thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-28 10:31:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge https://github.com/ClickHouse/ClickHouse into ch_canh_fix_sparkbar

Browse Source
This commit is contained in:
Duc Canh Le 2023-01-04 22:11:19 +08:00
commit 03e6ef2a30
760 changed files with 21782 additions and 11473 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
.github/workflows/backport_branches.yml vendored
View File

@ -12,11 +12,10 @@ jobs:
PythonUnitTests:
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
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
@ -24,34 +23,32 @@ jobs:
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
@ -59,18 +56,17 @@ jobs:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download changed aarch64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
@ -79,7 +75,7 @@ jobs:
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
@ -94,13 +90,12 @@ jobs:
REPO_COPY=${{runner.temp}}/compatibility_check/ClickHouse
REPORTS_PATH=${{runner.temp}}/reports_dir
EOF
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: CompatibilityCheck
@ -132,28 +127,25 @@ jobs:
BUILD_NAME=package_release
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -177,28 +169,25 @@ jobs:
BUILD_NAME=package_aarch64
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
fetch-depth: 0 # For a proper version and performance artifacts
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -222,26 +211,24 @@ jobs:
BUILD_NAME=package_asan
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -265,26 +252,24 @@ jobs:
BUILD_NAME=package_tsan
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -308,26 +293,24 @@ jobs:
BUILD_NAME=package_debug
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -351,28 +334,25 @@ jobs:
BUILD_NAME=binary_darwin
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -396,28 +376,25 @@ jobs:
BUILD_NAME=binary_darwin_aarch64
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: true
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
run: |
git -C "$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" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
@ -436,12 +413,10 @@ jobs:
- 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
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
- name: Check docker clickhouse/clickhouse-server building
run: |
@ -477,14 +452,13 @@ jobs:
NEEDS_DATA_PATH=${{runner.temp}}/needs.json
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Report Builder
run: |
sudo rm -fr "$TEMP_PATH"
@ -516,14 +490,13 @@ jobs:
NEEDS_DATA_PATH=${{runner.temp}}/needs.json
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Report Builder
run: |
sudo rm -fr "$TEMP_PATH"
@ -556,14 +529,13 @@ jobs:
KILL_TIMEOUT=10800
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
@ -594,14 +566,13 @@ jobs:
KILL_TIMEOUT=3600
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Functional test
run: |
sudo rm -fr "$TEMP_PATH"
@ -635,14 +606,13 @@ jobs:
REPO_COPY=${{runner.temp}}/stress_thread/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Stress test
run: |
sudo rm -fr "$TEMP_PATH"
@ -672,14 +642,13 @@ jobs:
REPO_COPY=${{runner.temp}}/integration_tests_release/ClickHouse
EOF
- name: Download json reports
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Integration test
run: |
sudo rm -fr "$TEMP_PATH"
@ -706,11 +675,10 @@ jobs:
- CompatibilityCheck
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
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

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

@ -28,8 +28,9 @@ jobs:
REPO_TEAM=core
EOF
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Cherry pick

63
.github/workflows/docs_check.yml vendored
View File

@ -21,11 +21,10 @@ jobs:
CheckLabels:
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -rf "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
@ -34,17 +33,16 @@ jobs:
needs: CheckLabels
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
@ -52,17 +50,16 @@ jobs:
needs: CheckLabels
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
@ -70,18 +67,17 @@ jobs:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download changed aarch64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
@ -90,7 +86,7 @@ jobs:
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
@ -110,15 +106,14 @@ jobs:
- name: Download changed images
# even if artifact does not exist, e.g. on `do not test` label or failed Docker job
continue-on-error: true
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.TEMP_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Style Check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
@ -140,15 +135,14 @@ jobs:
REPO_COPY=${{runner.temp}}/docs_check/ClickHouse
EOF
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.TEMP_PATH }}
- name: Clear repository
run: |
sudo rm -rf "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Docs Check
run: |
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
@ -167,11 +161,10 @@ jobs:
- DocsCheck
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

40
.github/workflows/docs_release.yml vendored
View File

@ -23,34 +23,32 @@ jobs:
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
@ -58,18 +56,17 @@ jobs:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download changed aarch64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
@ -78,7 +75,7 @@ jobs:
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
@ -97,13 +94,12 @@ jobs:
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
EOF
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.TEMP_PATH }}

12
.github/workflows/jepsen.yml vendored
View File

@ -19,12 +19,10 @@ jobs:
TEMP_PATH=${{runner.temp}}/keeper_jepsen
REPO_COPY=${{runner.temp}}/keeper_jepsen/ClickHouse
EOF
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0
- name: Jepsen Test
run: |
@ -50,12 +48,10 @@ jobs:
# 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
# uses: ClickHouse/checkout@v1
# with:
# clear-repository: true
# fetch-depth: 0
# - name: Jepsen Test
# run: |

948
.github/workflows/master.yml vendored
View File

File diff suppressed because it is too large Load Diff

48
.github/workflows/nightly.yml vendored
View File

@ -16,34 +16,32 @@ jobs:
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64 --all
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64 --all
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
@ -51,18 +49,17 @@ jobs:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Download changed aarch64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
@ -71,7 +68,7 @@ jobs:
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
@ -90,22 +87,17 @@ jobs:
EOF
echo "COVERITY_TOKEN=${{ secrets.COVERITY_TOKEN }}" >> "$GITHUB_ENV"
- name: Download changed images
uses: actions/download-artifact@v2
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
id: coverity-checkout
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
fetch-depth: 0 # otherwise we will have no info about contributors
clear-repository: true
submodules: true
- name: Build
run: |
git -C "$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"
@ -134,8 +126,10 @@ jobs:
CC: clang-15
CXX: clang++-15
steps:
- uses: actions/checkout@v2
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # Shallow clones should be disabled for a better relevancy of analysis
submodules: true
- name: Set up JDK 11

1247
.github/workflows/pull_request.yml vendored
View File

File diff suppressed because it is too large Load Diff

8
.github/workflows/release.yml vendored
View File

@ -20,7 +20,7 @@ jobs:
REPO_COPY=${{runner.temp}}/release_packages/ClickHouse
EOF
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
# Always use the most recent script version
ref: master
@ -50,12 +50,10 @@ jobs:
DockerServerImages:
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # otherwise we will have no version info
- name: Check docker clickhouse/clickhouse-server building
run: |

514
.github/workflows/release_branches.yml vendored
View File

File diff suppressed because it is too large Load Diff

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

@ -34,7 +34,7 @@ jobs:
run: |
echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
ref: master
fetch-depth: 0

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

@ -21,12 +21,10 @@ jobs:
REPO_COPY=${{runner.temp}}/codebrowser/ClickHouse
IMAGES_PATH=${{runner.temp}}/images_path
EOF
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
uses: ClickHouse/checkout@v1
with:
clear-repository: true
submodules: 'true'
- name: Codebrowser
run: |

55
CMakeLists.txt
View File

@ -73,22 +73,7 @@ message (STATUS "CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}")
string (TOUPPER ${CMAKE_BUILD_TYPE} CMAKE_BUILD_TYPE_UC)
option(USE_STATIC_LIBRARIES "Disable to use shared libraries" ON)
# DEVELOPER ONLY.
# Faster linking if turned on.
option(SPLIT_SHARED_LIBRARIES "Keep all internal libraries as separate .so files" OFF)
if (USE_STATIC_LIBRARIES AND SPLIT_SHARED_LIBRARIES)
message(FATAL_ERROR "SPLIT_SHARED_LIBRARIES=1 must not be used together with USE_STATIC_LIBRARIES=1")
endif()
if (NOT USE_STATIC_LIBRARIES AND SPLIT_SHARED_LIBRARIES)
set(BUILD_SHARED_LIBS 1 CACHE INTERNAL "")
endif ()
if (USE_STATIC_LIBRARIES)
list(REVERSE CMAKE_FIND_LIBRARY_SUFFIXES)
endif ()
list(REVERSE CMAKE_FIND_LIBRARY_SUFFIXES)
option (ENABLE_FUZZING "Fuzzy testing using libfuzzer" OFF)
@ -171,7 +156,7 @@ option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests"
option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
option(ENABLE_BENCHMARKS "Build all benchmark programs in 'benchmarks' subdirectories" OFF)
if (OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64) AND USE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND NOT USE_MUSL)
if (OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64) AND NOT USE_MUSL)
# Only for Linux, x86_64 or aarch64.
option(GLIBC_COMPATIBILITY "Enable compatibility with older glibc libraries." ON)
elseif(GLIBC_COMPATIBILITY)
@ -377,15 +362,15 @@ set (DEBUG_INFO_FLAGS "-g -gdwarf-4")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${COMPILER_FLAGS}")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} -fno-inline ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${COMPILER_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} -fno-inline ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_RELWITHDEBINFO "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} -fno-inline ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
if (COMPILER_CLANG)
if (OS_DARWIN)
@ -467,22 +452,13 @@ endif ()
set (CMAKE_POSTFIX_VARIABLE "CMAKE_${CMAKE_BUILD_TYPE_UC}_POSTFIX")
if (USE_STATIC_LIBRARIES)
set (CMAKE_POSITION_INDEPENDENT_CODE OFF)
if (OS_LINUX AND NOT ARCH_AARCH64)
# Slightly more efficient code can be generated
# It's disabled for ARM because otherwise ClickHouse cannot run on Android.
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-pie")
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -fno-pie")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -no-pie -Wl,-no-pie")
endif ()
else ()
set (CMAKE_POSITION_INDEPENDENT_CODE ON)
# This is required for clang on Arch linux, that uses PIE by default.
# See enable-SSP-and-PIE-by-default.patch [1].
#
# [1]: https://github.com/archlinux/svntogit-packages/blob/6e681aa860e65ad46a1387081482eb875c2200f2/trunk/enable-SSP-and-PIE-by-default.patch
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -no-pie")
set (CMAKE_POSITION_INDEPENDENT_CODE OFF)
if (OS_LINUX AND NOT ARCH_AARCH64)
# Slightly more efficient code can be generated
# It's disabled for ARM because otherwise ClickHouse cannot run on Android.
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-pie")
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -fno-pie")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -no-pie -Wl,-no-pie")
endif ()
if (ENABLE_TESTS)
@ -504,10 +480,7 @@ else ()
set (CLICKHOUSE_ETC_DIR "${CMAKE_INSTALL_PREFIX}/etc")
endif ()
message (STATUS
"Building for: ${CMAKE_SYSTEM} ${CMAKE_SYSTEM_PROCESSOR} ${CMAKE_LIBRARY_ARCHITECTURE} ;
USE_STATIC_LIBRARIES=${USE_STATIC_LIBRARIES}
SPLIT_SHARED_LIBRARIES=${SPLIT_SHARED_LIBRARIES}")
message (STATUS "Building for: ${CMAKE_SYSTEM} ${CMAKE_SYSTEM_PROCESSOR} ${CMAKE_LIBRARY_ARCHITECTURE}")
include (GNUInstallDirs)
@ -553,7 +526,7 @@ macro (clickhouse_add_executable target)
# - _je_zone_register due to JEMALLOC_PRIVATE_NAMESPACE=je_ under OS X.
# - but jemalloc-cmake does not run private_namespace.sh
# so symbol name should be _zone_register
if (ENABLE_JEMALLOC AND USE_STATIC_LIBRARIES AND OS_DARWIN)
if (ENABLE_JEMALLOC AND OS_DARWIN)
set_property(TARGET ${target} APPEND PROPERTY LINK_OPTIONS -u_zone_register)
endif()
endif()

4
LICENSE
View File

@ -1,4 +1,4 @@
Copyright 2016-2022 ClickHouse, Inc.
Copyright 2016-2023 ClickHouse, Inc.
Apache License
Version 2.0, January 2004
@ -188,7 +188,7 @@ Copyright 2016-2022 ClickHouse, Inc.
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2016-2022 ClickHouse, Inc.
Copyright 2016-2023 ClickHouse, Inc.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.

2
base/base/BorrowedObjectPool.h
View File

@ -10,7 +10,7 @@
#include <base/MoveOrCopyIfThrow.h>
/** Pool for limited size objects that cannot be used from different threads simultaneously.
* The main use case is to have fixed size of objects that can be reused in difference threads during their lifetime
* The main use case is to have fixed size of objects that can be reused in different threads during their lifetime
* and have to be initialized on demand.
* Two main properties of pool are allocated objects size and borrowed objects size.
* Allocated objects size is size of objects that are currently allocated by the pool.

12
base/base/CMakeLists.txt
View File

@ -8,16 +8,13 @@ set (SRCS
getPageSize.cpp
getThreadId.cpp
JSON.cpp
LineReader.cpp
mremap.cpp
phdr_cache.cpp
preciseExp10.cpp
setTerminalEcho.cpp
shift10.cpp
sleep.cpp
terminalColors.cpp
errnoToString.cpp
ReplxxLineReader.cpp
StringRef.cpp
safeExit.cpp
throwError.cpp
@ -40,17 +37,8 @@ else ()
target_compile_definitions(common PUBLIC WITH_COVERAGE=0)
endif ()
# FIXME: move libraries for line reading out from base
if (TARGET ch_rust::skim)
target_link_libraries(common PUBLIC ch_rust::skim)
endif()
target_include_directories(common PUBLIC .. "${CMAKE_CURRENT_BINARY_DIR}/..")
if (OS_DARWIN AND NOT USE_STATIC_LIBRARIES)
target_link_libraries(common PUBLIC -Wl,-U,_inside_main)
endif()
target_link_libraries (common
PUBLIC
ch_contrib::cityhash

28
base/base/setTerminalEcho.cpp
View File

@ -1,28 +0,0 @@
#include <base/setTerminalEcho.h>
#include <base/errnoToString.h>
#include <stdexcept>
#include <cstring>
#include <string>
#include <termios.h>
#include <unistd.h>
void setTerminalEcho(bool enable)
{
/// Obtain terminal attributes,
/// toggle the ECHO flag
/// and set them back.
struct termios tty{};
if (0 != tcgetattr(STDIN_FILENO, &tty))
throw std::runtime_error(std::string("setTerminalEcho failed get: ") + errnoToString());
if (enable)
tty.c_lflag |= ECHO;
else
tty.c_lflag &= ~ECHO;
if (0 != tcsetattr(STDIN_FILENO, TCSANOW, &tty))
throw std::runtime_error(std::string("setTerminalEcho failed set: ") + errnoToString());
}

4
base/base/setTerminalEcho.h
View File

@ -1,4 +0,0 @@
#pragma once
/// Enable or disable echoing of typed characters. Throws std::runtime_error on error.
void setTerminalEcho(bool enable);

2
base/glibc-compatibility/CMakeLists.txt
View File

@ -37,7 +37,7 @@ if (GLIBC_COMPATIBILITY)
target_include_directories(glibc-compatibility PRIVATE libcxxabi ${musl_arch_include_dir})
if (( NOT USE_STATIC_LIBRARIES AND NOT USE_STATIC_LIBRARIES ) OR ENABLE_OPENSSL_DYNAMIC)
if (ENABLE_OPENSSL_DYNAMIC)
target_compile_options(glibc-compatibility PRIVATE -fPIC)
endif ()

5
cmake/cpu_features.cmake
View File

@ -102,6 +102,11 @@ elseif (ARCH_AMD64)
SET(ENABLE_AVX512_FOR_SPEC_OP 0)
endif()
# ClickHouse can be cross-compiled (e.g. on an ARM host for x86) but it is also possible to build ClickHouse on x86 w/o AVX for x86 w/
# AVX. We only check that the compiler can emit certain SIMD instructions, we don't care if the host system is able to run the binary.
# Therefore, use check_cxx_source_compiles (= does the code compile+link?) instead of check_cxx_source_runs (= does the code
# compile+link+run).
set (TEST_FLAG "-mssse3")
set (CMAKE_REQUIRED_FLAGS "${TEST_FLAG} -O0")
check_cxx_source_compiles("

8
cmake/sanitize.cmake
View File

@ -25,7 +25,7 @@ if (SANITIZE)
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} ${ASAN_FLAGS}")
endif()
if (USE_STATIC_LIBRARIES AND CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libasan")
endif ()
if (COMPILER_GCC)
@ -50,7 +50,7 @@ if (SANITIZE)
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=memory")
endif()
if (USE_STATIC_LIBRARIES AND CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libmsan")
endif ()
@ -71,7 +71,7 @@ if (SANITIZE)
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread")
endif()
if (USE_STATIC_LIBRARIES AND CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libtsan")
endif ()
if (COMPILER_GCC)
@ -103,7 +103,7 @@ if (SANITIZE)
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined")
endif()
if (USE_STATIC_LIBRARIES AND CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libubsan")
endif ()
if (COMPILER_GCC)

15
contrib/arrow-cmake/CMakeLists.txt
View File

@ -78,23 +78,14 @@ set(FLATBUFFERS_BINARY_DIR "${ClickHouse_BINARY_DIR}/contrib/flatbuffers")
set(FLATBUFFERS_INCLUDE_DIR "${FLATBUFFERS_SRC_DIR}/include")
# set flatbuffers CMake options
if (USE_STATIC_LIBRARIES)
set(FLATBUFFERS_BUILD_FLATLIB ON CACHE BOOL "Enable the build of the flatbuffers library")
set(FLATBUFFERS_BUILD_SHAREDLIB OFF CACHE BOOL "Disable the build of the flatbuffers shared library")
else ()
set(FLATBUFFERS_BUILD_SHAREDLIB ON CACHE BOOL "Enable the build of the flatbuffers shared library")
set(FLATBUFFERS_BUILD_FLATLIB OFF CACHE BOOL "Disable the build of the flatbuffers library")
endif ()
set(FLATBUFFERS_BUILD_FLATLIB ON CACHE BOOL "Enable the build of the flatbuffers library")
set(FLATBUFFERS_BUILD_SHAREDLIB OFF CACHE BOOL "Disable the build of the flatbuffers shared library")
set(FLATBUFFERS_BUILD_TESTS OFF CACHE BOOL "Skip flatbuffers tests")
add_subdirectory(${FLATBUFFERS_SRC_DIR} "${FLATBUFFERS_BINARY_DIR}")
add_library(_flatbuffers INTERFACE)
if(USE_STATIC_LIBRARIES)
target_link_libraries(_flatbuffers INTERFACE flatbuffers)
else()
target_link_libraries(_flatbuffers INTERFACE flatbuffers_shared)
endif()
target_link_libraries(_flatbuffers INTERFACE flatbuffers)
target_include_directories(_flatbuffers INTERFACE ${FLATBUFFERS_INCLUDE_DIR})
# === hdfs

7
contrib/boringssl-cmake/CMakeLists.txt
View File

@ -139,13 +139,6 @@ if(NOT OPENSSL_NO_ASM)
endif()
endif()
if(BUILD_SHARED_LIBS)
add_definitions(-DBORINGSSL_SHARED_LIBRARY)
# Enable position-independent code globally. This is needed because
# some library targets are OBJECT libraries.
set(CMAKE_POSITION_INDEPENDENT_CODE TRUE)
endif()
set(
CRYPTO_ios_aarch64_SOURCES

9
contrib/c-ares-cmake/CMakeLists.txt
View File

@ -63,13 +63,8 @@ SET(SRCS
"${LIBRARY_DIR}/src/lib/windows_port.c"
)
if (USE_STATIC_LIBRARIES)
add_library(_c-ares STATIC ${SRCS})
target_compile_definitions(_c-ares PUBLIC CARES_STATICLIB)
else()
add_library(_c-ares SHARED ${SRCS})
target_compile_definitions(_c-ares PUBLIC CARES_BUILDING_LIBRARY)
endif()
add_library(_c-ares STATIC ${SRCS})
target_compile_definitions(_c-ares PUBLIC CARES_STATICLIB)
target_compile_definitions(_c-ares PRIVATE HAVE_CONFIG_H=1)

2
contrib/cctz vendored

@ -1 +1 @@
Subproject commit 5c8528fb35e89ee0b3a7157490423fba0d4dd7b5
Subproject commit 7c78edd52b4d65acc103c2f195818ffcabe6fe0d

5
contrib/libunwind-cmake/CMakeLists.txt
View File

@ -43,7 +43,10 @@ set_target_properties(unwind PROPERTIES FOLDER "contrib/libunwind-cmake")
target_include_directories(unwind SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBUNWIND_SOURCE_DIR}/include>)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_NO_HEAP=1 -D_DEBUG -D_LIBUNWIND_IS_NATIVE_ONLY)
target_compile_options(unwind PRIVATE -fno-exceptions -funwind-tables -fno-sanitize=all $<$<COMPILE_LANGUAGE:CXX>:-nostdinc++ -fno-rtti>)
# We should enable optimizations (otherwise it will be too slow in debug)
# and disable sanitizers (otherwise infinite loop may happen)
target_compile_options(unwind PRIVATE -O3 -fno-exceptions -funwind-tables -fno-sanitize=all $<$<COMPILE_LANGUAGE:CXX>:-nostdinc++ -fno-rtti>)
check_c_compiler_flag(-Wunused-but-set-variable HAVE_WARNING_UNUSED_BUT_SET_VARIABLE)
if (HAVE_WARNING_UNUSED_BUT_SET_VARIABLE)

5
contrib/libuv-cmake/CMakeLists.txt
View File

@ -136,11 +136,6 @@ add_library(ch_contrib::uv ALIAS _uv)
target_compile_definitions(_uv PRIVATE ${uv_defines})
target_include_directories(_uv SYSTEM PUBLIC ${SOURCE_DIR}/include PRIVATE ${SOURCE_DIR}/src)
target_link_libraries(_uv ${uv_libraries})
if (NOT USE_STATIC_LIBRARIES)
target_compile_definitions(_uv
INTERFACE USING_UV_SHARED=1
PRIVATE BUILDING_UV_SHARED=1)
endif()
if(UNIX)
# Now for some gibbering horrors from beyond the stars...

2
contrib/llvm-project-cmake/CMakeLists.txt
View File

@ -6,8 +6,6 @@ endif()
option (ENABLE_EMBEDDED_COMPILER "Enable support for 'compile_expressions' option for query execution" ${ENABLE_EMBEDDED_COMPILER_DEFAULT})
# If USE_STATIC_LIBRARIES=0 was passed to CMake, we'll still build LLVM statically to keep complexity minimal.
if (NOT ENABLE_EMBEDDED_COMPILER)
message(STATUS "Not using LLVM")
return()

8
contrib/sentry-native-cmake/CMakeLists.txt
View File

@ -1,4 +1,4 @@
if (NOT OS_FREEBSD AND NOT SPLIT_SHARED_LIBRARIES AND NOT (OS_DARWIN AND COMPILER_CLANG))
if (NOT OS_FREEBSD AND NOT (OS_DARWIN AND COMPILER_CLANG))
option (ENABLE_SENTRY "Enable Sentry" ${ENABLE_LIBRARIES})
else()
option (ENABLE_SENTRY "Enable Sentry" OFF)
@ -51,11 +51,7 @@ endif()
add_library(_sentry ${SRCS})
if(BUILD_SHARED_LIBS)
target_compile_definitions(_sentry PRIVATE SENTRY_BUILD_SHARED)
else()
target_compile_definitions(_sentry PUBLIC SENTRY_BUILD_STATIC)
endif()
target_compile_definitions(_sentry PUBLIC SENTRY_BUILD_STATIC)
target_link_libraries(_sentry PRIVATE ch_contrib::curl pthread)
target_include_directories(_sentry PUBLIC "${SRC_DIR}/include" PRIVATE "${SRC_DIR}/src")

5
docker/images.json
View File

@ -2,7 +2,6 @@
"docker/packager/binary": {
"name": "clickhouse/binary-builder",
"dependent": [
"docker/test/split_build_smoke_test",
"docker/test/codebrowser"
]
},
@ -55,10 +54,6 @@
"name": "clickhouse/stress-test",
"dependent": []
},
"docker/test/split_build_smoke_test": {
"name": "clickhouse/split-build-smoke-test",
"dependent": []
},
"docker/test/codebrowser": {
"name": "clickhouse/codebrowser",
"dependent": []

4
docker/packager/binary/build.sh
View File

@ -107,8 +107,6 @@ fi
mv ./programs/clickhouse* /output
[ -x ./programs/self-extracting/clickhouse ] && mv ./programs/self-extracting/clickhouse /output
mv ./src/unit_tests_dbms /output ||: # may not exist for some binary builds
find . -name '*.so' -print -exec mv '{}' /output \;
find . -name '*.so.*' -print -exec mv '{}' /output \;
prepare_combined_output () {
local OUTPUT
@ -165,7 +163,7 @@ then
)
fi
# May be set for split build or for performance test.
# May be set for performance test.
if [ "" != "$COMBINED_OUTPUT" ]
then
prepare_combined_output /output

21
docker/packager/packager
View File

@ -100,12 +100,11 @@ def run_docker_image_with_env(
subprocess.check_call(cmd, shell=True)
def is_release_build(build_type, package_type, sanitizer, shared_libraries):
def is_release_build(build_type, package_type, sanitizer):
return (
build_type == ""
and package_type == "deb"
and sanitizer == ""
and not shared_libraries
)
@ -116,7 +115,6 @@ def parse_env_variables(
package_type,
cache,
distcc_hosts,
shared_libraries,
clang_tidy,
version,
author,
@ -218,7 +216,7 @@ def parse_env_variables(
cmake_flags.append("-DCMAKE_INSTALL_PREFIX=/usr")
cmake_flags.append("-DCMAKE_INSTALL_SYSCONFDIR=/etc")
cmake_flags.append("-DCMAKE_INSTALL_LOCALSTATEDIR=/var")
if is_release_build(build_type, package_type, sanitizer, shared_libraries):
if is_release_build(build_type, package_type, sanitizer):
cmake_flags.append("-DSPLIT_DEBUG_SYMBOLS=ON")
result.append("WITH_PERFORMANCE=1")
if is_cross_arm:
@ -231,12 +229,10 @@ def parse_env_variables(
cmake_flags.append(f"-DCMAKE_C_COMPILER={cc}")
cmake_flags.append(f"-DCMAKE_CXX_COMPILER={cxx}")
# Create combined output archive for shared library build and for performance tests.
# Create combined output archive for performance tests.
if package_type == "coverity":
result.append("COMBINED_OUTPUT=coverity")
result.append('COVERITY_TOKEN="$COVERITY_TOKEN"')
elif shared_libraries:
result.append("COMBINED_OUTPUT=shared_build")
if sanitizer:
result.append(f"SANITIZER={sanitizer}")
@ -285,15 +281,6 @@ def parse_env_variables(
result.append("BINARY_OUTPUT=tests")
cmake_flags.append("-DENABLE_TESTS=1")
if shared_libraries:
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.
cmake_flags.append("-DENABLE_UTILS=1")
# utils are not included into clickhouse-bundle, so build everything
build_target = "all"
if clang_tidy:
cmake_flags.append("-DENABLE_CLANG_TIDY=1")
cmake_flags.append("-DENABLE_TESTS=1")
@ -371,7 +358,6 @@ if __name__ == "__main__":
default="",
)
parser.add_argument("--shared-libraries", action="store_true")
parser.add_argument("--clang-tidy", action="store_true")
parser.add_argument("--cache", choices=("ccache", "distcc", ""), default="")
parser.add_argument(
@ -424,7 +410,6 @@ if __name__ == "__main__":
args.package_type,
args.cache,
args.distcc_hosts,
args.shared_libraries,
args.clang_tidy,
args.version,
args.author,

2
docker/server/entrypoint.sh
View File

@ -80,7 +80,7 @@ do
done
# if clickhouse user is defined - create it (user "default" already exists out of box)
if [ -n "$CLICKHOUSE_USER" ] && [ "$CLICKHOUSE_USER" != "default" ] || [ -n "$CLICKHOUSE_PASSWORD" ]; then
if [ -n "$CLICKHOUSE_USER" ] && [ "$CLICKHOUSE_USER" != "default" ] || [ -n "$CLICKHOUSE_PASSWORD" ] || [ "$CLICKHOUSE_ACCESS_MANAGEMENT" != "0" ]; then
echo "$0: create new user '$CLICKHOUSE_USER' instead 'default'"
cat <<EOT > /etc/clickhouse-server/users.d/default-user.xml
<clickhouse>

6
docker/test/fuzzer/query-fuzzer-tweaks-users.xml
View File

@ -2,6 +2,7 @@
<profiles>
<default>
<max_execution_time>10</max_execution_time>
<!--
Don't let the fuzzer change this setting (I've actually seen it
do this before).
@ -14,6 +15,11 @@
<max_memory_usage>
<max>10G</max>
</max_memory_usage>
<!-- Analyzer is unstable, not ready for testing. -->
<allow_experimental_analyzer>
<readonly/>
</allow_experimental_analyzer>
</constraints>
</default>
</profiles>

68
docker/test/fuzzer/run-fuzzer.sh
View File

@ -51,7 +51,6 @@ function clone
)
ls -lath ||:
}
function wget_with_retry
@ -75,6 +74,7 @@ function download
./clickhouse ||:
ln -s ./clickhouse ./clickhouse-server
ln -s ./clickhouse ./clickhouse-client
ln -s ./clickhouse ./clickhouse-local
# clickhouse-server is in the current dir
export PATH="$PWD:$PATH"
@ -91,6 +91,12 @@ function configure
cp -av --dereference "$script_dir"/query-fuzzer-tweaks-users.xml db/users.d
cp -av --dereference "$script_dir"/allow-nullable-key.xml db/config.d
cat > db/config.d/max_server_memory_usage_to_ram_ratio.xml <<EOL
<clickhouse>
<max_server_memory_usage_to_ram_ratio>0.75</max_server_memory_usage_to_ram_ratio>
</clickhouse>
EOL
cat > db/config.d/core.xml <<EOL
<clickhouse>
<core_dump>
@ -151,7 +157,7 @@ function fuzz
mkdir -p /var/run/clickhouse-server
# NOTE: we use process substitution here to preserve keep $! as a pid of clickhouse-server
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db 2>&1 | pigz > server.log.gz &
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db > server.log 2>&1 &
server_pid=$!
kill -0 $server_pid
@ -256,12 +262,21 @@ quit
if [ "$server_died" == 1 ]
then
# The server has died.
task_exit_code=210
echo "failure" > status.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
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
then
echo "Lost connection to server. See the logs." > description.txt
fi
if grep -E --text 'Sanitizer: (out-of-memory|failed to allocate)' description.txt
then
# OOM of sanitizer is not a problem we can handle - treat it as success, but preserve the description.
task_exit_code=0
echo "success" > status.txt
else
task_exit_code=210
echo "failure" > status.txt
fi
elif [ "$fuzzer_exit_code" == "143" ] || [ "$fuzzer_exit_code" == "0" ]
then
# Variants of a normal run:
@ -327,24 +342,28 @@ case "$stage" in
time fuzz
;&
"report")
CORE_LINK=''
if [ -f core.gz ]; then
CORE_LINK='<a href="core.gz">core.gz</a>'
fi
grep --text -F '<Fatal>' server.log > fatal.log ||:
pigz server.log
cat > report.html <<EOF ||:
<!DOCTYPE html>
<html lang="en">
<style>
body { font-family: "DejaVu Sans", "Noto Sans", Arial, sans-serif; background: #EEE; }
h1 { margin-left: 10px; }
th, td { border: 0; padding: 5px 10px 5px 10px; text-align: left; vertical-align: top; line-height: 1.5; background-color: #FFF;
td { white-space: pre; font-family: Monospace, Courier New; }
border: 0; box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.05), 0 8px 25px -5px rgba(0, 0, 0, 0.1); }
th, td { border: 0; padding: 5px 10px 5px 10px; text-align: left; vertical-align: top; line-height: 1.5; background-color: #FFF; }
td { white-space: pre; font-family: Monospace, Courier New; box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.05), 0 8px 25px -5px rgba(0, 0, 0, 0.1); }
a { color: #06F; text-decoration: none; }
a:hover, a:active { color: #F40; text-decoration: underline; }
table { border: 0; }
p.links a { padding: 5px; margin: 3px; background: #FFF; line-height: 2; white-space: nowrap; box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.05), 0 8px 25px -5px rgba(0, 0, 0, 0.1); }
th { cursor: pointer; }
</style>
<title>AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST}</title>
@ -352,17 +371,32 @@ th { cursor: pointer; }
<body>
<div class="main">
<h1>AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST}</h1>
<h1>AST Fuzzer for PR <a href="https://github.com/ClickHouse/ClickHouse/pull/${PR_TO_TEST}">#${PR_TO_TEST}</a> @ ${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.gz">server.log.gz</a>
<a href="main.log">main.log</a>
${CORE_LINK}
<a href="run.log">run.log</a>
<a href="fuzzer.log">fuzzer.log</a>
<a href="server.log.gz">server.log.gz</a>
<a href="main.log">main.log</a>
${CORE_LINK}
</p>
<table>
<tr><th>Test name</th><th>Test status</th><th>Description</th></tr>
<tr><td>AST Fuzzer</td><td>$(cat status.txt)</td><td>$(cat description.txt)</td></tr>
<tr>
<th>Test name</th>
<th>Test status</th>
<th>Description</th>
</tr>
<tr>
<td>AST Fuzzer</td>
<td>$(cat status.txt)</td>
<td>$(
clickhouse-local --input-format RawBLOB --output-format RawBLOB --query "SELECT encodeXMLComponent(*) FROM table" < description.txt || cat description.txt
)</td>
</tr>
<tr>
<td colspan="3" style="white-space: pre-wrap;">$(
clickhouse-local --input-format RawBLOB --output-format RawBLOB --query "SELECT encodeXMLComponent(*) FROM table" < fatal.log || cat fatal.log
)</td>
</tr>
</table>
</body>
</html>

1
docker/test/integration/runner/Dockerfile
View File

@ -83,6 +83,7 @@ RUN python3 -m pip install \
pytest \
pytest-order==1.0.0 \
pytest-timeout \
pytest-random \
pytest-xdist \
pytest-repeat \
pytz \

1
docker/test/performance-comparison/perf.py
View File

@ -297,6 +297,7 @@ if not args.use_existing_tables:
# Let's sync the data to avoid writeback affects performance
os.system("sync")
reportStageEnd("sync")
# By default, test all queries.
queries_to_run = range(0, len(test_queries))

9
docker/test/split_build_smoke_test/Dockerfile
View File

@ -1,9 +0,0 @@
# rebuild in #33610
# docker build -t clickhouse/split-build-smoke-test .
ARG FROM_TAG=latest
FROM clickhouse/binary-builder:$FROM_TAG
COPY run.sh /run.sh
COPY process_split_build_smoke_test_result.py /
CMD /run.sh

64
docker/test/split_build_smoke_test/process_split_build_smoke_test_result.py
View File

@ -1,64 +0,0 @@
#!/usr/bin/env python3
import os
import logging
import argparse
import csv
RESULT_LOG_NAME = "run.log"
def process_result(result_folder):
status = "success"
description = "Server started and responded"
summary = [("Smoke test", "OK")]
with open(os.path.join(result_folder, RESULT_LOG_NAME), "r") as run_log:
lines = run_log.read().split("\n")
if not lines or lines[0].strip() != "OK":
status = "failure"
logging.info("Lines is not ok: %s", str("\n".join(lines)))
summary = [("Smoke test", "FAIL")]
description = "Server failed to respond, see result in logs"
result_logs = []
server_log_path = os.path.join(result_folder, "clickhouse-server.log")
stderr_log_path = os.path.join(result_folder, "stderr.log")
client_stderr_log_path = os.path.join(result_folder, "clientstderr.log")
if os.path.exists(server_log_path):
result_logs.append(server_log_path)
if os.path.exists(stderr_log_path):
result_logs.append(stderr_log_path)
if os.path.exists(client_stderr_log_path):
result_logs.append(client_stderr_log_path)
return status, description, summary, result_logs
def write_results(results_file, status_file, results, status):
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)
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
parser = argparse.ArgumentParser(
description="ClickHouse script for parsing results of split build smoke 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")
args = parser.parse_args()
state, description, test_results, 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)
logging.info("Result written")

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

@ -1,22 +0,0 @@
#!/bin/bash
set -x
install_and_run_server() {
mkdir /unpacked
tar -xzf /package_folder/shared_build.tgz -C /unpacked --strip 1
LD_LIBRARY_PATH=/unpacked /unpacked/clickhouse-server --config /unpacked/config/config.xml >/test_output/stderr.log 2>&1 &
}
run_client() {
for i in {1..100}; do
sleep 1
LD_LIBRARY_PATH=/unpacked /unpacked/clickhouse-client --query "select 'OK'" > /test_output/run.log 2> /test_output/clientstderr.log && break
[[ $i == 100 ]] && echo 'FAIL'
done
}
install_and_run_server
run_client
mv /var/log/clickhouse-server/clickhouse-server.log /test_output/clickhouse-server.log
/process_split_build_smoke_test_result.py || echo -e "failure\tCannot parse results" > /test_output/check_status.tsv

209
docker/test/stateless/setup_minio.sh
View File

@ -1,90 +1,151 @@
#!/bin/bash
USAGE='Usage for local run:
set -euxf -o pipefail
./docker/test/stateless/setup_minio.sh { stateful | stateless } ./tests/
export MINIO_ROOT_USER=${MINIO_ROOT_USER:-clickhouse}
export MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-clickhouse}
'
usage() {
echo $"Usage: $0 <stateful|stateless> <test_path> (default path: /usr/share/clickhouse-test)"
exit 1
}
set -e -x -a -u
TEST_TYPE="$1"
shift
case $TEST_TYPE in
stateless) QUERY_DIR=0_stateless ;;
stateful) QUERY_DIR=1_stateful ;;
*) echo "unknown test type $TEST_TYPE"; echo "${USAGE}"; exit 1 ;;
esac
ls -lha
mkdir -p ./minio_data
if [ ! -f ./minio ]; then
MINIO_SERVER_VERSION=${MINIO_SERVER_VERSION:-2022-09-07T22-25-02Z}
MINIO_CLIENT_VERSION=${MINIO_CLIENT_VERSION:-2022-08-28T20-08-11Z}
case $(uname -m) in
x86_64) BIN_ARCH=amd64 ;;
aarch64) BIN_ARCH=arm64 ;;
*) echo "unknown architecture $(uname -m)"; exit 1 ;;
esac
echo 'MinIO binary not found, downloading...'
BINARY_TYPE=$(uname -s | tr '[:upper:]' '[:lower:]')
wget "https://dl.min.io/server/minio/release/${BINARY_TYPE}-${BIN_ARCH}/archive/minio.RELEASE.${MINIO_SERVER_VERSION}" -O ./minio \
&& wget "https://dl.min.io/client/mc/release/${BINARY_TYPE}-${BIN_ARCH}/archive/mc.RELEASE.${MINIO_CLIENT_VERSION}" -O ./mc \
&& chmod +x ./mc ./minio
fi
MINIO_ROOT_USER=${MINIO_ROOT_USER:-clickhouse}
MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-clickhouse}
./minio --version
./minio server --address ":11111" ./minio_data &
i=0
while ! curl -v --silent http://localhost:11111 2>&1 | grep AccessDenied
do
if [[ $i == 60 ]]; then
echo "Failed to setup minio"
exit 0
check_arg() {
local query_dir
if [ ! $# -eq 1 ]; then
if [ ! $# -eq 2 ]; then
echo "ERROR: need either one or two arguments, <stateful|stateless> <test_path> (default path: /usr/share/clickhouse-test)"
usage
fi
fi
echo "Trying to connect to minio"
sleep 1
i=$((i + 1))
done
case "$1" in
stateless)
query_dir="0_stateless"
;;
stateful)
query_dir="1_stateful"
;;
*)
echo "unknown test type ${test_type}"
usage
;;
esac
echo ${query_dir}
}
lsof -i :11111
find_arch() {
local arch
case $(uname -m) in
x86_64)
arch="amd64"
;;
aarch64)
arch="arm64"
;;
*)
echo "unknown architecture $(uname -m)";
exit 1
;;
esac
echo ${arch}
}
sleep 5
find_os() {
local os
os=$(uname -s | tr '[:upper:]' '[:lower:]')
echo "${os}"
}
./mc alias set clickminio http://localhost:11111 clickhouse clickhouse
./mc admin user add clickminio test testtest
./mc admin policy set clickminio readwrite user=test
./mc mb clickminio/test
if [ "$TEST_TYPE" = "stateless" ]; then
./mc policy set public clickminio/test
fi
download_minio() {
local os
local arch
local minio_server_version=${MINIO_SERVER_VERSION:-2022-09-07T22-25-02Z}
local minio_client_version=${MINIO_CLIENT_VERSION:-2022-08-28T20-08-11Z}
os=$(find_os)
arch=$(find_arch)
wget "https://dl.min.io/server/minio/release/${os}-${arch}/archive/minio.RELEASE.${minio_server_version}" -O ./minio
wget "https://dl.min.io/client/mc/release/${os}-${arch}/archive/mc.RELEASE.${minio_client_version}" -O ./mc
chmod +x ./mc ./minio
}
# Upload data to Minio. By default after unpacking all tests will in
# /usr/share/clickhouse-test/queries
start_minio() {
mkdir -p ./minio_data
./minio --version
./minio server --address ":11111" ./minio_data &
wait_for_it
lsof -i :11111
sleep 5
}
TEST_PATH=${1:-/usr/share/clickhouse-test}
MINIO_DATA_PATH=${TEST_PATH}/queries/${QUERY_DIR}/data_minio
setup_minio() {
local test_type=$1
./mc alias set clickminio http://localhost:11111 clickhouse clickhouse
./mc admin user add clickminio test testtest
./mc admin policy set clickminio readwrite user=test
./mc mb clickminio/test
if [ "$test_type" = "stateless" ]; then
./mc policy set public clickminio/test
fi
}
# Iterating over globs will cause redudant FILE variale to be a path to a file, not a filename
# shellcheck disable=SC2045
for FILE in $(ls "${MINIO_DATA_PATH}"); do
echo "$FILE";
./mc cp "${MINIO_DATA_PATH}"/"$FILE" clickminio/test/"$FILE";
done
# uploads data to minio, by default after unpacking all tests
# will be in /usr/share/clickhouse-test/queries
upload_data() {
local query_dir=$1
local test_path=$2
local data_path=${test_path}/queries/${query_dir}/data_minio
mkdir -p ~/.aws
cat <<EOT >> ~/.aws/credentials
# iterating over globs will cause redundant file variable to be
# a path to a file, not a filename
# shellcheck disable=SC2045
for file in $(ls "${data_path}"); do
echo "${file}";
./mc cp "${data_path}"/"${file}" clickminio/test/"${file}";
done
}
setup_aws_credentials() {
local minio_root_user=${MINIO_ROOT_USER:-clickhouse}
local minio_root_password=${MINIO_ROOT_PASSWORD:-clickhouse}
mkdir -p ~/.aws
cat <<EOT >> ~/.aws/credentials
[default]
aws_access_key_id=${MINIO_ROOT_USER}
aws_secret_access_key=${MINIO_ROOT_PASSWORD}
aws_access_key_id=${minio_root_user}
aws_secret_access_key=${minio_root_password}
EOT
}
wait_for_it() {
local counter=0
local max_counter=60
local url="http://localhost:11111"
local params=(
--silent
--verbose
)
while ! curl "${params[@]}" "${url}" 2>&1 | grep AccessDenied
do
if [[ ${counter} == "${max_counter}" ]]; then
echo "failed to setup minio"
exit 0
fi
echo "trying to connect to minio"
sleep 1
counter=$((counter + 1))
done
}
main() {
local query_dir
query_dir=$(check_arg "$@")
if [ ! -f ./minio ]; then
download_minio
fi
start_minio
setup_minio "$1"
upload_data "${query_dir}" "${2:-/usr/share/clickhouse-test}"
setup_aws_credentials
}
main "$@"

4
docker/test/stress/README.md
View File

@ -1,6 +1,6 @@
Allow to run simple ClickHouse stress test in Docker from debian packages.
Allows to run simple ClickHouse stress test in Docker from debian packages.
Actually it runs multiple copies of clickhouse-test (functional tests).
This allows to find problems like segmentation fault which cause shutdown of server.
This allows to find problems like failed assertions and memory safety issues.
Usage:
```

110
docker/test/stress/run.sh
View File

@ -11,31 +11,6 @@ set -x
# core.COMM.PID-TID
sysctl kernel.core_pattern='core.%e.%p-%P'
# Thread Fuzzer allows to check more permutations of possible thread scheduling
# and find more potential issues.
# Temporarily disable ThreadFuzzer with tsan because of https://github.com/google/sanitizers/issues/1540
is_tsan_build=$(clickhouse local -q "select value like '% -fsanitize=thread %' from system.build_options where name='CXX_FLAGS'")
if [ "$is_tsan_build" -eq "0" ]; then
export THREAD_FUZZER_CPU_TIME_PERIOD_US=1000
export THREAD_FUZZER_SLEEP_PROBABILITY=0.1
export THREAD_FUZZER_SLEEP_TIME_US=100000
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_TIME_US=10000
fi
function install_packages()
{
@ -54,7 +29,7 @@ function configure()
# we mount tests folder from repo to /usr/share
ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
ln -s /usr/share/clickhouse-test/ci/download_release_packets.py /usr/bin/download_release_packets
ln -s /usr/share/clickhouse-test/ci/download_release_packages.py /usr/bin/download_release_packages
ln -s /usr/share/clickhouse-test/ci/get_previous_release_tag.py /usr/bin/get_previous_release_tag
# avoid too slow startup
@ -78,6 +53,7 @@ function configure()
local total_mem
total_mem=$(awk '/MemTotal/ { print $(NF-1) }' /proc/meminfo) # KiB
total_mem=$(( total_mem*1024 )) # bytes
# Set maximum memory usage as half of total memory (less chance of OOM).
#
# But not via max_server_memory_usage but via max_memory_usage_for_user,
@ -90,16 +66,17 @@ function configure()
# max_server_memory_usage will be hard limit, and queries that should be
# executed regardless memory limits will use max_memory_usage_for_user=0,
# instead of relying on max_untracked_memory
local max_server_mem
max_server_mem=$((total_mem*75/100)) # 75%
echo "Setting max_server_memory_usage=$max_server_mem"
max_server_memory_usage_to_ram_ratio=0.5
echo "Setting max_server_memory_usage_to_ram_ratio to ${max_server_memory_usage_to_ram_ratio}"
cat > /etc/clickhouse-server/config.d/max_server_memory_usage.xml <<EOL
<clickhouse>
<max_server_memory_usage>${max_server_mem}</max_server_memory_usage>
<max_server_memory_usage_to_ram_ratio>${max_server_memory_usage_to_ram_ratio}</max_server_memory_usage_to_ram_ratio>
</clickhouse>
EOL
local max_users_mem
max_users_mem=$((total_mem*50/100)) # 50%
max_users_mem=$((total_mem*30/100)) # 30%
echo "Setting max_memory_usage_for_user=$max_users_mem"
cat > /etc/clickhouse-server/users.d/max_memory_usage_for_user.xml <<EOL
<clickhouse>
@ -123,6 +100,29 @@ EOL
<core_path>$PWD</core_path>
</clickhouse>
EOL
# Let OOM killer terminate other processes before clickhouse-server:
cat > /etc/clickhouse-server/config.d/oom_score.xml <<EOL
<clickhouse>
<oom_score>-1000</oom_score>
</clickhouse>
EOL
# Analyzer is not yet ready for testing
cat > /etc/clickhouse-server/users.d/no_analyzer.xml <<EOL
<clickhouse>
<profiles>
<default>
<constraints>
<allow_experimental_analyzer>
<readonly/>
</allow_experimental_analyzer>
</constraints>
</default>
</profiles>
</clickhouse>
EOL
}
function stop()
@ -210,6 +210,31 @@ quit
install_packages package_folder
# Thread Fuzzer allows to check more permutations of possible thread scheduling
# and find more potential issues.
# Temporarily disable ThreadFuzzer with tsan because of https://github.com/google/sanitizers/issues/1540
is_tsan_build=$(clickhouse local -q "select value like '% -fsanitize=thread %' from system.build_options where name='CXX_FLAGS'")
if [ "$is_tsan_build" -eq "0" ]; then
export THREAD_FUZZER_CPU_TIME_PERIOD_US=1000
export THREAD_FUZZER_SLEEP_PROBABILITY=0.1
export THREAD_FUZZER_SLEEP_TIME_US=100000
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_TIME_US=10000
fi
export ZOOKEEPER_FAULT_INJECTION=1
configure
@ -344,10 +369,10 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
echo "Clone previous release repository"
git clone https://github.com/ClickHouse/ClickHouse.git --no-tags --progress --branch=$previous_release_tag --no-recurse-submodules --depth=1 previous_release_repository
echo "Download previous release server"
echo "Download clickhouse-server from the previous release"
mkdir previous_release_package_folder
echo $previous_release_tag | download_release_packets && echo -e 'Download script exit code\tOK' >> /test_output/test_results.tsv \
echo $previous_release_tag | download_release_packages && echo -e 'Download script exit code\tOK' >> /test_output/test_results.tsv \
|| echo -e 'Download script failed\tFAIL' >> /test_output/test_results.tsv
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.clean.log
@ -364,10 +389,10 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
echo -e "Backward compatibility check: Failed to clone previous release tests\tFAIL" >> /test_output/test_results.tsv
elif ! [ "$(ls -A previous_release_package_folder/clickhouse-common-static_*.deb && ls -A previous_release_package_folder/clickhouse-server_*.deb)" ]
then
echo -e "Backward compatibility check: Failed to download previous release packets\tFAIL" >> /test_output/test_results.tsv
echo -e "Backward compatibility check: Failed to download previous release packages\tFAIL" >> /test_output/test_results.tsv
else
echo -e "Successfully cloned previous release tests\tOK" >> /test_output/test_results.tsv
echo -e "Successfully downloaded previous release packets\tOK" >> /test_output/test_results.tsv
echo -e "Successfully downloaded previous release packages\tOK" >> /test_output/test_results.tsv
# Uninstall current packages
dpkg --remove clickhouse-client
@ -431,7 +456,13 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
|| echo -e 'Backward compatibility check: Test script failed\tFAIL' >> /test_output/test_results.tsv
rm -rf tmp_stress_output
clickhouse-client --query="SELECT 'Tables count:', count() FROM system.tables"
# We experienced deadlocks in this command in very rare cases. Let's debug it:
timeout 10m clickhouse-client --query="SELECT 'Tables count:', count() FROM system.tables" ||
(
echo "thread apply all backtrace (on select tables count)" >> /test_output/gdb.log
timeout 30m gdb -batch -ex 'thread apply all backtrace' -p "$(cat /var/run/clickhouse-server/clickhouse-server.pid)" | ts '%Y-%m-%d %H:%M:%S' >> /test_output/gdb.log
clickhouse stop --force
)
stop 1
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.backward.stress.log
@ -439,7 +470,8 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
# Start new server
mv package_folder/clickhouse /usr/bin/
mv package_folder/clickhouse.debug /usr/lib/debug/usr/bin/clickhouse.debug
export ZOOKEEPER_FAULT_INJECTION=1
# Disable fault injections on start (we don't test them here, and it can lead to tons of requests in case of huge number of tables).
export ZOOKEEPER_FAULT_INJECTION=0
configure
start 500
clickhouse-client --query "SELECT 'Backward compatibility check: Server successfully started', 'OK'" >> /test_output/test_results.tsv \
@ -452,7 +484,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
sleep 60
stop
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.backward.clean.log
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.backward.dirty.log
# Error messages (we should ignore some errors)
# FIXME https://github.com/ClickHouse/ClickHouse/issues/38643 ("Unknown index: idx.")
@ -500,7 +532,7 @@ if [ "$DISABLE_BC_CHECK" -ne "1" ]; then
-e "MutateFromLogEntryTask" \
-e "No connection to ZooKeeper, cannot get shared table ID" \
-e "Session expired" \
/var/log/clickhouse-server/clickhouse-server.backward.clean.log | zgrep -Fa "<Error>" > /test_output/bc_check_error_messages.txt \
/var/log/clickhouse-server/clickhouse-server.backward.dirty.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

3
docker/test/stress/stress
View File

@ -14,9 +14,6 @@ def get_options(i, backward_compatibility_check):
if 0 < i:
options.append("--order=random")
if i % 3 == 1:
options.append("--db-engine=Ordinary")
if i % 3 == 2 and not backward_compatibility_check:
options.append(
'''--db-engine="Replicated('/test/db/test_{}', 's1', 'r1')"'''.format(i)

82
docker/test/testflows/runner/Dockerfile
View File

@ -1,82 +0,0 @@
# docker build -t clickhouse/testflows-runner .
FROM ubuntu:20.04
# ARG for quick switch to a given ubuntu mirror
ARG apt_archive="http://archive.ubuntu.com"
RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
RUN apt-get update \
&& env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
ca-certificates \
bash \
btrfs-progs \
e2fsprogs \
iptables \
xfsprogs \
tar \
pigz \
wget \
git \
iproute2 \
cgroupfs-mount \
python3-pip \
tzdata \
libicu-dev \
bsdutils \
curl \
liblua5.1-dev \
luajit \
libssl-dev \
libcurl4-openssl-dev \
gdb \
&& rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \
/tmp/* \
&& apt-get clean
ENV TZ=Europe/Moscow
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
RUN pip3 install urllib3 testflows==1.7.20 docker-compose==1.29.2 docker==5.0.0 dicttoxml kazoo tzlocal==2.1 pytz python-dateutil numpy
ENV DOCKER_CHANNEL stable
ENV DOCKER_VERSION 20.10.6
# Architecture of the image when BuildKit/buildx is used
ARG TARGETARCH
# Install docker
RUN arch=${TARGETARCH:-amd64} \
&& case $arch in \
amd64) rarch=x86_64 ;; \
arm64) rarch=aarch64 ;; \
esac \
&& set -eux \
&& if ! wget -nv -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/${rarch}/docker-${DOCKER_VERSION}.tgz"; then \
echo >&2 "error: failed to download 'docker-${DOCKER_VERSION}' from '${DOCKER_CHANNEL}' for '${rarch}'" \
&& exit 1; \
fi \
&& tar --extract \
--file docker.tgz \
--strip-components 1 \
--directory /usr/local/bin/ \
&& rm docker.tgz \
&& dockerd --version \
&& docker --version
COPY modprobe.sh /usr/local/bin/modprobe
COPY dockerd-entrypoint.sh /usr/local/bin/
COPY process_testflows_result.py /usr/local/bin/
RUN set -x \
&& addgroup --system dockremap \
&& adduser --system dockremap \
&& adduser dockremap dockremap \
&& echo 'dockremap:165536:65536' >> /etc/subuid \
&& echo 'dockremap:165536:65536' >> /etc/subgid
VOLUME /var/lib/docker
EXPOSE 2375
ENTRYPOINT ["dockerd-entrypoint.sh"]
CMD ["sh", "-c", "python3 regression.py --no-color -o new-fails --local --clickhouse-binary-path ${CLICKHOUSE_TESTS_SERVER_BIN_PATH} --log test.log ${TESTFLOWS_OPTS}; cat test.log | tfs report results --format json > results.json; /usr/local/bin/process_testflows_result.py || echo -e 'failure\tCannot parse results' > check_status.tsv; find * -type f | grep _instances | grep clickhouse-server | xargs -n1 tar -rvf clickhouse_logs.tar; gzip -9 clickhouse_logs.tar"]

39
docker/test/testflows/runner/dockerd-entrypoint.sh
View File

@ -1,39 +0,0 @@
#!/bin/bash
set -e
echo "Configure to use Yandex dockerhub-proxy"
mkdir -p /etc/docker/
cat > /etc/docker/daemon.json << EOF
{
"insecure-registries" : ["dockerhub-proxy.dockerhub-proxy-zone:5000"],
"registry-mirrors" : ["http://dockerhub-proxy.dockerhub-proxy-zone:5000"]
}
EOF
# In case of test hung it is convenient to use pytest --pdb to debug it,
# and on hung you can simply press Ctrl-C and it will spawn a python pdb,
# but on SIGINT dockerd will exit, so ignore it to preserve the daemon.
trap '' INT
dockerd --host=unix:///var/run/docker.sock --host=tcp://0.0.0.0:2375 &>/var/log/somefile &
set +e
reties=0
while true; do
docker info &>/dev/null && break
reties=$((reties+1))
if [[ $reties -ge 100 ]]; then # 10 sec max
echo "Can't start docker daemon, timeout exceeded." >&2
exit 1;
fi
sleep 0.1
done
set -e
echo "Start tests"
export CLICKHOUSE_TESTS_SERVER_BIN_PATH=/clickhouse
export CLICKHOUSE_TESTS_CLIENT_BIN_PATH=/clickhouse
export CLICKHOUSE_TESTS_BASE_CONFIG_DIR=/clickhouse-config
export CLICKHOUSE_ODBC_BRIDGE_BINARY_PATH=/clickhouse-odbc-bridge
cd /ClickHouse/tests/testflows
exec "$@"

20
docker/test/testflows/runner/modprobe.sh
View File

@ -1,20 +0,0 @@
#!/bin/sh
set -eu
# "modprobe" without modprobe
# https://twitter.com/lucabruno/status/902934379835662336
# this isn't 100% fool-proof, but it'll have a much higher success rate than simply using the "real" modprobe
# Docker often uses "modprobe -va foo bar baz"
# so we ignore modules that start with "-"
for module; do
if [ "${module#-}" = "$module" ]; then
ip link show "$module" || true
lsmod | grep "$module" || true
fi
done
# remove /usr/local/... from PATH so we can exec the real modprobe as a last resort
export PATH='/usr/sbin:/usr/bin:/sbin:/bin'
exec modprobe "$@"

71
docker/test/testflows/runner/process_testflows_result.py
View File

@ -1,71 +0,0 @@
#!/usr/bin/env python3
import os
import logging
import argparse
import csv
import json
def process_result(result_folder):
json_path = os.path.join(result_folder, "results.json")
if not os.path.exists(json_path):
return "success", "No testflows in branch", None, []
test_binary_log = os.path.join(result_folder, "test.log")
with open(json_path) as source:
results = json.loads(source.read())
total_tests = 0
total_ok = 0
total_fail = 0
total_other = 0
test_results = []
for test in results["tests"]:
test_name = test["test"]["test_name"]
test_result = test["result"]["result_type"].upper()
test_time = str(test["result"]["message_rtime"])
total_tests += 1
if test_result == "OK":
total_ok += 1
elif test_result == "FAIL" or test_result == "ERROR":
total_fail += 1
else:
total_other += 1
test_results.append((test_name, test_result, test_time))
if total_fail != 0:
status = "failure"
else:
status = "success"
description = "failed: {}, passed: {}, other: {}".format(
total_fail, total_ok, total_other
)
return status, description, test_results, [json_path, test_binary_log]
def write_results(results_file, status_file, results, status):
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)
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
parser = argparse.ArgumentParser(
description="ClickHouse script for parsing results of Testflows tests"
)
parser.add_argument("--in-results-dir", default="./")
parser.add_argument("--out-results-file", default="./test_results.tsv")
parser.add_argument("--out-status-file", default="./check_status.tsv")
args = parser.parse_args()
state, description, test_results, 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)
logging.info("Result written")

12
docs/en/development/continuous-integration.md
View File

@ -118,7 +118,6 @@ Builds ClickHouse in various configurations for use in further steps. You have t
- **Compiler**: `gcc-9` or `clang-10` (or `clang-10-xx` for other architectures e.g. `clang-10-freebsd`).
- **Build type**: `Debug` or `RelWithDebInfo` (cmake).
- **Sanitizer**: `none` (without sanitizers), `address` (ASan), `memory` (MSan), `undefined` (UBSan), or `thread` (TSan).
- **Split** `splitted` is a [split build](../development/build.md#split-build)
- **Status**: `success` or `fail`
- **Build log**: link to the building and files copying log, useful when build failed.
- **Build time**.
@ -130,7 +129,6 @@ Builds ClickHouse in various configurations for use in further steps. You have t
- `clickhouse`: Main built binary.
- `clickhouse-odbc-bridge`
- `unit_tests_dbms`: GoogleTest binary with ClickHouse unit tests.
- `shared_build.tgz`: build with shared libraries.
- `performance.tgz`: Special package for performance tests.
@ -169,16 +167,6 @@ concurrency-related errors. If it fails:
of error.
## Split Build Smoke Test
Checks that the server build in [split build](../development/developer-instruction.md#split-build)
configuration can start and run simple queries. If it fails:
* Fix other test errors first;
* Build the server in [split build](../development/developer-instruction.md#split-build) configuration
locally and check whether it can start and run `select 1`.
## Compatibility Check
Checks that `clickhouse` binary runs on distributions with old libc versions. If it fails, ask a maintainer for help.

38
docs/en/engines/table-engines/integrations/kafka.md
View File

@ -34,7 +34,14 @@ SETTINGS
[kafka_max_block_size = 0,]
[kafka_skip_broken_messages = N,]
[kafka_commit_every_batch = 0,]
[kafka_thread_per_consumer = 0]
[kafka_client_id = '',]
[kafka_poll_timeout_ms = 0,]
[kafka_poll_max_batch_size = 0,]
[kafka_flush_interval_ms = 0,]
[kafka_thread_per_consumer = 0,]
[kafka_handle_error_mode = 'default',]
[kafka_commit_on_select = false,]
[kafka_max_rows_per_message = 1];
```
Required parameters:
@ -46,13 +53,20 @@ Required parameters:
Optional parameters:
- `kafka_row_delimiter` — Delimiter character, which ends the message.
- `kafka_row_delimiter` — Delimiter character, which ends the message. **This setting is deprecated and is no longer used, not left for compatibility reasons.**
- `kafka_schema` — Parameter that must be used if the format requires a schema definition. For example, [Cap’n Proto](https://capnproto.org/) requires the path to the schema file and the name of the root `schema.capnp:Message` object.
- `kafka_num_consumers` — The number of consumers per table. Default: `1`. Specify more consumers if the throughput of one consumer is insufficient. The total number of consumers should not exceed the number of partitions in the topic, since only one consumer can be assigned per partition, and must not be greater than the number of physical cores on the server where ClickHouse is deployed.
- `kafka_max_block_size` — The maximum batch size (in messages) for poll (default: `max_block_size`).
- `kafka_skip_broken_messages` — Kafka message parser tolerance to schema-incompatible messages per block. Default: `0`. If `kafka_skip_broken_messages = N` then the engine skips *N* Kafka messages that cannot be parsed (a message equals a row of data).
- `kafka_commit_every_batch` — Commit every consumed and handled batch instead of a single commit after writing a whole block (default: `0`).
- `kafka_thread_per_consumer` — Provide independent thread for each consumer (default: `0`). When enabled, every consumer flush the data independently, in parallel (otherwise — rows from several consumers squashed to form one block).
- `kafka_num_consumers` — The number of consumers per table. Specify more consumers if the throughput of one consumer is insufficient. The total number of consumers should not exceed the number of partitions in the topic, since only one consumer can be assigned per partition, and must not be greater than the number of physical cores on the server where ClickHouse is deployed. Default: `1`.
- `kafka_max_block_size` — The maximum batch size (in messages) for poll. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
- `kafka_skip_broken_messages` — Kafka message parser tolerance to schema-incompatible messages per block. If `kafka_skip_broken_messages = N` then the engine skips *N* Kafka messages that cannot be parsed (a message equals a row of data). Default: `0`.
- `kafka_commit_every_batch` — Commit every consumed and handled batch instead of a single commit after writing a whole block. Default: `0`.
- `kafka_client_id` — Client identifier. Empty by default.
- `kafka_poll_timeout_ms` — Timeout for single poll from Kafka. Default: [stream_poll_timeout_ms](../../../operations/settings/settings.md#stream_poll_timeout_ms).
- `kafka_poll_max_batch_size` — Maximum amount of messages to be polled in a single Kafka poll. Default: [max_block_size](../../../operations/settings/settings.md#setting-max_block_size).
- `kafka_flush_interval_ms` — Timeout for flushing data from Kafka. Default: [stream_flush_interval_ms](../../../operations/settings/settings.md#stream-flush-interval-ms).
- `kafka_thread_per_consumer` — Provide independent thread for each consumer. When enabled, every consumer flush the data independently, in parallel (otherwise — rows from several consumers squashed to form one block). Default: `0`.
- `kafka_handle_error_mode` — How to handle errors for Kafka engine. Possible values: default, stream.
- `kafka_commit_on_select` — Commit messages when select query is made. Default: `false`.
- `kafka_max_rows_per_message` — The maximum number of rows written in one kafka message for row-based formats. Default : `1`.
Examples:
@ -94,7 +108,7 @@ Do not use this method in new projects. If possible, switch old projects to the
``` sql
Kafka(kafka_broker_list, kafka_topic_list, kafka_group_name, kafka_format
[, kafka_row_delimiter, kafka_schema, kafka_num_consumers, kafka_skip_broken_messages])
[, kafka_row_delimiter, kafka_schema, kafka_num_consumers, kafka_max_block_size, kafka_skip_broken_messages, kafka_commit_every_batch, kafka_client_id, kafka_poll_timeout_ms, kafka_poll_max_batch_size, kafka_flush_interval_ms, kafka_thread_per_consumer, kafka_handle_error_mode, kafka_commit_on_select, kafka_max_rows_per_message]);
```
</details>
@ -193,6 +207,14 @@ Example:
- `_headers.name` — Array of message's headers keys.
- `_headers.value` — Array of message's headers values.
## Data formats support {#data-formats-support}
Kafka engine supports all [formats](../../../interfaces/formats.md) supported in ClickHouse.
The number of rows in one Kafka message depends on whether the format is row-based or block-based:
- For row-based formats the number of rows in one Kafka message can be controlled by setting `kafka_max_rows_per_message`.
- For block-based formats we cannot divide block into smaller parts, but the number of rows in one block can be controlled by general setting [max_block_size](../../../operations/settings/settings.md#setting-max_block_size).
**See Also**
- [Virtual columns](../../../engines/table-engines/index.md#table_engines-virtual_columns)

24
docs/en/engines/table-engines/integrations/nats.md
View File

@ -37,8 +37,10 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
[nats_max_block_size = N,]
[nats_flush_interval_ms = N,]
[nats_username = 'user',]
[nats_password = 'password']
[redis_password = 'clickhouse']
[nats_password = 'password',]
[nats_token = 'clickhouse',]
[nats_startup_connect_tries = '5']
[nats_max_rows_per_message = 1]
```
Required parameters:
@ -49,7 +51,7 @@ Required parameters:
Optional parameters:
- `nats_row_delimiter` – Delimiter character, which ends the message.
- `nats_row_delimiter` – Delimiter character, which ends the message. **This setting is deprecated and is no longer used, not left for compatibility reasons.**
- `nats_schema` – Parameter that must be used if the format requires a schema definition. For example, [Cap’n Proto](https://capnproto.org/) requires the path to the schema file and the name of the root `schema.capnp:Message` object.
- `nats_num_consumers` – The number of consumers per table. Default: `1`. Specify more consumers if the throughput of one consumer is insufficient.
- `nats_queue_group` – Name for queue group of NATS subscribers. Default is the table name.
@ -57,11 +59,13 @@ Optional parameters:
- `nats_reconnect_wait` – Amount of time in milliseconds to sleep between each reconnect attempt. Default: `5000`.
- `nats_server_list` - Server list for connection. Can be specified to connect to NATS cluster.
- `nats_skip_broken_messages` - NATS message parser tolerance to schema-incompatible messages per block. Default: `0`. If `nats_skip_broken_messages = N` then the engine skips *N* RabbitMQ messages that cannot be parsed (a message equals a row of data).
- `nats_max_block_size` - Number of row collected by poll(s) for flushing data from NATS.
- `nats_flush_interval_ms` - Timeout for flushing data read from NATS.
- `nats_max_block_size` - Number of row collected by poll(s) for flushing data from NATS. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
- `nats_flush_interval_ms` - Timeout for flushing data read from NATS. Default: [stream_flush_interval_ms](../../../operations/settings/settings.md#stream-flush-interval-ms).
- `nats_username` - NATS username.
- `nats_password` - NATS password.
- `nats_token` - NATS auth token.
- `nats_startup_connect_tries` - Number of connect tries at startup. Default: `5`.
- `nats_max_rows_per_message` — The maximum number of rows written in one NATS message for row-based formats. (default : `1`).
SSL connection:
@ -159,6 +163,14 @@ If you want to change the target table by using `ALTER`, we recommend disabling
## Virtual Columns {#virtual-columns}
- `_subject` - NATS message subject.
- `_subject` - NATS message subject.
## Data formats support {#data-formats-support}
NATS engine supports all [formats](../../../interfaces/formats.md) supported in ClickHouse.
The number of rows in one NATS message depends on whether the format is row-based or block-based:
- For row-based formats the number of rows in one NATS message can be controlled by setting `nats_max_rows_per_message`.
- For block-based formats we cannot divide block into smaller parts, but the number of rows in one block can be controlled by general setting [max_block_size](../../../operations/settings/settings.md#setting-max_block_size).
[Original article](https://clickhouse.com/docs/en/engines/table-engines/integrations/nats/) <!--hide-->

67
docs/en/engines/table-engines/integrations/rabbitmq.md
View File

@ -37,8 +37,16 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
[rabbitmq_persistent = 0,]
[rabbitmq_skip_broken_messages = N,]
[rabbitmq_max_block_size = N,]
[rabbitmq_flush_interval_ms = N]
[rabbitmq_queue_settings_list = 'x-dead-letter-exchange=my-dlx,x-max-length=10,x-overflow=reject-publish']
[rabbitmq_flush_interval_ms = N,]
[rabbitmq_queue_settings_list = 'x-dead-letter-exchange=my-dlx,x-max-length=10,x-overflow=reject-publish',]
[rabbitmq_queue_consume = false,]
[rabbitmq_address = '',]
[rabbitmq_vhost = '/',]
[rabbitmq_queue_consume = false,]
[rabbitmq_username = '',]
[rabbitmq_password = '',]
[rabbitmq_commit_on_select = false,]
[rabbitmq_max_rows_per_message = 1]
```
Required parameters:
@ -49,19 +57,27 @@ Required parameters:
Optional parameters:
- `rabbitmq_exchange_type` – The type of RabbitMQ exchange: `direct`, `fanout`, `topic`, `headers`, `consistent_hash`. Default: `fanout`.
- `rabbitmq_routing_key_list` – A comma-separated list of routing keys.
- `rabbitmq_row_delimiter` – Delimiter character, which ends the message.
- `rabbitmq_schema` – Parameter that must be used if the format requires a schema definition. For example, [Cap’n Proto](https://capnproto.org/) requires the path to the schema file and the name of the root `schema.capnp:Message` object.
- `rabbitmq_num_consumers` – The number of consumers per table. Default: `1`. Specify more consumers if the throughput of one consumer is insufficient.
- `rabbitmq_num_queues` – Total number of queues. Default: `1`. Increasing this number can significantly improve performance.
- `rabbitmq_queue_base` - Specify a hint for queue names. Use cases of this setting are described below.
- `rabbitmq_deadletter_exchange` - Specify name for a [dead letter exchange](https://www.rabbitmq.com/dlx.html). You can create another table with this exchange name and collect messages in cases when they are republished to dead letter exchange. By default dead letter exchange is not specified.
- `rabbitmq_persistent` - If set to 1 (true), in insert query delivery mode will be set to 2 (marks messages as 'persistent'). Default: `0`.
- `rabbitmq_skip_broken_messages` – RabbitMQ message parser tolerance to schema-incompatible messages per block. Default: `0`. If `rabbitmq_skip_broken_messages = N` then the engine skips *N* RabbitMQ messages that cannot be parsed (a message equals a row of data).
- `rabbitmq_max_block_size`
- `rabbitmq_flush_interval_ms`
- `rabbitmq_queue_settings_list` - allows to set RabbitMQ settings when creating a queue. Available settings: `x-max-length`, `x-max-length-bytes`, `x-message-ttl`, `x-expires`, `x-priority`, `x-max-priority`, `x-overflow`, `x-dead-letter-exchange`, `x-queue-type`. The `durable` setting is enabled automatically for the queue.
- `rabbitmq_exchange_type` – The type of RabbitMQ exchange: `direct`, `fanout`, `topic`, `headers`, `consistent_hash`. Default: `fanout`.
- `rabbitmq_routing_key_list` – A comma-separated list of routing keys.
- `rabbitmq_row_delimiter` – Delimiter character, which ends the message. **This setting is deprecated and is no longer used, not left for compatibility reasons.**
- `rabbitmq_schema` – Parameter that must be used if the format requires a schema definition. For example, [Cap’n Proto](https://capnproto.org/) requires the path to the schema file and the name of the root `schema.capnp:Message` object.
- `rabbitmq_num_consumers` – The number of consumers per table. Specify more consumers if the throughput of one consumer is insufficient. Default: `1`
- `rabbitmq_num_queues` – Total number of queues. Increasing this number can significantly improve performance. Default: `1`.
- `rabbitmq_queue_base` - Specify a hint for queue names. Use cases of this setting are described below.
- `rabbitmq_deadletter_exchange` - Specify name for a [dead letter exchange](https://www.rabbitmq.com/dlx.html). You can create another table with this exchange name and collect messages in cases when they are republished to dead letter exchange. By default dead letter exchange is not specified.
- `rabbitmq_persistent` - If set to 1 (true), in insert query delivery mode will be set to 2 (marks messages as 'persistent'). Default: `0`.
- `rabbitmq_skip_broken_messages` – RabbitMQ message parser tolerance to schema-incompatible messages per block. If `rabbitmq_skip_broken_messages = N` then the engine skips *N* RabbitMQ messages that cannot be parsed (a message equals a row of data). Default: `0`.
- `rabbitmq_max_block_size` - Number of row collected before flushing data from RabbitMQ. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
- `rabbitmq_flush_interval_ms` - Timeout for flushing data from RabbitMQ. Default: [stream_flush_interval_ms](../../../operations/settings/settings.md#stream-flush-interval-ms).
- `rabbitmq_queue_settings_list` - allows to set RabbitMQ settings when creating a queue. Available settings: `x-max-length`, `x-max-length-bytes`, `x-message-ttl`, `x-expires`, `x-priority`, `x-max-priority`, `x-overflow`, `x-dead-letter-exchange`, `x-queue-type`. The `durable` setting is enabled automatically for the queue.
- `rabbitmq_address` - Address for connection. Use ether this setting or `rabbitmq_host_port`.
- `rabbitmq_vhost` - RabbitMQ vhost. Default: `'\'`.
- `rabbitmq_queue_consume` - Use user-defined queues and do not make any RabbitMQ setup: declaring exchanges, queues, bindings. Default: `false`.
- `rabbitmq_username` - RabbitMQ username.
- `rabbitmq_password` - RabbitMQ password.
- `rabbitmq_commit_on_select` - Commit messages when select query is made. Default: `false`.
- `rabbitmq_max_rows_per_message` — The maximum number of rows written in one RabbitMQ message for row-based formats. Default : `1`.
SSL connection:
@ -166,11 +182,20 @@ Example:
## Virtual Columns {#virtual-columns}
- `_exchange_name` - RabbitMQ exchange name.
- `_channel_id` - ChannelID, on which consumer, who received the message, was declared.
- `_delivery_tag` - DeliveryTag of the received message. Scoped per channel.
- `_redelivered` - `redelivered` flag of the message.
- `_message_id` - messageID of the received message; non-empty if was set, when message was published.
- `_timestamp` - timestamp of the received message; non-empty if was set, when message was published.
- `_exchange_name` - RabbitMQ exchange name.
- `_channel_id` - ChannelID, on which consumer, who received the message, was declared.
- `_delivery_tag` - DeliveryTag of the received message. Scoped per channel.
- `_redelivered` - `redelivered` flag of the message.
- `_message_id` - messageID of the received message; non-empty if was set, when message was published.
- `_timestamp` - timestamp of the received message; non-empty if was set, when message was published.
## Data formats support {#data-formats-support}
RabbitMQ engine supports all [formats](../../../interfaces/formats.md) supported in ClickHouse.
The number of rows in one RabbitMQ message depends on whether the format is row-based or block-based:
- For row-based formats the number of rows in one RabbitMQ message can be controlled by setting `rabbitmq_max_rows_per_message`.
- For block-based formats we cannot divide block into smaller parts, but the number of rows in one block can be controlled by general setting [max_block_size](../../../operations/settings/settings.md#setting-max_block_size).
[Original article](https://clickhouse.com/docs/en/engines/table-engines/integrations/rabbitmq/) <!--hide-->

659
docs/en/interfaces/formats.md
View File

File diff suppressed because it is too large Load Diff

1573
docs/en/interfaces/schema-inference.md Normal file
View File

File diff suppressed because it is too large Load Diff

23
docs/en/operations/backup.md
View File

@ -9,6 +9,29 @@ slug: /en/operations/backup
- [Backup/restore using an S3 disk](#backuprestore-using-an-s3-disk)
- [Alternatives](#alternatives)
## Command summary
```bash
BACKUP|RESTORE
TABLE [db.]table_name [AS [db.]table_name_in_backup]
[PARTITION[S] partition_expr [,...]] |
DICTIONARY [db.]dictionary_name [AS [db.]name_in_backup] |
DATABASE database_name [AS database_name_in_backup]
[EXCEPT TABLES ...] |
TEMPORARY TABLE table_name [AS table_name_in_backup] |
VIEW view_name [AS view_name_in_backup]
ALL TEMPORARY TABLES [EXCEPT ...] |
ALL DATABASES [EXCEPT ...] } [,...]
[ON CLUSTER 'cluster_name']
TO|FROM File('<path>/<filename>') | Disk('<disk_name>', '<path>/') | S3('<S3 endpoint>/<path>', '<Access key ID>', '<Secret access key>')
[SETTINGS base_backup = File('<path>/<filename>') | Disk(...) | S3('<S3 endpoint>/<path>', '<Access key ID>', '<Secret access key>')]
```
:::note ALL
`ALL` is only applicable to the `RESTORE` command.
:::
## Background
While [replication](../engines/table-engines/mergetree-family/replication.md) provides protection from hardware failures, it does not protect against human errors: accidental deletion of data, deletion of the wrong table or a table on the wrong cluster, and software bugs that result in incorrect data processing or data corruption. In many cases mistakes like these will affect all replicas. ClickHouse has built-in safeguards to prevent some types of mistakes — for example, by default [you can’t just drop tables with a MergeTree-like engine containing more than 50 Gb of data](server-configuration-parameters/settings.md#max-table-size-to-drop). However, these safeguards do not cover all possible cases and can be circumvented.

7
docs/en/operations/settings/merge-tree-settings.md
View File

@ -127,6 +127,13 @@ Default value: 100000.
A large number of parts in a table reduces performance of ClickHouse queries and increases ClickHouse boot time. Most often this is a consequence of an incorrect design (mistakes when choosing a partitioning strategy - too small partitions).
## simultaneous_parts_removal_limit {#simultaneous-parts-removal-limit}
If there are a lot of outdated parts cleanup thread will try to delete up to `simultaneous_parts_removal_limit` parts during one iteration.
`simultaneous_parts_removal_limit` set to `0` means unlimited.
Default value: 0.
## replicated_deduplication_window {#replicated-deduplication-window}
The number of most recently inserted blocks for which ClickHouse Keeper stores hash sums to check for duplicates.

8
docs/en/operations/settings/settings.md
View File

@ -1011,6 +1011,12 @@ The default value is 7500.
The smaller the value, the more often data is flushed into the table. Setting the value too low leads to poor performance.
## stream_poll_timeout_ms {#stream_poll_timeout_ms}
Timeout for polling data from/to streaming storages.
Default value: 500.
## load_balancing {#settings-load_balancing}
Specifies the algorithm of replicas selection that is used for distributed query processing.
@ -3625,7 +3631,7 @@ z IPv4
Controls making inferred types `Nullable` in schema inference for formats without information about nullability.
If the setting is enabled, the inferred type will be `Nullable` only if column contains `NULL` in a sample that is parsed during schema inference.
Default value: `false`.
Default value: `true`.
## input_format_try_infer_integers {#input_format_try_infer_integers}

70
docs/en/operations/system-tables/schema_inference_cache.md Normal file
View File

@ -0,0 +1,70 @@
---
slug: /en/operations/system-tables/schema_inference_cache
---
# Schema inference cache
Contains information about all cached file schemas.
Columns:
- `storage` ([String](/docs/en/sql-reference/data-types/string.md)) — Storage name: File, URL, S3 or HDFS.
- `source` ([String](/docs/en/sql-reference/data-types/string.md)) — File source.
- `format` ([String](/docs/en/sql-reference/data-types/string.md)) — Format name.
- `additional_format_info` ([String](/docs/en/sql-reference/data-types/string.md)) - Additional information required to identify the schema. For example, format specific settings.
- `registration_time` ([DateTime](/docs/en/sql-reference/data-types/datetime.md)) — Timestamp when schema was added in cache.
- `schema` ([String](/docs/en/sql-reference/data-types/string.md)) - Cached schema.
**Example**
Let's say we have a file `data.jsonl` with this content:
```json
{"id" : 1, "age" : 25, "name" : "Josh", "hobbies" : ["football", "cooking", "music"]}
{"id" : 2, "age" : 19, "name" : "Alan", "hobbies" : ["tennis", "art"]}
{"id" : 3, "age" : 32, "name" : "Lana", "hobbies" : ["fitness", "reading", "shopping"]}
{"id" : 4, "age" : 47, "name" : "Brayan", "hobbies" : ["movies", "skydiving"]}
```
:::tip
Place `data.jsonl` in the `user_files_path` directory. You can find this by looking
in your ClickHouse configuration files. The default is:
```
<user_files_path>/var/lib/clickhouse/user_files/</user_files_path>
```
:::
Open `clickhouse-client` and run the `DESCRIBE` query:
```sql
DESCRIBE file('data.jsonl') SETTINGS input_format_try_infer_integers=0;
```
```response
┌─name────┬─type────────────────────┬─default_type─┬─default_expression─┬─comment─┬─codec_expression─┬─ttl_expression─┐
│ id │ Nullable(Float64) │ │ │ │ │ │
│ age │ Nullable(Float64) │ │ │ │ │ │
│ name │ Nullable(String) │ │ │ │ │ │
│ hobbies │ Array(Nullable(String)) │ │ │ │ │ │
└─────────┴─────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
```
Let's see the content of the `system.schema_inference_cache` table:
```sql
SELECT *
FROM system.schema_inference_cache
FORMAT Vertical
```
```response
Row 1:
──────
storage: File
source: /home/droscigno/user_files/data.jsonl
format: JSONEachRow
additional_format_info: schema_inference_hints=, max_rows_to_read_for_schema_inference=25000, schema_inference_make_columns_nullable=true, try_infer_integers=false, try_infer_dates=true, try_infer_datetimes=true, try_infer_numbers_from_strings=true, read_bools_as_numbers=true, try_infer_objects=false
registration_time: 2022-12-29 17:49:52
schema: id Nullable(Float64), age Nullable(Float64), name Nullable(String), hobbies Array(Nullable(String))
```
**See also**
- [Automatic schema inference from input data](/docs/en/interfaces/schema-inference.md)

41
docs/en/sql-reference/aggregate-functions/reference/grouparraylast.md Normal file
View File

@ -0,0 +1,41 @@
---
slug: /en/sql-reference/aggregate-functions/reference/grouparraylast
sidebar_position: 110
---
# groupArrayLast
Syntax: `groupArrayLast(max_size)(x)`
Creates an array of last argument values.
For example, `groupArrayLast(1)(x)` is equivalent to `[anyLast (x)]`.
In some cases, you can still rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY`.
**Example**
Query:
```sql
select groupArrayLast(2)(number+1) numbers from numbers(10)
```
Result:
```text
┌─numbers─┐
│ [9,10] │
└─────────┘
```
In compare to `groupArray`:
```sql
select groupArray(2)(number+1) numbers from numbers(10)
```
```text
┌─numbers─┐
│ [1,2] │
└─────────┘
```

1
docs/en/sql-reference/aggregate-functions/reference/index.md
View File

@ -32,6 +32,7 @@ ClickHouse-specific aggregate functions:
- [topK](../../../sql-reference/aggregate-functions/reference/topk.md)
- [topKWeighted](../../../sql-reference/aggregate-functions/reference/topkweighted.md)
- [groupArray](../../../sql-reference/aggregate-functions/reference/grouparray.md)
- [groupArrayLast](../../../sql-reference/aggregate-functions/reference/grouparraylast.md)
- [groupUniqArray](../../../sql-reference/aggregate-functions/reference/groupuniqarray.md)
- [groupArrayInsertAt](../../../sql-reference/aggregate-functions/reference/grouparrayinsertat.md)
- [groupArrayMovingAvg](../../../sql-reference/aggregate-functions/reference/grouparraymovingavg.md)

322
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -410,35 +410,35 @@ Converts a date with time to a certain fixed date, while preserving the time.
## toRelativeYearNum
Converts a date with time or date to the number of the year, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the year, starting from a certain fixed point in the past.
## toRelativeQuarterNum
Converts a date with time or date to the number of the quarter, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the quarter, starting from a certain fixed point in the past.
## toRelativeMonthNum
Converts a date with time or date to the number of the month, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the month, starting from a certain fixed point in the past.
## toRelativeWeekNum
Converts a date with time or date to the number of the week, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the week, starting from a certain fixed point in the past.
## toRelativeDayNum
Converts a date with time or date to the number of the day, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the day, starting from a certain fixed point in the past.
## toRelativeHourNum
Converts a date with time or date to the number of the hour, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the hour, starting from a certain fixed point in the past.
## toRelativeMinuteNum
Converts a date with time or date to the number of the minute, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the minute, starting from a certain fixed point in the past.
## toRelativeSecondNum
Converts a date with time or date to the number of the second, starting from a certain fixed point in the past.
Converts a date or date with time to the number of the second, starting from a certain fixed point in the past.
## toISOYear
@ -517,6 +517,154 @@ SELECT toDate('2016-12-27') AS date, toYearWeek(date) AS yearWeek0, toYearWeek(d
└────────────┴───────────┴───────────┴───────────┘
```
## age
Returns the `unit` component of the difference between `startdate` and `enddate`. The difference is calculated using a precision of 1 second.
E.g. the difference between `2021-12-29` and `2022-01-01` is 3 days for `day` unit, 0 months for `month` unit, 0 years for `year` unit.
**Syntax**
``` sql
age('unit', startdate, enddate, [timezone])
```
**Arguments**
- `unit` — The type of interval for result. [String](../../sql-reference/data-types/string.md).
Possible values:
- `second` (possible abbreviations: `ss`, `s`)
- `minute` (possible abbreviations: `mi`, `n`)
- `hour` (possible abbreviations: `hh`, `h`)
- `day` (possible abbreviations: `dd`, `d`)
- `week` (possible abbreviations: `wk`, `ww`)
- `month` (possible abbreviations: `mm`, `m`)
- `quarter` (possible abbreviations: `qq`, `q`)
- `year` (possible abbreviations: `yyyy`, `yy`)
- `startdate` — The first time value to subtract (the subtrahend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — The second time value to subtract from (the minuend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (optional). If specified, it is applied to both `startdate` and `enddate`. If not specified, timezones of `startdate` and `enddate` are used. If they are not the same, the result is unspecified. [String](../../sql-reference/data-types/string.md).
**Returned value**
Difference between `enddate` and `startdate` expressed in `unit`.
Type: [Int](../../sql-reference/data-types/int-uint.md).
**Example**
Query:
``` sql
SELECT age('hour', toDateTime('2018-01-01 22:30:00'), toDateTime('2018-01-02 23:00:00'));
```
Result:
``` text
┌─age('hour', toDateTime('2018-01-01 22:30:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 24 │
└───────────────────────────────────────────────────────────────────────────────────┘
```
Query:
``` sql
SELECT
toDate('2022-01-01') AS e,
toDate('2021-12-29') AS s,
age('day', s, e) AS day_age,
age('month', s, e) AS month__age,
age('year', s, e) AS year_age;
```
Result:
``` text
┌──────────e─┬──────────s─┬─day_age─┬─month__age─┬─year_age─┐
│ 2022-01-01 │ 2021-12-29 │ 3 │ 0 │ 0 │
└────────────┴────────────┴─────────┴────────────┴──────────┘
```
## date\_diff
Returns the count of the specified `unit` boundaries crossed between the `startdate` and `enddate`.
The difference is calculated using relative units, e.g. the difference between `2021-12-29` and `2022-01-01` is 3 days for day unit (see [toRelativeDayNum](#torelativedaynum)), 1 month for month unit (see [toRelativeMonthNum](#torelativemonthnum)), 1 year for year unit (see [toRelativeYearNum](#torelativeyearnum)).
**Syntax**
``` sql
date_diff('unit', startdate, enddate, [timezone])
```
Aliases: `dateDiff`, `DATE_DIFF`.
**Arguments**
- `unit` — The type of interval for result. [String](../../sql-reference/data-types/string.md).
Possible values:
- `second` (possible abbreviations: `ss`, `s`)
- `minute` (possible abbreviations: `mi`, `n`)
- `hour` (possible abbreviations: `hh`, `h`)
- `day` (possible abbreviations: `dd`, `d`)
- `week` (possible abbreviations: `wk`, `ww`)
- `month` (possible abbreviations: `mm`, `m`)
- `quarter` (possible abbreviations: `qq`, `q`)
- `year` (possible abbreviations: `yyyy`, `yy`)
- `startdate` — The first time value to subtract (the subtrahend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — The second time value to subtract from (the minuend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (optional). If specified, it is applied to both `startdate` and `enddate`. If not specified, timezones of `startdate` and `enddate` are used. If they are not the same, the result is unspecified. [String](../../sql-reference/data-types/string.md).
**Returned value**
Difference between `enddate` and `startdate` expressed in `unit`.
Type: [Int](../../sql-reference/data-types/int-uint.md).
**Example**
Query:
``` sql
SELECT dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'));
```
Result:
``` text
┌─dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 25 │
└────────────────────────────────────────────────────────────────────────────────────────┘
```
Query:
``` sql
SELECT
toDate('2022-01-01') AS e,
toDate('2021-12-29') AS s,
dateDiff('day', s, e) AS day_diff,
dateDiff('month', s, e) AS month__diff,
dateDiff('year', s, e) AS year_diff;
```
Result:
``` text
┌──────────e─┬──────────s─┬─day_diff─┬─month__diff─┬─year_diff─┐
│ 2022-01-01 │ 2021-12-29 │ 3 │ 1 │ 1 │
└────────────┴────────────┴──────────┴─────────────┴───────────┘
```
## date\_trunc
Truncates date and time data to the specified part of date.
@ -637,80 +785,6 @@ Result:
└───────────────────────────────────────────────┘
```
## date\_diff
Returns the difference between two dates or dates with time values.
The difference is calculated using relative units, e.g. the difference between `2022-01-01` and `2021-12-29` is 3 days for day unit (see [toRelativeDayNum](#torelativedaynum)), 1 month for month unit (see [toRelativeMonthNum](#torelativemonthnum)), 1 year for year unit (see [toRelativeYearNum](#torelativeyearnum)).
**Syntax**
``` sql
date_diff('unit', startdate, enddate, [timezone])
```
Aliases: `dateDiff`, `DATE_DIFF`.
**Arguments**
- `unit` — The type of interval for result. [String](../../sql-reference/data-types/string.md).
Possible values:
- `second`
- `minute`
- `hour`
- `day`
- `week`
- `month`
- `quarter`
- `year`
- `startdate` — The first time value to subtract (the subtrahend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — The second time value to subtract from (the minuend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (optional). If specified, it is applied to both `startdate` and `enddate`. If not specified, timezones of `startdate` and `enddate` are used. If they are not the same, the result is unspecified. [String](../../sql-reference/data-types/string.md).
**Returned value**
Difference between `enddate` and `startdate` expressed in `unit`.
Type: [Int](../../sql-reference/data-types/int-uint.md).
**Example**
Query:
``` sql
SELECT dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'));
```
Result:
``` text
┌─dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 25 │
└────────────────────────────────────────────────────────────────────────────────────────┘
```
Query:
``` sql
SELECT
toDate('2022-01-01') AS e,
toDate('2021-12-29') AS s,
dateDiff('day', s, e) AS day_diff,
dateDiff('month', s, e) AS month__diff,
dateDiff('year', s, e) AS year_diff;
```
Result:
``` text
┌──────────e─┬──────────s─┬─day_diff─┬─month__diff─┬─year_diff─┐
│ 2022-01-01 │ 2021-12-29 │ 3 │ 1 │ 1 │
└────────────┴────────────┴──────────┴─────────────┴───────────┘
```
## date\_sub
Subtracts the time interval or date interval from the provided date or date with time.
@ -1085,6 +1159,8 @@ SELECT timeSlots(toDateTime64('1980-12-12 21:01:02.1234', 4, 'UTC'), toDecimal64
Formats a Time according to the given Format string. Format is a constant expression, so you cannot have multiple formats for a single result column.
formatDateTime uses MySQL datetime format style, refer to https://dev.mysql.com/doc/refman/8.0/en/date-and-time-functions.html#function_date-format.
**Syntax**
``` sql
@ -1158,6 +1234,64 @@ Result:
└─────────────────────────────────────────────────────────────────────┘
```
**See Also**
- [formatDateTimeInJodaSyntax](##formatDateTimeInJodaSyntax)
## formatDateTimeInJodaSyntax
Similar to formatDateTime, except that it formats datetime in Joda style instead of MySQL style. Refer to https://joda-time.sourceforge.net/apidocs/org/joda/time/format/DateTimeFormat.html.
**Replacement fields**
Using replacement fields, you can define a pattern for the resulting string.
| Placeholder | Description | Presentation | Examples |
| ----------- | ----------- | ------------- | -------- |
| G | era | text | AD |
| C | century of era (>=0) | number | 20 |
| Y | year of era (>=0) | year | 1996 |
| x | weekyear(not supported yet) | year | 1996 |
| w | week of weekyear(not supported yet) | number | 27 |
| e | day of week | number | 2 |
| E | day of week | text | Tuesday; Tue |
| y | year | year | 1996 |
| D | day of year | number | 189 |
| M | month of year | month | July; Jul; 07 |
| d | day of month | number | 10 |
| a | halfday of day | text | PM |
| K | hour of halfday (0~11) | number | 0 |
| h | clockhour of halfday (1~12) | number | 12 |
| H | hour of day (0~23) | number | 0 |
| k | clockhour of day (1~24) | number | 24 |
| m | minute of hour | number | 30 |
| s | second of minute | number | 55 |
| S | fraction of second(not supported yet) | number | 978 |
| z | time zone(short name not supported yet) | text | Pacific Standard Time; PST |
| Z | time zone offset/id(not supported yet) | zone | -0800; -08:00; America/Los_Angeles |
| ' | escape for text | delimiter| |
| '' | single quote | literal | ' |
**Example**
Query:
``` sql
SELECT formatDateTimeInJodaSyntax(toDateTime('2010-01-04 12:34:56'), 'yyyy-MM-dd HH:mm:ss')
```
Result:
```
┌─formatDateTimeInJodaSyntax(toDateTime('2010-01-04 12:34:56'), 'yyyy-MM-dd HH:mm:ss')─┐
│ 2010-01-04 12:34:56 │
└─────────────────────────────────────────────────────────────────────────────────────────┘
```
## dateName
Returns specified part of date.
@ -1241,6 +1375,8 @@ Result:
Function converts Unix timestamp to a calendar date and a time of a day. When there is only a single argument of [Integer](../../sql-reference/data-types/int-uint.md) type, it acts in the same way as [toDateTime](../../sql-reference/functions/type-conversion-functions.md#todatetime) and return [DateTime](../../sql-reference/data-types/datetime.md) type.
FROM_UNIXTIME uses MySQL datetime format style, refer to https://dev.mysql.com/doc/refman/8.0/en/date-and-time-functions.html#function_date-format.
Alias: `fromUnixTimestamp`.
**Example:**
@ -1273,6 +1409,28 @@ SELECT FROM_UNIXTIME(1234334543, '%Y-%m-%d %R:%S') AS DateTime;
└─────────────────────┘
```
**See Also**
- [fromUnixTimestampInJodaSyntax](##fromUnixTimestampInJodaSyntax)
## fromUnixTimestampInJodaSyntax
Similar to FROM_UNIXTIME, except that it formats time in Joda style instead of MySQL style. Refer to https://joda-time.sourceforge.net/apidocs/org/joda/time/format/DateTimeFormat.html.
**Example:**
Query:
``` sql
SELECT fromUnixTimestampInJodaSyntax(1669804872, 'yyyy-MM-dd HH:mm:ss', 'UTC');
```
Result:
```
┌─fromUnixTimestampInJodaSyntax(1669804872, 'yyyy-MM-dd HH:mm:ss', 'UTC')─┐
│ 2022-11-30 10:41:12 │
└────────────────────────────────────────────────────────────────────────────┘
```
## toModifiedJulianDay
Converts a [Proleptic Gregorian calendar](https://en.wikipedia.org/wiki/Proleptic_Gregorian_calendar) date in text form `YYYY-MM-DD` to a [Modified Julian Day](https://en.wikipedia.org/wiki/Julian_day#Variants) number in Int32. This function supports date from `0000-01-01` to `9999-12-31`. It raises an exception if the argument cannot be parsed as a date, or the date is invalid.

262
docs/en/sql-reference/functions/type-conversion-functions.md
View File

@ -14,7 +14,7 @@ ClickHouse has the [same behavior as C++ programs](https://en.cppreference.com/w
## toInt(8\|16\|32\|64\|128\|256)
Converts an input value to the [Int](../../sql-reference/data-types/int-uint.md) data type. This function family includes:
Converts an input value to the [Int](/docs/en/sql-reference/data-types/int-uint.md) data type. This function family includes:
- `toInt8(expr)` — Results in the `Int8` data type.
- `toInt16(expr)` — Results in the `Int16` data type.
@ -25,7 +25,7 @@ Converts an input value to the [Int](../../sql-reference/data-types/int-uint.md)
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a number or a string with the decimal representation of a number. Binary, octal, and hexadecimal representations of numbers are not supported. Leading zeroes are stripped.
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions) returning a number or a string with the decimal representation of a number. Binary, octal, and hexadecimal representations of numbers are not supported. Leading zeroes are stripped.
**Returned value**
@ -33,7 +33,7 @@ Integer value in the `Int8`, `Int16`, `Int32`, `Int64`, `Int128` or `Int256` dat
Functions use [rounding towards zero](https://en.wikipedia.org/wiki/Rounding#Rounding_towards_zero), meaning they truncate fractional digits of numbers.
The behavior of functions for the [NaN and Inf](../../sql-reference/data-types/float.md#data_type-float-nan-inf) arguments is undefined. Remember about [numeric conversions issues](#numeric-conversion-issues), when using the functions.
The behavior of functions for the [NaN and Inf](/docs/en/sql-reference/data-types/float.md/#data_type-float-nan-inf) arguments is undefined. Remember about [numeric conversions issues](#numeric-conversion-issues), when using the functions.
**Example**
@ -114,7 +114,7 @@ Result:
## toUInt(8\|16\|32\|64\|256)
Converts an input value to the [UInt](../../sql-reference/data-types/int-uint.md) data type. This function family includes:
Converts an input value to the [UInt](/docs/en/sql-reference/data-types/int-uint.md) data type. This function family includes:
- `toUInt8(expr)` — Results in the `UInt8` data type.
- `toUInt16(expr)` — Results in the `UInt16` data type.
@ -124,7 +124,7 @@ Converts an input value to the [UInt](../../sql-reference/data-types/int-uint.md
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a number or a string with the decimal representation of a number. Binary, octal, and hexadecimal representations of numbers are not supported. Leading zeroes are stripped.
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions) returning a number or a string with the decimal representation of a number. Binary, octal, and hexadecimal representations of numbers are not supported. Leading zeroes are stripped.
**Returned value**
@ -132,7 +132,7 @@ Integer value in the `UInt8`, `UInt16`, `UInt32`, `UInt64` or `UInt256` data typ
Functions use [rounding towards zero](https://en.wikipedia.org/wiki/Rounding#Rounding_towards_zero), meaning they truncate fractional digits of numbers.
The behavior of functions for negative arguments and for the [NaN and Inf](../../sql-reference/data-types/float.md#data_type-float-nan-inf) arguments is undefined. If you pass a string with a negative number, for example `'-32'`, ClickHouse raises an exception. Remember about [numeric conversions issues](#numeric-conversion-issues), when using the functions.
The behavior of functions for negative arguments and for the [NaN and Inf](/docs/en/sql-reference/data-types/float.md/#data_type-float-nan-inf) arguments is undefined. If you pass a string with a negative number, for example `'-32'`, ClickHouse raises an exception. Remember about [numeric conversions issues](#numeric-conversion-issues), when using the functions.
**Example**
@ -166,7 +166,111 @@ Result:
## toDate
Alias: `DATE`.
Converts the argument to `Date` data type.
If the argument is `DateTime` or `DateTime64`, it truncates it, leaving the date component of the DateTime:
```sql
SELECT
now() AS x,
toDate(x)
```
```response
┌───────────────────x─┬─toDate(now())─┐
│ 2022-12-30 13:44:17 │ 2022-12-30 │
└─────────────────────┴───────────────┘
```
If the argument is a string, it is parsed as Date or DateTime. If it was parsed as DateTime, the date component is being used:
```sql
SELECT
toDate('2022-12-30') AS x,
toTypeName(x)
```
```response
┌──────────x─┬─toTypeName(toDate('2022-12-30'))─┐
│ 2022-12-30 │ Date │
└────────────┴──────────────────────────────────┘
1 row in set. Elapsed: 0.001 sec.
```
```sql
SELECT
toDate('2022-12-30 01:02:03') AS x,
toTypeName(x)
```
```response
┌──────────x─┬─toTypeName(toDate('2022-12-30 01:02:03'))─┐
│ 2022-12-30 │ Date │
└────────────┴───────────────────────────────────────────┘
```
If the argument is a number and it looks like a UNIX timestamp (is greater than 65535), it is interpreted as a DateTime, then truncated to Date in the current timezone. The timezone argument can be specified as a second argument of the function. The truncation to Date depends on the timezone:
```sql
SELECT
now() AS current_time,
toUnixTimestamp(current_time) AS ts,
toDateTime(ts) AS time_Amsterdam,
toDateTime(ts, 'Pacific/Apia') AS time_Samoa,
toDate(time_Amsterdam) AS date_Amsterdam,
toDate(time_Samoa) AS date_Samoa,
toDate(ts) AS date_Amsterdam_2,
toDate(ts, 'Pacific/Apia') AS date_Samoa_2
```
```response
Row 1:
──────
current_time: 2022-12-30 13:51:54
ts: 1672404714
time_Amsterdam: 2022-12-30 13:51:54
time_Samoa: 2022-12-31 01:51:54
date_Amsterdam: 2022-12-30
date_Samoa: 2022-12-31
date_Amsterdam_2: 2022-12-30
date_Samoa_2: 2022-12-31
```
The example above demonstrates how the same UNIX timestamp can be interpreted as different dates in different time zones.
If the argument is a number and it is smaller than 65536, it is interpreted as the number of days since 1970-01-01 (a UNIX day) and converted to Date. It corresponds to the internal numeric representation of the `Date` data type. Example:
```sql
SELECT toDate(12345)
```
```response
┌─toDate(12345)─┐
│ 2003-10-20 │
└───────────────┘
```
This conversion does not depend on timezones.
If the argument does not fit in the range of the Date type, it results in an implementation-defined behavior, that can saturate to the maximum supported date or overflow:
```sql
SELECT toDate(10000000000.)
```
```response
┌─toDate(10000000000.)─┐
│ 2106-02-07 │
└──────────────────────┘
```
The function `toDate` can be also written in alternative forms:
```sql
SELECT
now() AS time,
toDate(time),
DATE(time),
CAST(time, 'Date')
```
```response
┌────────────────time─┬─toDate(now())─┬─DATE(now())─┬─CAST(now(), 'Date')─┐
│ 2022-12-30 13:54:58 │ 2022-12-30 │ 2022-12-30 │ 2022-12-30 │
└─────────────────────┴───────────────┴─────────────┴─────────────────────┘
```
Have a nice day working with dates and times.
## toDateOrZero
@ -184,7 +288,7 @@ Alias: `DATE`.
## toDate32
Converts the argument to the [Date32](../../sql-reference/data-types/date32.md) data type. If the value is outside the range returns the border values supported by `Date32`. If the argument has [Date](../../sql-reference/data-types/date.md) type, borders of `Date` are taken into account.
Converts the argument to the [Date32](/docs/en/sql-reference/data-types/date32.md) data type. If the value is outside the range, `toDate32` returns the border values supported by `Date32`. If the argument has [Date](/docs/en/sql-reference/data-types/date.md) type, borders of `Date` are taken into account.
**Syntax**
@ -194,13 +298,13 @@ toDate32(expr)
**Arguments**
- `expr` — The value. [String](../../sql-reference/data-types/string.md), [UInt32](../../sql-reference/data-types/int-uint.md) or [Date](../../sql-reference/data-types/date.md).
- `expr` — The value. [String](/docs/en/sql-reference/data-types/string.md), [UInt32](/docs/en/sql-reference/data-types/int-uint.md) or [Date](/docs/en/sql-reference/data-types/date.md).
**Returned value**
- A calendar date.
Type: [Date32](../../sql-reference/data-types/date32.md).
Type: [Date32](/docs/en/sql-reference/data-types/date32.md).
**Example**
@ -242,7 +346,7 @@ SELECT toDate32(toDate('1899-01-01')) AS value, toTypeName(value);
## toDate32OrZero
The same as [toDate32](#todate32) but returns the min value of [Date32](../../sql-reference/data-types/date32.md) if invalid argument is received.
The same as [toDate32](#todate32) but returns the min value of [Date32](/docs/en/sql-reference/data-types/date32.md) if an invalid argument is received.
**Example**
@ -262,7 +366,7 @@ Result:
## toDate32OrNull
The same as [toDate32](#todate32) but returns `NULL` if invalid argument is received.
The same as [toDate32](#todate32) but returns `NULL` if an invalid argument is received.
**Example**
@ -282,7 +386,7 @@ Result:
## toDate32OrDefault
Converts the argument to the [Date32](../../sql-reference/data-types/date32.md) data type. If the value is outside the range returns the lower border value supported by `Date32`. If the argument has [Date](../../sql-reference/data-types/date.md) type, borders of `Date` are taken into account. Returns default value if invalid argument is received.
Converts the argument to the [Date32](/docs/en/sql-reference/data-types/date32.md) data type. If the value is outside the range, `toDate32OrDefault` returns the lower border value supported by `Date32`. If the argument has [Date](/docs/en/sql-reference/data-types/date.md) type, borders of `Date` are taken into account. Returns default value if an invalid argument is received.
**Example**
@ -304,7 +408,7 @@ Result:
## toDateTime64
Converts the argument to the [DateTime64](../../sql-reference/data-types/datetime64.md) data type.
Converts the argument to the [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) data type.
**Syntax**
@ -314,7 +418,7 @@ toDateTime64(expr, scale, [timezone])
**Arguments**
- `expr` — The value. [String](../../sql-reference/data-types/string.md), [UInt32](../../sql-reference/data-types/int-uint.md), [Float](../../sql-reference/data-types/float.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `expr` — The value. [String](/docs/en/sql-reference/data-types/string.md), [UInt32](/docs/en/sql-reference/data-types/int-uint.md), [Float](/docs/en/sql-reference/data-types/float.md) or [DateTime](/docs/en/sql-reference/data-types/datetime.md).
- `scale` - Tick size (precision): 10<sup>-precision</sup> seconds. Valid range: [ 0 : 9 ].
- `timezone` - Time zone of the specified datetime64 object.
@ -322,7 +426,7 @@ toDateTime64(expr, scale, [timezone])
- A calendar date and time of day, with sub-second precision.
Type: [DateTime64](../../sql-reference/data-types/datetime64.md).
Type: [DateTime64](/docs/en/sql-reference/data-types/datetime64.md).
**Example**
@ -378,7 +482,7 @@ SELECT toDateTime64('2019-01-01 00:00:00', 3, 'Asia/Istanbul') AS value, toTypeN
## toDecimal(32\|64\|128\|256)
Converts `value` to the [Decimal](../../sql-reference/data-types/decimal.md) data type with precision of `S`. The `value` can be a number or a string. The `S` (scale) parameter specifies the number of decimal places.
Converts `value` to the [Decimal](/docs/en/sql-reference/data-types/decimal.md) data type with precision of `S`. The `value` can be a number or a string. The `S` (scale) parameter specifies the number of decimal places.
- `toDecimal32(value, S)`
- `toDecimal64(value, S)`
@ -387,7 +491,7 @@ Converts `value` to the [Decimal](../../sql-reference/data-types/decimal.md) dat
## toDecimal(32\|64\|128\|256)OrNull
Converts an input string to a [Nullable(Decimal(P,S))](../../sql-reference/data-types/decimal.md) data type value. This family of functions include:
Converts an input string to a [Nullable(Decimal(P,S))](/docs/en/sql-reference/data-types/decimal.md) data type value. This family of functions includes:
- `toDecimal32OrNull(expr, S)` — Results in `Nullable(Decimal32(S))` data type.
- `toDecimal64OrNull(expr, S)` — Results in `Nullable(Decimal64(S))` data type.
@ -398,7 +502,7 @@ These functions should be used instead of `toDecimal*()` functions, if you prefe
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions), returns a value in the [String](../../sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions), returns a value in the [String](/docs/en/sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `S` — Scale, the number of decimal places in the resulting value.
**Returned value**
@ -441,7 +545,7 @@ Result:
## toDecimal(32\|64\|128\|256)OrDefault
Converts an input string to a [Decimal(P,S)](../../sql-reference/data-types/decimal.md) data type value. This family of functions include:
Converts an input string to a [Decimal(P,S)](/docs/en/sql-reference/data-types/decimal.md) data type value. This family of functions includes:
- `toDecimal32OrDefault(expr, S)` — Results in `Decimal32(S)` data type.
- `toDecimal64OrDefault(expr, S)` — Results in `Decimal64(S)` data type.
@ -452,7 +556,7 @@ These functions should be used instead of `toDecimal*()` functions, if you prefe
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions), returns a value in the [String](../../sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions), returns a value in the [String](/docs/en/sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `S` — Scale, the number of decimal places in the resulting value.
**Returned value**
@ -494,7 +598,7 @@ Result:
## toDecimal(32\|64\|128\|256)OrZero
Converts an input value to the [Decimal(P,S)](../../sql-reference/data-types/decimal.md) data type. This family of functions include:
Converts an input value to the [Decimal(P,S)](/docs/en/sql-reference/data-types/decimal.md) data type. This family of functions includes:
- `toDecimal32OrZero( expr, S)` — Results in `Decimal32(S)` data type.
- `toDecimal64OrZero( expr, S)` — Results in `Decimal64(S)` data type.
@ -505,7 +609,7 @@ These functions should be used instead of `toDecimal*()` functions, if you prefe
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions), returns a value in the [String](../../sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions), returns a value in the [String](/docs/en/sql-reference/data-types/string.md) data type. ClickHouse expects the textual representation of the decimal number. For example, `'1.111'`.
- `S` — Scale, the number of decimal places in the resulting value.
**Returned value**
@ -564,7 +668,7 @@ YYYY-MM-DD hh:mm:ss
As an exception, if converting from UInt32, Int32, UInt64, or Int64 numeric types to Date, and if the number is greater than or equal to 65536, the number is interpreted as a Unix timestamp (and not as the number of days) and is rounded to the date. This allows support for the common occurrence of writing ‘toDate(unix_timestamp)’, which otherwise would be an error and would require writing the more cumbersome ‘toDate(toDateTime(unix_timestamp))’.
Conversion between a date and date with time is performed the natural way: by adding a null time or dropping the time.
Conversion between a date and a date with time is performed the natural way: by adding a null time or dropping the time.
Conversion between numeric types uses the same rules as assignments between different numeric types in C++.
@ -643,15 +747,15 @@ These functions accept a string and interpret the bytes placed at the beginning
## reinterpretAsString
This function accepts a number or date or date with time, and returns a string containing bytes representing the corresponding value in host order (little endian). Null bytes are dropped from the end. For example, a UInt32 type value of 255 is a string that is one byte long.
This function accepts a number or date or date with time and returns a string containing bytes representing the corresponding value in host order (little endian). Null bytes are dropped from the end. For example, a UInt32 type value of 255 is a string that is one byte long.
## reinterpretAsFixedString
This function accepts a number or date or date with time, and returns a FixedString containing bytes representing the corresponding value in host order (little endian). Null bytes are dropped from the end. For example, a UInt32 type value of 255 is a FixedString that is one byte long.
This function accepts a number or date or date with time and returns a FixedString containing bytes representing the corresponding value in host order (little endian). Null bytes are dropped from the end. For example, a UInt32 type value of 255 is a FixedString that is one byte long.
## reinterpretAsUUID
Accepts 16 bytes string and returns UUID containing bytes representing the corresponding value in network byte order (big-endian). If the string isn't long enough, the function works as if the string is padded with the necessary number of null bytes to the end. If the string longer than 16 bytes, the extra bytes at the end are ignored.
Accepts 16 bytes string and returns UUID containing bytes representing the corresponding value in network byte order (big-endian). If the string isn't long enough, the function works as if the string is padded with the necessary number of null bytes to the end. If the string is longer than 16 bytes, the extra bytes at the end are ignored.
**Syntax**
@ -661,11 +765,11 @@ reinterpretAsUUID(fixed_string)
**Arguments**
- `fixed_string` — Big-endian byte string. [FixedString](../../sql-reference/data-types/fixedstring.md#fixedstring).
- `fixed_string` — Big-endian byte string. [FixedString](/docs/en/sql-reference/data-types/fixedstring.md/#fixedstring).
**Returned value**
- The UUID type value. [UUID](../../sql-reference/data-types/uuid.md#uuid-data-type).
- The UUID type value. [UUID](/docs/en/sql-reference/data-types/uuid.md/#uuid-data-type).
**Examples**
@ -718,7 +822,7 @@ reinterpret(x, type)
**Arguments**
- `x` — Any type.
- `type` — Destination type. [String](../../sql-reference/data-types/string.md).
- `type` — Destination type. [String](/docs/en/sql-reference/data-types/string.md).
**Returned value**
@ -757,7 +861,7 @@ x::t
**Arguments**
- `x` — A value to convert. May be of any type.
- `T` — The name of the target data type. [String](../../sql-reference/data-types/string.md).
- `T` — The name of the target data type. [String](/docs/en/sql-reference/data-types/string.md).
- `t` — The target data type.
**Returned value**
@ -806,9 +910,9 @@ Result:
└─────────────────────┴─────────────────────┴────────────┴─────────────────────┴───────────────────────────┘
```
Conversion to FixedString(N) only works for arguments of type [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md).
Conversion to FixedString(N) only works for arguments of type [String](/docs/en/sql-reference/data-types/string.md) or [FixedString](/docs/en/sql-reference/data-types/fixedstring.md).
Type conversion to [Nullable](../../sql-reference/data-types/nullable.md) and back is supported.
Type conversion to [Nullable](/docs/en/sql-reference/data-types/nullable.md) and back is supported.
**Example**
@ -844,7 +948,7 @@ Result:
**See also**
- [cast_keep_nullable](../../operations/settings/settings.md#cast_keep_nullable) setting
- [cast_keep_nullable](/docs/en/operations/settings/settings.md/#cast_keep_nullable) setting
## accurateCast(x, T)
@ -882,7 +986,7 @@ Code: 70. DB::Exception: Received from localhost:9000. DB::Exception: Value in c
## accurateCastOrNull(x, T)
Converts input value `x` to the specified data type `T`. Always returns [Nullable](../../sql-reference/data-types/nullable.md) type and returns [NULL](../../sql-reference/syntax.md#null-literal) if the casted value is not representable in the target type.
Converts input value `x` to the specified data type `T`. Always returns [Nullable](/docs/en/sql-reference/data-types/nullable.md) type and returns [NULL](/docs/en/sql-reference/syntax.md/#null-literal) if the casted value is not representable in the target type.
**Syntax**
@ -991,7 +1095,7 @@ Result:
## toInterval(Year\|Quarter\|Month\|Week\|Day\|Hour\|Minute\|Second)
Converts a Number type argument to an [Interval](../../sql-reference/data-types/special-data-types/interval.md) data type.
Converts a Number type argument to an [Interval](/docs/en/sql-reference/data-types/special-data-types/interval.md) data type.
**Syntax**
@ -1039,7 +1143,7 @@ Result:
## parseDateTimeBestEffort
## parseDateTime32BestEffort
Converts a date and time in the [String](../../sql-reference/data-types/string.md) representation to [DateTime](../../sql-reference/data-types/datetime.md#data_type-datetime) data type.
Converts a date and time in the [String](/docs/en/sql-reference/data-types/string.md) representation to [DateTime](/docs/en/sql-reference/data-types/datetime.md/#data_type-datetime) data type.
The function parses [ISO 8601](https://en.wikipedia.org/wiki/ISO_8601), [RFC 1123 - 5.2.14 RFC-822 Date and Time Specification](https://tools.ietf.org/html/rfc1123#page-55), ClickHouse’s and some other date and time formats.
@ -1051,8 +1155,8 @@ parseDateTimeBestEffort(time_string [, time_zone])
**Arguments**
- `time_string` — String containing a date and time to convert. [String](../../sql-reference/data-types/string.md).
- `time_zone` — Time zone. The function parses `time_string` according to the time zone. [String](../../sql-reference/data-types/string.md).
- `time_string` — String containing a date and time to convert. [String](/docs/en/sql-reference/data-types/string.md).
- `time_zone` — Time zone. The function parses `time_string` according to the time zone. [String](/docs/en/sql-reference/data-types/string.md).
**Supported non-standard formats**
@ -1175,7 +1279,7 @@ Same as [parseDateTimeBestEffortUS](#parsedatetimebesteffortUS) function except
## parseDateTime64BestEffort
Same as [parseDateTimeBestEffort](#parsedatetimebesteffort) function but also parse milliseconds and microseconds and returns [DateTime](../../sql-reference/functions/type-conversion-functions.md#data_type-datetime) data type.
Same as [parseDateTimeBestEffort](#parsedatetimebesteffort) function but also parse milliseconds and microseconds and returns [DateTime](/docs/en/sql-reference/functions/type-conversion-functions.md/#data_type-datetime) data type.
**Syntax**
@ -1185,13 +1289,13 @@ parseDateTime64BestEffort(time_string [, precision [, time_zone]])
**Parameters**
- `time_string` — String containing a date or date with time to convert. [String](../../sql-reference/data-types/string.md).
- `precision` — Required precision. `3` — for milliseconds, `6` — for microseconds. Default — `3`. Optional. [UInt8](../../sql-reference/data-types/int-uint.md).
- `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](../../sql-reference/data-types/string.md).
- `time_string` — String containing a date or date with time to convert. [String](/docs/en/sql-reference/data-types/string.md).
- `precision` — Required precision. `3` — for milliseconds, `6` — for microseconds. Default — `3`. Optional. [UInt8](/docs/en/sql-reference/data-types/int-uint.md).
- `time_zone` — [Timezone](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](/docs/en/sql-reference/data-types/string.md).
**Returned value**
- `time_string` converted to the [DateTime](../../sql-reference/data-types/datetime.md) data type.
- `time_string` converted to the [DateTime](/docs/en/sql-reference/data-types/datetime.md) data type.
**Examples**
@ -1242,7 +1346,7 @@ Same as for [parseDateTime64BestEffort](#parsedatetime64besteffort), except that
## toLowCardinality
Converts input parameter to the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) version of same data type.
Converts input parameter to the [LowCardinality](/docs/en/sql-reference/data-types/lowcardinality.md) version of same data type.
To convert data from the `LowCardinality` data type use the [CAST](#type_conversion_function-cast) function. For example, `CAST(x as String)`.
@ -1254,7 +1358,7 @@ toLowCardinality(expr)
**Arguments**
- `expr` — [Expression](../../sql-reference/syntax.md#syntax-expressions) resulting in one of the [supported data types](../../sql-reference/data-types/index.md#data_types).
- `expr` — [Expression](/docs/en/sql-reference/syntax.md/#syntax-expressions) resulting in one of the [supported data types](/docs/en/sql-reference/data-types/index.md/#data_types).
**Returned values**
@ -1388,12 +1492,12 @@ formatRow(format, x, y, ...)
**Arguments**
- `format` — Text format. For example, [CSV](../../interfaces/formats.md#csv), [TSV](../../interfaces/formats.md#tabseparated).
- `format` — Text format. For example, [CSV](/docs/en/interfaces/formats.md/#csv), [TSV](/docs/en/interfaces/formats.md/#tabseparated).
- `x`,`y`, ... — Expressions.
**Returned value**
- A formatted string (for text formats it's usually terminated with the new line character).
- A formatted string. (for text formats it's usually terminated with the new line character).
**Example**
@ -1417,9 +1521,39 @@ Result:
└──────────────────────────────────┘
```
**Note**: If format contains suffix/prefix, it will be written in each row.
**Example**
Query:
``` sql
SELECT formatRow('CustomSeparated', number, 'good')
FROM numbers(3)
SETTINGS format_custom_result_before_delimiter='<prefix>\n', format_custom_result_after_delimiter='<suffix>'
```
Result:
``` text
┌─formatRow('CustomSeparated', number, 'good')─┐
│ <prefix>
0 good
<suffix> │
│ <prefix>
1 good
<suffix> │
│ <prefix>
2 good
<suffix> │
└──────────────────────────────────────────────┘
```
Note: Only row-based formats are supported in this function.
## formatRowNoNewline
Converts arbitrary expressions into a string via given format. The function trims the last `\n` if any.
Converts arbitrary expressions into a string via given format. Differs from formatRow in that this function trims the last `\n` if any.
**Syntax**
@ -1429,7 +1563,7 @@ formatRowNoNewline(format, x, y, ...)
**Arguments**
- `format` — Text format. For example, [CSV](../../interfaces/formats.md#csv), [TSV](../../interfaces/formats.md#tabseparated).
- `format` — Text format. For example, [CSV](/docs/en/interfaces/formats.md/#csv), [TSV](/docs/en/interfaces/formats.md/#tabseparated).
- `x`,`y`, ... — Expressions.
**Returned value**
@ -1457,7 +1591,7 @@ Result:
## snowflakeToDateTime
Extracts time from [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) as [DateTime](../data-types/datetime.md) format.
Extracts time from [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) as [DateTime](/docs/en/sql-reference/data-types/datetime.md) format.
**Syntax**
@ -1467,12 +1601,12 @@ snowflakeToDateTime(value [, time_zone])
**Parameters**
- `value` — Snowflake ID. [Int64](../data-types/int-uint.md).
- `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](../../sql-reference/data-types/string.md).
- `value` — Snowflake ID. [Int64](/docs/en/sql-reference/data-types/int-uint.md).
- `time_zone` — [Timezone](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](/docs/en/sql-reference/data-types/string.md).
**Returned value**
- Input value converted to the [DateTime](../data-types/datetime.md) data type.
- Input value converted to the [DateTime](/docs/en/sql-reference/data-types/datetime.md) data type.
**Example**
@ -1493,7 +1627,7 @@ Result:
## snowflakeToDateTime64
Extracts time from [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) as [DateTime64](../data-types/datetime64.md) format.
Extracts time from [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) as [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) format.
**Syntax**
@ -1503,12 +1637,12 @@ snowflakeToDateTime64(value [, time_zone])
**Parameters**
- `value` — Snowflake ID. [Int64](../data-types/int-uint.md).
- `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](../../sql-reference/data-types/string.md).
- `value` — Snowflake ID. [Int64](/docs/en/sql-reference/data-types/int-uint.md).
- `time_zone` — [Timezone](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](/docs/en/sql-reference/data-types/string.md).
**Returned value**
- Input value converted to the [DateTime64](../data-types/datetime64.md) data type.
- Input value converted to the [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) data type.
**Example**
@ -1529,7 +1663,7 @@ Result:
## dateTimeToSnowflake
Converts [DateTime](../data-types/datetime.md) value to the first [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) at the giving time.
Converts [DateTime](/docs/en/sql-reference/data-types/datetime.md) value to the first [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) at the giving time.
**Syntax**
@ -1539,11 +1673,11 @@ dateTimeToSnowflake(value)
**Parameters**
- `value` — Date and time. [DateTime](../../sql-reference/data-types/datetime.md).
- `value` — Date and time. [DateTime](/docs/en/sql-reference/data-types/datetime.md).
**Returned value**
- Input value converted to the [Int64](../data-types/int-uint.md) data type as the first Snowflake ID at that time.
- Input value converted to the [Int64](/docs/en/sql-reference/data-types/int-uint.md) data type as the first Snowflake ID at that time.
**Example**
@ -1563,7 +1697,7 @@ Result:
## dateTime64ToSnowflake
Convert [DateTime64](../data-types/datetime64.md) to the first [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) at the giving time.
Convert [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) to the first [Snowflake ID](https://en.wikipedia.org/wiki/Snowflake_ID) at the giving time.
**Syntax**
@ -1573,11 +1707,11 @@ dateTime64ToSnowflake(value)
**Parameters**
- `value` — Date and time. [DateTime64](../../sql-reference/data-types/datetime64.md).
- `value` — Date and time. [DateTime64](/docs/en/sql-reference/data-types/datetime64.md).
**Returned value**
- Input value converted to the [Int64](../data-types/int-uint.md) data type as the first Snowflake ID at that time.
- Input value converted to the [Int64](/docs/en/sql-reference/data-types/int-uint.md) data type as the first Snowflake ID at that time.
**Example**

6
docs/ru/development/developer-instruction.md
View File

@ -169,12 +169,6 @@ sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"
cmake -D CMAKE_BUILD_TYPE=Debug ..
В случае использования на разработческой машине старого HDD или SSD, а также при желании использовать меньше места для артефактов сборки можно использовать следующую команду:
```bash
cmake -DUSE_DEBUG_HELPERS=1 -DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1 ..
```
При этом надо учесть, что получаемые в результате сборки исполнимые файлы будут динамически слинкованы с библиотеками, и поэтому фактически станут непереносимыми на другие компьютеры (либо для этого нужно будет предпринять значительно больше усилий по сравнению со статической сборкой). Плюсом же в данном случае является значительно меньшее время сборки (это проявляется не на первой сборке, а на последующих, после внесения изменений в исходный код - тратится меньшее время на линковку по сравнению со статической сборкой) и значительно меньшее использование места на жёстком диске (экономия более, чем в 3 раза по сравнению со статической сборкой). Для целей разработки, когда планируются только отладочные запуски на том же компьютере, где осуществлялась сборка, это может быть наиболее удобным вариантом.
Вы можете изменить вариант сборки, выполнив новую команду в директории build.
Запустите ninja для сборки:

196
docs/ru/sql-reference/functions/date-time-functions.md
View File

@ -424,23 +424,23 @@ WITH toDateTime64('2020-01-01 10:20:30.999', 3) AS dt64 SELECT toStartOfSecond(d
## toRelativeYearNum {#torelativeyearnum}
Переводит дату-с-временем или дату в номер года, начиная с некоторого фиксированного момента в прошлом.
Переводит дату или дату-с-временем в номер года, начиная с некоторого фиксированного момента в прошлом.
## toRelativeQuarterNum {#torelativequarternum}
Переводит дату-с-временем или дату в номер квартала, начиная с некоторого фиксированного момента в прошлом.
Переводит дату или дату-с-временем в номер квартала, начиная с некоторого фиксированного момента в прошлом.
## toRelativeMonthNum {#torelativemonthnum}
Переводит дату-с-временем или дату в номер месяца, начиная с некоторого фиксированного момента в прошлом.
Переводит дату или дату-с-временем в номер месяца, начиная с некоторого фиксированного момента в прошлом.
## toRelativeWeekNum {#torelativeweeknum}
Переводит дату-с-временем или дату в номер недели, начиная с некоторого фиксированного момента в прошлом.
Переводит дату или дату-с-временем в номер недели, начиная с некоторого фиксированного момента в прошлом.
## toRelativeDayNum {#torelativedaynum}
Переводит дату-с-временем или дату в номер дня, начиная с некоторого фиксированного момента в прошлом.
Переводит дату или дату-с-временем в номер дня, начиная с некоторого фиксированного момента в прошлом.
## toRelativeHourNum {#torelativehournum}
@ -456,7 +456,7 @@ WITH toDateTime64('2020-01-01 10:20:30.999', 3) AS dt64 SELECT toStartOfSecond(d
## toISOYear {#toisoyear}
Переводит дату-с-временем или дату в число типа UInt16, содержащее номер ISO года. ISO год отличается от обычного года, потому что в соответствии с [ISO 8601:1988](https://en.wikipedia.org/wiki/ISO_8601) ISO год начинается необязательно первого января.
Переводит дату или дату-с-временем в число типа UInt16, содержащее номер ISO года. ISO год отличается от обычного года, потому что в соответствии с [ISO 8601:1988](https://en.wikipedia.org/wiki/ISO_8601) ISO год начинается необязательно первого января.
**Пример**
@ -479,7 +479,7 @@ SELECT
## toISOWeek {#toisoweek}
Переводит дату-с-временем или дату в число типа UInt8, содержащее номер ISO недели.
Переводит дату или дату-с-временем в число типа UInt8, содержащее номер ISO недели.
Начало ISO года отличается от начала обычного года, потому что в соответствии с [ISO 8601:1988](https://en.wikipedia.org/wiki/ISO_8601) первая неделя года - это неделя с четырьмя или более днями в этом году.
1 Января 2017 г. - воскресение, т.е. первая ISO неделя 2017 года началась в понедельник 2 января, поэтому 1 января 2017 это последняя неделя 2016 года.
@ -503,7 +503,7 @@ SELECT
```
## toWeek(date\[, mode\]\[, timezone\]) {#toweek}
Переводит дату-с-временем или дату в число UInt8, содержащее номер недели. Второй аргументам mode задает режим, начинается ли неделя с воскресенья или с понедельника и должно ли возвращаемое значение находиться в диапазоне от 0 до 53 или от 1 до 53. Если аргумент mode опущен, то используется режим 0.
Переводит дату или дату-с-временем в число UInt8, содержащее номер недели. Второй аргументам mode задает режим, начинается ли неделя с воскресенья или с понедельника и должно ли возвращаемое значение находиться в диапазоне от 0 до 53 или от 1 до 53. Если аргумент mode опущен, то используется режим 0.
`toISOWeek() ` эквивалентно `toWeek(date,3)`.
@ -569,6 +569,132 @@ SELECT toDate('2016-12-27') AS date, toYearWeek(date) AS yearWeek0, toYearWeek(d
└────────────┴───────────┴───────────┴───────────┘
```
## age
Вычисляет компонент `unit` разницы между `startdate` и `enddate`. Разница вычисляется с точностью в 1 секунду.
Например, разница между `2021-12-29` и `2022-01-01` 3 дня для единицы `day`, 0 месяцев для единицы `month`, 0 лет для единицы `year`.
**Синтаксис**
``` sql
age('unit', startdate, enddate, [timezone])
```
**Аргументы**
- `unit` — единица измерения времени, в которой будет выражено возвращаемое значение функции. [String](../../sql-reference/data-types/string.md).
Возможные значения:
- `second` (возможные сокращения: `ss`, `s`)
- `minute` (возможные сокращения: `mi`, `n`)
- `hour` (возможные сокращения: `hh`, `h`)
- `day` (возможные сокращения: `dd`, `d`)
- `week` (возможные сокращения: `wk`, `ww`)
- `month` (возможные сокращения: `mm`, `m`)
- `quarter` (возможные сокращения: `qq`, `q`)
- `year` (возможные сокращения: `yyyy`, `yy`)
- `startdate` — первая дата или дата со временем, которая вычитается из `enddate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — вторая дата или дата со временем, из которой вычитается `startdate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [часовой пояс](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (необязательно). Если этот аргумент указан, то он применяется как для `startdate`, так и для `enddate`. Если этот аргумент не указан, то используются часовые пояса аргументов `startdate` и `enddate`. Если часовые пояса аргументов `startdate` и `enddate` не совпадают, то результат не определен. [String](../../sql-reference/data-types/string.md).
**Возвращаемое значение**
Разница между `enddate` и `startdate`, выраженная в `unit`.
Тип: [Int](../../sql-reference/data-types/int-uint.md).
**Пример**
Запрос:
``` sql
SELECT age('hour', toDateTime('2018-01-01 22:30:00'), toDateTime('2018-01-02 23:00:00'));
```
Результат:
``` text
┌─age('hour', toDateTime('2018-01-01 22:30:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 24 │
└───────────────────────────────────────────────────────────────────────────────────┘
```
Запрос:
``` sql
SELECT
toDate('2022-01-01') AS e,
toDate('2021-12-29') AS s,
age('day', s, e) AS day_age,
age('month', s, e) AS month__age,
age('year', s, e) AS year_age;
```
Результат:
``` text
┌──────────e─┬──────────s─┬─day_age─┬─month__age─┬─year_age─┐
│ 2022-01-01 │ 2021-12-29 │ 3 │ 0 │ 0 │
└────────────┴────────────┴─────────┴────────────┴──────────┘
```
## date\_diff {#date_diff}
Вычисляет разницу указанных границ `unit` пересекаемых между `startdate` и `enddate`.
**Синтаксис**
``` sql
date_diff('unit', startdate, enddate, [timezone])
```
Синонимы: `dateDiff`, `DATE_DIFF`.
**Аргументы**
- `unit` — единица измерения времени, в которой будет выражено возвращаемое значение функции. [String](../../sql-reference/data-types/string.md).
Возможные значения:
- `second` (возможные сокращения: `ss`, `s`)
- `minute` (возможные сокращения: `mi`, `n`)
- `hour` (возможные сокращения: `hh`, `h`)
- `day` (возможные сокращения: `dd`, `d`)
- `week` (возможные сокращения: `wk`, `ww`)
- `month` (возможные сокращения: `mm`, `m`)
- `quarter` (возможные сокращения: `qq`, `q`)
- `year` (возможные сокращения: `yyyy`, `yy`)
- `startdate` — первая дата или дата со временем, которая вычитается из `enddate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — вторая дата или дата со временем, из которой вычитается `startdate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [часовой пояс](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (необязательно). Если этот аргумент указан, то он применяется как для `startdate`, так и для `enddate`. Если этот аргумент не указан, то используются часовые пояса аргументов `startdate` и `enddate`. Если часовые пояса аргументов `startdate` и `enddate` не совпадают, то результат не определен. [String](../../sql-reference/data-types/string.md).
**Возвращаемое значение**
Разница между `enddate` и `startdate`, выраженная в `unit`.
Тип: [Int](../../sql-reference/data-types/int-uint.md).
**Пример**
Запрос:
``` sql
SELECT dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'));
```
Результат:
``` text
┌─dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 25 │
└────────────────────────────────────────────────────────────────────────────────────────┘
```
## date_trunc {#date_trunc}
Отсекает от даты и времени части, меньшие чем указанная часть.
@ -689,60 +815,6 @@ SELECT date_add(YEAR, 3, toDate('2018-01-01'));
└───────────────────────────────────────────────┘
```
## date\_diff {#date_diff}
Вычисляет разницу между двумя значениями дат или дат со временем.
**Синтаксис**
``` sql
date_diff('unit', startdate, enddate, [timezone])
```
Синонимы: `dateDiff`, `DATE_DIFF`.
**Аргументы**
- `unit` — единица измерения времени, в которой будет выражено возвращаемое значение функции. [String](../../sql-reference/data-types/string.md).
Возможные значения:
- `second`
- `minute`
- `hour`
- `day`
- `week`
- `month`
- `quarter`
- `year`
- `startdate` — первая дата или дата со временем, которая вычитается из `enddate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `enddate` — вторая дата или дата со временем, из которой вычитается `startdate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
- `timezone` — [часовой пояс](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (необязательно). Если этот аргумент указан, то он применяется как для `startdate`, так и для `enddate`. Если этот аргумент не указан, то используются часовые пояса аргументов `startdate` и `enddate`. Если часовые пояса аргументов `startdate` и `enddate` не совпадают, то результат не определен. [String](../../sql-reference/data-types/string.md).
**Возвращаемое значение**
Разница между `enddate` и `startdate`, выраженная в `unit`.
Тип: [Int](../../sql-reference/data-types/int-uint.md).
**Пример**
Запрос:
``` sql
SELECT dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'));
```
Результат:
``` text
┌─dateDiff('hour', toDateTime('2018-01-01 22:00:00'), toDateTime('2018-01-02 23:00:00'))─┐
│ 25 │
└────────────────────────────────────────────────────────────────────────────────────────┘
```
## date\_sub {#date_sub}
Вычитает интервал времени или даты из указанной даты или даты со временем.

34
docs/ru/sql-reference/functions/type-conversion-functions.md
View File

@ -1316,7 +1316,7 @@ formatRow(format, x, y, ...)
**Возвращаемое значение**
- Отформатированная строка (в текстовых форматах обычно с завершающим переводом строки).
- Отформатированная строка. (в текстовых форматах обычно с завершающим переводом строки).
**Пример**
@ -1340,9 +1340,39 @@ FROM numbers(3);
└──────────────────────────────────┘
```
**Примечание**: если формат содержит префикс/суффикс, то он будет записан в каждой строке.
**Пример**
Запрос:
``` sql
SELECT formatRow('CustomSeparated', number, 'good')
FROM numbers(3)
SETTINGS format_custom_result_before_delimiter='<prefix>\n', format_custom_result_after_delimiter='<suffix>'
```
Результат:
``` text
┌─formatRow('CustomSeparated', number, 'good')─┐
│ <prefix>
0 good
<suffix> │
│ <prefix>
1 good
<suffix> │
│ <prefix>
2 good
<suffix> │
└──────────────────────────────────────────────┘
```
**Примечание**: данная функция поддерживает только строковые форматы вывода.
## formatRowNoNewline {#formatrownonewline}
Преобразует произвольные выражения в строку заданного формата. При этом удаляет лишние переводы строк `\n`, если они появились.
Преобразует произвольные выражения в строку заданного формата. Отличается от функции formatRow тем, что удаляет лишний перевод строки `\n` а конце, если он есть.
**Синтаксис**

10
docs/zh/development/continuous-integration.md
View File

@ -85,7 +85,6 @@ git push
- **Build type**: `Debug` or `RelWithDebInfo` (cmake).
- **Sanitizer**: `none` (without sanitizers), `address` (ASan), `memory` (MSan), `undefined` (UBSan), or `thread` (TSan).
- **Bundled**: `bundled` 构建使用来自 `contrib` 库, 而 `unbundled` 构建使用系统库.
- **Splitted**: `splitted` is a [split build](https://clickhouse.com/docs/en/development/build/#split-build)
- **Status**: `成功` 或 `失败`
- **Build log**: 链接到构建和文件复制日志, 当构建失败时很有用.
- **Build time**.
@ -97,7 +96,6 @@ git push
- `clickhouse`: Main built binary.
- `clickhouse-odbc-bridge`
- `unit_tests_dbms`: 带有 ClickHouse 单元测试的 GoogleTest 二进制文件.
- `shared_build.tgz`: 使用共享库构建.
- `performance.tgz`: 用于性能测试的特殊包.
## 特殊构建检查 {#special-buildcheck}
@ -123,14 +121,6 @@ git push
of error.
```
## 冒烟测试 {#split-build-smoke-test}
检查[拆分构建](./build.md#split-build)配置中的服务器构建是否可以启动并运行简单查询.如果失败:
```
* Fix other test errors first;
* Build the server in [split build](./build.md#split-build) configuration
locally and check whether it can start and run `select 1`.
```
## 兼容性检查 {#compatibility-check}
检查`clickhouse`二进制文件是否可以在带有旧libc版本的发行版上运行.如果失败, 请向维护人员寻求帮助.

2
docs/zh/engines/table-engines/log-family/index.md
View File

@ -11,7 +11,7 @@ sidebar_position: 29
这系列的引擎有：
- [StripeLog](stripelog.md)
- [日志](log.md)
- [Log](log.md)
- [TinyLog](tinylog.md)
## 共同属性 {#table_engines-log-engine-family-common-properties}

94
programs/CMakeLists.txt
View File

@ -13,12 +13,6 @@ option (ENABLE_CLICKHOUSE_SERVER "Server mode (main mode)" ${ENABLE_CLICKHOUSE_A
option (ENABLE_CLICKHOUSE_CLIENT "Client mode (interactive tui/shell that connects to the server)"
${ENABLE_CLICKHOUSE_ALL})
# Don't create self-extracting clickhouse for split build
if (ENABLE_CLICKHOUSE_SELF_EXTRACTING AND SPLIT_SHARED_LIBRARIES)
message (STATUS "Self-extracting on split build is not supported")
unset (ENABLE_CLICKHOUSE_SELF_EXTRACTING CACHE)
endif ()
# https://clickhouse.com/docs/en/operations/utilities/clickhouse-local/
option (ENABLE_CLICKHOUSE_LOCAL "Local files fast processing mode" ${ENABLE_CLICKHOUSE_ALL})
@ -173,10 +167,6 @@ else()
message(STATUS "ClickHouse keeper-converter mode: OFF")
endif()
if(NOT (USE_STATIC_LIBRARIES OR SPLIT_SHARED_LIBRARIES))
set(CLICKHOUSE_ONE_SHARED ON)
endif()
if (ENABLE_CLICKHOUSE_DISKS)
message(STATUS "Clickhouse disks mode: ON")
else()
@ -192,11 +182,7 @@ endif()
configure_file (config_tools.h.in ${CONFIG_INCLUDE_PATH}/config_tools.h)
macro(clickhouse_target_link_split_lib target name)
if(NOT CLICKHOUSE_ONE_SHARED)
target_link_libraries(${target} PRIVATE clickhouse-${name}-lib)
else()
target_link_libraries(${target} PRIVATE clickhouse-lib)
endif()
target_link_libraries(${target} PRIVATE clickhouse-${name}-lib)
endmacro()
macro(clickhouse_program_add_library name)
@ -208,18 +194,16 @@ macro(clickhouse_program_add_library name)
set(CLICKHOUSE_${name_uc}_LINK ${CLICKHOUSE_${name_uc}_LINK} PARENT_SCOPE)
set(CLICKHOUSE_${name_uc}_INCLUDE ${CLICKHOUSE_${name_uc}_INCLUDE} PARENT_SCOPE)
if(NOT CLICKHOUSE_ONE_SHARED)
add_library(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_SOURCES})
add_library(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_SOURCES})
set(_link ${CLICKHOUSE_${name_uc}_LINK}) # can't use ${} in if()
if(_link)
target_link_libraries(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_LINK})
endif()
set(_link ${CLICKHOUSE_${name_uc}_LINK}) # can't use ${} in if()
if(_link)
target_link_libraries(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_LINK})
endif()
set(_include ${CLICKHOUSE_${name_uc}_INCLUDE}) # can't use ${} in if()
if (_include)
target_include_directories(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_INCLUDE})
endif()
set(_include ${CLICKHOUSE_${name_uc}_INCLUDE}) # can't use ${} in if()
if (_include)
target_include_directories(clickhouse-${name}-lib ${CLICKHOUSE_${name_uc}_INCLUDE})
endif()
endmacro()
@ -263,68 +247,8 @@ if (ENABLE_CLICKHOUSE_SELF_EXTRACTING)
add_subdirectory (self-extracting)
endif ()
if (CLICKHOUSE_ONE_SHARED)
add_library(clickhouse-lib SHARED
${CLICKHOUSE_SERVER_SOURCES}
${CLICKHOUSE_CLIENT_SOURCES}
${CLICKHOUSE_LOCAL_SOURCES}
${CLICKHOUSE_BENCHMARK_SOURCES}
${CLICKHOUSE_COPIER_SOURCES}
${CLICKHOUSE_EXTRACT_FROM_CONFIG_SOURCES}
${CLICKHOUSE_COMPRESSOR_SOURCES}
${CLICKHOUSE_FORMAT_SOURCES}
${CLICKHOUSE_OBFUSCATOR_SOURCES}
${CLICKHOUSE_GIT_IMPORT_SOURCES}
${CLICKHOUSE_ODBC_BRIDGE_SOURCES}
${CLICKHOUSE_KEEPER_SOURCES}
${CLICKHOUSE_KEEPER_CONVERTER_SOURCES}
${CLICKHOUSE_STATIC_FILES_DISK_UPLOADER_SOURCES}
${CLICKHOUSE_SU_SOURCES})
target_link_libraries(clickhouse-lib
${CLICKHOUSE_SERVER_LINK}
${CLICKHOUSE_CLIENT_LINK}
${CLICKHOUSE_LOCAL_LINK}
${CLICKHOUSE_BENCHMARK_LINK}
${CLICKHOUSE_COPIER_LINK}
${CLICKHOUSE_EXTRACT_FROM_CONFIG_LINK}
${CLICKHOUSE_COMPRESSOR_LINK}
${CLICKHOUSE_FORMAT_LINK}
${CLICKHOUSE_OBFUSCATOR_LINK}
${CLICKHOUSE_GIT_IMPORT_LINK}
${CLICKHOUSE_ODBC_BRIDGE_LINK}
${CLICKHOUSE_KEEPER_LINK}
${CLICKHOUSE_KEEPER_CONVERTER_LINK}
${CLICKHOUSE_STATIC_FILES_DISK_UPLOADER_LINK}
${CLICKHOUSE_SU_LINK})
target_include_directories(clickhouse-lib
${CLICKHOUSE_SERVER_INCLUDE}
${CLICKHOUSE_CLIENT_INCLUDE}
${CLICKHOUSE_LOCAL_INCLUDE}
${CLICKHOUSE_BENCHMARK_INCLUDE}
${CLICKHOUSE_COPIER_INCLUDE}
${CLICKHOUSE_EXTRACT_FROM_CONFIG_INCLUDE}
${CLICKHOUSE_COMPRESSOR_INCLUDE}
${CLICKHOUSE_FORMAT_INCLUDE}
${CLICKHOUSE_OBFUSCATOR_INCLUDE}
${CLICKHOUSE_GIT_IMPORT_INCLUDE}
${CLICKHOUSE_ODBC_BRIDGE_INCLUDE}
${CLICKHOUSE_KEEPER_INCLUDE}
${CLICKHOUSE_KEEPER_CONVERTER_INCLUDE})
set_target_properties(clickhouse-lib PROPERTIES SOVERSION ${VERSION_MAJOR}.${VERSION_MINOR} VERSION ${VERSION_SO} OUTPUT_NAME clickhouse DEBUG_POSTFIX "")
install (TARGETS clickhouse-lib LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} COMPONENT clickhouse)
endif()
clickhouse_add_executable (clickhouse main.cpp)
if (NOT USE_STATIC_LIBRARIES AND SPLIT_SHARED_LIBRARIES)
# Shared split (dev) build: In CI, the server is run with custom LD_LIBRARY_PATH. This makes the harmful env check re-execute the
# process in a clean environment but as in CI the containing directory is not included in DT_RUNPATH/DT_RPATH, the server won't come up.
target_compile_definitions(clickhouse PRIVATE DISABLE_HARMFUL_ENV_VAR_CHECK)
endif ()
# A library that prevent usage of several functions from libc.
if (ARCH_AMD64 AND OS_LINUX AND NOT OS_ANDROID)
set (HARMFUL_LIB harmful)

4
programs/benchmark/Benchmark.cpp
View File

@ -683,7 +683,7 @@ int mainEntryClickHouseBenchmark(int argc, char ** argv)
("confidence", value<size_t>()->default_value(5), "set the level of confidence for T-test [0=80%, 1=90%, 2=95%, 3=98%, 4=99%, 5=99.5%(default)")
("query_id", value<std::string>()->default_value(""), "")
("max-consecutive-errors", value<size_t>()->default_value(0), "set number of allowed consecutive errors")
("continue_on_errors", "continue testing even if a query fails")
("ignore-error,continue_on_errors", "continue testing even if a query fails")
("reconnect", "establish new connection for every query")
("client-side-time", "display the time including network communication instead of server-side time; note that for server versions before 22.8 we always display client-side time")
;
@ -738,7 +738,7 @@ int mainEntryClickHouseBenchmark(int argc, char ** argv)
options["query_id"].as<std::string>(),
options["query"].as<std::string>(),
options["max-consecutive-errors"].as<size_t>(),
options.count("continue_on_errors"),
options.count("ignore-error"),
options.count("reconnect"),
options.count("client-side-time"),
print_stacktrace,

4
programs/benchmark/CMakeLists.txt
View File

@ -10,6 +10,4 @@ set (CLICKHOUSE_BENCHMARK_LINK
clickhouse_program_add(benchmark)
if(NOT CLICKHOUSE_ONE_SHARED)
target_link_libraries (clickhouse-benchmark-lib PRIVATE clickhouse-client-lib)
endif()
target_link_libraries (clickhouse-benchmark-lib PRIVATE clickhouse-client-lib)

12
programs/clickhouse-split-helper
View File

@ -1,12 +0,0 @@
#!/bin/sh
# Helper for split build mode.
# Allows to run commands like
# clickhouse client
# clickhouse server
# ...
set -e
CMD=$1
shift
clickhouse-$CMD $*

4
programs/client/CMakeLists.txt
View File

@ -13,6 +13,10 @@ set (CLICKHOUSE_CLIENT_LINK
string_utils
)
if (TARGET ch_rust::skim)
list(APPEND CLICKHOUSE_CLIENT_LINK PRIVATE ch_rust::skim)
endif()
# Always use internal readpassphrase
list(APPEND CLICKHOUSE_CLIENT_LINK PRIVATE readpassphrase)

21
programs/client/Client.cpp
View File

@ -30,9 +30,10 @@
#include <IO/ReadBufferFromString.h>
#include <IO/ReadHelpers.h>
#include <IO/WriteHelpers.h>
#include <IO/WriteBufferFromOStream.h>
#include <IO/UseSSL.h>
#include <IO/WriteBufferFromOStream.h>
#include <IO/WriteHelpers.h>
#include <IO/copyData.h>
#include <Parsers/ASTCreateQuery.h>
#include <Parsers/ASTDropQuery.h>
@ -41,6 +42,8 @@
#include <Parsers/ASTInsertQuery.h>
#include <Parsers/ASTSelectQuery.h>
#include <Processors/Transforms/getSourceFromASTInsertQuery.h>
#include <Interpreters/InterpreterSetQuery.h>
#include <Functions/registerFunctions.h>
@ -827,6 +830,20 @@ bool Client::processWithFuzzing(const String & full_query)
WriteBufferFromOStream ast_buf(std::cout, 4096);
formatAST(*query, ast_buf, false /*highlight*/);
ast_buf.next();
if (const auto * insert = query->as<ASTInsertQuery>())
{
/// For inserts with data it's really useful to have the data itself available in the logs, as formatAST doesn't print it
if (insert->hasInlinedData())
{
String bytes;
{
auto read_buf = getReadBufferFromASTInsertQuery(query);
WriteBufferFromString write_buf(bytes);
copyData(*read_buf, write_buf);
}
std::cout << std::endl << bytes;
}
}
std::cout << std::endl << std::endl;
try

85
programs/install/Install.cpp
View File

@ -1051,18 +1051,12 @@ namespace
return pid;
}
int stop(const fs::path & pid_file, bool force, bool do_not_kill, unsigned max_tries)
bool sendSignalAndWaitForStop(const fs::path & pid_file, int signal, unsigned max_tries, unsigned wait_ms, const char * signal_name)
{
if (force && do_not_kill)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Specified flags are incompatible");
int pid = isRunning(pid_file);
if (!pid)
return 0;
int signal = force ? SIGKILL : SIGTERM;
const char * signal_name = force ? "kill" : "terminate";
return true;
if (0 == kill(pid, signal))
fmt::print("Sent {} signal to process with pid {}.\n", signal_name, pid);
@ -1078,46 +1072,51 @@ namespace
fmt::print("Server stopped\n");
break;
}
sleepForSeconds(1);
sleepForMilliseconds(wait_ms);
}
if (try_num == max_tries)
return try_num < max_tries;
}
int stop(const fs::path & pid_file, bool force, bool do_not_kill, unsigned max_tries)
{
if (force && do_not_kill)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Specified flags are incompatible");
int signal = force ? SIGKILL : SIGTERM;
const char * signal_name = force ? "kill" : "terminate";
if (sendSignalAndWaitForStop(pid_file, signal, max_tries, 1000, signal_name))
return 0;
int pid = isRunning(pid_file);
if (!pid)
return 0;
if (do_not_kill)
{
if (do_not_kill)
{
fmt::print("Process (pid = {}) is still running. Will not try to kill it.\n", pid);
return 1;
}
fmt::print("Will terminate forcefully (pid = {}).\n", pid);
if (0 == kill(pid, 9))
fmt::print("Sent kill signal (pid = {}).\n", pid);
else
throwFromErrno("Cannot send kill signal", ErrorCodes::SYSTEM_ERROR);
/// Wait for the process (100 seconds).
constexpr size_t num_kill_check_tries = 1000;
constexpr size_t kill_check_delay_ms = 100;
for (size_t i = 0; i < num_kill_check_tries; ++i)
{
fmt::print("Waiting for server to be killed\n");
if (!isRunning(pid_file))
{
fmt::print("Server exited\n");
break;
}
sleepForMilliseconds(kill_check_delay_ms);
}
if (isRunning(pid_file))
{
throw Exception(ErrorCodes::CANNOT_KILL,
"The server process still exists after {} tries (delay: {} ms)",
num_kill_check_tries, kill_check_delay_ms);
}
fmt::print("Process (pid = {}) is still running. Will not try to kill it.\n", pid);
return 1;
}
return 0;
/// Send termination signal again, the server will receive it and immediately terminate.
fmt::print("Will send the termination signal again to force the termination (pid = {}).\n", pid);
if (sendSignalAndWaitForStop(pid_file, signal, std::min(10U, max_tries), 1000, signal_name))
return 0;
/// Send kill signal. Total wait is 100 seconds.
constexpr size_t num_kill_check_tries = 1000;
constexpr size_t kill_check_delay_ms = 100;
fmt::print("Will terminate forcefully (pid = {}).\n", pid);
if (sendSignalAndWaitForStop(pid_file, SIGKILL, num_kill_check_tries, kill_check_delay_ms, signal_name))
return 0;
if (!isRunning(pid_file))
return 0;
throw Exception(ErrorCodes::CANNOT_KILL,
"The server process still exists after {} tries (delay: {} ms)",
num_kill_check_tries, kill_check_delay_ms);
}
}

6
programs/local/CMakeLists.txt
View File

@ -14,8 +14,10 @@ set (CLICKHOUSE_LOCAL_LINK
clickhouse_program_add(local)
if(NOT CLICKHOUSE_ONE_SHARED)
target_link_libraries(clickhouse-local-lib PRIVATE clickhouse-server-lib)
target_link_libraries(clickhouse-local-lib PRIVATE clickhouse-server-lib)
if (TARGET ch_rust::skim)
target_link_libraries(clickhouse-local-lib PRIVATE ch_rust::skim)
endif()
# Always use internal readpassphrase

4
programs/main.cpp
View File

@ -345,7 +345,7 @@ struct Checker
;
#if !defined(DISABLE_HARMFUL_ENV_VAR_CHECK) && !defined(USE_MUSL)
#if !defined(USE_MUSL)
/// NOTE: We will migrate to full static linking or our own dynamic loader to make this code obsolete.
void checkHarmfulEnvironmentVariables(char ** argv)
{
@ -457,7 +457,7 @@ int main(int argc_, char ** argv_)
/// Note: we forbid dlopen in our code.
updatePHDRCache();
#if !defined(DISABLE_HARMFUL_ENV_VAR_CHECK) && !defined(USE_MUSL)
#if !defined(USE_MUSL)
checkHarmfulEnvironmentVariables(argv_);
#endif

62
programs/server/Server.cpp
View File

@ -420,6 +420,33 @@ void Server::createServer(
}
}
#if defined(OS_LINUX)
namespace
{
void setOOMScore(int value, Poco::Logger * log)
{
try
{
std::string value_string = std::to_string(value);
DB::WriteBufferFromFile buf("/proc/self/oom_score_adj");
buf.write(value_string.c_str(), value_string.size());
buf.next();
buf.close();
}
catch (const Poco::Exception & e)
{
LOG_WARNING(log, "Failed to adjust OOM score: '{}'.", e.displayText());
return;
}
LOG_INFO(log, "Set OOM score adjustment to {}", value);
}
}
#endif
void Server::uninitialize()
{
logger().information("shutting down");
@ -703,6 +730,13 @@ try
global_context->addWarningMessage("Server was built with sanitizer. It will work slowly.");
#endif
const auto memory_amount = getMemoryAmount();
LOG_INFO(log, "Available RAM: {}; physical cores: {}; logical cores: {}.",
formatReadableSizeWithBinarySuffix(memory_amount),
getNumberOfPhysicalCPUCores(), // on ARM processors it can show only enabled at current moment cores
std::thread::hardware_concurrency());
sanityChecks(*this);
// Initialize global thread pool. Do it before we fetch configs from zookeeper
@ -776,8 +810,6 @@ try
Settings::checkNoSettingNamesAtTopLevel(config(), config_path);
const auto memory_amount = getMemoryAmount();
#if defined(OS_LINUX)
std::string executable_path = getExecutablePath();
@ -876,6 +908,21 @@ try
}
}
}
int default_oom_score = 0;
#if !defined(NDEBUG)
/// In debug version on Linux, increase oom score so that clickhouse is killed
/// first, instead of some service. Use a carefully chosen random score of 555:
/// the maximum is 1000, and chromium uses 300 for its tab processes. Ignore
/// whatever errors that occur, because it's just a debugging aid and we don't
/// care if it breaks.
default_oom_score = 555;
#endif
int oom_score = config().getInt("oom_score", default_oom_score);
if (oom_score)
setOOMScore(oom_score, log);
#endif
global_context->setRemoteHostFilter(config());
@ -1044,8 +1091,8 @@ try
bool continue_if_corrupted = config().getBool("merge_tree_metadata_cache.continue_if_corrupted", false);
try
{
LOG_DEBUG(
log, "Initializing merge tree metadata cache lru_cache_size:{} continue_if_corrupted:{}", size, continue_if_corrupted);
LOG_DEBUG(log, "Initializing MergeTree metadata cache, lru_cache_size: {} continue_if_corrupted: {}",
ReadableSize(size), continue_if_corrupted);
global_context->initializeMergeTreeMetadataCache(path_str + "/" + "rocksdb", size);
}
catch (...)
@ -1718,13 +1765,6 @@ try
main_config_reloader->start();
access_control.startPeriodicReloading();
{
LOG_INFO(log, "Available RAM: {}; physical cores: {}; logical cores: {}.",
formatReadableSizeWithBinarySuffix(memory_amount),
getNumberOfPhysicalCPUCores(), // on ARM processors it can show only enabled at current moment cores
std::thread::hardware_concurrency());
}
/// try to load dictionaries immediately, throw on error and die
try
{

1
programs/server/config.d/graphite.xml Symbolic link
View File

@ -0,0 +1 @@
../../../tests/config/config.d/graphite.xml

4
programs/server/config.xml
View File

@ -1464,4 +1464,8 @@
I don't recommend to change this setting.
<show_addresses_in_stack_traces>false</show_addresses_in_stack_traces>
-->
<!-- On Linux systems this can control the behavior of OOM killer.
<oom_score>-1000</oom_score>
-->
</clickhouse>

20
rust/CMakeLists.txt
View File

@ -39,5 +39,21 @@ function(clickhouse_import_crate)
corrosion_import_crate(NO_STD ${ARGN})
endfunction()
add_subdirectory (BLAKE3)
add_subdirectory (skim)
# Add crate from the build directory.
#
# Our crates has configuration files:
# - config for cargo (see config.toml.in)
# - and possibly config for build (build.rs.in)
#
# And to avoid overlaps different builds for one source directory, crate will
# be copied from source directory to the binary directory.
file(COPY ".cargo" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}")
function(add_rust_subdirectory src)
set(dst "${CMAKE_CURRENT_BINARY_DIR}/${src}")
message(STATUS "Copy ${src} to ${dst}")
file(COPY "${src}" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}")
add_subdirectory("${dst}" "${dst}")
endfunction()
add_rust_subdirectory (BLAKE3)
add_rust_subdirectory (skim)

10
rust/skim/CMakeLists.txt
View File

@ -35,15 +35,7 @@ add_custom_command(OUTPUT ${ffi_binding_final_path}
DEPENDS cargo-build__ch_rust_skim_rust)
add_library(_ch_rust_skim_ffi ${ffi_binding_final_path})
if (USE_STATIC_LIBRARIES OR NOT SPLIT_SHARED_LIBRARIES)
# static
else()
if (OS_DARWIN)
target_link_libraries(_ch_rust_skim_ffi PRIVATE -Wl,-undefined,dynamic_lookup)
else()
target_link_libraries(_ch_rust_skim_ffi PRIVATE -Wl,--unresolved-symbols=ignore-all)
endif()
endif()
# cxx bridge compiles such bindings
set_target_properties(_ch_rust_skim_ffi PROPERTIES COMPILE_FLAGS "${CXXBRIDGE_CXXFLAGS}")

1
rust/skim/build.rs.in
View File

@ -5,4 +5,5 @@ fn main() {
}
build.compile("skim");
println!("cargo:rerun-if-changed=src/lib.rs");
println!("cargo:rerun-if-changed=.cargo/config.toml");
}

2
rust/skim/include/skim.h
View File

@ -87,4 +87,4 @@ private:
} // namespace cxxbridge1
} // namespace rust
::rust::String skim(::std::vector<::std::string> const &words);
::rust::String skim(::std::string const &prefix, ::std::vector<::std::string> const &words);

5
rust/skim/src/lib.rs
View File

@ -5,7 +5,7 @@ use cxx::{CxxString, CxxVector};
#[cxx::bridge]
mod ffi {
extern "Rust" {
fn skim(words: &CxxVector<CxxString>) -> Result<String>;
fn skim(prefix: &CxxString, words: &CxxVector<CxxString>) -> Result<String>;
}
}
@ -18,7 +18,7 @@ impl SkimItem for Item {
}
}
fn skim(words: &CxxVector<CxxString>) -> Result<String, String> {
fn skim(prefix: &CxxString, words: &CxxVector<CxxString>) -> Result<String, String> {
// Let's check is terminal available. To avoid panic.
if let Err(err) = TermInfo::from_env() {
return Err(format!("{}", err));
@ -26,6 +26,7 @@ fn skim(words: &CxxVector<CxxString>) -> Result<String, String> {
let options = SkimOptionsBuilder::default()
.height(Some("30%"))
.query(Some(prefix.to_str().unwrap()))
.tac(true)
.tiebreak(Some("-score".to_string()))
.build()

9
src/AggregateFunctions/AggregateFunctionFactory.cpp
View File

@ -72,9 +72,12 @@ AggregateFunctionPtr AggregateFunctionFactory::get(
{
auto types_without_low_cardinality = convertLowCardinalityTypesToNested(argument_types);
/// If one of the types is Nullable, we apply aggregate function combinator "Null".
if (std::any_of(types_without_low_cardinality.begin(), types_without_low_cardinality.end(),
/// If one of the types is Nullable, we apply aggregate function combinator "Null" if it's not window function.
/// Window functions are not real aggregate functions. Applying combinators doesn't make sense for them,
/// they must handle the nullability themselves
auto properties = tryGetPropertiesImpl(name);
bool is_window_function = properties.has_value() && properties->is_window_function;
if (!is_window_function && std::any_of(types_without_low_cardinality.begin(), types_without_low_cardinality.end(),
[](const auto & type) { return type->isNullable(); }))
{
AggregateFunctionCombinatorPtr combinator = AggregateFunctionCombinatorFactory::instance().tryFindSuffix("Null");

647
src/AggregateFunctions/AggregateFunctionFlameGraph.cpp
View File

@ -1,647 +0,0 @@
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/IAggregateFunction.h>
#include <AggregateFunctions/FactoryHelpers.h>
#include <Common/HashTable/HashMap.h>
#include <Common/SymbolIndex.h>
#include <Common/ArenaAllocator.h>
#include <Core/Settings.h>
#include <Columns/ColumnArray.h>
#include <Columns/ColumnString.h>
#include <Columns/ColumnsNumber.h>
#include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeString.h>
#include <DataTypes/DataTypesNumber.h>
#include <IO/WriteHelpers.h>
#include <IO/Operators.h>
#include <filesystem>
namespace DB
{
namespace ErrorCodes
{
extern const int FUNCTION_NOT_ALLOWED;
extern const int NOT_IMPLEMENTED;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
struct AggregateFunctionFlameGraphTree
{
struct ListNode;
struct TreeNode
{
TreeNode * parent = nullptr;
ListNode * children = nullptr;
UInt64 ptr = 0;
size_t allocated = 0;
};
struct ListNode
{
ListNode * next = nullptr;
TreeNode * child = nullptr;
};
TreeNode root;
static ListNode * createChild(TreeNode * parent, UInt64 ptr, Arena * arena)
{
ListNode * list_node = reinterpret_cast<ListNode *>(arena->alloc(sizeof(ListNode)));
TreeNode * tree_node = reinterpret_cast<TreeNode *>(arena->alloc(sizeof(TreeNode)));
list_node->child = tree_node;
list_node->next = nullptr;
tree_node->parent =parent;
tree_node->children = nullptr;
tree_node->ptr = ptr;
tree_node->allocated = 0;
return list_node;
}
TreeNode * find(const UInt64 * stack, size_t stack_size, Arena * arena)
{
TreeNode * node = &root;
for (size_t i = 0; i < stack_size; ++i)
{
UInt64 ptr = stack[i];
if (ptr == 0)
break;
if (!node->children)
{
node->children = createChild(node, ptr, arena);
node = node->children->child;
}
else
{
ListNode * list = node->children;
while (list->child->ptr != ptr && list->next)
list = list->next;
if (list->child->ptr != ptr)
{
list->next = createChild(node, ptr, arena);
list = list->next;
}
node = list->child;
}
}
return node;
}
static void append(DB::PaddedPODArray<UInt64> & values, DB::PaddedPODArray<UInt64> & offsets, std::vector<UInt64> & frame)
{
UInt64 prev = offsets.empty() ? 0 : offsets.back();
offsets.push_back(prev + frame.size());
for (UInt64 val : frame)
values.push_back(val);
}
struct Trace
{
using Frames = std::vector<UInt64>;
Frames frames;
/// The total number of bytes allocated for traces with the same prefix.
size_t allocated_total = 0;
/// This counter is relevant in case we want to filter some traces with small amount of bytes.
/// It shows the total number of bytes for *filtered* traces with the same prefix.
/// This is the value which is used in flamegraph.
size_t allocated_self = 0;
};
using Traces = std::vector<Trace>;
Traces dump(size_t max_depth, size_t min_bytes) const
{
Traces traces;
Trace::Frames frames;
std::vector<size_t> allocated_total;
std::vector<size_t> allocated_self;
std::vector<ListNode *> nodes;
nodes.push_back(root.children);
allocated_total.push_back(root.allocated);
allocated_self.push_back(root.allocated);
while (!nodes.empty())
{
if (nodes.back() == nullptr)
{
traces.push_back({frames, allocated_total.back(), allocated_self.back()});
nodes.pop_back();
allocated_total.pop_back();
allocated_self.pop_back();
/// We don't have root's frame so framers are empty in the end.
if (!frames.empty())
frames.pop_back();
continue;
}
TreeNode * current = nodes.back()->child;
nodes.back() = nodes.back()->next;
bool enough_bytes = current->allocated >= min_bytes;
bool enough_depth = max_depth == 0 || nodes.size() < max_depth;
if (enough_bytes)
{
frames.push_back(current->ptr);
allocated_self.back() -= current->allocated;
if (enough_depth)
{
allocated_total.push_back(current->allocated);
allocated_self.push_back(current->allocated);
nodes.push_back(current->children);
}
else
{
traces.push_back({frames, current->allocated, current->allocated});
frames.pop_back();
}
}
}
return traces;
}
};
static void insertData(DB::PaddedPODArray<UInt8> & chars, DB::PaddedPODArray<UInt64> & offsets, const char * pos, size_t length)
{
const size_t old_size = chars.size();
const size_t new_size = old_size + length + 1;
chars.resize(new_size);
if (length)
memcpy(chars.data() + old_size, pos, length);
chars[old_size + length] = 0;
offsets.push_back(new_size);
}
/// Split str by line feed and write as separate row to ColumnString.
static void fillColumn(DB::PaddedPODArray<UInt8> & chars, DB::PaddedPODArray<UInt64> & offsets, const std::string & str)
{
size_t start = 0;
size_t end = 0;
size_t size = str.size();
while (end < size)
{
if (str[end] == '\n')
{
insertData(chars, offsets, str.data() + start, end - start);
start = end + 1;
}
++end;
}
if (start < end)
insertData(chars, offsets, str.data() + start, end - start);
}
void dumpFlameGraph(
const AggregateFunctionFlameGraphTree::Traces & traces,
DB::PaddedPODArray<UInt8> & chars,
DB::PaddedPODArray<UInt64> & offsets)
{
DB::WriteBufferFromOwnString out;
std::unordered_map<uintptr_t, size_t> mapping;
#if defined(__ELF__) && !defined(OS_FREEBSD)
auto symbol_index_ptr = DB::SymbolIndex::instance();
const DB::SymbolIndex & symbol_index = *symbol_index_ptr;
#endif
for (const auto & trace : traces)
{
if (trace.allocated_self == 0)
continue;
for (size_t i = 0; i < trace.frames.size(); ++i)
{
if (i)
out << ";";
const void * ptr = reinterpret_cast<const void *>(trace.frames[i]);
#if defined(__ELF__) && !defined(OS_FREEBSD)
if (const auto * symbol = symbol_index.findSymbol(ptr))
writeString(demangle(symbol->name), out);
else
DB::writePointerHex(ptr, out);
#else
DB::writePointerHex(ptr, out);
#endif
}
out << ' ' << trace.allocated_self << "\n";
}
fillColumn(chars, offsets, out.str());
}
struct AggregateFunctionFlameGraphData
{
struct Entry
{
AggregateFunctionFlameGraphTree::TreeNode * trace;
UInt64 size;
Entry * next = nullptr;
};
struct Pair
{
Entry * allocation = nullptr;
Entry * deallocation = nullptr;
};
using Entries = HashMap<UInt64, Pair>;
AggregateFunctionFlameGraphTree tree;
Entries entries;
Entry * free_list = nullptr;
Entry * alloc(Arena * arena)
{
if (free_list)
{
auto * res = free_list;
free_list = free_list->next;
return res;
}
return reinterpret_cast<Entry *>(arena->alloc(sizeof(Entry)));
}
void release(Entry * entry)
{
entry->next = free_list;
free_list = entry;
}
static void track(Entry * allocation)
{
auto * node = allocation->trace;
while (node)
{
node->allocated += allocation->size;
node = node->parent;
}
}
static void untrack(Entry * allocation)
{
auto * node = allocation->trace;
while (node)
{
node->allocated -= allocation->size;
node = node->parent;
}
}
static Entry * tryFindMatchAndRemove(Entry *& list, UInt64 size)
{
if (!list)
return nullptr;
if (list->size == size)
{
Entry * entry = list;
list = list->next;
return entry;
}
else
{
Entry * parent = list;
while (parent->next && parent->next->size != size)
parent = parent->next;
if (parent->next && parent->next->size == size)
{
Entry * entry = parent->next;
parent->next = entry->next;
return entry;
}
return nullptr;
}
}
void add(UInt64 ptr, Int64 size, const UInt64 * stack, size_t stack_size, Arena * arena)
{
/// In case if argument is nullptr, only track allocations.
if (ptr == 0)
{
if (size > 0)
{
auto * node = tree.find(stack, stack_size, arena);
Entry entry{.trace = node, .size = UInt64(size)};
track(&entry);
}
return;
}
auto & place = entries[ptr];
if (size > 0)
{
if (auto * deallocation = tryFindMatchAndRemove(place.deallocation, size))
{
release(deallocation);
}
else
{
auto * node = tree.find(stack, stack_size, arena);
auto * allocation = alloc(arena);
allocation->size = UInt64(size);
allocation->trace = node;
track(allocation);
allocation->next = place.allocation;
place.allocation = allocation;
}
}
else if (size < 0)
{
UInt64 abs_size = -size;
if (auto * allocation = tryFindMatchAndRemove(place.allocation, abs_size))
{
untrack(allocation);
release(allocation);
}
else
{
auto * deallocation = alloc(arena);
deallocation->size = abs_size;
deallocation->next = place.deallocation;
place.deallocation = deallocation;
}
}
}
void merge(const AggregateFunctionFlameGraphTree & other_tree, Arena * arena)
{
AggregateFunctionFlameGraphTree::Trace::Frames frames;
std::vector<AggregateFunctionFlameGraphTree::ListNode *> nodes;
nodes.push_back(other_tree.root.children);
while (!nodes.empty())
{
if (nodes.back() == nullptr)
{
nodes.pop_back();
/// We don't have root's frame so framers are empty in the end.
if (!frames.empty())
frames.pop_back();
continue;
}
AggregateFunctionFlameGraphTree::TreeNode * current = nodes.back()->child;
nodes.back() = nodes.back()->next;
frames.push_back(current->ptr);
if (current->children)
nodes.push_back(current->children);
else
{
if (current->allocated)
add(0, current->allocated, frames.data(), frames.size(), arena);
frames.pop_back();
}
}
}
void merge(const AggregateFunctionFlameGraphData & other, Arena * arena)
{
AggregateFunctionFlameGraphTree::Trace::Frames frames;
for (const auto & entry : other.entries)
{
for (auto * allocation = entry.value.second.allocation; allocation; allocation = allocation->next)
{
frames.clear();
const auto * node = allocation->trace;
while (node->ptr)
{
frames.push_back(node->ptr);
node = node->parent;
}
std::reverse(frames.begin(), frames.end());
add(entry.value.first, allocation->size, frames.data(), frames.size(), arena);
untrack(allocation);
}
for (auto * deallocation = entry.value.second.deallocation; deallocation; deallocation = deallocation->next)
{
add(entry.value.first, -Int64(deallocation->size), nullptr, 0, arena);
}
}
merge(other.tree, arena);
}
void dumpFlameGraph(
DB::PaddedPODArray<UInt8> & chars,
DB::PaddedPODArray<UInt64> & offsets,
size_t max_depth, size_t min_bytes) const
{
DB::dumpFlameGraph(tree.dump(max_depth, min_bytes), chars, offsets);
}
};
/// Aggregate function which builds a flamegraph using the list of stacktraces.
/// The output is an array of strings which can be used by flamegraph.pl util.
/// See https://github.com/brendangregg/FlameGraph
///
/// Syntax: flameGraph(traces, [size = 1], [ptr = 0])
/// - trace : Array(UInt64), a stacktrace
/// - size : Int64, an allocation size (for memory profiling)
/// - ptr : UInt64, an allocation address
/// In case if ptr != 0, a flameGraph will map allocations (size > 0) and deallocations (size < 0) with the same size and ptr.
/// Only allocations which were not freed are shown. Not mapped deallocations are ignored.
///
/// Usage:
///
/// * Build a flamegraph based on CPU query profiler
/// set query_profiler_cpu_time_period_ns=10000000;
/// SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
/// clickhouse client --allow_introspection_functions=1
/// -q "select arrayJoin(flameGraph(arrayReverse(trace))) from system.trace_log where trace_type = 'CPU' and query_id = 'xxx'"
/// | ~/dev/FlameGraph/flamegraph.pl > flame_cpu.svg
///
/// * Build a flamegraph based on memory query profiler, showing all allocations
/// set memory_profiler_sample_probability=1, max_untracked_memory=1;
/// SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
/// clickhouse client --allow_introspection_functions=1
/// -q "select arrayJoin(flameGraph(trace, size)) from system.trace_log where trace_type = 'MemorySample' and query_id = 'xxx'"
/// | ~/dev/FlameGraph/flamegraph.pl --countname=bytes --color=mem > flame_mem.svg
///
/// * Build a flamegraph based on memory query profiler, showing allocations which were not deallocated in query context
/// set memory_profiler_sample_probability=1, max_untracked_memory=1, use_uncompressed_cache=1, merge_tree_max_rows_to_use_cache=100000000000, merge_tree_max_bytes_to_use_cache=1000000000000;
/// SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
/// clickhouse client --allow_introspection_functions=1
/// -q "select arrayJoin(flameGraph(trace, size, ptr)) from system.trace_log where trace_type = 'MemorySample' and query_id = 'xxx'"
/// | ~/dev/FlameGraph/flamegraph.pl --countname=bytes --color=mem > flame_mem_untracked.svg
///
/// * Build a flamegraph based on memory query profiler, showing active allocations at the fixed point of time
/// set memory_profiler_sample_probability=1, max_untracked_memory=1;
/// SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
/// 1. Memory usage per second
/// select event_time, m, formatReadableSize(max(s) as m) from (select event_time, sum(size) over (order by event_time) as s from system.trace_log where query_id = 'xxx' and trace_type = 'MemorySample') group by event_time order by event_time;
/// 2. Find a time point with maximal memory usage
/// select argMax(event_time, s), max(s) from (select event_time, sum(size) over (order by event_time) as s from system.trace_log where query_id = 'xxx' and trace_type = 'MemorySample');
/// 3. Fix active allocations at fixed point of time
/// clickhouse client --allow_introspection_functions=1
/// -q "select arrayJoin(flameGraph(trace, size, ptr)) from (select * from system.trace_log where trace_type = 'MemorySample' and query_id = 'xxx' and event_time <= 'yyy' order by event_time)"
/// | ~/dev/FlameGraph/flamegraph.pl --countname=bytes --color=mem > flame_mem_time_point_pos.svg
/// 4. Find deallocations at fixed point of time
/// clickhouse client --allow_introspection_functions=1
/// -q "select arrayJoin(flameGraph(trace, -size, ptr)) from (select * from system.trace_log where trace_type = 'MemorySample' and query_id = 'xxx' and event_time > 'yyy' order by event_time desc)"
/// | ~/dev/FlameGraph/flamegraph.pl --countname=bytes --color=mem > flame_mem_time_point_neg.svg
class AggregateFunctionFlameGraph final : public IAggregateFunctionDataHelper<AggregateFunctionFlameGraphData, AggregateFunctionFlameGraph>
{
public:
explicit AggregateFunctionFlameGraph(const DataTypes & argument_types_)
: IAggregateFunctionDataHelper<AggregateFunctionFlameGraphData, AggregateFunctionFlameGraph>(argument_types_, {}, createResultType())
{}
String getName() const override { return "flameGraph"; }
static DataTypePtr createResultType()
{
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeString>());
}
bool allocatesMemoryInArena() const override { return true; }
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
{
const auto * trace = typeid_cast<const ColumnArray *>(columns[0]);
const auto & trace_offsets = trace->getOffsets();
const auto & trace_values = typeid_cast<const ColumnUInt64 *>(&trace->getData())->getData();
UInt64 prev_offset = 0;
if (row_num)
prev_offset = trace_offsets[row_num - 1];
UInt64 trace_size = trace_offsets[row_num] - prev_offset;
Int64 allocated = 1;
if (argument_types.size() >= 2)
{
const auto & sizes = typeid_cast<const ColumnInt64 *>(columns[1])->getData();
allocated = sizes[row_num];
}
UInt64 ptr = 0;
if (argument_types.size() >= 3)
{
const auto & ptrs = typeid_cast<const ColumnUInt64 *>(columns[2])->getData();
ptr = ptrs[row_num];
}
this->data(place).add(ptr, allocated, trace_values.data() + prev_offset, trace_size, arena);
}
void addManyDefaults(
AggregateDataPtr __restrict /*place*/,
const IColumn ** /*columns*/,
size_t /*length*/,
Arena * /*arena*/) const override
{
}
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const override
{
this->data(place).merge(this->data(rhs), arena);
}
void serialize(ConstAggregateDataPtr __restrict, WriteBuffer &, std::optional<size_t> /* version */) const override
{
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Serialization for function flameGraph is not implemented.");
}
void deserialize(AggregateDataPtr __restrict, ReadBuffer &, std::optional<size_t> /* version */, Arena *) const override
{
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Deserialization for function flameGraph is not implemented.");
}
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
{
auto & array = assert_cast<ColumnArray &>(to);
auto & str = assert_cast<ColumnString &>(array.getData());
this->data(place).dumpFlameGraph(str.getChars(), str.getOffsets(), 0, 0);
array.getOffsets().push_back(str.size());
}
};
static void check(const std::string & name, const DataTypes & argument_types, const Array & params)
{
assertNoParameters(name, params);
if (argument_types.empty() || argument_types.size() > 3)
throw Exception(
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
"Aggregate function {} requires 1 to 3 arguments : trace, [size = 1], [ptr = 0]",
name);
auto ptr_type = std::make_shared<DataTypeUInt64>();
auto trace_type = std::make_shared<DataTypeArray>(ptr_type);
auto size_type = std::make_shared<DataTypeInt64>();
if (!argument_types[0]->equals(*trace_type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"First argument (trace) for function {} must be Array(UInt64), but it has type {}",
name, argument_types[0]->getName());
if (argument_types.size() >= 2 && !argument_types[1]->equals(*size_type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Second argument (size) for function {} must be Int64, but it has type {}",
name, argument_types[1]->getName());
if (argument_types.size() >= 3 && !argument_types[2]->equals(*ptr_type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Third argument (ptr) for function {} must be UInt64, but it has type {}",
name, argument_types[2]->getName());
}
AggregateFunctionPtr createAggregateFunctionFlameGraph(const std::string & name, const DataTypes & argument_types, const Array & params, const Settings * settings)
{
if (!settings->allow_introspection_functions)
throw Exception(ErrorCodes::FUNCTION_NOT_ALLOWED,
"Introspection functions are disabled, because setting 'allow_introspection_functions' is set to 0");
check(name, argument_types, params);
return std::make_shared<AggregateFunctionFlameGraph>(argument_types);
}
void registerAggregateFunctionFlameGraph(AggregateFunctionFactory & factory)
{
AggregateFunctionProperties properties = { .returns_default_when_only_null = true, .is_order_dependent = true };
factory.registerFunction("flameGraph", { createAggregateFunctionFlameGraph, properties });
}
}

20
src/AggregateFunctions/AggregateFunctionGroupArray.cpp
View File

@ -40,15 +40,10 @@ inline AggregateFunctionPtr createAggregateFunctionGroupArrayImpl(const DataType
return std::make_shared<GroupArrayGeneralImpl<GroupArrayNodeString, Trait>>(argument_type, parameters, std::forward<TArgs>(args)...);
return std::make_shared<GroupArrayGeneralImpl<GroupArrayNodeGeneral, Trait>>(argument_type, parameters, std::forward<TArgs>(args)...);
// Link list implementation doesn't show noticeable performance improvement
// if (which.idx == TypeIndex::String)
// return std::make_shared<GroupArrayGeneralListImpl<GroupArrayListNodeString, Trait>>(argument_type, std::forward<TArgs>(args)...);
// return std::make_shared<GroupArrayGeneralListImpl<GroupArrayListNodeGeneral, Trait>>(argument_type, std::forward<TArgs>(args)...);
}
template <bool Tlast>
AggregateFunctionPtr createAggregateFunctionGroupArray(
const std::string & name, const DataTypes & argument_types, const Array & parameters, const Settings *)
{
@ -79,9 +74,13 @@ AggregateFunctionPtr createAggregateFunctionGroupArray(
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
if (!limit_size)
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait<false, Sampler::NONE>>(argument_types[0], parameters);
{
if (Tlast)
throw Exception("groupArrayLast make sense only with max_elems (groupArrayLast(max_elems)())", ErrorCodes::BAD_ARGUMENTS);
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait</* Thas_limit= */ false, Tlast, /* Tsampler= */ Sampler::NONE>>(argument_types[0], parameters);
}
else
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait<true, Sampler::NONE>>(argument_types[0], parameters, max_elems);
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait</* Thas_limit= */ true, Tlast, /* Tsampler= */ Sampler::NONE>>(argument_types[0], parameters, max_elems);
}
AggregateFunctionPtr createAggregateFunctionGroupArraySample(
@ -114,7 +113,7 @@ AggregateFunctionPtr createAggregateFunctionGroupArraySample(
else
seed = thread_local_rng();
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait<true, Sampler::RNG>>(argument_types[0], parameters, max_elems, seed);
return createAggregateFunctionGroupArrayImpl<GroupArrayTrait</* Thas_limit= */ true, /* Tlast= */ false, /* Tsampler= */ Sampler::RNG>>(argument_types[0], parameters, max_elems, seed);
}
}
@ -124,8 +123,9 @@ void registerAggregateFunctionGroupArray(AggregateFunctionFactory & factory)
{
AggregateFunctionProperties properties = { .returns_default_when_only_null = false, .is_order_dependent = true };
factory.registerFunction("groupArray", { createAggregateFunctionGroupArray, properties });
factory.registerFunction("groupArray", { createAggregateFunctionGroupArray<false>, properties });
factory.registerFunction("groupArraySample", { createAggregateFunctionGroupArraySample, properties });
factory.registerFunction("groupArrayLast", { createAggregateFunctionGroupArray<true>, properties });
}
}

512
src/AggregateFunctions/AggregateFunctionGroupArray.h
View File

@ -37,24 +37,25 @@ enum class Sampler
{
NONE,
RNG,
DETERMINATOR // TODO
};
template <bool Thas_limit, Sampler Tsampler>
template <bool Thas_limit, bool Tlast, Sampler Tsampler>
struct GroupArrayTrait
{
static constexpr bool has_limit = Thas_limit;
static constexpr bool last = Tlast;
static constexpr Sampler sampler = Tsampler;
};
template <typename Trait>
static constexpr const char * getNameByTrait()
{
if (Trait::last)
return "groupArrayLast";
if (Trait::sampler == Sampler::NONE)
return "groupArray";
else if (Trait::sampler == Sampler::RNG)
return "groupArraySample";
// else if (Trait::sampler == Sampler::DETERMINATOR) // TODO
UNREACHABLE();
}
@ -100,6 +101,8 @@ struct GroupArrayNumericData<T, false>
using Allocator = MixedAlignedArenaAllocator<alignof(T), 4096>;
using Array = PODArray<T, 32, Allocator>;
// For groupArrayLast()
size_t total_values = 0;
Array value;
};
@ -129,7 +132,7 @@ public:
String getName() const override { return getNameByTrait<Trait>(); }
void insert(Data & a, const T & v, Arena * arena) const
void insertWithSampler(Data & a, const T & v, Arena * arena) const
{
++a.total_values;
if (a.value.size() < max_elems)
@ -151,88 +154,107 @@ public:
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
{
const auto & row_value = assert_cast<const ColumnVector<T> &>(*columns[0]).getData()[row_num];
auto & cur_elems = this->data(place);
++cur_elems.total_values;
if constexpr (Trait::sampler == Sampler::NONE)
{
if (limit_num_elems && this->data(place).value.size() >= max_elems)
if (limit_num_elems && cur_elems.value.size() >= max_elems)
{
if constexpr (Trait::last)
cur_elems.value[(cur_elems.total_values - 1) % max_elems] = row_value;
return;
}
this->data(place).value.push_back(assert_cast<const ColumnVector<T> &>(*columns[0]).getData()[row_num], arena);
cur_elems.value.push_back(row_value, arena);
}
if constexpr (Trait::sampler == Sampler::RNG)
{
auto & a = this->data(place);
++a.total_values;
if (a.value.size() < max_elems)
a.value.push_back(assert_cast<const ColumnVector<T> &>(*columns[0]).getData()[row_num], arena);
if (cur_elems.value.size() < max_elems)
cur_elems.value.push_back(row_value, arena);
else
{
UInt64 rnd = a.genRandom(a.total_values);
UInt64 rnd = cur_elems.genRandom(cur_elems.total_values);
if (rnd < max_elems)
a.value[rnd] = assert_cast<const ColumnVector<T> &>(*columns[0]).getData()[row_num];
cur_elems.value[rnd] = row_value;
}
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const override
{
if constexpr (Trait::sampler == Sampler::NONE)
{
auto & cur_elems = this->data(place);
auto & rhs_elems = this->data(rhs);
auto & cur_elems = this->data(place);
auto & rhs_elems = this->data(rhs);
if (!limit_num_elems)
if (rhs_elems.value.empty())
return;
if constexpr (Trait::last)
mergeNoSamplerLast(cur_elems, rhs_elems, arena);
else if constexpr (Trait::sampler == Sampler::NONE)
mergeNoSampler(cur_elems, rhs_elems, arena);
else if constexpr (Trait::sampler == Sampler::RNG)
mergeWithRNGSampler(cur_elems, rhs_elems, arena);
}
void mergeNoSamplerLast(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
UInt64 new_elements = std::min(static_cast<size_t>(max_elems), cur_elems.value.size() + rhs_elems.value.size());
cur_elems.value.resize_exact(new_elements, arena);
for (auto & value : rhs_elems.value)
{
cur_elems.value[cur_elems.total_values % max_elems] = value;
++cur_elems.total_values;
}
assert(rhs_elems.total_values >= rhs_elems.value.size());
cur_elems.total_values += rhs_elems.total_values - rhs_elems.value.size();
}
void mergeNoSampler(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
if (!limit_num_elems)
{
if (rhs_elems.value.size())
cur_elems.value.insertByOffsets(rhs_elems.value, 0, rhs_elems.value.size(), arena);
}
else
{
UInt64 elems_to_insert = std::min(static_cast<size_t>(max_elems) - cur_elems.value.size(), rhs_elems.value.size());
if (elems_to_insert)
cur_elems.value.insertByOffsets(rhs_elems.value, 0, elems_to_insert, arena);
}
}
void mergeWithRNGSampler(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
if (rhs_elems.total_values <= max_elems)
{
for (size_t i = 0; i < rhs_elems.value.size(); ++i)
insertWithSampler(cur_elems, rhs_elems.value[i], arena);
}
else if (cur_elems.total_values <= max_elems)
{
decltype(cur_elems.value) from;
from.swap(cur_elems.value, arena);
cur_elems.value.assign(rhs_elems.value.begin(), rhs_elems.value.end(), arena);
cur_elems.total_values = rhs_elems.total_values;
for (size_t i = 0; i < from.size(); ++i)
insertWithSampler(cur_elems, from[i], arena);
}
else
{
cur_elems.randomShuffle();
cur_elems.total_values += rhs_elems.total_values;
for (size_t i = 0; i < max_elems; ++i)
{
if (rhs_elems.value.size())
cur_elems.value.insertByOffsets(rhs_elems.value, 0, rhs_elems.value.size(), arena);
}
else
{
UInt64 elems_to_insert = std::min(static_cast<size_t>(max_elems) - cur_elems.value.size(), rhs_elems.value.size());
if (elems_to_insert)
cur_elems.value.insertByOffsets(rhs_elems.value, 0, elems_to_insert, arena);
UInt64 rnd = cur_elems.genRandom(cur_elems.total_values);
if (rnd < rhs_elems.total_values)
cur_elems.value[i] = rhs_elems.value[i];
}
}
if constexpr (Trait::sampler == Sampler::RNG)
{
if (this->data(rhs).value.empty()) /// rhs state is empty
return;
auto & a = this->data(place);
auto & b = this->data(rhs);
if (b.total_values <= max_elems)
{
for (size_t i = 0; i < b.value.size(); ++i)
insert(a, b.value[i], arena);
}
else if (a.total_values <= max_elems)
{
decltype(a.value) from;
from.swap(a.value, arena);
a.value.assign(b.value.begin(), b.value.end(), arena);
a.total_values = b.total_values;
for (size_t i = 0; i < from.size(); ++i)
insert(a, from[i], arena);
}
else
{
a.randomShuffle();
a.total_values += b.total_values;
for (size_t i = 0; i < max_elems; ++i)
{
UInt64 rnd = a.genRandom(a.total_values);
if (rnd < b.total_values)
a.value[i] = b.value[i];
}
}
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void serialize(ConstAggregateDataPtr __restrict place, WriteBuffer & buf, std::optional<size_t> /* version */) const override
@ -242,6 +264,9 @@ public:
writeVarUInt(size, buf);
buf.write(reinterpret_cast<const char *>(value.data()), size * sizeof(value[0]));
if constexpr (Trait::last)
DB::writeIntBinary<size_t>(this->data(place).total_values, buf);
if constexpr (Trait::sampler == Sampler::RNG)
{
DB::writeIntBinary<size_t>(this->data(place).total_values, buf);
@ -249,9 +274,6 @@ public:
rng_buf << this->data(place).rng;
DB::writeStringBinary(rng_buf.str(), buf);
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void deserialize(AggregateDataPtr __restrict place, ReadBuffer & buf, std::optional<size_t> /* version */, Arena * arena) const override
@ -267,9 +289,12 @@ public:
auto & value = this->data(place).value;
value.resize(size, arena);
value.resize_exact(size, arena);
buf.readStrict(reinterpret_cast<char *>(value.data()), size * sizeof(value[0]));
if constexpr (Trait::last)
DB::readIntBinary<size_t>(this->data(place).total_values, buf);
if constexpr (Trait::sampler == Sampler::RNG)
{
DB::readIntBinary<size_t>(this->data(place).total_values, buf);
@ -278,9 +303,6 @@ public:
ReadBufferFromString rng_buf(rng_string);
rng_buf >> this->data(place).rng;
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
@ -396,6 +418,8 @@ struct GroupArrayGeneralData<Node, false>
using Allocator = MixedAlignedArenaAllocator<alignof(Node *), 4096>;
using Array = PODArray<Node *, 32, Allocator>;
// For groupArrayLast()
size_t total_values = 0;
Array value;
};
@ -430,7 +454,7 @@ public:
String getName() const override { return getNameByTrait<Trait>(); }
void insert(Data & a, const Node * v, Arena * arena) const
void insertWithSampler(Data & a, const Node * v, Arena * arena) const
{
++a.total_values;
if (a.value.size() < max_elems)
@ -452,96 +476,110 @@ public:
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
{
auto & cur_elems = data(place);
++cur_elems.total_values;
if constexpr (Trait::sampler == Sampler::NONE)
{
if (limit_num_elems && data(place).value.size() >= max_elems)
if (limit_num_elems && cur_elems.value.size() >= max_elems)
{
if (Trait::last)
{
Node * node = Node::allocate(*columns[0], row_num, arena);
cur_elems.value[(cur_elems.total_values - 1) % max_elems] = node;
}
return;
}
Node * node = Node::allocate(*columns[0], row_num, arena);
data(place).value.push_back(node, arena);
cur_elems.value.push_back(node, arena);
}
if constexpr (Trait::sampler == Sampler::RNG)
{
auto & a = data(place);
++a.total_values;
if (a.value.size() < max_elems)
a.value.push_back(Node::allocate(*columns[0], row_num, arena), arena);
if (cur_elems.value.size() < max_elems)
cur_elems.value.push_back(Node::allocate(*columns[0], row_num, arena), arena);
else
{
UInt64 rnd = a.genRandom(a.total_values);
UInt64 rnd = cur_elems.genRandom(cur_elems.total_values);
if (rnd < max_elems)
a.value[rnd] = Node::allocate(*columns[0], row_num, arena);
cur_elems.value[rnd] = Node::allocate(*columns[0], row_num, arena);
}
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const override
{
if constexpr (Trait::sampler == Sampler::NONE)
mergeNoSampler(place, rhs, arena);
else if constexpr (Trait::sampler == Sampler::RNG)
mergeWithRNGSampler(place, rhs, arena);
// TODO
// else if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
auto & cur_elems = data(place);
auto & rhs_elems = data(rhs);
void ALWAYS_INLINE mergeNoSampler(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const
{
if (data(rhs).value.empty()) /// rhs state is empty
if (rhs_elems.value.empty())
return;
if constexpr (Trait::last)
mergeNoSamplerLast(cur_elems, rhs_elems, arena);
else if constexpr (Trait::sampler == Sampler::NONE)
mergeNoSampler(cur_elems, rhs_elems, arena);
else if constexpr (Trait::sampler == Sampler::RNG)
mergeWithRNGSampler(cur_elems, rhs_elems, arena);
}
void ALWAYS_INLINE mergeNoSamplerLast(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
UInt64 new_elements = std::min(static_cast<size_t>(max_elems), cur_elems.value.size() + rhs_elems.value.size());
cur_elems.value.resize_exact(new_elements, arena);
for (auto & value : rhs_elems.value)
{
cur_elems.value[cur_elems.total_values % max_elems] = value->clone(arena);
++cur_elems.total_values;
}
assert(rhs_elems.total_values >= rhs_elems.value.size());
cur_elems.total_values += rhs_elems.total_values - rhs_elems.value.size();
}
void ALWAYS_INLINE mergeNoSampler(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
UInt64 new_elems;
if (limit_num_elems)
{
if (data(place).value.size() >= max_elems)
if (cur_elems.value.size() >= max_elems)
return;
new_elems = std::min(data(rhs).value.size(), static_cast<size_t>(max_elems) - data(place).value.size());
new_elems = std::min(rhs_elems.value.size(), static_cast<size_t>(max_elems) - cur_elems.value.size());
}
else
new_elems = data(rhs).value.size();
new_elems = rhs_elems.value.size();
auto & a = data(place).value;
auto & b = data(rhs).value;
for (UInt64 i = 0; i < new_elems; ++i)
a.push_back(b[i]->clone(arena), arena);
cur_elems.value.push_back(rhs_elems.value[i]->clone(arena), arena);
}
void ALWAYS_INLINE mergeWithRNGSampler(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const
void ALWAYS_INLINE mergeWithRNGSampler(Data & cur_elems, const Data & rhs_elems, Arena * arena) const
{
if (data(rhs).value.empty()) /// rhs state is empty
return;
auto & a = data(place);
auto & b = data(rhs);
if (b.total_values <= max_elems)
if (rhs_elems.total_values <= max_elems)
{
for (size_t i = 0; i < b.value.size(); ++i)
insert(a, b.value[i], arena);
for (size_t i = 0; i < rhs_elems.value.size(); ++i)
insertWithSampler(cur_elems, rhs_elems.value[i], arena);
}
else if (a.total_values <= max_elems)
else if (cur_elems.total_values <= max_elems)
{
decltype(a.value) from;
from.swap(a.value, arena);
for (auto & node : b.value)
a.value.push_back(node->clone(arena), arena);
a.total_values = b.total_values;
decltype(cur_elems.value) from;
from.swap(cur_elems.value, arena);
for (auto & node : rhs_elems.value)
cur_elems.value.push_back(node->clone(arena), arena);
cur_elems.total_values = rhs_elems.total_values;
for (size_t i = 0; i < from.size(); ++i)
insert(a, from[i], arena);
insertWithSampler(cur_elems, from[i], arena);
}
else
{
a.randomShuffle();
a.total_values += b.total_values;
cur_elems.randomShuffle();
cur_elems.total_values += rhs_elems.total_values;
for (size_t i = 0; i < max_elems; ++i)
{
UInt64 rnd = a.genRandom(a.total_values);
if (rnd < b.total_values)
a.value[i] = b.value[i]->clone(arena);
UInt64 rnd = cur_elems.genRandom(cur_elems.total_values);
if (rnd < rhs_elems.total_values)
cur_elems.value[i] = rhs_elems.value[i]->clone(arena);
}
}
}
@ -554,6 +592,9 @@ public:
for (auto & node : value)
node->write(buf);
if constexpr (Trait::last)
DB::writeIntBinary<size_t>(data(place).total_values, buf);
if constexpr (Trait::sampler == Sampler::RNG)
{
DB::writeIntBinary<size_t>(data(place).total_values, buf);
@ -561,9 +602,6 @@ public:
rng_buf << data(place).rng;
DB::writeStringBinary(rng_buf.str(), buf);
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void deserialize(AggregateDataPtr __restrict place, ReadBuffer & buf, std::optional<size_t> /* version */, Arena * arena) const override
@ -582,10 +620,13 @@ public:
auto & value = data(place).value;
value.resize(elems, arena);
value.resize_exact(elems, arena);
for (UInt64 i = 0; i < elems; ++i)
value[i] = Node::read(buf, arena);
if constexpr (Trait::last)
DB::readIntBinary<size_t>(data(place).total_values, buf);
if constexpr (Trait::sampler == Sampler::RNG)
{
DB::readIntBinary<size_t>(data(place).total_values, buf);
@ -594,9 +635,6 @@ public:
ReadBufferFromString rng_buf(rng_string);
rng_buf >> data(place).rng;
}
// TODO
// if constexpr (Trait::sampler == Sampler::DETERMINATOR)
}
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
@ -622,222 +660,6 @@ public:
bool allocatesMemoryInArena() const override { return true; }
};
template <typename Node>
struct GroupArrayListNodeBase : public GroupArrayNodeBase<Node>
{
Node * next;
};
struct GroupArrayListNodeString : public GroupArrayListNodeBase<GroupArrayListNodeString>
{
using Node = GroupArrayListNodeString;
/// Create node from string
static Node * allocate(const IColumn & column, size_t row_num, Arena * arena)
{
StringRef string = assert_cast<const ColumnString &>(column).getDataAt(row_num);
Node * node = reinterpret_cast<Node *>(arena->alignedAlloc(sizeof(Node) + string.size, alignof(Node)));
node->next = nullptr;
node->size = string.size;
memcpy(node->data(), string.data, string.size);
return node;
}
void insertInto(IColumn & column) { assert_cast<ColumnString &>(column).insertData(data(), size); }
};
struct GroupArrayListNodeGeneral : public GroupArrayListNodeBase<GroupArrayListNodeGeneral>
{
using Node = GroupArrayListNodeGeneral;
static Node * allocate(const IColumn & column, size_t row_num, Arena * arena)
{
const char * begin = arena->alignedAlloc(sizeof(Node), alignof(Node));
StringRef value = column.serializeValueIntoArena(row_num, *arena, begin);
Node * node = reinterpret_cast<Node *>(const_cast<char *>(begin));
node->next = nullptr;
node->size = value.size;
return node;
}
void insertInto(IColumn & column) { column.deserializeAndInsertFromArena(data()); }
};
template <typename Node>
struct GroupArrayGeneralListData
{
UInt64 elems = 0;
Node * first = nullptr;
Node * last = nullptr;
};
/// Implementation of groupArray for String or any ComplexObject via linked list
/// It has poor performance in case of many small objects
template <typename Node, typename Trait>
class GroupArrayGeneralListImpl final
: public IAggregateFunctionDataHelper<GroupArrayGeneralListData<Node>, GroupArrayGeneralListImpl<Node, Trait>>
{
static constexpr bool limit_num_elems = Trait::has_limit;
using Data = GroupArrayGeneralListData<Node>;
static Data & data(AggregateDataPtr __restrict place) { return *reinterpret_cast<Data *>(place); }
static const Data & data(ConstAggregateDataPtr __restrict place) { return *reinterpret_cast<const Data *>(place); }
DataTypePtr & data_type;
UInt64 max_elems;
public:
GroupArrayGeneralListImpl(const DataTypePtr & data_type_, const Array & parameters_, UInt64 max_elems_ = std::numeric_limits<UInt64>::max())
: IAggregateFunctionDataHelper<GroupArrayGeneralListData<Node>, GroupArrayGeneralListImpl<Node, Trait>>({data_type_}, parameters_, std::make_shared<DataTypeArray>(data_type_))
, data_type(this->argument_types[0])
, max_elems(max_elems_)
{
}
String getName() const override { return getNameByTrait<Trait>(); }
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
{
if (limit_num_elems && data(place).elems >= max_elems)
return;
Node * node = Node::allocate(*columns[0], row_num, arena);
if (unlikely(!data(place).first))
{
data(place).first = node;
data(place).last = node;
}
else
{
data(place).last->next = node;
data(place).last = node;
}
++data(place).elems;
}
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const override
{
/// It is sadly, but rhs's Arena could be destroyed
if (!data(rhs).first) /// rhs state is empty
return;
UInt64 new_elems;
UInt64 cur_elems = data(place).elems;
if (limit_num_elems)
{
if (data(place).elems >= max_elems)
return;
new_elems = std::min(data(place).elems + data(rhs).elems, static_cast<size_t>(max_elems));
}
else
{
new_elems = data(place).elems + data(rhs).elems;
}
Node * p_rhs = data(rhs).first;
Node * p_lhs;
if (unlikely(!data(place).last)) /// lhs state is empty
{
p_lhs = p_rhs->clone(arena);
data(place).first = data(place).last = p_lhs;
p_rhs = p_rhs->next;
++cur_elems;
}
else
{
p_lhs = data(place).last;
}
for (; cur_elems < new_elems; ++cur_elems)
{
Node * p_new = p_rhs->clone(arena);
p_lhs->next = p_new;
p_rhs = p_rhs->next;
p_lhs = p_new;
}
p_lhs->next = nullptr;
data(place).last = p_lhs;
data(place).elems = new_elems;
}
void serialize(ConstAggregateDataPtr __restrict place, WriteBuffer & buf) const override
{
writeVarUInt(data(place).elems, buf);
Node * p = data(place).first;
while (p)
{
p->write(buf);
p = p->next;
}
}
void deserialize(AggregateDataPtr __restrict place, ReadBuffer & buf, Arena * arena) const override
{
UInt64 elems;
readVarUInt(elems, buf);
data(place).elems = elems;
if (unlikely(elems == 0))
return;
if (unlikely(elems > AGGREGATE_FUNCTION_GROUP_ARRAY_MAX_ARRAY_SIZE))
throw Exception("Too large array size", ErrorCodes::TOO_LARGE_ARRAY_SIZE);
if (limit_num_elems && unlikely(elems > max_elems))
throw Exception("Too large array size, it should not exceed " + toString(max_elems), ErrorCodes::TOO_LARGE_ARRAY_SIZE);
Node * prev = Node::read(buf, arena);
data(place).first = prev;
for (UInt64 i = 1; i < elems; ++i)
{
Node * cur = Node::read(buf, arena);
prev->next = cur;
prev = cur;
}
prev->next = nullptr;
data(place).last = prev;
}
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
{
auto & column_array = assert_cast<ColumnArray &>(to);
auto & offsets = column_array.getOffsets();
offsets.push_back(offsets.back() + data(place).elems);
auto & column_data = column_array.getData();
if (std::is_same_v<Node, GroupArrayListNodeString>)
{
auto & string_offsets = assert_cast<ColumnString &>(column_data).getOffsets();
string_offsets.reserve(string_offsets.size() + data(place).elems);
}
Node * p = data(place).first;
while (p)
{
p->insertInto(column_data);
p = p->next;
}
}
bool allocatesMemoryInArena() const override { return true; }
};
#undef AGGREGATE_FUNCTION_GROUP_ARRAY_MAX_ARRAY_SIZE
}

34
src/AggregateFunctions/AggregateFunctionIf.cpp
View File

@ -23,7 +23,7 @@ public:
throw Exception("Incorrect number of arguments for aggregate function with " + getName() + " suffix",
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
if (!isUInt8(arguments.back()))
if (!isUInt8(arguments.back()) && !arguments.back()->onlyNull())
throw Exception("Illegal type " + arguments.back()->getName() + " of last argument for aggregate function with " + getName() + " suffix",
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
@ -52,6 +52,7 @@ class AggregateFunctionIfNullUnary final
private:
size_t num_arguments;
bool filter_is_nullable = false;
bool filter_is_only_null = false;
/// The name of the nested function, including combinators (i.e. *If)
///
@ -84,10 +85,8 @@ private:
return assert_cast<const ColumnUInt8 &>(*filter_column).getData()[row_num] && !filter_null_map[row_num];
}
else
{
return assert_cast<const ColumnUInt8 &>(*filter_column).getData()[row_num];
}
return assert_cast<const ColumnUInt8 &>(*filter_column).getData()[row_num];
}
public:
@ -106,10 +105,14 @@ public:
"Aggregate function {} require at least one argument", getName());
filter_is_nullable = arguments[num_arguments - 1]->isNullable();
filter_is_only_null = arguments[num_arguments - 1]->onlyNull();
}
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
{
if (filter_is_only_null)
return;
const ColumnNullable * column = assert_cast<const ColumnNullable *>(columns[0]);
const IColumn * nested_column = &column->getNestedColumn();
if (!column->isNullAt(row_num) && singleFilter(columns, row_num))
@ -127,6 +130,9 @@ public:
Arena * arena,
ssize_t) const override
{
if (filter_is_only_null)
return;
const ColumnNullable * column = assert_cast<const ColumnNullable *>(columns[0]);
const UInt8 * null_map = column->getNullMapData().data();
const IColumn * columns_param[] = {&column->getNestedColumn()};
@ -177,6 +183,11 @@ public:
#if USE_EMBEDDED_COMPILER
bool isCompilable() const override
{
return canBeNativeType(*this->argument_types.back()) && this->nested_function->isCompilable();
}
void compileAdd(llvm::IRBuilderBase & builder, llvm::Value * aggregate_data_ptr, const DataTypes & arguments_types, const std::vector<llvm::Value *> & argument_values) const override
{
llvm::IRBuilder<> & b = static_cast<llvm::IRBuilder<> &>(builder);
@ -224,6 +235,9 @@ class AggregateFunctionIfNullVariadic final : public AggregateFunctionNullBase<
serialize_flag,
AggregateFunctionIfNullVariadic<result_is_nullable, serialize_flag>>
{
private:
bool filter_is_only_null = false;
public:
String getName() const override
@ -243,6 +257,8 @@ public:
for (size_t i = 0; i < number_of_arguments; ++i)
is_nullable[i] = arguments[i]->isNullable();
filter_is_only_null = arguments.back()->onlyNull();
}
static inline bool singleFilter(const IColumn ** columns, size_t row_num, size_t num_arguments)
@ -282,6 +298,9 @@ public:
void addBatchSinglePlace(
size_t row_begin, size_t row_end, AggregateDataPtr __restrict place, const IColumn ** columns, Arena * arena, ssize_t) const final
{
if (filter_is_only_null)
return;
std::unique_ptr<UInt8[]> final_null_flags = std::make_unique<UInt8[]>(row_end);
const size_t filter_column_num = number_of_arguments - 1;
@ -346,6 +365,11 @@ public:
#if USE_EMBEDDED_COMPILER
bool isCompilable() const override
{
return canBeNativeType(*this->argument_types.back()) && this->nested_function->isCompilable();
}
void compileAdd(llvm::IRBuilderBase & builder, llvm::Value * aggregate_data_ptr, const DataTypes & arguments_types, const std::vector<llvm::Value *> & argument_values) const override
{
/// TODO: Check

8
src/AggregateFunctions/AggregateFunctionIf.h
View File

@ -42,7 +42,7 @@ public:
if (num_arguments == 0)
throw Exception("Aggregate function " + getName() + " require at least one argument", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
if (!isUInt8(types.back()))
if (!isUInt8(types.back()) && !types.back()->onlyNull())
throw Exception("Last argument for aggregate function " + getName() + " must be UInt8", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
@ -199,12 +199,16 @@ public:
AggregateFunctionPtr getNestedFunction() const override { return nested_func; }
std::unordered_set<size_t> getArgumentsThatCanBeOnlyNull() const override
{
return {num_arguments - 1};
}
#if USE_EMBEDDED_COMPILER
bool isCompilable() const override
{
return nested_func->isCompilable();
return canBeNativeType(*this->argument_types.back()) && nested_func->isCompilable();
}
void compileCreate(llvm::IRBuilderBase & builder, llvm::Value * aggregate_data_ptr) const override

18
src/AggregateFunctions/AggregateFunctionNull.cpp
View File

@ -29,7 +29,13 @@ public:
size_t size = arguments.size();
DataTypes res(size);
for (size_t i = 0; i < size; ++i)
res[i] = removeNullable(arguments[i]);
{
/// Nullable(Nothing) is processed separately, don't convert it to Nothing.
if (arguments[i]->onlyNull())
res[i] = arguments[i];
else
res[i] = removeNullable(arguments[i]);
}
return res;
}
@ -41,12 +47,16 @@ public:
{
bool has_nullable_types = false;
bool has_null_types = false;
for (const auto & arg_type : arguments)
std::unordered_set<size_t> arguments_that_can_be_only_null;
if (nested_function)
arguments_that_can_be_only_null = nested_function->getArgumentsThatCanBeOnlyNull();
for (size_t i = 0; i < arguments.size(); ++i)
{
if (arg_type->isNullable())
if (arguments[i]->isNullable())
{
has_nullable_types = true;
if (arg_type->onlyNull())
if (arguments[i]->onlyNull() && !arguments_that_can_be_only_null.contains(i))
{
has_null_types = true;
break;

14
src/AggregateFunctions/AggregateFunctionSumMap.h
View File

@ -468,6 +468,7 @@ public:
bool keepKey(const T &) const { return true; }
};
template <typename T, bool overflow, bool tuple_argument>
class AggregateFunctionSumMapFiltered final :
public AggregateFunctionMapBase<T,
@ -502,6 +503,8 @@ public:
"Aggregate function {} requires an Array as a parameter",
getNameImpl());
this->parameters = params_;
keys_to_keep.reserve(keys_to_keep_values.size());
for (const Field & f : keys_to_keep_values)
@ -509,7 +512,16 @@ public:
}
static String getNameImpl()
{ return overflow ? "sumMapFilteredWithOverflow" : "sumMapFiltered"; }
{
if constexpr (overflow)
{
return "sumMapFilteredWithOverflow";
}
else
{
return "sumMapFiltered";
}
}
bool keepKey(const T & key) const { return keys_to_keep.count(key); }
};

11
src/AggregateFunctions/IAggregateFunction.h
View File

@ -345,6 +345,14 @@ public:
return nullptr;
}
/// For most functions if one of arguments is always NULL, we return NULL (it's implemented in combinator Null),
/// but in some functions we can want to process this argument somehow (for example condition argument in If combinator).
/// This method returns the set of argument indexes that can be always NULL, they will be skipped in combinator Null.
virtual std::unordered_set<size_t> getArgumentsThatCanBeOnlyNull() const
{
return {};
}
/** Return the nested function if this is an Aggregate Function Combinator.
* Otherwise return nullptr.
*/
@ -828,6 +836,9 @@ struct AggregateFunctionProperties
* Some may also name this property as "non-commutative".
*/
bool is_order_dependent = false;
/// Indicates if it's actually window function.
bool is_window_function = false;
};

2
src/AggregateFunctions/registerAggregateFunctions.cpp
View File

@ -73,7 +73,6 @@ void registerAggregateFunctionExponentialMovingAverage(AggregateFunctionFactory
void registerAggregateFunctionSparkbar(AggregateFunctionFactory &);
void registerAggregateFunctionIntervalLengthSum(AggregateFunctionFactory &);
void registerAggregateFunctionAnalysisOfVariance(AggregateFunctionFactory &);
void registerAggregateFunctionFlameGraph(AggregateFunctionFactory &);
class AggregateFunctionCombinatorFactory;
void registerAggregateFunctionCombinatorIf(AggregateFunctionCombinatorFactory &);
@ -159,7 +158,6 @@ void registerAggregateFunctions()
registerAggregateFunctionExponentialMovingAverage(factory);
registerAggregateFunctionSparkbar(factory);
registerAggregateFunctionAnalysisOfVariance(factory);
registerAggregateFunctionFlameGraph(factory);
registerWindowFunctions(factory);
}

14
src/Analyzer/Passes/QueryAnalysisPass.cpp
View File

@ -4307,6 +4307,8 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
}
}
const auto & settings = scope.context->getSettingsRef();
if (function_node.isWindowFunction())
{
if (!AggregateFunctionFactory::instance().isAggregateFunctionName(function_name))
@ -4324,8 +4326,12 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
"Window function '{}' does not support lambda arguments",
function_name);
bool need_add_or_null = settings.aggregate_functions_null_for_empty && !function_name.ends_with("OrNull");
AggregateFunctionProperties properties;
auto aggregate_function = AggregateFunctionFactory::instance().get(function_name, argument_types, parameters, properties);
auto aggregate_function = need_add_or_null
? AggregateFunctionFactory::instance().get(function_name + "OrNull", argument_types, parameters, properties)
: AggregateFunctionFactory::instance().get(function_name, argument_types, parameters, properties);
function_node.resolveAsWindowFunction(aggregate_function);
@ -4384,8 +4390,12 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
"Aggregate function '{}' does not support lambda arguments",
function_name);
bool need_add_or_null = settings.aggregate_functions_null_for_empty && !function_name.ends_with("OrNull");
AggregateFunctionProperties properties;
auto aggregate_function = AggregateFunctionFactory::instance().get(function_name, argument_types, parameters, properties);
auto aggregate_function = need_add_or_null
? AggregateFunctionFactory::instance().get(function_name + "OrNull", argument_types, parameters, properties)
: AggregateFunctionFactory::instance().get(function_name, argument_types, parameters, properties);
function_node.resolveAsAggregateFunction(aggregate_function);
return result_projection_names;
}

5
src/Analyzer/Passes/SumIfToCountIfPass.cpp
View File

@ -81,6 +81,7 @@ public:
if (nested_if_function_arguments_nodes.size() != 3)
return;
auto & cond_argument = nested_if_function_arguments_nodes[0];
const auto * if_true_condition_constant_node = nested_if_function_arguments_nodes[1]->as<ConstantNode>();
const auto * if_false_condition_constant_node = nested_if_function_arguments_nodes[2]->as<ConstantNode>();
@ -107,8 +108,8 @@ public:
return;
}
/// Rewrite `sum(if(cond, 0, 1))` into `countIf(not(cond))`.
if (if_true_condition_value == 0 && if_false_condition_value == 1)
/// Rewrite `sum(if(cond, 0, 1))` into `countIf(not(cond))` if condition is not Nullable (otherwise the result can be different).
if (if_true_condition_value == 0 && if_false_condition_value == 1 && !cond_argument->getResultType()->isNullable())
{
DataTypePtr not_function_result_type = std::make_shared<DataTypeUInt8>();

9
src/Backups/BackupCoordinationLocal.cpp
View File

@ -188,15 +188,6 @@ std::optional<FileInfo> BackupCoordinationLocal::getFileInfo(const SizeAndChecks
return it->second;
}
std::optional<SizeAndChecksum> BackupCoordinationLocal::getFileSizeAndChecksum(const String & file_name) const
{
std::lock_guard lock{mutex};
auto it = file_names.find(file_name);
if (it == file_names.end())
return std::nullopt;
return it->second;
}
String BackupCoordinationLocal::getNextArchiveSuffix()
{
std::lock_guard lock{mutex};

1
src/Backups/BackupCoordinationLocal.h
View File

@ -48,7 +48,6 @@ public:
std::optional<FileInfo> getFileInfo(const String & file_name) const override;
std::optional<FileInfo> getFileInfo(const SizeAndChecksum & size_and_checksum) const override;
std::optional<SizeAndChecksum> getFileSizeAndChecksum(const String & file_name) const override;
String getNextArchiveSuffix() override;
Strings getAllArchiveSuffixes() const override;

9
src/Backups/BackupCoordinationRemote.cpp
View File

@ -575,15 +575,6 @@ std::optional<FileInfo> BackupCoordinationRemote::getFileInfo(const SizeAndCheck
return deserializeFileInfo(file_info_str);
}
std::optional<SizeAndChecksum> BackupCoordinationRemote::getFileSizeAndChecksum(const String & file_name) const
{
auto zk = getZooKeeper();
String size_and_checksum;
if (!zk->tryGet(zookeeper_path + "/file_names/" + escapeForFileName(file_name), size_and_checksum))
return std::nullopt;
return deserializeSizeAndChecksum(size_and_checksum);
}
String BackupCoordinationRemote::getNextArchiveSuffix()
{
auto zk = getZooKeeper();

1
src/Backups/BackupCoordinationRemote.h
View File

@ -51,7 +51,6 @@ public:
bool hasFiles(const String & directory) const override;
std::optional<FileInfo> getFileInfo(const String & file_name) const override;
std::optional<FileInfo> getFileInfo(const SizeAndChecksum & size_and_checksum) const override;
std::optional<SizeAndChecksum> getFileSizeAndChecksum(const String & file_name) const override;
String getNextArchiveSuffix() override;
Strings getAllArchiveSuffixes() const override;

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