse-server/config.d/storage_conf.xml ||:
rm -f /etc/clickhouse-server/config.d/azure_storage_conf.xml ||:
# Turn on after 22.12
rm -f /etc/clickhouse-server/config.d/compressed_marks_and_index.xml ||:
# it uses recently introduced settings which previous versions may not have
rm -f /etc/clickhouse-server/users.d/insert_keeper_retries.xml ||:
start
clickhouse-client --query="SELECT 'Server version: ', version()"
@ -448,11 +460,12 @@ else
# FIXME https://github.com/ClickHouse/ClickHouse/issues/39197 ("Missing columns: 'v3' while processing query: 'v3, k, v1, v2, p'")
# NOTE Incompatibility was introduced in https://github.com/ClickHouse/ClickHouse/pull/39263, it's expected
# ("This engine is deprecated and is not supported in transactions", "[Queue = DB::MergeMutateRuntimeQueue]: Code: 235. DB::Exception: Part")
# FIXME https://github.com/ClickHouse/ClickHouse/issues/39174 - bad mutation does not indicate backward incompatibility
echo "Check for Error messages in server log:"
zgrep -Fav -e "Code: 236. DB::Exception: Cancelled merging parts" \
-e "Code: 236. DB::Exception: Cancelled mutating parts" \
-e "REPLICA_IS_ALREADY_ACTIVE" \
-e "REPLICA_IS_ALREADY_EXIST" \
-e "REPLICA_ALREADY_EXISTS" \
-e "ALL_REPLICAS_LOST" \
-e "DDLWorker: Cannot parse DDL task query" \
-e "RaftInstance: failed to accept a rpc connection due to error 125" \
@ -481,6 +494,9 @@ else
-e "The set of parts restored in place of" \
-e "(ReplicatedMergeTreeAttachThread): Initialization failed. Error" \
-e "Code: 269. DB::Exception: Destination table is myself" \
-e "Coordination::Exception: Connection loss" \
-e "MutateFromLogEntryTask" \
-e "No connection to ZooKeeper, cannot get shared table ID" \
/var/log/clickhouse-server/clickhouse-server.backward.clean.log | zgrep -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)\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'Backward compatibility check: No Error messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv

6
docker/test/style/Dockerfile
View File

@ -1,7 +1,7 @@
# docker build -t clickhouse/style-test .
FROM ubuntu:20.04
ARG ACT_VERSION=0.2.25
ARG ACTIONLINT_VERSION=1.6.8
ARG ACT_VERSION=0.2.33
ARG ACTIONLINT_VERSION=1.6.22
# ARG for quick switch to a given ubuntu mirror
ARG apt_archive="http://archive.ubuntu.com"
@ -17,7 +17,7 @@ RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
python3-pip \
shellcheck \
yamllint \
&& pip3 install black==22.8.0 boto3 codespell==2.2.1 dohq-artifactory PyGithub unidiff pylint==2.6.2 \
&& pip3 install black==22.8.0 boto3 codespell==2.2.1 dohq-artifactory mypy PyGithub unidiff pylint==2.6.2 \
&& apt-get clean \
&& rm -rf /root/.cache/pip

20
docker/test/style/process_style_check_result.py
View File

@ -11,17 +11,19 @@ def process_result(result_folder):
description = ""
test_results = []
checks = (
("header duplicates", "duplicate_output.txt"),
("shellcheck", "shellcheck_output.txt"),
("style", "style_output.txt"),
("black", "black_output.txt"),
("typos", "typos_output.txt"),
("whitespaces", "whitespaces_output.txt"),
("workflows", "workflows_output.txt"),
("doc typos", "doc_spell_output.txt"),
"duplicate includes",
"shellcheck",
"style",
"black",
"mypy",
"typos",
"whitespaces",
"workflows",
"docs spelling",
)
for name, out_file in checks:
for name in checks:
out_file = name.replace(" ", "_") + "_output.txt"
full_path = os.path.join(result_folder, out_file)
if not os.path.exists(full_path):
logging.info("No %s check log on path %s", name, full_path)

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

@ -4,15 +4,17 @@
cd /ClickHouse/utils/check-style || echo -e "failure\tRepo not found" > /test_output/check_status.tsv
echo "Check duplicates" | ts
./check-duplicate-includes.sh |& tee /test_output/duplicate_output.txt
./check-duplicate-includes.sh |& tee /test_output/duplicate_includes_output.txt
echo "Check style" | ts
./check-style -n |& tee /test_output/style_output.txt
echo "Check python formatting with black" | ts
./check-black -n |& tee /test_output/black_output.txt
echo "Check python type hinting with mypy" | ts
./check-mypy -n |& tee /test_output/mypy_output.txt
echo "Check typos" | ts
./check-typos |& tee /test_output/typos_output.txt
echo "Check docs spelling" | ts
./check-doc-aspell |& tee /test_output/doc_spell_output.txt
./check-doc-aspell |& tee /test_output/docs_spelling_output.txt
echo "Check whitespaces" | ts
./check-whitespaces -n |& tee /test_output/whitespaces_output.txt
echo "Check workflows" | ts

10
docker/test/util/Dockerfile
View File

@ -13,6 +13,7 @@ RUN apt-get update \
apt-transport-https \
apt-utils \
ca-certificates \
curl \
dnsutils \
gnupg \
iputils-ping \
@ -24,10 +25,16 @@ RUN apt-get update \
&& echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \
&& apt-key add /tmp/llvm-snapshot.gpg.key \
&& export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \
&& echo "deb [trusted=yes] https://apt.llvm.org/${CODENAME}/ llvm-toolchain-${CODENAME}-${LLVM_VERSION} main" >> \
&& echo "deb https://apt.llvm.org/${CODENAME}/ llvm-toolchain-${CODENAME}-${LLVM_VERSION} main" >> \
/etc/apt/sources.list \
&& apt-get clean
# Install cmake 3.20+ for rust support
# Used https://askubuntu.com/a/1157132 as reference
RUN curl -s https://apt.kitware.com/keys/kitware-archive-latest.asc | \
gpg --dearmor - > /etc/apt/trusted.gpg.d/kitware.gpg && \
echo "deb https://apt.kitware.com/ubuntu/ $(lsb_release -cs) main" >> /etc/apt/sources.list
# initial packages
RUN apt-get update \
&& apt-get install \
@ -37,7 +44,6 @@ RUN apt-get update \
clang-${LLVM_VERSION} \
clang-tidy-${LLVM_VERSION} \
cmake \
curl \
fakeroot \
gdb \
git \

2
docs/README.md
View File

@ -212,4 +212,4 @@ Templates:
## How to Build Documentation
You can build your documentation manually by following the instructions in [docs/tools/README.md](../docs/tools/README.md). Also, our CI runs the documentation build after the `documentation` label is added to PR. You can see the results of a build in the GitHub interface. If you have no permissions to add labels, a reviewer of your PR will add it.
You can build your documentation manually by following the instructions in the docs repo [contrib-writing-guide](https://github.com/ClickHouse/clickhouse-docs/blob/main/contrib-writing-guide.md). Also, our CI runs the documentation build after the `documentation` label is added to PR. You can see the results of a build in the GitHub interface. If you have no permissions to add labels, a reviewer of your PR will add it.

18
docs/changelogs/v22.10.2.11-stable.md Normal file
View File

@ -0,0 +1,18 @@
---
sidebar_position: 1
sidebar_label: 2022
---
# 2022 Changelog
### ClickHouse release v22.10.2.11-stable (d2bfcaba002) FIXME as compared to v22.10.1.1877-stable (98ab5a3c189)
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Backported in [#42750](https://github.com/ClickHouse/ClickHouse/issues/42750): A segmentation fault related to DNS & c-ares has been reported. The below error ocurred in multiple threads: ``` 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008088 [ 356 ] {} <Fatal> BaseDaemon: ######################################## 2022-09-28 15:41:19.008,"2022.09.28 15:41:19.008147 [ 356 ] {} <Fatal> BaseDaemon: (version 22.8.5.29 (official build), build id: 92504ACA0B8E2267) (from thread 353) (no query) Received signal Segmentation fault (11)" 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008196 [ 356 ] {} <Fatal> BaseDaemon: Address: 0xf Access: write. Address not mapped to object. 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008216 [ 356 ] {} <Fatal> BaseDaemon: Stack trace: 0x188f8212 0x1626851b 0x1626a69e 0x16269b3f 0x16267eab 0x13cf8284 0x13d24afc 0x13c5217e 0x14ec2495 0x15ba440f 0x15b9d13b 0x15bb2699 0x1891ccb3 0x1891e00d 0x18ae0769 0x18ade022 0x7f76aa985609 0x7f76aa8aa133 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008274 [ 356 ] {} <Fatal> BaseDaemon: 2. Poco::Net::IPAddress::family() const @ 0x188f8212 in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008297 [ 356 ] {} <Fatal> BaseDaemon: 3. ? @ 0x1626851b in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008309 [ 356 ] {} <Fatal> BaseDaemon: 4. ? @ 0x1626a69e in /usr/bin/clickhouse ```. [#42234](https://github.com/ClickHouse/ClickHouse/pull/42234) ([Arthur Passos](https://github.com/arthurpassos)).
* Backported in [#42793](https://github.com/ClickHouse/ClickHouse/issues/42793): Fix a bug in ParserFunction that could have led to a segmentation fault. [#42724](https://github.com/ClickHouse/ClickHouse/pull/42724) ([Nikolay Degterinsky](https://github.com/evillique)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Always run `BuilderReport` and `BuilderSpecialReport` in all CI types [#42684](https://github.com/ClickHouse/ClickHouse/pull/42684) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).

249
docs/changelogs/v22.11.1.1360-stable.md Normal file
View File

@ -0,0 +1,249 @@
---
sidebar_position: 1
sidebar_label: 2022
---
# 2022 Changelog
### ClickHouse release v22.11.1.1360-stable (0d211ed1984) FIXME as compared to v22.10.1.1877-stable (98ab5a3c189)
#### Backward Incompatible Change
* JSONExtract family of functions will now attempt to coerce to the request type. [#41502](https://github.com/ClickHouse/ClickHouse/pull/41502) ([Márcio Martins](https://github.com/marcioapm)).
#### New Feature
* - Add function `displayName`, closes [#36770](https://github.com/ClickHouse/ClickHouse/issues/36770). [#37681](https://github.com/ClickHouse/ClickHouse/pull/37681) ([hongbin](https://github.com/xlwh)).
* Added applied row-level policies to `system.query_log`. [#39819](https://github.com/ClickHouse/ClickHouse/pull/39819) ([Vladimir Chebotaryov](https://github.com/quickhouse)).
* Add Hudi and DeltaLake table engines, read-only, only for tables on S3. [#41054](https://github.com/ClickHouse/ClickHouse/pull/41054) ([Daniil Rubin](https://github.com/rubin-do)).
* Add 4LW command `csnp` for manually creating snapshots. Additionally, `lgif` was added to get Raft information for a specific node (e.g. index of last created snapshot, last committed log index). [#41766](https://github.com/ClickHouse/ClickHouse/pull/41766) ([JackyWoo](https://github.com/JackyWoo)).
* Support for keeper request retries during insert into replicated merge trees. Apart from fault tolerance, it aims to provide better user experience, - avoid returning a user an error during insert if keeper is restarted (for example, due to upgrade). [#42607](https://github.com/ClickHouse/ClickHouse/pull/42607) ([Igor Nikonov](https://github.com/devcrafter)).
* Add function ascii like in spark: https://spark.apache.org/docs/latest/api/sql/#ascii. [#42670](https://github.com/ClickHouse/ClickHouse/pull/42670) ([李扬](https://github.com/taiyang-li)).
* Add function pmod which return non-negative result based on modulo. [#42755](https://github.com/ClickHouse/ClickHouse/pull/42755) ([李扬](https://github.com/taiyang-li)).
* Published function `formatReadableDecimalSize`. [#42774](https://github.com/ClickHouse/ClickHouse/pull/42774) ([Alejandro](https://github.com/alexon1234)).
* Added S3 PUTs and GETs request per second rate throttling. Settings `s3_max_get_rps`, `s3_max_get_burst`, `s3_max_put_rps`, `s3_max_put_burst` are used to configure token bucket throttler. Can be used with both S3 ObjectStorage and S3 table function. Different limits can be configured for different S3 disks or endpoints. [#43014](https://github.com/ClickHouse/ClickHouse/pull/43014) ([Sergei Trifonov](https://github.com/serxa)).
* Add table function hudi and deltaLake. [#43080](https://github.com/ClickHouse/ClickHouse/pull/43080) ([flynn](https://github.com/ucasfl)).
* Add function factorial, as in Impala or Spark. [#43110](https://github.com/ClickHouse/ClickHouse/pull/43110) ([李扬](https://github.com/taiyang-li)).
* Add function randCanonical, which is similar to rand function in spark or impala. The function generates pseudo random results with independent and identically distributed uniformly distributed values in [0, 1). [#43124](https://github.com/ClickHouse/ClickHouse/pull/43124) ([李扬](https://github.com/taiyang-li)).
#### Performance Improvement
* Currently, the only saturable operators are And and Or, and their code paths are affected by this change. [#42214](https://github.com/ClickHouse/ClickHouse/pull/42214) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* `match` function can use the index if it's a condition on string prefix. This closes [#37333](https://github.com/ClickHouse/ClickHouse/issues/37333). [#42458](https://github.com/ClickHouse/ClickHouse/pull/42458) ([clarkcaoliu](https://github.com/Clark0)).
* Fixed slowness in JSONExtract with LowCardinality(String) tuples. [#42761](https://github.com/ClickHouse/ClickHouse/pull/42761) ([AlfVII](https://github.com/AlfVII)).
* Support parallel parsing for LineAsString input format. This improves performance just slightly. This closes [#42502](https://github.com/ClickHouse/ClickHouse/issues/42502). [#42780](https://github.com/ClickHouse/ClickHouse/pull/42780) ([Kruglov Pavel](https://github.com/Avogar)).
* Keeper performance improvement: improve commit performance for cases when many different nodes have uncommitted states. This should help with cases when a follower node can't sync fast enough. [#42926](https://github.com/ClickHouse/ClickHouse/pull/42926) ([Antonio Andelic](https://github.com/antonio2368)).
* Parallelized merging of `uniqExact` states for aggregation without a key, i.e. queries like `SELECT uniqExact(number) FROM table`. The improvement becomes noticeable when the number of unique keys approaches 10^6. Also `uniq` performance is slightly optimized. This closes [#4510](https://github.com/ClickHouse/ClickHouse/issues/4510). [#43072](https://github.com/ClickHouse/ClickHouse/pull/43072) ([Nikita Taranov](https://github.com/nickitat)).
#### Improvement
* Support type `Object` inside other types, e.g. `Array(JSON)`. [#36969](https://github.com/ClickHouse/ClickHouse/pull/36969) ([Anton Popov](https://github.com/CurtizJ)).
* Remove covered parts for fetched part (to avoid possible replication delay grows). [#39737](https://github.com/ClickHouse/ClickHouse/pull/39737) ([Azat Khuzhin](https://github.com/azat)).
* ClickHouse Client and ClickHouse Local will show progress by default even in non-interactive mode. If `/dev/tty` is available, the progress will be rendered directly to the terminal, without writing to stderr. It allows to get progress even if stderr is redirected to a file, and the file will not be polluted by terminal escape sequences. The progress can be disabled by `--progress false`. This closes [#32238](https://github.com/ClickHouse/ClickHouse/issues/32238). [#42003](https://github.com/ClickHouse/ClickHouse/pull/42003) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* 1. Add, subtract and negate operations are now available on Intervals. In case when the types of Intervals are different they will be transformed into the Tuple of those types. 2. A tuple of intervals can be added to or subtracted from a Date/DateTime field. 3. Added parsing of Intervals with different types, for example: `INTERVAL '1 HOUR 1 MINUTE 1 SECOND'`. [#42195](https://github.com/ClickHouse/ClickHouse/pull/42195) ([Nikolay Degterinsky](https://github.com/evillique)).
* - Add `notLike` to key condition atom map, so condition like `NOT LIKE 'prefix%'` can use primary index. [#42209](https://github.com/ClickHouse/ClickHouse/pull/42209) ([Duc Canh Le](https://github.com/canhld94)).
* Add support for FixedString input to base64 coding functions. [#42285](https://github.com/ClickHouse/ClickHouse/pull/42285) ([ltrk2](https://github.com/ltrk2)).
* Add columns `bytes_on_disk` and `path` to `system.detached_parts`. Closes [#42264](https://github.com/ClickHouse/ClickHouse/issues/42264). [#42303](https://github.com/ClickHouse/ClickHouse/pull/42303) ([chen](https://github.com/xiedeyantu)).
* Improve using structure from insertion table in table functions, now setting `use_structure_from_insertion_table_in_table_functions` has new possible value - `2` that means that ClickHouse will try to determine if we can use structure from insertion table or not automatically. Closes [#40028](https://github.com/ClickHouse/ClickHouse/issues/40028). [#42320](https://github.com/ClickHouse/ClickHouse/pull/42320) ([Kruglov Pavel](https://github.com/Avogar)).
* Added ** glob support for recursive directory traversal to filesystem and S3. resolves [#36316](https://github.com/ClickHouse/ClickHouse/issues/36316). [#42376](https://github.com/ClickHouse/ClickHouse/pull/42376) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Mask passwords and secret keys both in `system.query_log` and `/var/log/clickhouse-server/*.log` and also in error messages. [#42484](https://github.com/ClickHouse/ClickHouse/pull/42484) ([Vitaly Baranov](https://github.com/vitlibar)).
* Add a new variable call `limit` in query_info, indicating whether this query is a limit-trivial query. If so, we will adjust the approximate total rows for later estimation. Closes [#7071](https://github.com/ClickHouse/ClickHouse/issues/7071). [#42580](https://github.com/ClickHouse/ClickHouse/pull/42580) ([Han Fei](https://github.com/hanfei1991)).
* Implement `ATTACH` of `MergeTree` table for `s3_plain` disk (plus some fixes for `s3_plain`). [#42628](https://github.com/ClickHouse/ClickHouse/pull/42628) ([Azat Khuzhin](https://github.com/azat)).
* Fix no progress indication on INSERT FROM INFILE. Closes [#42548](https://github.com/ClickHouse/ClickHouse/issues/42548). [#42634](https://github.com/ClickHouse/ClickHouse/pull/42634) ([chen](https://github.com/xiedeyantu)).
* Add `min_age_to_force_merge_on_partition_only` setting to optimize old parts for the entire partition only. [#42659](https://github.com/ClickHouse/ClickHouse/pull/42659) ([Antonio Andelic](https://github.com/antonio2368)).
* Throttling algorithm changed to token bucket. [#42665](https://github.com/ClickHouse/ClickHouse/pull/42665) ([Sergei Trifonov](https://github.com/serxa)).
* Refactor FunctionTokens to enable max tokens returned for related functions(default disabled). [#42673](https://github.com/ClickHouse/ClickHouse/pull/42673) ([李扬](https://github.com/taiyang-li)).
* Added new field allow_readonly in system.table_functions to allow using table functions in readonly mode resolves [#42414](https://github.com/ClickHouse/ClickHouse/issues/42414) Implementation: * Added a new field allow_readonly to table system.table_functions. * Updated to use new field allow_readonly to allow using table functions in readonly mode. Testing: * Added a test for filesystem tests/queries/0_stateless/02473_functions_in_readonly_mode.sh Documentation: * Updated the english documentation for Table Functions. [#42708](https://github.com/ClickHouse/ClickHouse/pull/42708) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Allow to use Date32 arguments for formatDateTime and FROM_UNIXTIME functions. [#42737](https://github.com/ClickHouse/ClickHouse/pull/42737) ([Roman Vasin](https://github.com/rvasin)).
* Update tzdata to 2022f. Mexico will no longer observe DST except near the US border: https://www.timeanddate.com/news/time/mexico-abolishes-dst-2022.html. Chihuahua moves to year-round UTC-6 on 2022-10-30. Fiji no longer observes DST. See https://github.com/google/cctz/pull/235 and https://bugs.launchpad.net/ubuntu/+source/tzdata/+bug/1995209. [#42796](https://github.com/ClickHouse/ClickHouse/pull/42796) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add `FailedAsyncInsertQuery` event metric for async inserts. [#42814](https://github.com/ClickHouse/ClickHouse/pull/42814) ([Krzysztof Góralski](https://github.com/kgoralski)).
* Implement `read-in-order` optimization on top of query plan. It is enabled by default. Set `query_plan_read_in_order = 0` to use previous AST-based version. [#42829](https://github.com/ClickHouse/ClickHouse/pull/42829) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Increase the size of upload part exponentially for backup to S3. [#42833](https://github.com/ClickHouse/ClickHouse/pull/42833) ([Vitaly Baranov](https://github.com/vitlibar)).
* When the merge task is continuously busy and the disk space is insufficient, the completely expired parts cannot be selected and dropped, resulting in insufficient disk space. My idea is that when the entire Part expires, there is no need for additional disk space to guarantee, ensure the normal execution of TTL. [#42869](https://github.com/ClickHouse/ClickHouse/pull/42869) ([zhongyuankai](https://github.com/zhongyuankai)).
* bugfix： [#42856](https://github.com/ClickHouse/ClickHouse/issues/42856) ignore Mysql binlog SAVEPOINT event. [#42931](https://github.com/ClickHouse/ClickHouse/pull/42931) ([zzsmdfj](https://github.com/zzsmdfj)).
* Add support for interactive parameters in INSERT VALUES queries. [#43077](https://github.com/ClickHouse/ClickHouse/pull/43077) ([Nikolay Degterinsky](https://github.com/evillique)).
* Add generic implementation for arbitrary structured named collections, access type and system.named_collections. [#43147](https://github.com/ClickHouse/ClickHouse/pull/43147) ([Kseniia Sumarokova](https://github.com/kssenii)).
* add oss function and StorageOSS (This is convenient for users). oss is fully compatible with s3. [#43155](https://github.com/ClickHouse/ClickHouse/pull/43155) ([zzsmdfj](https://github.com/zzsmdfj)).
* Improve error reporting in the collection of OS-related info for the `system.asynchronous_metrics` table. [#43192](https://github.com/ClickHouse/ClickHouse/pull/43192) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The `system.asynchronous_metrics` gets embedded documentation. This documentation is also exported to Prometheus. Fixed an error with the metrics about `cache` disks - they were calculated only for one arbitrary cache disk instead all of them. This closes [#7644](https://github.com/ClickHouse/ClickHouse/issues/7644). [#43194](https://github.com/ClickHouse/ClickHouse/pull/43194) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Modify the `INFORMATION_SCHEMA` tables in a way so that now ClickHouse can connect to itself using the MySQL compatibility protocol. Add columns instead of aliases (related to [#9769](https://github.com/ClickHouse/ClickHouse/issues/9769)). It will improve the compatibility with various MySQL clients. [#43198](https://github.com/ClickHouse/ClickHouse/pull/43198) ([Filatenkov Artur](https://github.com/FArthur-cmd)).
* Disable `deltaLake` and `hudi` table functions in readonly mode. [#43316](https://github.com/ClickHouse/ClickHouse/pull/43316) ([Antonio Andelic](https://github.com/antonio2368)).
#### Bug Fix
* Updated normaliser to clone the alias ast. resolves [#42452](https://github.com/ClickHouse/ClickHouse/issues/42452) Implementation: * Updated QueryNormalizer to clone alias ast, when its replaced. Previously just assigning the same leads to exception in LogicalExpressinsOptimizer as it would be the same parent being inserted again. * This bug is not seen with new analyser (allow_experimental_analyzer), so no changes for it. I added a test for the same. [#42827](https://github.com/ClickHouse/ClickHouse/pull/42827) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix race for backup of tables in Lazy databases. [#43104](https://github.com/ClickHouse/ClickHouse/pull/43104) ([Vitaly Baranov](https://github.com/vitlibar)).
* fix skip_unavailable_shards does not work using s3Cluster table function. [#43131](https://github.com/ClickHouse/ClickHouse/pull/43131) ([chen](https://github.com/xiedeyantu)).
#### Build/Testing/Packaging Improvement
* Run SQLancer for each pull request and commit to master. [SQLancer](https://github.com/sqlancer/sqlancer) is an OpenSource fuzzer that focuses on automatic detection of logical bugs. [#42397](https://github.com/ClickHouse/ClickHouse/pull/42397) ([Ilya Yatsishin](https://github.com/qoega)).
* Update to latest zlib-ng. [#42463](https://github.com/ClickHouse/ClickHouse/pull/42463) ([Boris Kuschel](https://github.com/bkuschel)).
* use llvm `l64.lld` in macOS suppress ld warnings, close [#42282](https://github.com/ClickHouse/ClickHouse/issues/42282). [#42470](https://github.com/ClickHouse/ClickHouse/pull/42470) ([Lloyd-Pottiger](https://github.com/Lloyd-Pottiger)).
* Add support for testing ClickHouse server with Jepsen. By the way, we already have support for testing ClickHouse Keeper with Jepsen. This pull request extends it to Replicated tables. [#42619](https://github.com/ClickHouse/ClickHouse/pull/42619) ([Antonio Andelic](https://github.com/antonio2368)).
* * Improve bugfix validation check: fix bug with skipping the check, port separate status in CI, run after check labels and style check. Close [#40349](https://github.com/ClickHouse/ClickHouse/issues/40349). [#42702](https://github.com/ClickHouse/ClickHouse/pull/42702) ([Vladimir C](https://github.com/vdimir)).
* Wait for all files are in sync before archiving them in integration tests. [#42891](https://github.com/ClickHouse/ClickHouse/pull/42891) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Use https://github.com/matus-chochlik/ctcache for clang-tidy results caching. [#42913](https://github.com/ClickHouse/ClickHouse/pull/42913) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Before the fix, the user-defined config was preserved by RPM in `$file.rpmsave`. The PR fixes it and won't replace the user's files from packages. [#42936](https://github.com/ClickHouse/ClickHouse/pull/42936) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add a CI step to mark commits as ready for release; soft-forbid launching a release script from branches but master. [#43017](https://github.com/ClickHouse/ClickHouse/pull/43017) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Fix schema inference in s3Cluster and improve in hdfsCluster. [#41979](https://github.com/ClickHouse/ClickHouse/pull/41979) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix retries while reading from http table engines / table function. (retrtiable errors could be retries more times than needed, non-retrialble errors resulted in failed assertion in code). [#42224](https://github.com/ClickHouse/ClickHouse/pull/42224) ([Kseniia Sumarokova](https://github.com/kssenii)).
* A segmentation fault related to DNS & c-ares has been reported. The below error ocurred in multiple threads: ``` 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008088 [ 356 ] {} <Fatal> BaseDaemon: ######################################## 2022-09-28 15:41:19.008,"2022.09.28 15:41:19.008147 [ 356 ] {} <Fatal> BaseDaemon: (version 22.8.5.29 (official build), build id: 92504ACA0B8E2267) (from thread 353) (no query) Received signal Segmentation fault (11)" 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008196 [ 356 ] {} <Fatal> BaseDaemon: Address: 0xf Access: write. Address not mapped to object. 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008216 [ 356 ] {} <Fatal> BaseDaemon: Stack trace: 0x188f8212 0x1626851b 0x1626a69e 0x16269b3f 0x16267eab 0x13cf8284 0x13d24afc 0x13c5217e 0x14ec2495 0x15ba440f 0x15b9d13b 0x15bb2699 0x1891ccb3 0x1891e00d 0x18ae0769 0x18ade022 0x7f76aa985609 0x7f76aa8aa133 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008274 [ 356 ] {} <Fatal> BaseDaemon: 2. Poco::Net::IPAddress::family() const @ 0x188f8212 in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008297 [ 356 ] {} <Fatal> BaseDaemon: 3. ? @ 0x1626851b in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008309 [ 356 ] {} <Fatal> BaseDaemon: 4. ? @ 0x1626a69e in /usr/bin/clickhouse ```. [#42234](https://github.com/ClickHouse/ClickHouse/pull/42234) ([Arthur Passos](https://github.com/arthurpassos)).
* Fix `LOGICAL_ERROR` `Arguments of 'plus' have incorrect data types` which may happen in PK analysis (monotonicity check). Fix invalid PK analysis for monotonic binary functions with first constant argument. [#42410](https://github.com/ClickHouse/ClickHouse/pull/42410) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix incorrect key analysis when key types cannot be inside Nullable. This fixes [#42456](https://github.com/ClickHouse/ClickHouse/issues/42456). [#42469](https://github.com/ClickHouse/ClickHouse/pull/42469) ([Amos Bird](https://github.com/amosbird)).
* Fix typo in setting name that led to bad usage of schema inference cache while using setting `input_format_csv_use_best_effort_in_schema_inference`. Closes [#41735](https://github.com/ClickHouse/ClickHouse/issues/41735). [#42536](https://github.com/ClickHouse/ClickHouse/pull/42536) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix create Set with wrong header when data type is LowCardinality. Closes [#42460](https://github.com/ClickHouse/ClickHouse/issues/42460). [#42579](https://github.com/ClickHouse/ClickHouse/pull/42579) ([flynn](https://github.com/ucasfl)).
* `(U)Int128` and `(U)Int256` values are correctly checked in `PREWHERE`. [#42605](https://github.com/ClickHouse/ClickHouse/pull/42605) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix a bug in ParserFunction that could have led to a segmentation fault. [#42724](https://github.com/ClickHouse/ClickHouse/pull/42724) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix truncate table does not hold lock correctly. [#42728](https://github.com/ClickHouse/ClickHouse/pull/42728) ([flynn](https://github.com/ucasfl)).
* Fix possible SIGSEGV for web disks when file does not exists (or `OPTIMIZE TABLE FINAL`, that also can got the same error eventually). [#42767](https://github.com/ClickHouse/ClickHouse/pull/42767) ([Azat Khuzhin](https://github.com/azat)).
* Fix `auth_type` mapping in `system.session_log`, by including `SSL_CERTIFICATE` for the enum values. [#42782](https://github.com/ClickHouse/ClickHouse/pull/42782) ([Miel Donkers](https://github.com/mdonkers)).
* Fix stack-use-after-return under ASAN build in ParserCreateUserQuery. [#42804](https://github.com/ClickHouse/ClickHouse/pull/42804) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix lowerUTF8()/upperUTF8() in case of symbol was in between 16-byte boundary (very frequent case of you have strings > 16 bytes long). [#42812](https://github.com/ClickHouse/ClickHouse/pull/42812) ([Azat Khuzhin](https://github.com/azat)).
* Additional bound check was added to lz4 decompression routine to fix misbehaviour in case of malformed input. [#42868](https://github.com/ClickHouse/ClickHouse/pull/42868) ([Nikita Taranov](https://github.com/nickitat)).
* Fix rare possible hung on query cancellation. [#42874](https://github.com/ClickHouse/ClickHouse/pull/42874) ([Azat Khuzhin](https://github.com/azat)).
* * Fix incorrect saved_block_sample with multiple disjuncts in hash join, close [#42832](https://github.com/ClickHouse/ClickHouse/issues/42832). [#42876](https://github.com/ClickHouse/ClickHouse/pull/42876) ([Vladimir C](https://github.com/vdimir)).
* A null pointer will be generated when select if as from ‘three table join’ , For example, the SQL:. [#42883](https://github.com/ClickHouse/ClickHouse/pull/42883) ([zzsmdfj](https://github.com/zzsmdfj)).
* Fix memory sanitizer report in ClusterDiscovery, close [#42763](https://github.com/ClickHouse/ClickHouse/issues/42763). [#42905](https://github.com/ClickHouse/ClickHouse/pull/42905) ([Vladimir C](https://github.com/vdimir)).
* Fix datetime schema inference in case of empty string. [#42911](https://github.com/ClickHouse/ClickHouse/pull/42911) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix rare NOT_FOUND_COLUMN_IN_BLOCK error when projection is possible to use but there is no projection available. This fixes [#42771](https://github.com/ClickHouse/ClickHouse/issues/42771) . The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/25563. [#42938](https://github.com/ClickHouse/ClickHouse/pull/42938) ([Amos Bird](https://github.com/amosbird)).
* Fixes for s3_plain disk that will allow to attach Wide parts. [#42950](https://github.com/ClickHouse/ClickHouse/pull/42950) ([Azat Khuzhin](https://github.com/azat)).
* Fix ATTACH TABLE in PostgreSQL database engine if the table contains DATETIME data type. Closes [#42817](https://github.com/ClickHouse/ClickHouse/issues/42817). [#42960](https://github.com/ClickHouse/ClickHouse/pull/42960) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix lambda parsing. Closes [#41848](https://github.com/ClickHouse/ClickHouse/issues/41848). [#42979](https://github.com/ClickHouse/ClickHouse/pull/42979) ([Nikolay Degterinsky](https://github.com/evillique)).
* Handle (ignore) SAVEPOINT queries in MaterializedMySQL. [#43086](https://github.com/ClickHouse/ClickHouse/pull/43086) ([Stig Bakken](https://github.com/stigsb)).
* Fix incorrect key analysis when nullable keys appear in the middle of a hyperrectangle. This fixes [#43111](https://github.com/ClickHouse/ClickHouse/issues/43111) . [#43133](https://github.com/ClickHouse/ClickHouse/pull/43133) ([Amos Bird](https://github.com/amosbird)).
* - Fix several buffer over-reads. [#43159](https://github.com/ClickHouse/ClickHouse/pull/43159) ([Raúl Marín](https://github.com/Algunenano)).
* Fix function if in case of NULL and const Nullable arguments. Closes [#43069](https://github.com/ClickHouse/ClickHouse/issues/43069). [#43178](https://github.com/ClickHouse/ClickHouse/pull/43178) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix decimal math overflow in parsing datetime with 'best effort' algorithm. Closes [#43061](https://github.com/ClickHouse/ClickHouse/issues/43061). [#43180](https://github.com/ClickHouse/ClickHouse/pull/43180) ([Kruglov Pavel](https://github.com/Avogar)).
* The `indent` field produced by the `git-import` tool was miscalculated. See https://clickhouse.com/docs/en/getting-started/example-datasets/github/. [#43191](https://github.com/ClickHouse/ClickHouse/pull/43191) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fixed unexpected behaviour of Interval types with subquery and casting. [#43193](https://github.com/ClickHouse/ClickHouse/pull/43193) ([jh0x](https://github.com/jh0x)).
* * Fix logical error in `sumMap/minMap/maxMap` functions executing `TOTALS/ROLLUP/CUBE` on `NULL` values. Close [#43022](https://github.com/ClickHouse/ClickHouse/issues/43022). [#43232](https://github.com/ClickHouse/ClickHouse/pull/43232) ([Vladimir C](https://github.com/vdimir)).
* - Fix ubsan in AggregateFunctionMinMaxAny::read with high sizes. [#43249](https://github.com/ClickHouse/ClickHouse/pull/43249) ([Raúl Marín](https://github.com/Algunenano)).
* Fix IS (NOT) NULL operator priority in regard to other operators. [#43265](https://github.com/ClickHouse/ClickHouse/pull/43265) ([Nikolay Degterinsky](https://github.com/evillique)).
#### Build Improvement
* ... Add support for format ipv6 on s390x. [#42412](https://github.com/ClickHouse/ClickHouse/pull/42412) ([Suzy Wang](https://github.com/SuzyWangIBMer)).
#### NO CL ENTRY
* NO CL ENTRY: 'Revert "Sonar Cloud Workflow"'. [#42725](https://github.com/ClickHouse/ClickHouse/pull/42725) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert " Keeper retries during insert (clean)"'. [#43116](https://github.com/ClickHouse/ClickHouse/pull/43116) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Revert " Keeper retries during insert (clean)""'. [#43122](https://github.com/ClickHouse/ClickHouse/pull/43122) ([Igor Nikonov](https://github.com/devcrafter)).
* NO CL ENTRY: 'Revert "Optimize TTL merge, completely expired parts can be removed in time"'. [#43134](https://github.com/ClickHouse/ClickHouse/pull/43134) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Randomize keeper fault injection settings in stress tests"'. [#43218](https://github.com/ClickHouse/ClickHouse/pull/43218) ([Alexander Gololobov](https://github.com/davenger)).
* NO CL ENTRY: 'Revert "S3 request per second rate throttling"'. [#43306](https://github.com/ClickHouse/ClickHouse/pull/43306) ([Alexander Tokmakov](https://github.com/tavplubix)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Better logging for docs builder [#41903](https://github.com/ClickHouse/ClickHouse/pull/41903) ([filimonov](https://github.com/filimonov)).
* Save full server log in AST Fuzzer checks [#42316](https://github.com/ClickHouse/ClickHouse/pull/42316) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Build with libcxx(abi) 15 [#42513](https://github.com/ClickHouse/ClickHouse/pull/42513) ([Robert Schulze](https://github.com/rschu1ze)).
* Sonar Cloud Workflow [#42534](https://github.com/ClickHouse/ClickHouse/pull/42534) ([Julio Jimenez](https://github.com/juliojimenez)).
* Invalid type in where for Merge table (logical error) [#42576](https://github.com/ClickHouse/ClickHouse/pull/42576) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix frequent memory drift message and clarify things in comments [#42582](https://github.com/ClickHouse/ClickHouse/pull/42582) ([Azat Khuzhin](https://github.com/azat)).
* Add functions for PowerBI connect [#42612](https://github.com/ClickHouse/ClickHouse/pull/42612) ([Filatenkov Artur](https://github.com/FArthur-cmd)).
* Try to save `IDataPartStorage` interface [#42618](https://github.com/ClickHouse/ClickHouse/pull/42618) ([Anton Popov](https://github.com/CurtizJ)).
* Remove Ubuntu cruft [#42622](https://github.com/ClickHouse/ClickHouse/pull/42622) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Analyzer change setting into allow_experimental_analyzer [#42649](https://github.com/ClickHouse/ClickHouse/pull/42649) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer IQueryTreeNode remove getName method [#42651](https://github.com/ClickHouse/ClickHouse/pull/42651) ([Maksim Kita](https://github.com/kitaisreal)).
* Minor fix iotest_nonblock build [#42658](https://github.com/ClickHouse/ClickHouse/pull/42658) ([Jordi Villar](https://github.com/jrdi)).
* Add tests and doc for some url-related functions [#42664](https://github.com/ClickHouse/ClickHouse/pull/42664) ([Vladimir C](https://github.com/vdimir)).
* Update version_date.tsv and changelogs after v22.10.1.1875-stable [#42676](https://github.com/ClickHouse/ClickHouse/pull/42676) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Fix error handling in clickhouse_helper.py [#42678](https://github.com/ClickHouse/ClickHouse/pull/42678) ([Ilya Yatsishin](https://github.com/qoega)).
* Fix execution of version_helper.py to use git tweaks [#42679](https://github.com/ClickHouse/ClickHouse/pull/42679) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* MergeTree indexes use RPNBuilderTree [#42681](https://github.com/ClickHouse/ClickHouse/pull/42681) ([Maksim Kita](https://github.com/kitaisreal)).
* Always run `BuilderReport` and `BuilderSpecialReport` in all CI types [#42684](https://github.com/ClickHouse/ClickHouse/pull/42684) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Support optimize_syntax_fuse_functions for sum/count/avg via analyzer [#42689](https://github.com/ClickHouse/ClickHouse/pull/42689) ([Vladimir C](https://github.com/vdimir)).
* Update version after release [#42699](https://github.com/ClickHouse/ClickHouse/pull/42699) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Update version_date.tsv and changelogs after v22.10.1.1877-stable [#42700](https://github.com/ClickHouse/ClickHouse/pull/42700) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* OrderByLimitByDuplicateEliminationPass improve performance [#42704](https://github.com/ClickHouse/ClickHouse/pull/42704) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer improve subqueries representation [#42705](https://github.com/ClickHouse/ClickHouse/pull/42705) ([Maksim Kita](https://github.com/kitaisreal)).
* Update version_date.tsv and changelogs after v22.9.4.32-stable [#42712](https://github.com/ClickHouse/ClickHouse/pull/42712) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v22.8.7.34-lts [#42713](https://github.com/ClickHouse/ClickHouse/pull/42713) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v22.7.7.24-stable [#42714](https://github.com/ClickHouse/ClickHouse/pull/42714) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Move SonarCloud Job to nightly [#42718](https://github.com/ClickHouse/ClickHouse/pull/42718) ([Julio Jimenez](https://github.com/juliojimenez)).
* Update version_date.tsv and changelogs after v22.8.8.3-lts [#42738](https://github.com/ClickHouse/ClickHouse/pull/42738) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Minor fix implicit cast CaresPTRResolver [#42747](https://github.com/ClickHouse/ClickHouse/pull/42747) ([Jordi Villar](https://github.com/jrdi)).
* Fix build on master [#42752](https://github.com/ClickHouse/ClickHouse/pull/42752) ([Igor Nikonov](https://github.com/devcrafter)).
* Update version_date.tsv and changelogs after v22.3.14.18-lts [#42759](https://github.com/ClickHouse/ClickHouse/pull/42759) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Fix anchor links [#42760](https://github.com/ClickHouse/ClickHouse/pull/42760) ([Sergei Trifonov](https://github.com/serxa)).
* Update version_date.tsv and changelogs after v22.3.14.23-lts [#42764](https://github.com/ClickHouse/ClickHouse/pull/42764) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update README.md [#42783](https://github.com/ClickHouse/ClickHouse/pull/42783) ([Yuko Takagi](https://github.com/yukotakagi)).
* Slightly better code with projections [#42794](https://github.com/ClickHouse/ClickHouse/pull/42794) ([Anton Popov](https://github.com/CurtizJ)).
* Fix some races in MergeTree [#42805](https://github.com/ClickHouse/ClickHouse/pull/42805) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix typo in comments [#42809](https://github.com/ClickHouse/ClickHouse/pull/42809) ([Gabriel](https://github.com/Gabriel39)).
* Fix compilation of LLVM with cmake cache [#42816](https://github.com/ClickHouse/ClickHouse/pull/42816) ([Azat Khuzhin](https://github.com/azat)).
* Fix link in docs [#42821](https://github.com/ClickHouse/ClickHouse/pull/42821) ([Sergei Trifonov](https://github.com/serxa)).
* Link to proper place in docs [#42822](https://github.com/ClickHouse/ClickHouse/pull/42822) ([Sergei Trifonov](https://github.com/serxa)).
* Fix argument type check in AggregateFunctionAnalysisOfVariance [#42823](https://github.com/ClickHouse/ClickHouse/pull/42823) ([Vladimir C](https://github.com/vdimir)).
* Tests/lambda analyzer [#42824](https://github.com/ClickHouse/ClickHouse/pull/42824) ([Denny Crane](https://github.com/den-crane)).
* Fix Missing Quotes - Sonar Nightly [#42831](https://github.com/ClickHouse/ClickHouse/pull/42831) ([Julio Jimenez](https://github.com/juliojimenez)).
* Add exclusions from the Snyk scan [#42834](https://github.com/ClickHouse/ClickHouse/pull/42834) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix Missing Env Vars - Sonar Nightly [#42843](https://github.com/ClickHouse/ClickHouse/pull/42843) ([Julio Jimenez](https://github.com/juliojimenez)).
* Fix typo [#42855](https://github.com/ClickHouse/ClickHouse/pull/42855) ([GoGoWen](https://github.com/GoGoWen)).
* Add timezone to 02458_datediff_date32 [#42857](https://github.com/ClickHouse/ClickHouse/pull/42857) ([Vladimir C](https://github.com/vdimir)).
* Adjust cancel and rerun workflow names to the actual [#42862](https://github.com/ClickHouse/ClickHouse/pull/42862) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Analyzer subquery in JOIN TREE with aggregation [#42865](https://github.com/ClickHouse/ClickHouse/pull/42865) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix getauxval for sanitizer builds [#42866](https://github.com/ClickHouse/ClickHouse/pull/42866) ([Amos Bird](https://github.com/amosbird)).
* Update version_date.tsv and changelogs after v22.10.2.11-stable [#42871](https://github.com/ClickHouse/ClickHouse/pull/42871) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Better usability for dashboard.html on changes [#42872](https://github.com/ClickHouse/ClickHouse/pull/42872) ([Vladimir C](https://github.com/vdimir)).
* Some fixes for ReplicatedMergeTree [#42878](https://github.com/ClickHouse/ClickHouse/pull/42878) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Validate Query Tree in debug [#42879](https://github.com/ClickHouse/ClickHouse/pull/42879) ([Dmitry Novik](https://github.com/novikd)).
* changed type name for s3 plain storage [#42890](https://github.com/ClickHouse/ClickHouse/pull/42890) ([Aleksandr](https://github.com/AVMusorin)).
* Cleanup implementation of regexpReplace(All|One) [#42907](https://github.com/ClickHouse/ClickHouse/pull/42907) ([Robert Schulze](https://github.com/rschu1ze)).
* Do not show status for Bugfix validate check in non bugfix PRs [#42932](https://github.com/ClickHouse/ClickHouse/pull/42932) ([Vladimir C](https://github.com/vdimir)).
* fix(typo): Passible -> Possible [#42933](https://github.com/ClickHouse/ClickHouse/pull/42933) ([Yakko Majuri](https://github.com/yakkomajuri)).
* Pin the cryptography version to not break lambdas [#42934](https://github.com/ClickHouse/ClickHouse/pull/42934) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix: bad cast from type DB::ColumnLowCardinality to DB::ColumnString [#42937](https://github.com/ClickHouse/ClickHouse/pull/42937) ([Igor Nikonov](https://github.com/devcrafter)).
* Attach thread pool for loading parts to the query [#42947](https://github.com/ClickHouse/ClickHouse/pull/42947) ([Azat Khuzhin](https://github.com/azat)).
* Fix macOS M1 builds due to sprintf deprecation [#42962](https://github.com/ClickHouse/ClickHouse/pull/42962) ([Jordi Villar](https://github.com/jrdi)).
* Less use of CH-specific bit_cast() [#42968](https://github.com/ClickHouse/ClickHouse/pull/42968) ([Robert Schulze](https://github.com/rschu1ze)).
* Remove some utils [#42972](https://github.com/ClickHouse/ClickHouse/pull/42972) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix a bug in CAST function parser [#42980](https://github.com/ClickHouse/ClickHouse/pull/42980) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix old bug to remove `refs/head` from ref name [#42981](https://github.com/ClickHouse/ClickHouse/pull/42981) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add debug information to nightly builds [#42997](https://github.com/ClickHouse/ClickHouse/pull/42997) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add some guard rails around aggregation memory management [#42999](https://github.com/ClickHouse/ClickHouse/pull/42999) ([Raúl Marín](https://github.com/Algunenano)).
* Add `on: workflow_call` to debug CI [#43000](https://github.com/ClickHouse/ClickHouse/pull/43000) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Analyzer added identifier typo corrections [#43002](https://github.com/ClickHouse/ClickHouse/pull/43002) ([Maksim Kita](https://github.com/kitaisreal)).
* Simple fixes for restart replica description [#43004](https://github.com/ClickHouse/ClickHouse/pull/43004) ([Igor Nikonov](https://github.com/devcrafter)).
* Cleanup match code [#43006](https://github.com/ClickHouse/ClickHouse/pull/43006) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix TSan errors (correctly ignore _exit interception) [#43009](https://github.com/ClickHouse/ClickHouse/pull/43009) ([Azat Khuzhin](https://github.com/azat)).
* fix bandwidth throttlers initialization order [#43015](https://github.com/ClickHouse/ClickHouse/pull/43015) ([Sergei Trifonov](https://github.com/serxa)).
* Add test for issue [#42520](https://github.com/ClickHouse/ClickHouse/issues/42520) [#43027](https://github.com/ClickHouse/ClickHouse/pull/43027) ([Robert Schulze](https://github.com/rschu1ze)).
* Analyzer improve ARRAY JOIN with JOIN [#43048](https://github.com/ClickHouse/ClickHouse/pull/43048) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix projection part removal with zero-copy replication [#43060](https://github.com/ClickHouse/ClickHouse/pull/43060) ([alesapin](https://github.com/alesapin)).
* Fix msan warning [#43065](https://github.com/ClickHouse/ClickHouse/pull/43065) ([Raúl Marín](https://github.com/Algunenano)).
* Analyzer AST key condition crash fix [#43070](https://github.com/ClickHouse/ClickHouse/pull/43070) ([Maksim Kita](https://github.com/kitaisreal)).
* Better logging for mark range filtering on projection parts [#43076](https://github.com/ClickHouse/ClickHouse/pull/43076) ([Duc Canh Le](https://github.com/canhld94)).
* Fix ub type punning [#43088](https://github.com/ClickHouse/ClickHouse/pull/43088) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Analyzer improve aliases support for table expressions [#43089](https://github.com/ClickHouse/ClickHouse/pull/43089) ([Maksim Kita](https://github.com/kitaisreal)).
* Throw not implemented for window frame type 'groups' in analyzer [#43090](https://github.com/ClickHouse/ClickHouse/pull/43090) ([Vladimir C](https://github.com/vdimir)).
* Disable clickhouse local and client non-interactive progress by default. [#43092](https://github.com/ClickHouse/ClickHouse/pull/43092) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Make error message after dropping current user more correct. [#43097](https://github.com/ClickHouse/ClickHouse/pull/43097) ([Vitaly Baranov](https://github.com/vitlibar)).
* More stable test [#43102](https://github.com/ClickHouse/ClickHouse/pull/43102) ([alesapin](https://github.com/alesapin)).
* Rewrite tests for memory overcommit [#43105](https://github.com/ClickHouse/ClickHouse/pull/43105) ([Dmitry Novik](https://github.com/novikd)).
* Fix trailing \n from SQLancer status [#43114](https://github.com/ClickHouse/ClickHouse/pull/43114) ([Ilya Yatsishin](https://github.com/qoega)).
* Fix `test_keeper_four_word_command::test_cmd_stat` [#43115](https://github.com/ClickHouse/ClickHouse/pull/43115) ([Antonio Andelic](https://github.com/antonio2368)).
* Enable keeper fault injection for inserts in functional tests [#43117](https://github.com/ClickHouse/ClickHouse/pull/43117) ([Igor Nikonov](https://github.com/devcrafter)).
* Analyzer aggregation crash fix [#43118](https://github.com/ClickHouse/ClickHouse/pull/43118) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer aggregation totals crash fix [#43119](https://github.com/ClickHouse/ClickHouse/pull/43119) ([Maksim Kita](https://github.com/kitaisreal)).
* Improve commit_status_helper.py [#43121](https://github.com/ClickHouse/ClickHouse/pull/43121) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Skip hash logging on sanitizer builds [#43129](https://github.com/ClickHouse/ClickHouse/pull/43129) ([Raúl Marín](https://github.com/Algunenano)).
* Analyzer improve JOIN with constants [#43141](https://github.com/ClickHouse/ClickHouse/pull/43141) ([Maksim Kita](https://github.com/kitaisreal)).
* Remove POCO_CLICKHOUSE_PATCH [#43146](https://github.com/ClickHouse/ClickHouse/pull/43146) ([Azat Khuzhin](https://github.com/azat)).
* Update CompressionCodecDeflateQpl.cpp [#43150](https://github.com/ClickHouse/ClickHouse/pull/43150) ([Tiaonmmn](https://github.com/Tiaonmmn)).
* Randomize keeper fault injection settings in stress tests [#43187](https://github.com/ClickHouse/ClickHouse/pull/43187) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix for missing columns bug with projections an ALTER UPDATE [#43189](https://github.com/ClickHouse/ClickHouse/pull/43189) ([Alexander Gololobov](https://github.com/davenger)).
* A workaround for LLVM bug, https://github.com/llvm/llvm-project/issues/58633 [#43195](https://github.com/ClickHouse/ClickHouse/pull/43195) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Stop `ConfigReloader` first to avoid data race [#43201](https://github.com/ClickHouse/ClickHouse/pull/43201) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix typo [#43203](https://github.com/ClickHouse/ClickHouse/pull/43203) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Miscellaneous changes [#43206](https://github.com/ClickHouse/ClickHouse/pull/43206) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix flaky 02449_check_dependencies_and_table_shutdown [#43212](https://github.com/ClickHouse/ClickHouse/pull/43212) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Add test to check [#43167](https://github.com/ClickHouse/ClickHouse/issues/43167) for all builds [#43216](https://github.com/ClickHouse/ClickHouse/pull/43216) ([Ilya Yatsishin](https://github.com/qoega)).
* Don't throw if shared ID already created in `StorageReplicatedMergeTree` [#43244](https://github.com/ClickHouse/ClickHouse/pull/43244) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix nullptr dereference in collectScopeValidIdentifiersForTypoCorrection [#43245](https://github.com/ClickHouse/ClickHouse/pull/43245) ([Vladimir C](https://github.com/vdimir)).
* Better message in wait_zookeeper_to_start [#43256](https://github.com/ClickHouse/ClickHouse/pull/43256) ([Vladimir C](https://github.com/vdimir)).
* Make test_global_overcommit_tracker non-parallel [#43266](https://github.com/ClickHouse/ClickHouse/pull/43266) ([Dmitry Novik](https://github.com/novikd)).
* Rename canonicalRand to randCanonical [#43283](https://github.com/ClickHouse/ClickHouse/pull/43283) ([Nikita Taranov](https://github.com/nickitat)).
* check limits for an AST in select parser fuzzer [#43285](https://github.com/ClickHouse/ClickHouse/pull/43285) ([Sema Checherinda](https://github.com/CheSema)).
* Allow autoremoval of old parts if detach_not_byte_identical_parts enabled [#43287](https://github.com/ClickHouse/ClickHouse/pull/43287) ([filimonov](https://github.com/filimonov)).
* `pmod`: compatibility with Spark, better documentation [#43313](https://github.com/ClickHouse/ClickHouse/pull/43313) ([Alexey Milovidov](https://github.com/alexey-milovidov)).

26
docs/changelogs/v22.3.14.18-lts.md Normal file
View File

@ -0,0 +1,26 @@
---
sidebar_position: 1
sidebar_label: 2022
---
# 2022 Changelog
### ClickHouse release v22.3.14.18-lts (642946f61b2) FIXME as compared to v22.3.13.80-lts (e2708b01fba)
#### Bug Fix
* Backported in [#42432](https://github.com/ClickHouse/ClickHouse/issues/42432): - Choose correct aggregation method for LowCardinality with BigInt. [#42342](https://github.com/ClickHouse/ClickHouse/pull/42342) ([Duc Canh Le](https://github.com/canhld94)).
#### Build/Testing/Packaging Improvement
* Backported in [#42328](https://github.com/ClickHouse/ClickHouse/issues/42328): Update cctz to the latest master, update tzdb to 2020e. [#42273](https://github.com/ClickHouse/ClickHouse/pull/42273) ([Dom Del Nano](https://github.com/ddelnano)).
* Backported in [#42358](https://github.com/ClickHouse/ClickHouse/issues/42358): Update tzdata to 2022e to support the new timezone changes. Palestine transitions are now Saturdays at 02:00. Simplify three Ukraine zones into one. Jordan and Syria switch from +02/+03 with DST to year-round +03. (https://data.iana.org/time-zones/tzdb/NEWS). This closes [#42252](https://github.com/ClickHouse/ClickHouse/issues/42252). [#42327](https://github.com/ClickHouse/ClickHouse/pull/42327) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Backported in [#42298](https://github.com/ClickHouse/ClickHouse/issues/42298): Fix a bug with projections and the `aggregate_functions_null_for_empty` setting. This bug is very rare and appears only if you enable the `aggregate_functions_null_for_empty` setting in the server's config. This closes [#41647](https://github.com/ClickHouse/ClickHouse/issues/41647). [#42198](https://github.com/ClickHouse/ClickHouse/pull/42198) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Backported in [#42592](https://github.com/ClickHouse/ClickHouse/issues/42592): This closes [#42453](https://github.com/ClickHouse/ClickHouse/issues/42453). [#42573](https://github.com/ClickHouse/ClickHouse/pull/42573) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Add a warning message to release.py script, require release type [#41975](https://github.com/ClickHouse/ClickHouse/pull/41975) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Revert [#27787](https://github.com/ClickHouse/ClickHouse/issues/27787) [#42136](https://github.com/ClickHouse/ClickHouse/pull/42136) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).

29
docs/changelogs/v22.3.14.23-lts.md Normal file
View File

@ -0,0 +1,29 @@
---
sidebar_position: 1
sidebar_label: 2022
---
# 2022 Changelog
### ClickHouse release v22.3.14.23-lts (74956bfee4d) FIXME as compared to v22.3.13.80-lts (e2708b01fba)
#### Improvement
* Backported in [#42527](https://github.com/ClickHouse/ClickHouse/issues/42527): Fix issue with passing MySQL timeouts for MySQL database engine and MySQL table function. Closes [#34168](https://github.com/ClickHouse/ClickHouse/issues/34168)?notification_referrer_id=NT_kwDOAzsV57MzMDMxNjAzNTY5OjU0MjAzODc5. [#40751](https://github.com/ClickHouse/ClickHouse/pull/40751) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Bug Fix
* Backported in [#42432](https://github.com/ClickHouse/ClickHouse/issues/42432): - Choose correct aggregation method for LowCardinality with BigInt. [#42342](https://github.com/ClickHouse/ClickHouse/pull/42342) ([Duc Canh Le](https://github.com/canhld94)).
#### Build/Testing/Packaging Improvement
* Backported in [#42328](https://github.com/ClickHouse/ClickHouse/issues/42328): Update cctz to the latest master, update tzdb to 2020e. [#42273](https://github.com/ClickHouse/ClickHouse/pull/42273) ([Dom Del Nano](https://github.com/ddelnano)).
* Backported in [#42358](https://github.com/ClickHouse/ClickHouse/issues/42358): Update tzdata to 2022e to support the new timezone changes. Palestine transitions are now Saturdays at 02:00. Simplify three Ukraine zones into one. Jordan and Syria switch from +02/+03 with DST to year-round +03. (https://data.iana.org/time-zones/tzdb/NEWS). This closes [#42252](https://github.com/ClickHouse/ClickHouse/issues/42252). [#42327](https://github.com/ClickHouse/ClickHouse/pull/42327) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Backported in [#42298](https://github.com/ClickHouse/ClickHouse/issues/42298): Fix a bug with projections and the `aggregate_functions_null_for_empty` setting. This bug is very rare and appears only if you enable the `aggregate_functions_null_for_empty` setting in the server's config. This closes [#41647](https://github.com/ClickHouse/ClickHouse/issues/41647). [#42198](https://github.com/ClickHouse/ClickHouse/pull/42198) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Backported in [#42592](https://github.com/ClickHouse/ClickHouse/issues/42592): This closes [#42453](https://github.com/ClickHouse/ClickHouse/issues/42453). [#42573](https://github.com/ClickHouse/ClickHouse/pull/42573) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Add a warning message to release.py script, require release type [#41975](https://github.com/ClickHouse/ClickHouse/pull/41975) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Revert [#27787](https://github.com/ClickHouse/ClickHouse/issues/27787) [#42136](https://github.com/ClickHouse/ClickHouse/pull/42136) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).

31
docs/changelogs/v22.8.9.24-lts.md Normal file
View File

@ -0,0 +1,31 @@
---
sidebar_position: 1
sidebar_label: 2022
---
# 2022 Changelog
### ClickHouse release v22.8.9.24-lts (a1b69551d40) FIXME as compared to v22.8.8.3-lts (ac5a6cababc)
#### Performance Improvement
* Backported in [#43012](https://github.com/ClickHouse/ClickHouse/issues/43012): Keeper performance improvement: improve commit performance for cases when many different nodes have uncommitted states. This should help with cases when a follower node can't sync fast enough. [#42926](https://github.com/ClickHouse/ClickHouse/pull/42926) ([Antonio Andelic](https://github.com/antonio2368)).
#### Improvement
* Backported in [#42840](https://github.com/ClickHouse/ClickHouse/issues/42840): Update tzdata to 2022f. Mexico will no longer observe DST except near the US border: https://www.timeanddate.com/news/time/mexico-abolishes-dst-2022.html. Chihuahua moves to year-round UTC-6 on 2022-10-30. Fiji no longer observes DST. See https://github.com/google/cctz/pull/235 and https://bugs.launchpad.net/ubuntu/+source/tzdata/+bug/1995209. [#42796](https://github.com/ClickHouse/ClickHouse/pull/42796) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### Build/Testing/Packaging Improvement
* Backported in [#42964](https://github.com/ClickHouse/ClickHouse/issues/42964): Before the fix, the user-defined config was preserved by RPM in `$file.rpmsave`. The PR fixes it and won't replace the user's files from packages. [#42936](https://github.com/ClickHouse/ClickHouse/pull/42936) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#43040](https://github.com/ClickHouse/ClickHouse/issues/43040): Add a CI step to mark commits as ready for release; soft-forbid launching a release script from branches but master. [#43017](https://github.com/ClickHouse/ClickHouse/pull/43017) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
#### Bug Fix (user-visible misbehavior in official stable or prestable release)
* Backported in [#42720](https://github.com/ClickHouse/ClickHouse/issues/42720): Fixed `Unknown identifier (aggregate-function)` exception which appears when a user tries to calculate WINDOW ORDER BY/PARTITION BY expressions over aggregate functions: ``` CREATE TABLE default.tenk1 ( `unique1` Int32, `unique2` Int32, `ten` Int32 ) ENGINE = MergeTree ORDER BY tuple() SETTINGS index_granularity = 8192; SELECT ten, sum(unique1) + sum(unique2) AS res, rank() OVER (ORDER BY sum(unique1) + sum(unique2) ASC) AS rank FROM _complex GROUP BY ten ORDER BY ten ASC; ``` which gives: ``` Code: 47. DB::Exception: Received from localhost:9000. DB::Exception: Unknown identifier: sum(unique1); there are columns: unique1, unique2, ten: While processing sum(unique1) + sum(unique2) ASC. (UNKNOWN_IDENTIFIER) ```. [#39762](https://github.com/ClickHouse/ClickHouse/pull/39762) ([Vladimir Chebotaryov](https://github.com/quickhouse)).
* Backported in [#42748](https://github.com/ClickHouse/ClickHouse/issues/42748): A segmentation fault related to DNS & c-ares has been reported. The below error ocurred in multiple threads: ``` 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008088 [ 356 ] {} <Fatal> BaseDaemon: ######################################## 2022-09-28 15:41:19.008,"2022.09.28 15:41:19.008147 [ 356 ] {} <Fatal> BaseDaemon: (version 22.8.5.29 (official build), build id: 92504ACA0B8E2267) (from thread 353) (no query) Received signal Segmentation fault (11)" 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008196 [ 356 ] {} <Fatal> BaseDaemon: Address: 0xf Access: write. Address not mapped to object. 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008216 [ 356 ] {} <Fatal> BaseDaemon: Stack trace: 0x188f8212 0x1626851b 0x1626a69e 0x16269b3f 0x16267eab 0x13cf8284 0x13d24afc 0x13c5217e 0x14ec2495 0x15ba440f 0x15b9d13b 0x15bb2699 0x1891ccb3 0x1891e00d 0x18ae0769 0x18ade022 0x7f76aa985609 0x7f76aa8aa133 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008274 [ 356 ] {} <Fatal> BaseDaemon: 2. Poco::Net::IPAddress::family() const @ 0x188f8212 in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008297 [ 356 ] {} <Fatal> BaseDaemon: 3. ? @ 0x1626851b in /usr/bin/clickhouse 2022-09-28 15:41:19.008,2022.09.28 15:41:19.008309 [ 356 ] {} <Fatal> BaseDaemon: 4. ? @ 0x1626a69e in /usr/bin/clickhouse ```. [#42234](https://github.com/ClickHouse/ClickHouse/pull/42234) ([Arthur Passos](https://github.com/arthurpassos)).
* Backported in [#43062](https://github.com/ClickHouse/ClickHouse/issues/43062): Fix rare NOT_FOUND_COLUMN_IN_BLOCK error when projection is possible to use but there is no projection available. This fixes [#42771](https://github.com/ClickHouse/ClickHouse/issues/42771) . The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/25563. [#42938](https://github.com/ClickHouse/ClickHouse/pull/42938) ([Amos Bird](https://github.com/amosbird)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Do not warn about kvm-clock [#41217](https://github.com/ClickHouse/ClickHouse/pull/41217) ([Sergei Trifonov](https://github.com/serxa)).
* Revert revert 41268 disable s3 parallel write for part moves to disk s3 [#42617](https://github.com/ClickHouse/ClickHouse/pull/42617) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Always run `BuilderReport` and `BuilderSpecialReport` in all CI types [#42684](https://github.com/ClickHouse/ClickHouse/pull/42684) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).

2
docs/en/development/build.md
View File

@ -105,7 +105,7 @@ ninja
Example for Fedora Rawhide:
``` bash
sudo yum update
yum --nogpg install git cmake make clang-c++ python3
sudo yum --nogpg install git cmake make clang python3 ccache
git clone --recursive https://github.com/ClickHouse/ClickHouse.git
mkdir build && cd build
cmake ../ClickHouse

78
docs/en/engines/database-engines/materialized-mysql.md
View File

@ -77,15 +77,15 @@ While turning on `gtid_mode` you should also specify `enforce_gtid_consistency =
## Virtual Columns {#virtual-columns}
When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
### \_version
`_version` — Transaction counter. Type [UInt64](../../sql-reference/data-types/int-uint.md).
`_version` — Transaction counter. Type [UInt64](/docs/en/sql-reference/data-types/int-uint.md).
### \_sign
`_sign` — Deletion mark. Type [Int8](../../sql-reference/data-types/int-uint.md). Possible values:
`_sign` — Deletion mark. Type [Int8](/docs/en/sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `-1` — Row is deleted.
@ -93,29 +93,29 @@ When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](
| MySQL | ClickHouse |
|-------------------------|--------------------------------------------------------------|
| TINY | [Int8](../../sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](../../sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](../../sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](../../sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](../../sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](../../sql-reference/data-types/float.md) |
| DOUBLE | [Float64](../../sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](../../sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](../../sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](../../sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](../../sql-reference/data-types/datetime64.md) |
| YEAR | [UInt16](../../sql-reference/data-types/int-uint.md) |
| TIME | [Int64](../../sql-reference/data-types/int-uint.md) |
| ENUM | [Enum](../../sql-reference/data-types/enum.md) |
| STRING | [String](../../sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) |
| BLOB | [String](../../sql-reference/data-types/string.md) |
| GEOMETRY | [String](../../sql-reference/data-types/string.md) |
| BINARY | [FixedString](../../sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](../../sql-reference/data-types/int-uint.md) |
| SET | [UInt64](../../sql-reference/data-types/int-uint.md) |
| TINY | [Int8](/docs/en/sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](/docs/en/sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](/docs/en/sql-reference/data-types/float.md) |
| DOUBLE | [Float64](/docs/en/sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](/docs/en/sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](/docs/en/sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](/docs/en/sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| YEAR | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) |
| TIME | [Int64](/docs/en/sql-reference/data-types/int-uint.md) |
| ENUM | [Enum](/docs/en/sql-reference/data-types/enum.md) |
| STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| BLOB | [String](/docs/en/sql-reference/data-types/string.md) |
| GEOMETRY | [String](/docs/en/sql-reference/data-types/string.md) |
| BINARY | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| SET | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
[Nullable](../../sql-reference/data-types/nullable.md) is supported.
[Nullable](/docs/en/sql-reference/data-types/nullable.md) is supported.
The data of TIME type in MySQL is converted to microseconds in ClickHouse.
@ -133,7 +133,7 @@ Apart of the data types limitations there are few restrictions comparing to `MyS
### DDL Queries {#ddl-queries}
MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([ALTER](../../sql-reference/statements/alter/index.md), [CREATE](../../sql-reference/statements/create/index.md), [DROP](../../sql-reference/statements/drop), [RENAME](../../sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([ALTER](/docs/en/sql-reference/statements/alter/index.md), [CREATE](/docs/en/sql-reference/statements/create/index.md), [DROP](/docs/en/sql-reference/statements/drop.md), [RENAME](/docs/en/sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
### Data Replication {#data-replication}
@ -151,7 +151,7 @@ MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([
`SELECT` query from `MaterializedMySQL` tables has some specifics:
- If `_version` is not specified in the `SELECT` query, the
[FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier is used, so only rows with
[FINAL](/docs/en/sql-reference/statements/select/from.md/#select-from-final) modifier is used, so only rows with
`MAX(_version)` are returned for each primary key value.
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not
@ -164,7 +164,7 @@ MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([
MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in ClickHouse tables.
ClickHouse has only one physical order, which is determined by `ORDER BY` clause. To create a new physical order, use
[materialized views](../../sql-reference/statements/create/view.md#materialized).
[materialized views](/docs/en/sql-reference/statements/create/view.md/#materialized).
**Notes**
@ -173,7 +173,7 @@ ClickHouse has only one physical order, which is determined by `ORDER BY` clause
MySQL binlog.
- Replication can be easily broken.
- Manual operations on database and tables are forbidden.
- `MaterializedMySQL` is affected by the [optimize_on_insert](../../operations/settings/settings.md#optimize-on-insert)
- `MaterializedMySQL` is affected by the [optimize_on_insert](/docs/en/operations/settings/settings.md/#optimize-on-insert)
setting. Data is merged in the corresponding table in the `MaterializedMySQL` database when a table in the MySQL
server changes.
@ -187,19 +187,19 @@ These are the schema conversion manipulations you can do with table overrides fo
* Modify column type. Must be compatible with the original type, or replication will fail. For example,
you can modify a UInt32 column to UInt64, but you can not modify a String column to Array(String).
* Modify [column TTL](../table-engines/mergetree-family/mergetree/#mergetree-column-ttl).
* Modify [column compression codec](../../sql-reference/statements/create/table/#codecs).
* Add [ALIAS columns](../../sql-reference/statements/create/table/#alias).
* Add [skipping indexes](../table-engines/mergetree-family/mergetree/#table_engine-mergetree-data_skipping-indexes)
* Add [projections](../table-engines/mergetree-family/mergetree/#projections). Note that projection optimizations are
* Modify [column TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-column-ttl).
* Modify [column compression codec](/docs/en/sql-reference/statements/create/table.md/#codecs).
* Add [ALIAS columns](/docs/en/sql-reference/statements/create/table.md/#alias).
* Add [skipping indexes](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-data_skipping-indexes)
* Add [projections](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#projections). Note that projection optimizations are
disabled when using `SELECT ... FINAL` (which MaterializedMySQL does by default), so their utility is limited here.
`INDEX ... TYPE hypothesis` as [described in the v21.12 blog post]](https://clickhouse.com/blog/en/2021/clickhouse-v21.12-released/)
may be more useful in this case.
* Modify [PARTITION BY](../table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Modify [PRIMARY KEY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [SAMPLE BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [table TTL](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Modify [PARTITION BY](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Modify [PRIMARY KEY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [SAMPLE BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [table TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
```sql
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)

2
docs/en/engines/database-engines/replicated.md
View File

@ -86,7 +86,7 @@ node1 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY
``` text
┌─hosts─┬─groupArray(n)─┐
│ node1 │ [1,3,5,7,9] │
│ node3 │ [1,3,5,7,9] │
│ node2 │ [0,2,4,6,8] │
└───────┴───────────────┘
```

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

@ -6,7 +6,7 @@ sidebar_label: Integrations
# Table Engines for Integrations
ClickHouse provides various means for integrating with external systems, including table engines. Like with all other table engines, the configuration is done using `CREATE TABLE` or `ALTER TABLE` queries. Then from a user perspective, the configured integration looks like a normal table, but queries to it are proxied to the external system. This transparent querying is one of the key advantages of this approach over alternative integration methods, like external dictionaries or table functions, which require to use custom query methods on each use.
ClickHouse provides various means for integrating with external systems, including table engines. Like with all other table engines, the configuration is done using `CREATE TABLE` or `ALTER TABLE` queries. Then from a user perspective, the configured integration looks like a normal table, but queries to it are proxied to the external system. This transparent querying is one of the key advantages of this approach over alternative integration methods, like dictionaries or table functions, which require to use custom query methods on each use.
List of supported integrations:

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

@ -180,6 +180,6 @@ Default value: `300`.
## See Also {#see-also}
- [The mysql table function](../../../sql-reference/table-functions/mysql.md)
- [Using MySQL as a source of external dictionary](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-mysql)
- [Using MySQL as a dictionary source](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-mysql)
[Original article](https://clickhouse.com/docs/en/engines/table-engines/integrations/mysql/) <!--hide-->

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

@ -126,7 +126,7 @@ SELECT * FROM odbc_t
## See Also {#see-also}
- [ODBC external dictionaries](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-odbc)
- [ODBC dictionaries](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-odbc)
- [ODBC table function](../../../sql-reference/table-functions/odbc.md)
[Original article](https://clickhouse.com/docs/en/engines/table-engines/integrations/odbc/) <!--hide-->

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

@ -174,6 +174,6 @@ CREATE TABLE pg_table_schema_with_dots (a UInt32)
**See Also**
- [The `postgresql` table function](../../../sql-reference/table-functions/postgresql.md)
- [Using PostgreSQL as a source of external dictionary](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-postgresql)
- [Using PostgreSQL as a dictionary source](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-postgresql)
[Original article](https://clickhouse.com/docs/en/engines/table-engines/integrations/postgresql/) <!--hide-->

7
docs/en/engines/table-engines/integrations/s3.md
View File

@ -127,6 +127,10 @@ The following settings can be set before query execution or placed into configur
- `s3_min_upload_part_size` — The minimum size of part to upload during multipart upload to [S3 Multipart upload](https://docs.aws.amazon.com/AmazonS3/latest/dev/uploadobjusingmpu.html). Default value is `512Mb`.
- `s3_max_redirects` — Max number of S3 redirects hops allowed. Default value is `10`.
- `s3_single_read_retries` — The maximum number of attempts during single read. Default value is `4`.
- `s3_max_put_rps` — Maximum PUT requests per second rate before throttling. Default value is `0` (unlimited).
- `s3_max_put_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_put_rps`.
- `s3_max_get_rps` — Maximum GET requests per second rate before throttling. Default value is `0` (unlimited).
- `s3_max_get_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_get_rps`.
Security consideration: if malicious user can specify arbitrary S3 URLs, `s3_max_redirects` must be set to zero to avoid [SSRF](https://en.wikipedia.org/wiki/Server-side_request_forgery) attacks; or alternatively, `remote_host_filter` must be specified in server configuration.
@ -139,9 +143,10 @@ The following settings can be specified in configuration file for given endpoint
- `use_environment_credentials` — If set to `true`, S3 client will try to obtain credentials from environment variables and [Amazon EC2](https://en.wikipedia.org/wiki/Amazon_Elastic_Compute_Cloud) metadata for given endpoint. Optional, default value is `false`.
- `region` — Specifies S3 region name. Optional.
- `use_insecure_imds_request` — If set to `true`, S3 client will use insecure IMDS request while obtaining credentials from Amazon EC2 metadata. Optional, default value is `false`.
- `header` — Adds specified HTTP header to a request to given endpoint. Optional, can be speficied multiple times.
- `header` — Adds specified HTTP header to a request to given endpoint. Optional, can be specified multiple times.
- `server_side_encryption_customer_key_base64` — If specified, required headers for accessing S3 objects with SSE-C encryption will be set. Optional.
- `max_single_read_retries` — The maximum number of attempts during single read. Default value is `4`. Optional.
- `max_put_rps`, `max_put_burst`, `max_get_rps` and `max_get_burst` - Throttling settings (see description above) to use for specific endpoint instead of per query. Optional.
**Example:**

10
docs/en/engines/table-engines/log-family/index.md
View File

@ -10,11 +10,11 @@ These engines were developed for scenarios when you need to quickly write many s
Engines of the family:
- [StripeLog](../../../engines/table-engines/log-family/stripelog.md)
- [Log](../../../engines/table-engines/log-family/log.md)
- [TinyLog](../../../engines/table-engines/log-family/tinylog.md)
- [StripeLog](/docs/en/engines/table-engines/log-family/stripelog.md)
- [Log](/docs/en/engines/table-engines/log-family/log.md)
- [TinyLog](/docs/en/engines/table-engines/log-family/tinylog.md)
`Log` family table engines can store data to [HDFS](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-hdfs) or [S3](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-s3) distributed file systems.
`Log` family table engines can store data to [HDFS](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-hdfs) or [S3](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3) distributed file systems.
## Common Properties {#common-properties}
@ -28,7 +28,7 @@ Engines:
During `INSERT` queries, the table is locked, and other queries for reading and writing data both wait for the table to unlock. If there are no data writing queries, any number of data reading queries can be performed concurrently.
- Do not support [mutations](../../../sql-reference/statements/alter/index.md#alter-mutations).
- Do not support [mutations](/docs/en/sql-reference/statements/alter/index.md#alter-mutations).
- Do not support indexes.

41
docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md
View File

@ -68,36 +68,57 @@ In the results of `SELECT` query, the values of `AggregateFunction` type have im
## Example of an Aggregated Materialized View {#example-of-an-aggregated-materialized-view}
`AggregatingMergeTree` materialized view that watches the `test.visits` table:
We will create the table `test.visits` that contain the raw data:
``` sql
CREATE MATERIALIZED VIEW test.basic
ENGINE = AggregatingMergeTree() PARTITION BY toYYYYMM(StartDate) ORDER BY (CounterID, StartDate)
CREATE TABLE test.visits
(
StartDate DateTime64 NOT NULL,
CounterID UInt64,
Sign Nullable(Int32),
UserID Nullable(Int32)
) ENGINE = MergeTree ORDER BY (StartDate, CounterID);
```
`AggregatingMergeTree` materialized view that watches the `test.visits` table, and use the `AggregateFunction` type:
``` sql
CREATE MATERIALIZED VIEW test.mv_visits
(
StartDate DateTime64 NOT NULL,
CounterID UInt64,
Visits AggregateFunction(sum, Nullable(Int32)),
Users AggregateFunction(uniq, Nullable(Int32))
)
ENGINE = AggregatingMergeTree() ORDER BY (StartDate, CounterID)
AS SELECT
CounterID,
StartDate,
sumState(Sign) AS Visits,
CounterID,
sumState(Sign) AS Visits,
uniqState(UserID) AS Users
FROM test.visits
GROUP BY CounterID, StartDate;
GROUP BY StartDate, CounterID;
```
Inserting data into the `test.visits` table.
``` sql
INSERT INTO test.visits ...
INSERT INTO test.visits (StartDate, CounterID, Sign, UserID)
VALUES (1667446031, 1, 3, 4)
INSERT INTO test.visits (StartDate, CounterID, Sign, UserID)
VALUES (1667446031, 1, 6, 3)
```
The data are inserted in both the table and view `test.basic` that will perform the aggregation.
The data are inserted in both the table and the materialized view `test.mv_visits`.
To get the aggregated data, we need to execute a query such as `SELECT ... GROUP BY ...` from the view `test.basic`:
To get the aggregated data, we need to execute a query such as `SELECT ... GROUP BY ...` from the materialized view `test.mv_visits`:
``` sql
SELECT
StartDate,
sumMerge(Visits) AS Visits,
uniqMerge(Users) AS Users
FROM test.basic
FROM test.mv_visits
GROUP BY StartDate
ORDER BY StartDate;
```

60
docs/en/engines/table-engines/mergetree-family/annindexes.md
View File

@ -2,13 +2,20 @@
The main task that indexes achieve is to quickly find nearest neighbors for multidimensional data. An example of such a problem can be finding similar pictures (texts) for a given picture (text). That problem can be reduced to finding the nearest [embeddings](https://cloud.google.com/architecture/overview-extracting-and-serving-feature-embeddings-for-machine-learning). They can be created from data using [UDF](../../../sql-reference/functions/index.md#executable-user-defined-functions).
The next query finds the closest neighbors in N-dimensional space using the L2 (Euclidean) distance:
The next queries find the closest neighbors in N-dimensional space using the L2 (Euclidean) distance:
``` sql
SELECT *
FROM table_name
WHERE L2Distance(Column, Point) < MaxDistance
LIMIT N
```
``` sql
SELECT *
FROM table_name
ORDER BY L2Distance(Column, Point)
LIMIT N
```
But it will take some time for execution because of the long calculation of the distance between `TargetEmbedding` and all other vectors. This is where ANN indexes can help. They store a compact approximation of the search space (e.g. using clustering, search trees, etc.) and are able to compute approximate neighbors quickly.
## Indexes Structure
@ -34,26 +41,27 @@ Approximate Nearest Neighbor Search Indexes (`ANNIndexes`) are similar to skip i
In these queries, `DistanceFunction` is selected from [distance functions](../../../sql-reference/functions/distance-functions). `Point` is a known vector (something like `(0.1, 0.1, ... )`). To avoid writing large vectors, use [client parameters](../../../interfaces/cli.md#queries-with-parameters-cli-queries-with-parameters). `Value` - a float value that will bound the neighbourhood.
!!! note "Note"
ANN index can't speed up query that satisfies both types(`where + order by`, only one of them). All queries must have the limit, as algorithms are used to find nearest neighbors and need a specific number of them.
:::note
ANN index can't speed up query that satisfies both types (`where + order by`, only one of them). All queries must have the limit, as algorithms are used to find nearest neighbors and need a specific number of them.
:::
!!! note "Note"
Indexes are applied only to queries with a limit less than the `max_limit_for_ann_queries` setting. This helps to avoid memory overflows in queries with a large limit. `max_limit_for_ann_queries` setting can be changed if you know you can provide enough memory. The default value is `1000000`.
:::note
Indexes are applied only to queries with a limit less than the `max_limit_for_ann_queries` setting. This helps to avoid memory overflows in queries with a large limit. `max_limit_for_ann_queries` setting can be changed if you know you can provide enough memory. The default value is `1000000`.
:::
Both types of queries are handled the same way. The indexes get `n` neighbors (where `n` is taken from the `LIMIT` clause) and work with them. In `ORDER BY` query they remember the numbers of all parts of the granule that have at least one of neighbor. In `WHERE` query they remember only those parts that satisfy the requirements.
## Create table with ANNIndex
This feature is disabled by default. To enable it, set `allow_experimental_annoy_index` to 1. Also, this feature is disabled for arm, due to likely problems with the algorithm.
This feature is disabled by default. To enable it, set `allow_experimental_annoy_index` to 1. Also, this feature is disabled on ARM, due to likely problems with the algorithm.
```sql
CREATE TABLE t
(
`id` Int64,
`number` Tuple(Float32, Float32, Float32),
INDEX x number TYPE annoy GRANULARITY N
`data` Tuple(Float32, Float32, Float32),
INDEX ann_index_name data TYPE ann_index_type(ann_index_parameters) GRANULARITY N
)
ENGINE = MergeTree
ORDER BY id;
@ -63,8 +71,8 @@ ORDER BY id;
CREATE TABLE t
(
`id` Int64,
`number` Array(Float32),
INDEX x number TYPE annoy GRANULARITY N
`data` Array(Float32),
INDEX ann_index_name data TYPE ann_index_type(ann_index_parameters) GRANULARITY N
)
ENGINE = MergeTree
ORDER BY id;
@ -73,7 +81,7 @@ ORDER BY id;
With greater `GRANULARITY` indexes remember the data structure better. The `GRANULARITY` indicates how many granules will be used to construct the index. The more data is provided for the index, the more of it can be handled by one index and the more chances that with the right hyperparameters the index will remember the data structure better. But some indexes can't be built if they don't have enough data, so this granule will always participate in the query. For more information, see the description of indexes.
As the indexes are built only during insertions into table, `INSERT` and `OPTIMIZE` queries are slower than for ordinary table. At this stage indexes remember all the information about the given data. ANNIndexes should be used if you have immutable or rarely changed data and many read requests.
You can create your table with index which uses certain algorithm. Now only indices based on the following algorithms are supported:
# Index list
@ -91,8 +99,8 @@ __Examples__:
CREATE TABLE t
(
id Int64,
number Tuple(Float32, Float32, Float32),
INDEX x number TYPE annoy(T) GRANULARITY N
data Tuple(Float32, Float32, Float32),
INDEX ann_index_name data TYPE annoy(NumTrees, DistanceName) GRANULARITY N
)
ENGINE = MergeTree
ORDER BY id;
@ -102,18 +110,30 @@ ORDER BY id;
CREATE TABLE t
(
id Int64,
number Array(Float32),
INDEX x number TYPE annoy(T) GRANULARITY N
data Array(Float32),
INDEX ann_index_name data TYPE annoy(NumTrees, DistanceName) GRANULARITY N
)
ENGINE = MergeTree
ORDER BY id;
```
!!! note "Note"
Table with array field will work faster, but all arrays **must** have same length. Use [CONSTRAINT](../../../sql-reference/statements/create/table.md#constraints) to avoid errors. For example, `CONSTRAINT constraint_name_1 CHECK length(number) = 256`.
Parameter `T` is the number of trees which algorithm will create. The bigger it is, the slower (approximately linear) it works (in both `CREATE` and `SELECT` requests), but the better accuracy you get (adjusted for randomness).
:::note
Table with array field will work faster, but all arrays **must** have same length. Use [CONSTRAINT](../../../sql-reference/statements/create/table.md#constraints) to avoid errors. For example, `CONSTRAINT constraint_name_1 CHECK length(data) = 256`.
:::
Annoy supports only `L2Distance`.
Parameter `NumTrees` is the number of trees which the algorithm will create. The bigger it is, the slower (approximately linear) it works (in both `CREATE` and `SELECT` requests), but the better accuracy you get (adjusted for randomness). By default it is set to `100`. Parameter `DistanceName` is name of distance function. By default it is set to `L2Distance`. It can be set without changing first parameter, for example
```sql
CREATE TABLE t
(
id Int64,
data Array(Float32),
INDEX ann_index_name data TYPE annoy('cosineDistance') GRANULARITY N
)
ENGINE = MergeTree
ORDER BY id;
```
Annoy supports `L2Distance` and `cosineDistance`.
In the `SELECT` in the settings (`ann_index_select_query_params`) you can specify the size of the internal buffer (more details in the description above or in the [original repository](https://github.com/spotify/annoy)). During the query it will inspect up to `search_k` nodes which defaults to `n_trees * n` if not provided. `search_k` gives you a run-time tradeoff between better accuracy and speed.

118
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -16,20 +16,20 @@ Main features:
This allows you to create a small sparse index that helps find data faster.
- Partitions can be used if the [partitioning key](../../../engines/table-engines/mergetree-family/custom-partitioning-key.md) is specified.
- Partitions can be used if the [partitioning key](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md) is specified.
ClickHouse supports certain operations with partitions that are more efficient than general operations on the same data with the same result. ClickHouse also automatically cuts off the partition data where the partitioning key is specified in the query.
- Data replication support.
The family of `ReplicatedMergeTree` tables provides data replication. For more information, see [Data replication](../../../engines/table-engines/mergetree-family/replication.md).
The family of `ReplicatedMergeTree` tables provides data replication. For more information, see [Data replication](/docs/en/engines/table-engines/mergetree-family/replication.md).
- Data sampling support.
If necessary, you can set the data sampling method in the table.
:::info
The [Merge](../../../engines/table-engines/special/merge.md#merge) engine does not belong to the `*MergeTree` family.
The [Merge](/docs/en/engines/table-engines/special/merge.md/#merge) engine does not belong to the `*MergeTree` family.
:::
## Creating a Table {#table_engine-mergetree-creating-a-table}
@ -57,7 +57,7 @@ ORDER BY expr
[SETTINGS name=value, ...]
```
For a description of parameters, see the [CREATE query description](../../../sql-reference/statements/create/table.md).
For a description of parameters, see the [CREATE query description](/docs/en/sql-reference/statements/create/table.md).
### Query Clauses {#mergetree-query-clauses}
@ -77,9 +77,9 @@ Use the `ORDER BY tuple()` syntax, if you do not need sorting. See [Selecting th
#### PARTITION BY
`PARTITION BY` — The [partitioning key](../../../engines/table-engines/mergetree-family/custom-partitioning-key.md). Optional. In most cases you don't need partition key, and in most other cases you don't need partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression). You should never use too granular partitioning. Don't partition your data by client identifiers or names (instead make client identifier or name the first column in the ORDER BY expression).
`PARTITION BY` — The [partitioning key](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md). Optional. In most cases you don't need partition key, and in most other cases you don't need partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression). You should never use too granular partitioning. Don't partition your data by client identifiers or names (instead make client identifier or name the first column in the ORDER BY expression).
For partitioning by month, use the `toYYYYMM(date_column)` expression, where `date_column` is a column with a date of the type [Date](../../../sql-reference/data-types/date.md). The partition names here have the `"YYYYMM"` format.
For partitioning by month, use the `toYYYYMM(date_column)` expression, where `date_column` is a column with a date of the type [Date](/docs/en/sql-reference/data-types/date.md). The partition names here have the `"YYYYMM"` format.
#### PRIMARY KEY
@ -127,7 +127,7 @@ Additional parameters that control the behavior of the `MergeTree` (optional):
#### use_minimalistic_part_header_in_zookeeper
`use_minimalistic_part_header_in_zookeeper` — Storage method of the data parts headers in ZooKeeper. If `use_minimalistic_part_header_in_zookeeper=1`, then ZooKeeper stores less data. For more information, see the [setting description](../../../operations/server-configuration-parameters/settings.md#server-settings-use_minimalistic_part_header_in_zookeeper) in “Server configuration parameters”.
`use_minimalistic_part_header_in_zookeeper` — Storage method of the data parts headers in ZooKeeper. If `use_minimalistic_part_header_in_zookeeper=1`, then ZooKeeper stores less data. For more information, see the [setting description](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings-use_minimalistic_part_header_in_zookeeper) in “Server configuration parameters”.
#### min_merge_bytes_to_use_direct_io
@ -166,15 +166,15 @@ Additional parameters that control the behavior of the `MergeTree` (optional):
#### max_compress_block_size
`max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](../../../operations/settings/settings.md#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
`max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](/docs/en/operations/settings/settings.md/#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
#### min_compress_block_size
`min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](../../../operations/settings/settings.md#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
`min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](/docs/en/operations/settings/settings.md/#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
#### max_partitions_to_read
`max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](../../../operations/settings/merge-tree-settings.md#max-partitions-to-read) in the global setting.
`max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](/docs/en/operations/settings/merge-tree-settings.md/#max-partitions-to-read) in the global setting.
**Example of Sections Setting**
@ -184,7 +184,7 @@ ENGINE MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDa
In the example, we set partitioning by month.
We also set an expression for sampling as a hash by the user ID. This allows you to pseudorandomize the data in the table for each `CounterID` and `EventDate`. If you define a [SAMPLE](../../../sql-reference/statements/select/sample.md#select-sample-clause) clause when selecting the data, ClickHouse will return an evenly pseudorandom data sample for a subset of users.
We also set an expression for sampling as a hash by the user ID. This allows you to pseudorandomize the data in the table for each `CounterID` and `EventDate`. If you define a [SAMPLE](/docs/en/sql-reference/statements/select/sample.md/#select-sample-clause) clause when selecting the data, ClickHouse will return an evenly pseudorandom data sample for a subset of users.
The `index_granularity` setting can be omitted because 8192 is the default value.
@ -207,9 +207,9 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
**MergeTree() Parameters**
- `date-column` — The name of a column of the [Date](../../../sql-reference/data-types/date.md) type. ClickHouse automatically creates partitions by month based on this column. The partition names are in the `"YYYYMM"` format.
- `date-column` — The name of a column of the [Date](/docs/en/sql-reference/data-types/date.md) type. ClickHouse automatically creates partitions by month based on this column. The partition names are in the `"YYYYMM"` format.
- `sampling_expression` — An expression for sampling.
- `(primary, key)` — Primary key. Type: [Tuple()](../../../sql-reference/data-types/tuple.md)
- `(primary, key)` — Primary key. Type: [Tuple()](/docs/en/sql-reference/data-types/tuple.md)
- `index_granularity` — The granularity of an index. The number of data rows between the “marks” of an index. The value 8192 is appropriate for most tasks.
**Example**
@ -262,7 +262,7 @@ Sparse indexes allow you to work with a very large number of table rows, because
ClickHouse does not require a unique primary key. You can insert multiple rows with the same primary key.
You can use `Nullable`-typed expressions in the `PRIMARY KEY` and `ORDER BY` clauses but it is strongly discouraged. To allow this feature, turn on the [allow_nullable_key](../../../operations/settings/settings.md#allow-nullable-key) setting. The [NULLS_LAST](../../../sql-reference/statements/select/order-by.md#sorting-of-special-values) principle applies for `NULL` values in the `ORDER BY` clause.
You can use `Nullable`-typed expressions in the `PRIMARY KEY` and `ORDER BY` clauses but it is strongly discouraged. To allow this feature, turn on the [allow_nullable_key](/docs/en/operations/settings/settings.md/#allow-nullable-key) setting. The [NULLS_LAST](/docs/en/sql-reference/statements/select/order-by.md/#sorting-of-special-values) principle applies for `NULL` values in the `ORDER BY` clause.
### Selecting the Primary Key {#selecting-the-primary-key}
@ -279,26 +279,26 @@ The number of columns in the primary key is not explicitly limited. Depending on
ClickHouse sorts data by primary key, so the higher the consistency, the better the compression.
- Provide additional logic when merging data parts in the [CollapsingMergeTree](../../../engines/table-engines/mergetree-family/collapsingmergetree.md#table_engine-collapsingmergetree) and [SummingMergeTree](../../../engines/table-engines/mergetree-family/summingmergetree.md) engines.
- Provide additional logic when merging data parts in the [CollapsingMergeTree](/docs/en/engines/table-engines/mergetree-family/collapsingmergetree.md/#table_engine-collapsingmergetree) and [SummingMergeTree](/docs/en/engines/table-engines/mergetree-family/summingmergetree.md) engines.
In this case it makes sense to specify the *sorting key* that is different from the primary key.
A long primary key will negatively affect the insert performance and memory consumption, but extra columns in the primary key do not affect ClickHouse performance during `SELECT` queries.
You can create a table without a primary key using the `ORDER BY tuple()` syntax. In this case, ClickHouse stores data in the order of inserting. If you want to save data order when inserting data by `INSERT ... SELECT` queries, set [max_insert_threads = 1](../../../operations/settings/settings.md#settings-max-insert-threads).
You can create a table without a primary key using the `ORDER BY tuple()` syntax. In this case, ClickHouse stores data in the order of inserting. If you want to save data order when inserting data by `INSERT ... SELECT` queries, set [max_insert_threads = 1](/docs/en/operations/settings/settings.md/#settings-max-insert-threads).
To select data in the initial order, use [single-threaded](../../../operations/settings/settings.md#settings-max_threads) `SELECT` queries.
To select data in the initial order, use [single-threaded](/docs/en/operations/settings/settings.md/#settings-max_threads) `SELECT` queries.
### Choosing a Primary Key that Differs from the Sorting Key {#choosing-a-primary-key-that-differs-from-the-sorting-key}
It is possible to specify a primary key (an expression with values that are written in the index file for each mark) that is different from the sorting key (an expression for sorting the rows in data parts). In this case the primary key expression tuple must be a prefix of the sorting key expression tuple.
This feature is helpful when using the [SummingMergeTree](../../../engines/table-engines/mergetree-family/summingmergetree.md) and
[AggregatingMergeTree](../../../engines/table-engines/mergetree-family/aggregatingmergetree.md) table engines. In a common case when using these engines, the table has two types of columns: *dimensions* and *measures*. Typical queries aggregate values of measure columns with arbitrary `GROUP BY` and filtering by dimensions. Because SummingMergeTree and AggregatingMergeTree aggregate rows with the same value of the sorting key, it is natural to add all dimensions to it. As a result, the key expression consists of a long list of columns and this list must be frequently updated with newly added dimensions.
This feature is helpful when using the [SummingMergeTree](/docs/en/engines/table-engines/mergetree-family/summingmergetree.md) and
[AggregatingMergeTree](/docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md) table engines. In a common case when using these engines, the table has two types of columns: *dimensions* and *measures*. Typical queries aggregate values of measure columns with arbitrary `GROUP BY` and filtering by dimensions. Because SummingMergeTree and AggregatingMergeTree aggregate rows with the same value of the sorting key, it is natural to add all dimensions to it. As a result, the key expression consists of a long list of columns and this list must be frequently updated with newly added dimensions.
In this case it makes sense to leave only a few columns in the primary key that will provide efficient range scans and add the remaining dimension columns to the sorting key tuple.
[ALTER](../../../sql-reference/statements/alter/index.md) of the sorting key is a lightweight operation because when a new column is simultaneously added to the table and to the sorting key, existing data parts do not need to be changed. Since the old sorting key is a prefix of the new sorting key and there is no data in the newly added column, the data is sorted by both the old and new sorting keys at the moment of table modification.
[ALTER](/docs/en/sql-reference/statements/alter/index.md) of the sorting key is a lightweight operation because when a new column is simultaneously added to the table and to the sorting key, existing data parts do not need to be changed. Since the old sorting key is a prefix of the new sorting key and there is no data in the newly added column, the data is sorted by both the old and new sorting keys at the moment of table modification.
### Use of Indexes and Partitions in Queries {#use-of-indexes-and-partitions-in-queries}
@ -342,7 +342,7 @@ In the example below, the index can’t be used.
SELECT count() FROM table WHERE CounterID = 34 OR URL LIKE '%upyachka%'
```
To check whether ClickHouse can use the index when running a query, use the settings [force_index_by_date](../../../operations/settings/settings.md#settings-force_index_by_date) and [force_primary_key](../../../operations/settings/settings.md#force-primary-key).
To check whether ClickHouse can use the index when running a query, use the settings [force_index_by_date](/docs/en/operations/settings/settings.md/#settings-force_index_by_date) and [force_primary_key](/docs/en/operations/settings/settings.md/#force-primary-key).
The key for partitioning by month allows reading only those data blocks which contain dates from the proper range. In this case, the data block may contain data for many dates (up to an entire month). Within a block, data is sorted by primary key, which might not contain the date as the first column. Because of this, using a query with only a date condition that does not specify the primary key prefix will cause more data to be read than for a single date.
@ -400,7 +400,7 @@ Stores unique values of the specified expression (no more than `max_rows` rows,
#### `ngrambf_v1(n, size_of_bloom_filter_in_bytes, number_of_hash_functions, random_seed)`
Stores a [Bloom filter](https://en.wikipedia.org/wiki/Bloom_filter) that contains all ngrams from a block of data. Works only with datatypes: [String](../../../sql-reference/data-types/string.md), [FixedString](../../../sql-reference/data-types/fixedstring.md) and [Map](../../../sql-reference/data-types/map.md). Can be used for optimization of `EQUALS`, `LIKE` and `IN` expressions.
Stores a [Bloom filter](https://en.wikipedia.org/wiki/Bloom_filter) that contains all ngrams from a block of data. Works only with datatypes: [String](/docs/en/sql-reference/data-types/string.md), [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) and [Map](/docs/en/sql-reference/data-types/map.md). Can be used for optimization of `EQUALS`, `LIKE` and `IN` expressions.
- `n` — ngram size,
- `size_of_bloom_filter_in_bytes` — Bloom filter size in bytes (you can use large values here, for example, 256 or 512, because it can be compressed well).
@ -417,11 +417,11 @@ The optional `false_positive` parameter is the probability of receiving a false
Supported data types: `Int*`, `UInt*`, `Float*`, `Enum`, `Date`, `DateTime`, `String`, `FixedString`, `Array`, `LowCardinality`, `Nullable`, `UUID`, `Map`.
For `Map` data type client can specify if index should be created for keys or values using [mapKeys](../../../sql-reference/functions/tuple-map-functions.md#mapkeys) or [mapValues](../../../sql-reference/functions/tuple-map-functions.md#mapvalues) function.
For `Map` data type client can specify if index should be created for keys or values using [mapKeys](/docs/en/sql-reference/functions/tuple-map-functions.md/#mapkeys) or [mapValues](/docs/en/sql-reference/functions/tuple-map-functions.md/#mapvalues) function.
There are also special-purpose and experimental indexes to support approximate nearest neighbor (ANN) queries. See [here](annindexes.md) for details.
The following functions can use the filter: [equals](../../../sql-reference/functions/comparison-functions.md), [notEquals](../../../sql-reference/functions/comparison-functions.md), [in](../../../sql-reference/functions/in-functions), [notIn](../../../sql-reference/functions/in-functions), [has](../../../sql-reference/functions/array-functions#hasarr-elem), [hasAny](../../../sql-reference/functions/array-functions#hasany), [hasAll](../../../sql-reference/functions/array-functions#hasall).
The following functions can use the filter: [equals](/docs/en/sql-reference/functions/comparison-functions.md), [notEquals](/docs/en/sql-reference/functions/comparison-functions.md), [in](/docs/en/sql-reference/functions/in-functions), [notIn](/docs/en/sql-reference/functions/in-functions), [has](/docs/en/sql-reference/functions/array-functions#hasarr-elem), [hasAny](/docs/en/sql-reference/functions/array-functions#hasany), [hasAll](/docs/en/sql-reference/functions/array-functions#hasall).
Example of index creation for `Map` data type
@ -445,21 +445,21 @@ The `set` index can be used with all functions. Function subsets for other index
| Function (operator) / Index | primary key | minmax | ngrambf_v1 | tokenbf_v1 | bloom_filter |
|------------------------------------------------------------------------------------------------------------|-------------|--------|-------------|-------------|---------------|
| [equals (=, ==)](../../../sql-reference/functions/comparison-functions.md#function-equals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notEquals(!=, &lt;&gt;)](../../../sql-reference/functions/comparison-functions.md#function-notequals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [like](../../../sql-reference/functions/string-search-functions.md#function-like) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [notLike](../../../sql-reference/functions/string-search-functions.md#function-notlike) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [startsWith](../../../sql-reference/functions/string-functions.md#startswith) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [endsWith](../../../sql-reference/functions/string-functions.md#endswith) | ✗ | ✗ | ✔ | ✔ | ✗ |
| [multiSearchAny](../../../sql-reference/functions/string-search-functions.md#function-multisearchany) | ✗ | ✗ | ✔ | ✗ | ✗ |
| [in](../../../sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notIn](../../../sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [less (<)](../../../sql-reference/functions/comparison-functions.md#function-less) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greater (>)](../../../sql-reference/functions/comparison-functions.md#function-greater) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [lessOrEquals (<=)](../../../sql-reference/functions/comparison-functions.md#function-lessorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greaterOrEquals (>=)](../../../sql-reference/functions/comparison-functions.md#function-greaterorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [empty](../../../sql-reference/functions/array-functions#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [notEmpty](../../../sql-reference/functions/array-functions#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [equals (=, ==)](/docs/en/sql-reference/functions/comparison-functions.md/#function-equals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notEquals(!=, &lt;&gt;)](/docs/en/sql-reference/functions/comparison-functions.md/#function-notequals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [like](/docs/en/sql-reference/functions/string-search-functions.md/#function-like) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [notLike](/docs/en/sql-reference/functions/string-search-functions.md/#function-notlike) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [startsWith](/docs/en/sql-reference/functions/string-functions.md/#startswith) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [endsWith](/docs/en/sql-reference/functions/string-functions.md/#endswith) | ✗ | ✗ | ✔ | ✔ | ✗ |
| [multiSearchAny](/docs/en/sql-reference/functions/string-search-functions.md/#function-multisearchany) | ✗ | ✗ | ✔ | ✗ | ✗ |
| [in](/docs/en/sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notIn](/docs/en/sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [less (<)](/docs/en/sql-reference/functions/comparison-functions.md/#function-less) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greater (>)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greater) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [lessOrEquals (<=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-lessorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greaterOrEquals (>=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greaterorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [empty](/docs/en/sql-reference/functions/array-functions#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [notEmpty](/docs/en/sql-reference/functions/array-functions#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| hasToken | ✗ | ✗ | ✗ | ✔ | ✗ |
Functions with a constant argument that is less than ngram size can’t be used by `ngrambf_v1` for query optimization.
@ -485,16 +485,16 @@ For example:
## Approximate Nearest Neighbor Search Indexes [experimental] {#table_engines-ANNIndex}
In addition to skip indices, there are also [Approximate Nearest Neighbor Search Indexes](../../../engines/table-engines/mergetree-family/annindexes.md).
In addition to skip indices, there are also [Approximate Nearest Neighbor Search Indexes](/docs/en/engines/table-engines/mergetree-family/annindexes.md).
## Projections {#projections}
Projections are like [materialized views](../../../sql-reference/statements/create/view.md#materialized) but defined in part-level. It provides consistency guarantees along with automatic usage in queries.
Projections are like [materialized views](/docs/en/sql-reference/statements/create/view.md/#materialized) but defined in part-level. It provides consistency guarantees along with automatic usage in queries.
:::note
When you are implementing projections you should also consider the [force_optimize_projection](../../../operations/settings/settings.md#force-optimize-projection) setting.
When you are implementing projections you should also consider the [force_optimize_projection](/docs/en/operations/settings/settings.md/#force-optimize-projection) setting.
:::
Projections are not supported in the `SELECT` statements with the [FINAL](../../../sql-reference/statements/select/from.md#select-from-final) modifier.
Projections are not supported in the `SELECT` statements with the [FINAL](/docs/en/sql-reference/statements/select/from.md/#select-from-final) modifier.
### Projection Query {#projection-query}
A projection query is what defines a projection. It implicitly selects data from the parent table.
@ -504,7 +504,7 @@ A projection query is what defines a projection. It implicitly selects data from
SELECT <column list expr> [GROUP BY] <group keys expr> [ORDER BY] <expr>
```
Projections can be modified or dropped with the [ALTER](../../../sql-reference/statements/alter/projection.md) statement.
Projections can be modified or dropped with the [ALTER](/docs/en/sql-reference/statements/alter/projection.md) statement.
### Projection Storage {#projection-storage}
Projections are stored inside the part directory. It's similar to an index but contains a subdirectory that stores an anonymous `MergeTree` table's part. The table is induced by the definition query of the projection. If there is a `GROUP BY` clause, the underlying storage engine becomes [AggregatingMergeTree](aggregatingmergetree.md), and all aggregate functions are converted to `AggregateFunction`. If there is an `ORDER BY` clause, the `MergeTree` table uses it as its primary key expression. During the merge process the projection part is merged via its storage's merge routine. The checksum of the parent table's part is combined with the projection's part. Other maintenance jobs are similar to skip indices.
@ -526,7 +526,7 @@ Determines the lifetime of values.
The `TTL` clause can be set for the whole table and for each individual column. Table-level `TTL` can also specify the logic of automatic moving data between disks and volumes, or recompressing parts where all the data has been expired.
Expressions must evaluate to [Date](../../../sql-reference/data-types/date.md) or [DateTime](../../../sql-reference/data-types/datetime.md) data type.
Expressions must evaluate to [Date](/docs/en/sql-reference/data-types/date.md) or [DateTime](/docs/en/sql-reference/data-types/datetime.md) data type.
**Syntax**
@ -537,7 +537,7 @@ TTL time_column
TTL time_column + interval
```
To define `interval`, use [time interval](../../../sql-reference/operators/index.md#operators-datetime) operators, for example:
To define `interval`, use [time interval](/docs/en/sql-reference/operators/index.md#operators-datetime) operators, for example:
``` sql
TTL date_time + INTERVAL 1 MONTH
@ -684,11 +684,11 @@ Data with an expired `TTL` is removed when ClickHouse merges data parts.
When ClickHouse detects that data is expired, it performs an off-schedule merge. To control the frequency of such merges, you can set `merge_with_ttl_timeout`. If the value is too low, it will perform many off-schedule merges that may consume a lot of resources.
If you perform the `SELECT` query between merges, you may get expired data. To avoid it, use the [OPTIMIZE](../../../sql-reference/statements/optimize.md) query before `SELECT`.
If you perform the `SELECT` query between merges, you may get expired data. To avoid it, use the [OPTIMIZE](/docs/en/sql-reference/statements/optimize.md) query before `SELECT`.
**See Also**
- [ttl_only_drop_parts](../../../operations/settings/settings.md#ttl_only_drop_parts) setting
- [ttl_only_drop_parts](/docs/en/operations/settings/settings.md/#ttl_only_drop_parts) setting
## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
@ -697,16 +697,16 @@ If you perform the `SELECT` query between merges, you may get expired data. To a
`MergeTree` family table engines can store data on multiple block devices. For example, it can be useful when the data of a certain table are implicitly split into “hot” and “cold”. The most recent data is regularly requested but requires only a small amount of space. On the contrary, the fat-tailed historical data is requested rarely. If several disks are available, the “hot” data may be located on fast disks (for example, NVMe SSDs or in memory), while the “cold” data - on relatively slow ones (for example, HDD).
Data part is the minimum movable unit for `MergeTree`-engine tables. The data belonging to one part are stored on one disk. Data parts can be moved between disks in the background (according to user settings) as well as by means of the [ALTER](../../../sql-reference/statements/alter/partition.md#alter_move-partition) queries.
Data part is the minimum movable unit for `MergeTree`-engine tables. The data belonging to one part are stored on one disk. Data parts can be moved between disks in the background (according to user settings) as well as by means of the [ALTER](/docs/en/sql-reference/statements/alter/partition.md/#alter_move-partition) queries.
### Terms {#terms}
- Disk — Block device mounted to the filesystem.
- Default disk — Disk that stores the path specified in the [path](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-path) server setting.
- Default disk — Disk that stores the path specified in the [path](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-path) server setting.
- Volume — Ordered set of equal disks (similar to [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures)).
- Storage policy — Set of volumes and the rules for moving data between them.
The names given to the described entities can be found in the system tables, [system.storage_policies](../../../operations/system-tables/storage_policies.md#system_tables-storage_policies) and [system.disks](../../../operations/system-tables/disks.md#system_tables-disks). To apply one of the configured storage policies for a table, use the `storage_policy` setting of `MergeTree`-engine family tables.
The names given to the described entities can be found in the system tables, [system.storage_policies](/docs/en/operations/system-tables/storage_policies.md/#system_tables-storage_policies) and [system.disks](/docs/en/operations/system-tables/disks.md/#system_tables-disks). To apply one of the configured storage policies for a table, use the `storage_policy` setting of `MergeTree`-engine family tables.
### Configuration {#table_engine-mergetree-multiple-volumes_configure}
@ -853,16 +853,16 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd'
The `default` storage policy implies using only one volume, which consists of only one disk given in `<path>`.
You could change storage policy after table creation with [ALTER TABLE ... MODIFY SETTING] query, new policy should include all old disks and volumes with same names.
The number of threads performing background moves of data parts can be changed by [background_move_pool_size](../../../operations/settings/settings.md#background_move_pool_size) setting.
The number of threads performing background moves of data parts can be changed by [background_move_pool_size](/docs/en/operations/settings/settings.md/#background_move_pool_size) setting.
### Details {#details}
In the case of `MergeTree` tables, data is getting to disk in different ways:
- As a result of an insert (`INSERT` query).
- During background merges and [mutations](../../../sql-reference/statements/alter/index.md#alter-mutations).
- During background merges and [mutations](/docs/en/sql-reference/statements/alter/index.md#alter-mutations).
- When downloading from another replica.
- As a result of partition freezing [ALTER TABLE … FREEZE PARTITION](../../../sql-reference/statements/alter/partition.md#alter_freeze-partition).
- As a result of partition freezing [ALTER TABLE … FREEZE PARTITION](/docs/en/sql-reference/statements/alter/partition.md/#alter_freeze-partition).
In all these cases except for mutations and partition freezing, a part is stored on a volume and a disk according to the given storage policy:
@ -872,16 +872,16 @@ In all these cases except for mutations and partition freezing, a part is stored
Under the hood, mutations and partition freezing make use of [hard links](https://en.wikipedia.org/wiki/Hard_link). Hard links between different disks are not supported, therefore in such cases the resulting parts are stored on the same disks as the initial ones.
In the background, parts are moved between volumes on the basis of the amount of free space (`move_factor` parameter) according to the order the volumes are declared in the configuration file.
Data is never transferred from the last one and into the first one. One may use system tables [system.part_log](../../../operations/system-tables/part_log.md#system_tables-part-log) (field `type = MOVE_PART`) and [system.parts](../../../operations/system-tables/parts.md#system_tables-parts) (fields `path` and `disk`) to monitor background moves. Also, the detailed information can be found in server logs.
Data is never transferred from the last one and into the first one. One may use system tables [system.part_log](/docs/en/operations/system-tables/part_log.md/#system_tables-part-log) (field `type = MOVE_PART`) and [system.parts](/docs/en/operations/system-tables/parts.md/#system_tables-parts) (fields `path` and `disk`) to monitor background moves. Also, the detailed information can be found in server logs.
User can force moving a part or a partition from one volume to another using the query [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](../../../sql-reference/statements/alter/partition.md#alter_move-partition), all the restrictions for background operations are taken into account. The query initiates a move on its own and does not wait for background operations to be completed. User will get an error message if not enough free space is available or if any of the required conditions are not met.
User can force moving a part or a partition from one volume to another using the query [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](/docs/en/sql-reference/statements/alter/partition.md/#alter_move-partition), all the restrictions for background operations are taken into account. The query initiates a move on its own and does not wait for background operations to be completed. User will get an error message if not enough free space is available or if any of the required conditions are not met.
Moving data does not interfere with data replication. Therefore, different storage policies can be specified for the same table on different replicas.
After the completion of background merges and mutations, old parts are removed only after a certain amount of time (`old_parts_lifetime`).
During this time, they are not moved to other volumes or disks. Therefore, until the parts are finally removed, they are still taken into account for evaluation of the occupied disk space.
User can assign new big parts to different disks of a [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures) volume in a balanced way using the [min_bytes_to_rebalance_partition_over_jbod](../../../operations/settings/merge-tree-settings.md#min-bytes-to-rebalance-partition-over-jbod) setting.
User can assign new big parts to different disks of a [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures) volume in a balanced way using the [min_bytes_to_rebalance_partition_over_jbod](/docs/en/operations/settings/merge-tree-settings.md/#min-bytes-to-rebalance-partition-over-jbod) setting.
## Using S3 for Data Storage {#table_engine-mergetree-s3}
@ -940,6 +940,10 @@ Optional parameters:
- `cache_path` — Path on local FS where to store cached mark and index files. Default value is `/var/lib/clickhouse/disks/<disk_name>/cache/`.
- `skip_access_check` — If true, disk access checks will not be performed on disk start-up. Default value is `false`.
- `server_side_encryption_customer_key_base64` — If specified, required headers for accessing S3 objects with SSE-C encryption will be set.
- `s3_max_put_rps` — Maximum PUT requests per second rate before throttling. Default value is `0` (unlimited).
- `s3_max_put_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_put_rps`.
- `s3_max_get_rps` — Maximum GET requests per second rate before throttling. Default value is `0` (unlimited).
- `s3_max_get_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_get_rps`.
S3 disk can be configured as `main` or `cold` storage:
``` xml

28
docs/en/engines/table-engines/mergetree-family/replication.md
View File

@ -20,7 +20,7 @@ Replication works at the level of an individual table, not the entire server. A
Replication does not depend on sharding. Each shard has its own independent replication.
Compressed data for `INSERT` and `ALTER` queries is replicated (for more information, see the documentation for [ALTER](../../../sql-reference/statements/alter/index.md#query_language_queries_alter)).
Compressed data for `INSERT` and `ALTER` queries is replicated (for more information, see the documentation for [ALTER](/docs/en/sql-reference/statements/alter/index.md#query_language_queries_alter)).
`CREATE`, `DROP`, `ATTACH`, `DETACH` and `RENAME` queries are executed on a single server and are not replicated:
@ -28,9 +28,9 @@ Compressed data for `INSERT` and `ALTER` queries is replicated (for more informa
- The `DROP TABLE` query deletes the replica located on the server where the query is run.
- The `RENAME` query renames the table on one of the replicas. In other words, replicated tables can have different names on different replicas.
ClickHouse uses [ClickHouse Keeper](../../../guides/sre/keeper/clickhouse-keeper.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
ClickHouse uses [ClickHouse Keeper](/docs/en/guides/sre/keeper/clickhouse-keeper.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
To use replication, set parameters in the [zookeeper](../../../operations/server-configuration-parameters/settings.md#server-settings_zookeeper) server configuration section.
To use replication, set parameters in the [zookeeper](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings_zookeeper) server configuration section.
:::warning
Don’t neglect the security setting. ClickHouse supports the `digest` [ACL scheme](https://zookeeper.apache.org/doc/current/zookeeperProgrammers.html#sc_ZooKeeperAccessControl) of the ZooKeeper security subsystem.
@ -85,7 +85,7 @@ Example of setting the addresses of the auxiliary ZooKeeper cluster:
</auxiliary_zookeepers>
```
To store table datameta in a auxiliary ZooKeeper cluster instead of default ZooKeeper cluster, we can use the SQL to create table with
To store table metadata in an auxiliary ZooKeeper cluster instead of default ZooKeeper cluster, we can use the SQL to create table with
ReplicatedMergeTree engine as follow:
```
@ -95,21 +95,21 @@ You can specify any existing ZooKeeper cluster and the system will use a directo
If ZooKeeper isn’t set in the config file, you can’t create replicated tables, and any existing replicated tables will be read-only.
ZooKeeper is not used in `SELECT` queries because replication does not affect the performance of `SELECT` and queries run just as fast as they do for non-replicated tables. When querying distributed replicated tables, ClickHouse behavior is controlled by the settings [max_replica_delay_for_distributed_queries](../../../operations/settings/settings.md#settings-max_replica_delay_for_distributed_queries) and [fallback_to_stale_replicas_for_distributed_queries](../../../operations/settings/settings.md#settings-fallback_to_stale_replicas_for_distributed_queries).
ZooKeeper is not used in `SELECT` queries because replication does not affect the performance of `SELECT` and queries run just as fast as they do for non-replicated tables. When querying distributed replicated tables, ClickHouse behavior is controlled by the settings [max_replica_delay_for_distributed_queries](/docs/en/operations/settings/settings.md/#settings-max_replica_delay_for_distributed_queries) and [fallback_to_stale_replicas_for_distributed_queries](/docs/en/operations/settings/settings.md/#settings-fallback_to_stale_replicas_for_distributed_queries).
For each `INSERT` query, approximately ten entries are added to ZooKeeper through several transactions. (To be more precise, this is for each inserted block of data; an INSERT query contains one block or one block per `max_insert_block_size = 1048576` rows.) This leads to slightly longer latencies for `INSERT` compared to non-replicated tables. But if you follow the recommendations to insert data in batches of no more than one `INSERT` per second, it does not create any problems. The entire ClickHouse cluster used for coordinating one ZooKeeper cluster has a total of several hundred `INSERTs` per second. The throughput on data inserts (the number of rows per second) is just as high as for non-replicated data.
For very large clusters, you can use different ZooKeeper clusters for different shards. However, from our experience this has not proven necessary based on production clusters with approximately 300 servers.
Replication is asynchronous and multi-master. `INSERT` queries (as well as `ALTER`) can be sent to any available server. Data is inserted on the server where the query is run, and then it is copied to the other servers. Because it is asynchronous, recently inserted data appears on the other replicas with some latency. If part of the replicas are not available, the data is written when they become available. If a replica is available, the latency is the amount of time it takes to transfer the block of compressed data over the network. The number of threads performing background tasks for replicated tables can be set by [background_schedule_pool_size](../../../operations/settings/settings.md#background_schedule_pool_size) setting.
Replication is asynchronous and multi-master. `INSERT` queries (as well as `ALTER`) can be sent to any available server. Data is inserted on the server where the query is run, and then it is copied to the other servers. Because it is asynchronous, recently inserted data appears on the other replicas with some latency. If part of the replicas are not available, the data is written when they become available. If a replica is available, the latency is the amount of time it takes to transfer the block of compressed data over the network. The number of threads performing background tasks for replicated tables can be set by [background_schedule_pool_size](/docs/en/operations/settings/settings.md/#background_schedule_pool_size) setting.
`ReplicatedMergeTree` engine uses a separate thread pool for replicated fetches. Size of the pool is limited by the [background_fetches_pool_size](../../../operations/settings/settings.md#background_fetches_pool_size) setting which can be tuned with a server restart.
`ReplicatedMergeTree` engine uses a separate thread pool for replicated fetches. Size of the pool is limited by the [background_fetches_pool_size](/docs/en/operations/settings/settings.md/#background_fetches_pool_size) setting which can be tuned with a server restart.
By default, an INSERT query waits for confirmation of writing the data from only one replica. If the data was successfully written to only one replica and the server with this replica ceases to exist, the stored data will be lost. To enable getting confirmation of data writes from multiple replicas, use the `insert_quorum` option.
Each block of data is written atomically. The INSERT query is divided into blocks up to `max_insert_block_size = 1048576` rows. In other words, if the `INSERT` query has less than 1048576 rows, it is made atomically.
Data blocks are deduplicated. For multiple writes of the same data block (data blocks of the same size containing the same rows in the same order), the block is only written once. The reason for this is in case of network failures when the client application does not know if the data was written to the DB, so the `INSERT` query can simply be repeated. It does not matter which replica INSERTs were sent to with identical data. `INSERTs` are idempotent. Deduplication parameters are controlled by [merge_tree](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-merge_tree) server settings.
Data blocks are deduplicated. For multiple writes of the same data block (data blocks of the same size containing the same rows in the same order), the block is only written once. The reason for this is in case of network failures when the client application does not know if the data was written to the DB, so the `INSERT` query can simply be repeated. It does not matter which replica INSERTs were sent to with identical data. `INSERTs` are idempotent. Deduplication parameters are controlled by [merge_tree](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-merge_tree) server settings.
During replication, only the source data to insert is transferred over the network. Further data transformation (merging) is coordinated and performed on all the replicas in the same way. This minimizes network usage, which means that replication works well when replicas reside in different datacenters. (Note that duplicating data in different datacenters is the main goal of replication.)
@ -165,7 +165,7 @@ CREATE TABLE table_name
</details>
As the example shows, these parameters can contain substitutions in curly brackets. The substituted values are taken from the [macros](../../../operations/server-configuration-parameters/settings.md#macros) section of the configuration file.
As the example shows, these parameters can contain substitutions in curly brackets. The substituted values are taken from the [macros](/docs/en/operations/server-configuration-parameters/settings.md/#macros) section of the configuration file.
Example:
@ -295,10 +295,10 @@ If the data in ClickHouse Keeper was lost or damaged, you can save data by movin
**See Also**
- [background_schedule_pool_size](../../../operations/settings/settings.md#background_schedule_pool_size)
- [background_fetches_pool_size](../../../operations/settings/settings.md#background_fetches_pool_size)
- [execute_merges_on_single_replica_time_threshold](../../../operations/settings/settings.md#execute-merges-on-single-replica-time-threshold)
- [max_replicated_fetches_network_bandwidth](../../../operations/settings/merge-tree-settings.md#max_replicated_fetches_network_bandwidth)
- [max_replicated_sends_network_bandwidth](../../../operations/settings/merge-tree-settings.md#max_replicated_sends_network_bandwidth)
- [background_schedule_pool_size](/docs/en/operations/settings/settings.md/#background_schedule_pool_size)
- [background_fetches_pool_size](/docs/en/operations/settings/settings.md/#background_fetches_pool_size)
- [execute_merges_on_single_replica_time_threshold](/docs/en/operations/settings/settings.md/#execute-merges-on-single-replica-time-threshold)
- [max_replicated_fetches_network_bandwidth](/docs/en/operations/settings/merge-tree-settings.md/#max_replicated_fetches_network_bandwidth)
- [max_replicated_sends_network_bandwidth](/docs/en/operations/settings/merge-tree-settings.md/#max_replicated_sends_network_bandwidth)
[Original article](https://clickhouse.com/docs/en/operations/table_engines/replication/) <!--hide-->

28
docs/en/engines/table-engines/special/join.md
View File

@ -6,10 +6,10 @@ sidebar_label: Join
# Join Table Engine
Optional prepared data structure for usage in [JOIN](../../../sql-reference/statements/select/join.md#select-join) operations.
Optional prepared data structure for usage in [JOIN](/docs/en/sql-reference/statements/select/join.md/#select-join) operations.
:::note
This is not an article about the [JOIN clause](../../../sql-reference/statements/select/join.md#select-join) itself.
This is not an article about the [JOIN clause](/docs/en/sql-reference/statements/select/join.md/#select-join) itself.
:::
## Creating a Table {#creating-a-table}
@ -22,17 +22,17 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
) ENGINE = Join(join_strictness, join_type, k1[, k2, ...])
```
See the detailed description of the [CREATE TABLE](../../../sql-reference/statements/create/table.md#create-table-query) query.
See the detailed description of the [CREATE TABLE](/docs/en/sql-reference/statements/create/table.md/#create-table-query) query.
## Engine Parameters
### join_strictness
`join_strictness` – [JOIN strictness](../../../sql-reference/statements/select/join.md#select-join-types).
`join_strictness` – [JOIN strictness](/docs/en/sql-reference/statements/select/join.md/#select-join-types).
### join_type
`join_type` – [JOIN type](../../../sql-reference/statements/select/join.md#select-join-types).
`join_type` – [JOIN type](/docs/en/sql-reference/statements/select/join.md/#select-join-types).
### Key columns
@ -55,11 +55,11 @@ You can use `INSERT` queries to add data to the `Join`-engine tables. If the tab
Main use-cases for `Join`-engine tables are following:
- Place the table to the right side in a `JOIN` clause.
- Call the [joinGet](../../../sql-reference/functions/other-functions.md#joinget) function, which lets you extract data from the table the same way as from a dictionary.
- Call the [joinGet](/docs/en/sql-reference/functions/other-functions.md/#joinget) function, which lets you extract data from the table the same way as from a dictionary.
### Deleting Data {#deleting-data}
`ALTER DELETE` queries for `Join`-engine tables are implemented as [mutations](../../../sql-reference/statements/alter/index.md#mutations). `DELETE` mutation reads filtered data and overwrites data of memory and disk.
`ALTER DELETE` queries for `Join`-engine tables are implemented as [mutations](/docs/en/sql-reference/statements/alter/index.md#mutations). `DELETE` mutation reads filtered data and overwrites data of memory and disk.
### Limitations and Settings {#join-limitations-and-settings}
@ -67,30 +67,30 @@ When creating a table, the following settings are applied:
#### join_use_nulls
[join_use_nulls](../../../operations/settings/settings.md#join_use_nulls)
[join_use_nulls](/docs/en/operations/settings/settings.md/#join_use_nulls)
#### max_rows_in_join
[max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join)
[max_rows_in_join](/docs/en/operations/settings/query-complexity.md/#settings-max_rows_in_join)
#### max_bytes_in_join
[max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join)
[max_bytes_in_join](/docs/en/operations/settings/query-complexity.md/#settings-max_bytes_in_join)
#### join_overflow_mode
[join_overflow_mode](../../../operations/settings/query-complexity.md#settings-join_overflow_mode)
[join_overflow_mode](/docs/en/operations/settings/query-complexity.md/#settings-join_overflow_mode)
#### join_any_take_last_row
[join_any_take_last_row](../../../operations/settings/settings.md#settings-join_any_take_last_row)
[join_any_take_last_row](/docs/en/operations/settings/settings.md/#settings-join_any_take_last_row)
#### join_use_nulls
[persistent](../../../operations/settings/settings.md#persistent)
[persistent](/docs/en/operations/settings/settings.md/#persistent)
The `Join`-engine tables can’t be used in `GLOBAL JOIN` operations.
The `Join`-engine allows to specify [join_use_nulls](../../../operations/settings/settings.md#join_use_nulls) setting in the `CREATE TABLE` statement. [SELECT](../../../sql-reference/statements/select/index.md) query should have the same `join_use_nulls` value.
The `Join`-engine allows to specify [join_use_nulls](/docs/en/operations/settings/settings.md/#join_use_nulls) setting in the `CREATE TABLE` statement. [SELECT](/docs/en/sql-reference/statements/select/index.md) query should have the same `join_use_nulls` value.
## Usage Examples {#example}

160
docs/en/getting-started/example-datasets/cell-towers.md
View File

@ -4,25 +4,39 @@ sidebar_label: Cell Towers
sidebar_position: 3
title: "Cell Towers"
---
import ConnectionDetails from '@site/docs/en/_snippets/_gather_your_details_http.mdx';
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import CodeBlock from '@theme/CodeBlock';
import ActionsMenu from '@site/docs/en/_snippets/_service_actions_menu.md';
import SQLConsoleDetail from '@site/docs/en/_snippets/_launch_sql_console.md';
import SupersetDocker from '@site/docs/en/_snippets/_add_superset_detail.md';
This dataset is from [OpenCellid](https://www.opencellid.org/) - The world's largest Open Database of Cell Towers.
## Goal
In this guide you will learn how to:
- Load the OpenCelliD data in Clickhouse
- Connect Apache Superset to ClickHouse
- Build a dashboard based on data available in the dataset
Here is a preview of the dashboard created in this guide:
![Dashboard of cell towers by radio type in mcc 204](@site/docs/en/getting-started/example-datasets/images/superset-cell-tower-dashboard.png)
## Get the Dataset {#get-the-dataset}
This dataset is from [OpenCelliD](https://www.opencellid.org/) - The world's largest Open Database of Cell Towers.
As of 2021, it contains more than 40 million records about cell towers (GSM, LTE, UMTS, etc.) around the world with their geographical coordinates and metadata (country code, network, etc).
OpenCelliD Project is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License, and we redistribute a snapshot of this dataset under the terms of the same license. The up-to-date version of the dataset is available to download after sign in.
## Get the Dataset {#get-the-dataset}
<Tabs groupId="deployMethod">
<TabItem value="serverless" label="ClickHouse Cloud" default>
### Load the sample data
ClickHouse Cloud provides an easy-button for uploading this dataset from S3. Log in to your ClickHouse Cloud organization, or create a free trial at [ClickHouse.cloud](https://clickhouse.cloud).
<ActionsMenu menu="Load Data" />
@ -30,13 +44,33 @@ Choose the **Cell Towers** dataset from the **Sample data** tab, and **Load data
![Load cell towers dataset](@site/docs/en/_snippets/images/cloud-load-data-sample.png)
Examine the schema of the cell_towers table:
### Examine the schema of the cell_towers table
```sql
DESCRIBE TABLE cell_towers
```
<SQLConsoleDetail />
This is the output of `DESCRIBE`. Down further in this guide the field type choices will be described.
```response
┌─name──────────┬─type──────────────────────────────────────────────────────────────────┬
│ radio │ Enum8('' = 0, 'CDMA' = 1, 'GSM' = 2, 'LTE' = 3, 'NR' = 4, 'UMTS' = 5) │
│ mcc │ UInt16 │
│ net │ UInt16 │
│ area │ UInt16 │
│ cell │ UInt64 │
│ unit │ Int16 │
│ lon │ Float64 │
│ lat │ Float64 │
│ range │ UInt32 │
│ samples │ UInt32 │
│ changeable │ UInt8 │
│ created │ DateTime │
│ updated │ DateTime │
│ averageSignal │ UInt8 │
└───────────────┴───────────────────────────────────────────────────────────────────────┴
```
</TabItem>
<TabItem value="selfmanaged" label="Self-managed">
@ -86,7 +120,7 @@ clickhouse-client --query "INSERT INTO cell_towers FORMAT CSVWithNames" < cell_t
</TabItem>
</Tabs>
## Example queries {#examples}
## Run some example queries {#examples}
1. A number of cell towers by type:
@ -127,13 +161,13 @@ SELECT mcc, count() FROM cell_towers GROUP BY mcc ORDER BY count() DESC LIMIT 10
10 rows in set. Elapsed: 0.019 sec. Processed 43.28 million rows, 86.55 MB (2.33 billion rows/s., 4.65 GB/s.)
```
So, the top countries are: the USA, Germany, and Russia.
Based on the above query and the [MCC list](https://en.wikipedia.org/wiki/Mobile_country_code), the countries with the most cell towers are: the USA, Germany, and Russia.
You may want to create an [External Dictionary](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md) in ClickHouse to decode these values.
You may want to create a [Dictionary](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md) in ClickHouse to decode these values.
## Use case: Incorporate geo data {#use-case}
Using `pointInPolygon` function.
Using the [`pointInPolygon`](/docs/en/sql-reference/functions/geo/coordinates.md/#pointinpolygon) function.
1. Create a table where we will store polygons:
@ -224,6 +258,110 @@ WHERE pointInPolygon((lon, lat), (SELECT * FROM moscow))
1 rows in set. Elapsed: 0.067 sec. Processed 43.28 million rows, 692.42 MB (645.83 million rows/s., 10.33 GB/s.)
```
The data is also available for interactive queries in the [Playground](https://play.clickhouse.com/play?user=play), [example](https://play.clickhouse.com/play?user=play#U0VMRUNUIG1jYywgY291bnQoKSBGUk9NIGNlbGxfdG93ZXJzIEdST1VQIEJZIG1jYyBPUkRFUiBCWSBjb3VudCgpIERFU0M=).
## Review of the schema
Although you cannot create temporary tables there.
Before building visualizations in Superset have a look at the columns that you will use. This dataset primarily provides the location (Longitude and Latitude) and radio types at mobile cellular towers worldwide. The column descriptions can be found in the [community forum](https://community.opencellid.org/t/documenting-the-columns-in-the-downloadable-cells-database-csv/186). The columns used in the visualizations that will be built are described below
Here is a description of the columns taken from the OpenCelliD forum:
| Column | Description |
|--------------|--------------------------------------------------------|
| radio | Technology generation: CDMA, GSM, UMTS, 5G NR |
| mcc | Mobile Country Code: `204` is The Netherlands |
| lon | Longitude: With Latitude, approximate tower location |
| lat | Latitude: With Longitude, approximate tower location |
:::tip mcc
To find your MCC check [Mobile network codes](https://en.wikipedia.org/wiki/Mobile_country_code), and use the three digits in the **Mobile country code** column.
:::
The schema for this table was designed for compact storage on disk and query speed.
- The `radio` data is stored as an `Enum8` (`UInt8`) rather than a string.
- `mcc` or Mobile country code, is stored as a `UInt16` as we know the range is 1 - 999.
- `lon` and `lat` are `Float64`.
None of the other fields are used in the queries or visualizations in this guide, but they are described in the forum linked above if you are interested.
## Build visualizations with Apache Superset
Superset is easy to run from Docker. If you already have Superset running, all you need to do is add ClickHouse Connect with `pip install clickhouse-connect`. If you need to install Superset open the **Launch Apache Superset in Docker** directly below.
<SupersetDocker />
To build a Superset dashboard using the OpenCelliD dataset you should:
- Add your ClickHouse service as a Superset **database**
- Add the table **cell_towers** as a Superset **dataset**
- Create some **charts**
- Add the charts to a **dashboard**
### Add your ClickHouse service as a Superset database
<ConnectionDetails />
In Superset a database can be added by choosing the database type, and then providing the connection details. Open Superset and look for the **+**, it has a menu with **Data** and then **Connect database** options.
![Add a database](@site/docs/en/getting-started/example-datasets/images/superset-add.png)
Choose **ClickHouse Connect** from the list:
![Choose clickhouse connect as database type](@site/docs/en/getting-started/example-datasets/images/superset-choose-a-database.png)
:::note
If **ClickHouse Connect** is not one of your options, then you will need to install it. The comand is `pip install clickhouse-connect`, and more info is [available here](https://pypi.org/project/clickhouse-connect/).
:::
#### Add your connection details:
:::tip
Make sure that you set **SSL** on when connecting to ClickHouse Cloud or other ClickHouse systems that enforce the use of SSL.
:::
![Add ClickHouse as a Superset datasource](@site/docs/en/getting-started/example-datasets/images/superset-connect-a-database.png)
### Add the table **cell_towers** as a Superset **dataset**
In Superset a **dataset** maps to a table within a database. Click on add a dataset and choose your ClickHouse service, the database containing your table (`default`), and choose the `cell_towers` table:
![Add cell_towers table as a dataset](@site/docs/en/getting-started/example-datasets/images/superset-add-dataset.png)
### Create some **charts**
When you choose to add a chart in Superset you have to specify the dataset (`cell_towers`) and the chart type. Since the OpenCelliD dataset provides longitude and latitude coordinates for cell towers we will create a **Map** chart. The **deck.gL Scatterplot** type is suited to this dataset as it works well with dense data points on a map.
![Create a map in Superset](@site/docs/en/getting-started/example-datasets/images/superset-create-map.png)
#### Specify the query used for the map
A deck.gl Scatterplot requires a longitude and latitude, and one or more filters can also be applied to the query. In this example two filters are applied, one for cell towers with UMTS radios, and one for the Mobile country code assigned to The Netherlands.
The fields `lon` and `lat` contain the longitude and latitude:
![Specify longitude and latitude fields](@site/docs/en/getting-started/example-datasets/images/superset-lon-lat.png)
Add a filter with `mcc` = `204` (or substitute any other `mcc` value):
![Filter on MCC 204](@site/docs/en/getting-started/example-datasets/images/superset-mcc-204.png)
Add a filter with `radio` = `'UMTS'` (or substitute any other `radio` value, you can see the choices in the output of `DESCRIBE TABLE cell_towers`):
![Filter on radio = UMTS](@site/docs/en/getting-started/example-datasets/images/superset-radio-umts.png)
This is the full configuration for the chart that filters on `radio = 'UMTS'` and `mcc = 204`:
![Chart for UMTS radios in MCC 204](@site/docs/en/getting-started/example-datasets/images/superset-umts-netherlands.png)
Click on **UPDATE CHART** to render the visualization.
### Add the charts to a **dashboard**
This screenshot shows cell tower locations with LTE, UMTS, and GSM radios. The charts are all created in the same way and they are added to a dashboard.
![Dashboard of cell towers by radio type in mcc 204](@site/docs/en/getting-started/example-datasets/images/superset-cell-tower-dashboard.png)
:::tip
The data is also available for interactive queries in the [Playground](https://play.clickhouse.com/play?user=play).
This [example](https://play.clickhouse.com/play?user=play#U0VMRUNUIG1jYywgY291bnQoKSBGUk9NIGNlbGxfdG93ZXJzIEdST1VQIEJZIG1jYyBPUkRFUiBCWSBjb3VudCgpIERFU0M=) will populate the username and even the query for you.
Although you cannot create tables in the Playground, you can run all of the queries and even use Superset (adjust the hostname and port number).
:::

2499
docs/en/getting-started/example-datasets/github.md Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
docs/en/getting-started/example-datasets/images/superset-add-dataset.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 35 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-add.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 35 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-authors-matrix.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 277 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-authors-matrix_v2.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 315 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-cell-tower-dashboard.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 475 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-choose-a-database.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 53 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-commits-authors.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 246 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-connect-a-database.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 73 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-create-map.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 290 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-github-lines-added-deleted.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 69 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-lon-lat.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-mcc-204.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-radio-umts.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-umts-netherlands.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 46 KiB

4
docs/en/getting-started/example-datasets/nyc-taxi.md
View File

@ -33,7 +33,7 @@ CREATE TABLE trips (
tip_amount Float32,
tolls_amount Float32,
total_amount Float32,
payment_type Enum('CSH' = 1, 'CRE' = 2, 'NOC' = 3, 'DIS' = 4),
payment_type Enum('CSH' = 1, 'CRE' = 2, 'NOC' = 3, 'DIS' = 4, 'UNK' = 5),
pickup_ntaname LowCardinality(String),
dropoff_ntaname LowCardinality(String)
)
@ -63,7 +63,7 @@ SELECT
payment_type,
pickup_ntaname,
dropoff_ntaname
FROM url(
FROM s3(
'https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/trips_{0..2}.gz',
'TabSeparatedWithNames'
)

2
docs/en/getting-started/example-datasets/recipes.md
View File

@ -4,7 +4,7 @@ sidebar_label: Recipes Dataset
title: "Recipes Dataset"
---
RecipeNLG dataset is available for download [here](https://recipenlg.cs.put.poznan.pl/dataset). It contains 2.2 million recipes. The size is slightly less than 1 GB.
The RecipeNLG dataset is available for download [here](https://recipenlg.cs.put.poznan.pl/dataset). It contains 2.2 million recipes. The size is slightly less than 1 GB.
## Download and Unpack the Dataset

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