thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 08:40:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge upstream/master into ncb/async-metrics-pri-key-size

Browse Source
This commit is contained in:
Bharat Nallan Chakravarthy 2023-12-18 09:46:51 -08:00
commit aef4e2e6ec
1007 changed files with 22179 additions and 12558 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.github/actions/common_setup/action.yml vendored
View File

@ -18,9 +18,6 @@ runs:
echo "Setup the common ENV variables"
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/${{inputs.job_type}}
REPO_COPY=${{runner.temp}}/${{inputs.job_type}}/git-repo-copy
IMAGES_PATH=${{runner.temp}}/images_path
REPORTS_PATH=${{runner.temp}}/reports_dir
EOF
if [ -z "${{env.GITHUB_JOB_OVERRIDDEN}}" ] && [ "true" == "${{inputs.nested_job}}" ]; then
echo "The GITHUB_JOB_OVERRIDDEN ENV is unset, and must be set for the nested jobs"
@ -30,6 +27,4 @@ runs:
shell: bash
run: |
# to remove every leftovers
sudo rm -fr "$TEMP_PATH"
mkdir -p "$REPO_COPY"
cp -a "$GITHUB_WORKSPACE"/. "$REPO_COPY"/
sudo rm -fr "$TEMP_PATH" && mkdir -p "$TEMP_PATH"

232
.github/workflows/backport_branches.yml vendored
View File

@ -10,27 +10,21 @@ on: # yamllint disable-line rule:truthy
branches:
- 'backport/**'
jobs:
CheckLabels:
RunConfig:
runs-on: [self-hosted, style-checker]
# Run the first check always, even if the CI is cancelled
if: ${{ always() }}
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 run_check.py
PythonUnitTests:
runs-on: [self-hosted, style-checker]
needs: CheckLabels
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
@ -40,273 +34,235 @@ jobs:
echo "Testing $dir"
python3 -m unittest discover -s "$dir" -p 'test_*.py'
done
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
needs: CheckLabels
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
- name: PrepareRunConfig
id: runconfig
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
runs-on: [self-hosted, style-checker]
needs: CheckLabels
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --outfile ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
echo "::group::CI run configure results"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
{
echo 'CI_DATA<<EOF'
cat ${{ runner.temp }}/ci_run_data.json
echo 'EOF'
} >> "$GITHUB_OUTPUT"
- name: Re-create GH statuses for skipped jobs if any
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --update-gh-statuses
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
DockerHubPush:
needs: [DockerHubPushAmd64, DockerHubPushAarch64, PythonUnitTests]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
filter: tree:0
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check X86
test_name: Compatibility check (amd64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
CompatibilityCheckAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check X86
test_name: Compatibility check (aarch64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
#########################################################################################
#################################### ORDINARY BUILDS ####################################
#########################################################################################
BuilderDebRelease:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_release
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebAarch64:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_aarch64
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebAsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_asan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebTsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_tsan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebDebug:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_debug
data: ${{ needs.RunConfig.outputs.data }}
BuilderBinDarwin:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: binary_darwin
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
BuilderBinDarwinAarch64:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: binary_darwin_aarch64
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
needs:
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
clear-repository: true
fetch-depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
filter: tree:0
- name: Check docker clickhouse/clickhouse-server building
run: |
test_name: Docker server and keeper images
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-server --image-path docker/server
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################
##################################### BUILD REPORTER #######################################
############################################################################################
BuilderReport:
if: ${{ success() || failure() }}
if: ${{ !failure() && !cancelled() }}
needs:
- BuilderDebRelease
- RunConfig
- BuilderDebAarch64
- BuilderDebAsan
- BuilderDebTsan
- BuilderDebDebug
- BuilderDebRelease
- BuilderDebTsan
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
additional_envs: |
NEEDS_DATA<<NDENV
${{ toJSON(needs) }}
NDENV
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 build_report_check.py "$CHECK_NAME"
BuilderSpecialReport:
if: ${{ success() || failure() }}
if: ${{ !failure() && !cancelled() }}
needs:
- RunConfig
- BuilderBinDarwin
- BuilderBinDarwinAarch64
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
additional_envs: |
NEEDS_DATA<<NDENV
${{ toJSON(needs) }}
NDENV
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 build_report_check.py "$CHECK_NAME"
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (amd64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
InstallPackagesTestAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (arm64)
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
FunctionalStatelessTestAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (asan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
##############################################################################################
############################ FUNCTIONAl STATEFUL TESTS #######################################
##############################################################################################
FunctionalStatefulTestDebug:
needs: [BuilderDebDebug]
needs: [RunConfig, BuilderDebDebug]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (debug)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
##############################################################################################
######################################### STRESS TESTS #######################################
##############################################################################################
StressTestTsan:
needs: [BuilderDebTsan]
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (tsan)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
#############################################################################################
############################# INTEGRATION TESTS #############################################
#############################################################################################
IntegrationTestsRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Integration tests (release)
runner_type: stress-tester
batches: 4
run_command: |
cd "$REPO_COPY/tests/ci"
python3 integration_test_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
FinishCheck:
if: ${{ !failure() && !cancelled() }}
needs:
- DockerHubPush
- DockerServerImages
- BuilderReport
- BuilderSpecialReport
- FunctionalStatelessTestAsan

138
.github/workflows/docs_check.yml vendored
View File

@ -1,138 +0,0 @@
name: DocsCheck
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
pull_request:
types:
- synchronize
- reopened
- opened
branches:
- master
paths:
- '**.md'
- 'docker/docs/**'
- 'docs/**'
- 'utils/check-style/aspell-ignore/**'
- 'tests/ci/docs_check.py'
- '.github/workflows/docs_check.yml'
jobs:
CheckLabels:
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 run_check.py
DockerHubPushAarch64:
needs: CheckLabels
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
needs: CheckLabels
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
DockerHubPush:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
filter: tree:0
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
StyleCheck:
needs: DockerHubPush
# We need additional `&& ! cancelled()` to have the job being able to cancel
if: ${{ success() || failure() || ( always() && ! cancelled() ) }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Style check
runner_type: style-checker
run_command: |
cd "$REPO_COPY/tests/ci"
python3 style_check.py
secrets:
secret_envs: |
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
DocsCheck:
needs: DockerHubPush
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docs check
runner_type: func-tester-aarch64
additional_envs: |
run_command: |
cd "$REPO_COPY/tests/ci"
python3 docs_check.py
FinishCheck:
needs:
- StyleCheck
- DockerHubPush
- DocsCheck
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
python3 merge_pr.py --check-approved

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

@ -11,16 +11,14 @@ on: # yamllint disable-line rule:truthy
workflow_call:
jobs:
KeeperJepsenRelease:
uses: ./.github/workflows/reusable_test.yml
uses: ./.github/workflows/reusable_simple_job.yml
with:
test_name: Jepsen keeper check
runner_type: style-checker
run_command: |
cd "$REPO_COPY/tests/ci"
python3 jepsen_check.py keeper
# ServerJepsenRelease:
# runs-on: [self-hosted, style-checker]
# uses: ./.github/workflows/reusable_test.yml
# uses: ./.github/workflows/reusable_simple_job.yml
# with:
# test_name: Jepsen server check
# runner_type: style-checker

9
.github/workflows/libfuzzer.yml vendored
View File

@ -8,19 +8,26 @@ on: # yamllint disable-line rule:truthy
# schedule:
# - cron: '0 0 2 31 1' # never for now
workflow_call:
inputs:
data:
description: json ci data
type: string
required: true
jobs:
BuilderFuzzers:
uses: ./.github/workflows/reusable_build.yml
with:
build_name: fuzzers
data: ${{ inputs.data }}
libFuzzerTest:
needs: [BuilderFuzzers]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: libFuzzer tests
runner_type: func-tester
data: ${{ inputs.data }}
additional_envs: |
KILL_TIMEOUT=10800
run_command: |
cd "$REPO_COPY/tests/ci"
python3 libfuzzer_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"

627
.github/workflows/master.yml vendored
View File

File diff suppressed because it is too large Load Diff

77
.github/workflows/nightly.yml vendored
View File

@ -13,67 +13,38 @@ jobs:
Debug:
# The task for having a preserved ENV and event.json for later investigation
uses: ./.github/workflows/debug.yml
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
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@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
RunConfig:
runs-on: [self-hosted, style-checker]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64 --all
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
DockerHubPush:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
- name: Images check
- name: PrepareRunConfig
id: runconfig
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --skip-jobs --rebuild-all-docker --outfile ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
echo "::group::CI run configure results"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
{
echo 'CI_DATA<<EOF'
cat ${{ runner.temp }}/ci_run_data.json
echo 'EOF'
} >> "$GITHUB_OUTPUT"
BuildDockers:
needs: [RunConfig]
uses: ./.github/workflows/reusable_docker.yml
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
data: "${{ needs.RunConfig.outputs.data }}"
set_latest: true
SonarCloud:
runs-on: [self-hosted, builder]
env:

802
.github/workflows/pull_request.yml vendored
View File

File diff suppressed because it is too large Load Diff

434
.github/workflows/release_branches.yml vendored
View File

@ -13,171 +13,190 @@ on: # yamllint disable-line rule:truthy
- '2[1-9].[1-9]'
jobs:
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
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@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
DockerHubPushAmd64:
RunConfig:
runs-on: [self-hosted, style-checker]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Images check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_images_check.py --suffix amd64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}/docker_images_check/changed_images_amd64.json
DockerHubPush:
needs: [DockerHubPushAmd64, DockerHubPushAarch64]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:
name: changed_images_aarch64
path: ${{ runner.temp }}
- name: Download changed amd64 images
uses: actions/download-artifact@v3
with:
name: changed_images_amd64
path: ${{ runner.temp }}
- name: Images check
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64
- name: Upload images files to artifacts
uses: actions/upload-artifact@v3
python3 run_check.py
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
echo "Testing the main ci directory"
python3 -m unittest discover -s . -p 'test_*.py'
for dir in *_lambda/; do
echo "Testing $dir"
python3 -m unittest discover -s "$dir" -p 'test_*.py'
done
- name: PrepareRunConfig
id: runconfig
run: |
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --rebuild-all-binaries --outfile ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
echo "::group::CI run configure results"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
{
echo 'CI_DATA<<EOF'
cat ${{ runner.temp }}/ci_run_data.json
echo 'EOF'
} >> "$GITHUB_OUTPUT"
- name: Re-create GH statuses for skipped jobs if any
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --update-gh-statuses
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
with:
name: changed_images
path: ${{ runner.temp }}/changed_images.json
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check X86
test_name: Compatibility check (amd64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
CompatibilityCheckAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check X86
test_name: Compatibility check (aarch64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
#########################################################################################
#################################### ORDINARY BUILDS ####################################
#########################################################################################
BuilderDebRelease:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_release
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebAarch64:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_aarch64
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebAsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_asan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebUBsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_ubsan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebTsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_tsan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebMsan:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_msan
data: ${{ needs.RunConfig.outputs.data }}
BuilderDebDebug:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: package_debug
data: ${{ needs.RunConfig.outputs.data }}
BuilderBinDarwin:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: binary_darwin
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
BuilderBinDarwinAarch64:
needs: [DockerHubPush]
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: binary_darwin_aarch64
checkout_depth: 0
data: ${{ needs.RunConfig.outputs.data }}
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
needs:
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
clear-repository: true
fetch-depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
filter: tree:0
- name: Check docker clickhouse/clickhouse-server building
run: |
test_name: Docker server and keeper images
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-server --image-path docker/server
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################
##################################### BUILD REPORTER #######################################
############################################################################################
BuilderReport:
if: ${{ success() || failure() }}
needs:
- RunConfig
- BuilderDebRelease
- BuilderDebAarch64
- BuilderDebAsan
- BuilderDebTsan
- BuilderDebUBsan
- BuilderDebMsan
- BuilderDebDebug
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
additional_envs: |
NEEDS_DATA<<NDENV
${{ toJSON(needs) }}
NDENV
run_command: |
python3 build_report_check.py "$CHECK_NAME"
BuilderSpecialReport:
if: ${{ !failure() && !cancelled() }}
needs:
- RunConfig
- BuilderDebRelease
- BuilderDebAarch64
- BuilderDebAsan
@ -186,33 +205,18 @@ jobs:
- BuilderDebMsan
- BuilderDebDebug
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker
additional_envs: |
NEEDS_DATA<<NDENV
${{ toJSON(needs) }}
NDENV
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 build_report_check.py "$CHECK_NAME"
BuilderSpecialReport:
if: ${{ success() || failure() }}
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
additional_envs: |
NEEDS_DATA<<NDENV
${{ toJSON(needs) }}
NDENV
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 build_report_check.py "$CHECK_NAME"
MarkReleaseReady:
if: ${{ !failure() && !cancelled() }}
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
@ -232,282 +236,224 @@ jobs:
#################################### INSTALL PACKAGES ######################################
############################################################################################
InstallPackagesTestRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (amd64)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
InstallPackagesTestAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (arm64)
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
cd "$REPO_COPY/tests/ci"
python3 install_check.py "$CHECK_NAME"
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
FunctionalStatelessTestRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (release)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (aarch64)
runner_type: func-tester-aarch64
additional_envs: |
KILL_TIMEOUT=10800
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (asan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
batches: 4
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestTsan:
needs: [BuilderDebTsan]
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (tsan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
batches: 5
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
FunctionalStatelessTestUBsan:
needs: [BuilderDebUBsan]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (ubsan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
batches: 2
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestMsan:
needs: [BuilderDebMsan]
needs: [RunConfig, BuilderDebMsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (msan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
batches: 6
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestUBsan:
needs: [RunConfig, BuilderDebUBsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (ubsan)
runner_type: func-tester
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestDebug:
needs: [BuilderDebDebug]
needs: [RunConfig, BuilderDebDebug]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (debug)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=10800
batches: 5
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
##############################################################################################
############################ FUNCTIONAl STATEFUL TESTS #######################################
##############################################################################################
FunctionalStatefulTestRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (release)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestAarch64:
needs: [BuilderDebAarch64]
needs: [RunConfig, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (aarch64)
runner_type: func-tester-aarch64
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (asan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestTsan:
needs: [BuilderDebTsan]
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (tsan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestMsan:
needs: [BuilderDebMsan]
needs: [RunConfig, BuilderDebMsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (msan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestUBsan:
needs: [BuilderDebUBsan]
needs: [RunConfig, BuilderDebUBsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (ubsan)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatefulTestDebug:
needs: [BuilderDebDebug]
needs: [RunConfig, BuilderDebDebug]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateful tests (debug)
runner_type: func-tester
additional_envs: |
KILL_TIMEOUT=3600
run_command: |
cd "$REPO_COPY/tests/ci"
python3 functional_test_check.py "$CHECK_NAME" "$KILL_TIMEOUT"
data: ${{ needs.RunConfig.outputs.data }}
##############################################################################################
######################################### STRESS TESTS #######################################
##############################################################################################
StressTestAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (asan)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
StressTestTsan:
needs: [BuilderDebTsan]
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (tsan)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
StressTestMsan:
needs: [BuilderDebMsan]
needs: [RunConfig, BuilderDebMsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (msan)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
StressTestUBsan:
needs: [BuilderDebUBsan]
needs: [RunConfig, BuilderDebUBsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (ubsan)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
StressTestDebug:
needs: [BuilderDebDebug]
needs: [RunConfig, BuilderDebDebug]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (debug)
runner_type: stress-tester
run_command: |
cd "$REPO_COPY/tests/ci"
python3 stress_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
#############################################################################################
############################# INTEGRATION TESTS #############################################
#############################################################################################
IntegrationTestsAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Integration tests (asan)
runner_type: stress-tester
batches: 4
run_command: |
cd "$REPO_COPY/tests/ci"
python3 integration_test_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
IntegrationTestsAnalyzerAsan:
needs: [BuilderDebAsan]
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Integration tests (asan, analyzer)
runner_type: stress-tester
batches: 6
run_command: |
cd "$REPO_COPY/tests/ci"
python3 integration_test_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
IntegrationTestsTsan:
needs: [BuilderDebTsan]
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Integration tests (tsan)
runner_type: stress-tester
batches: 6
run_command: |
cd "$REPO_COPY/tests/ci"
python3 integration_test_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
IntegrationTestsRelease:
needs: [BuilderDebRelease]
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Integration tests (release)
runner_type: stress-tester
batches: 4
run_command: |
cd "$REPO_COPY/tests/ci"
python3 integration_test_check.py "$CHECK_NAME"
data: ${{ needs.RunConfig.outputs.data }}
FinishCheck:
if: ${{ !failure() && !cancelled() }}
needs:
- DockerHubPush
- DockerServerImages
- BuilderReport
- BuilderSpecialReport

31
.github/workflows/reusable_build.yml vendored
View File

@ -22,6 +22,10 @@ name: Build ClickHouse
description: the label of runner to use
default: builder
type: string
data:
description: json ci data
type: string
required: true
additional_envs:
description: additional ENV variables to setup the job
type: string
@ -29,6 +33,7 @@ name: Build ClickHouse
jobs:
Build:
name: Build-${{inputs.build_name}}
if: contains(fromJson(inputs.data).jobs_data.jobs_to_do, inputs.build_name)
env:
GITHUB_JOB_OVERRIDDEN: Build-${{inputs.build_name}}
runs-on: [self-hosted, '${{inputs.runner_type}}']
@ -37,6 +42,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
ref: ${{ fromJson(inputs.data).git_ref }}
submodules: true
fetch-depth: ${{inputs.checkout_depth}}
filter: tree:0
@ -44,6 +50,9 @@ jobs:
run: |
cat >> "$GITHUB_ENV" << 'EOF'
${{inputs.additional_envs}}
DOCKER_TAG<<DOCKER_JSON
${{ toJson(fromJson(inputs.data).docker_data.images) }}
DOCKER_JSON
EOF
python3 "$GITHUB_WORKSPACE"/tests/ci/ci_config.py --build-name "${{inputs.build_name}}" >> "$GITHUB_ENV"
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
@ -60,20 +69,18 @@ jobs:
uses: ./.github/actions/common_setup
with:
job_type: build_check
- name: Download changed images
uses: actions/download-artifact@v3
with:
name: changed_images
path: ${{ env.IMAGES_PATH }}
- name: Pre
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --pre --job-name '${{inputs.build_name}}'
- name: Build
run: |
cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
- name: Upload build URLs to artifacts
if: ${{ success() || failure() }}
uses: actions/upload-artifact@v3
with:
name: ${{ env.BUILD_URLS }}
path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
python3 "$GITHUB_WORKSPACE/tests/ci/build_check.py" "$BUILD_NAME"
- name: Post
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --post --job-name '${{inputs.build_name}}'
- name: Mark as done
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --mark-success --job-name '${{inputs.build_name}}'
- name: Clean
if: always()
uses: ./.github/actions/clean

68
.github/workflows/reusable_docker.yml vendored Normal file
View File

@ -0,0 +1,68 @@
name: Build docker images
'on':
workflow_call:
inputs:
data:
description: json with ci data from todo job
required: true
type: string
set_latest:
description: set latest tag for resulting multiarch manifest
required: false
type: boolean
default: false
jobs:
DockerBuildAarch64:
runs-on: [self-hosted, style-checker-aarch64]
if: |
!failure() && !cancelled() && toJson(fromJson(inputs.data).docker_data.missing_aarch64) != '[]'
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
ref: ${{ fromJson(inputs.data).git_ref }}
- name: Build images
run: |
python3 "${GITHUB_WORKSPACE}/tests/ci/docker_images_check.py" \
--suffix aarch64 \
--image-tags '${{ toJson(fromJson(inputs.data).docker_data.images) }}' \
--missing-images '${{ toJson(fromJson(inputs.data).docker_data.missing_aarch64) }}'
DockerBuildAmd64:
runs-on: [self-hosted, style-checker]
if: |
!failure() && !cancelled() && toJson(fromJson(inputs.data).docker_data.missing_amd64) != '[]'
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
ref: ${{ fromJson(inputs.data).git_ref }}
- name: Build images
run: |
python3 "${GITHUB_WORKSPACE}/tests/ci/docker_images_check.py" \
--suffix amd64 \
--image-tags '${{ toJson(fromJson(inputs.data).docker_data.images) }}' \
--missing-images '${{ toJson(fromJson(inputs.data).docker_data.missing_amd64) }}'
DockerMultiArchManifest:
needs: [DockerBuildAmd64, DockerBuildAarch64]
runs-on: [self-hosted, style-checker]
if: |
!failure() && !cancelled() && toJson(fromJson(inputs.data).docker_data.missing_multi) != '[]'
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
ref: ${{ fromJson(inputs.data).git_ref }}
- name: Build images
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
if [ "${{ inputs.set_latest }}" == "true" ]; then
echo "latest tag will be set for resulting manifests"
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64 \
--image-tags '${{ toJson(fromJson(inputs.data).docker_data.images) }}' \
--missing-images '${{ toJson(fromJson(inputs.data).docker_data.missing_multi) }}' \
--set-latest
else
python3 docker_manifests_merge.py --suffix amd64 --suffix aarch64 \
--image-tags '${{ toJson(fromJson(inputs.data).docker_data.images) }}' \
--missing-images '${{ toJson(fromJson(inputs.data).docker_data.missing_multi) }}'
fi

90
.github/workflows/reusable_simple_job.yml vendored Normal file
View File

@ -0,0 +1,90 @@
### For the pure soul wishes to move it to another place
# https://github.com/orgs/community/discussions/9050
name: Simple job
'on':
workflow_call:
inputs:
test_name:
description: the value of test type from tests/ci/ci_config.py, ends up as $CHECK_NAME ENV
required: true
type: string
runner_type:
description: the label of runner to use
required: true
type: string
run_command:
description: the command to launch the check
default: ""
required: false
type: string
checkout_depth:
description: the value of the git shallow checkout
required: false
type: number
default: 1
submodules:
description: if the submodules should be checked out
required: false
type: boolean
default: false
additional_envs:
description: additional ENV variables to setup the job
type: string
working-directory:
description: sets custom working directory
type: string
default: ""
git_ref:
description: commit to use, merge commit for pr or head
required: false
type: string
default: ${{ github.event.after }} # no merge commit
secrets:
secret_envs:
description: if given, it's passed to the environments
required: false
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
CHECK_NAME: ${{inputs.test_name}}
jobs:
Test:
runs-on: [self-hosted, '${{inputs.runner_type}}']
name: ${{inputs.test_name}}
env:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
ref: ${{ inputs.git_ref }}
submodules: ${{inputs.submodules}}
fetch-depth: ${{inputs.checkout_depth}}
filter: tree:0
- name: Set build envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
CHECK_NAME=${{ inputs.test_name }}
${{inputs.additional_envs}}
${{secrets.secret_envs}}
EOF
- name: Common setup
uses: ./.github/actions/common_setup
with:
job_type: test
- name: Run
run: |
if [ -n '${{ inputs.working-directory }}' ]; then
cd "${{ inputs.working-directory }}"
else
cd "$GITHUB_WORKSPACE/tests/ci"
fi
${{ inputs.run_command }}
- name: Clean
if: always()
uses: ./.github/actions/clean

88
.github/workflows/reusable_test.yml vendored
View File

@ -14,13 +14,10 @@ name: Testing workflow
required: true
type: string
run_command:
description: the command to launch the check. Usually starts with `cd '$REPO_COPY/tests/ci'`
required: true
description: the command to launch the check
default: ""
required: false
type: string
batches:
description: how many batches for the test will be launched
default: 1
type: number
checkout_depth:
description: the value of the git shallow checkout
required: false
@ -34,80 +31,89 @@ name: Testing workflow
additional_envs:
description: additional ENV variables to setup the job
type: string
data:
description: ci data
type: string
required: true
working-directory:
description: sets custom working directory
type: string
default: ""
secrets:
secret_envs:
description: if given, it's passed to the environments
required: false
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
CHECK_NAME: ${{inputs.test_name}}
jobs:
PrepareStrategy:
# batches < 1 is misconfiguration,
# and we need this step only for batches > 1
if: ${{ inputs.batches > 1 }}
runs-on: [self-hosted, style-checker-aarch64]
outputs:
batches: ${{steps.batches.outputs.batches}}
steps:
- name: Calculate batches
id: batches
run: |
batches_output=$(python3 -c 'import json; print(json.dumps(list(range(${{inputs.batches}}))))')
echo "batches=${batches_output}" >> "$GITHUB_OUTPUT"
Test:
# If PrepareStrategy is skipped for batches == 1,
# we still need to launch the test.
# `! failure()` is mandatory here to launch on skipped Job
# `&& !cancelled()` to allow the be cancelable
if: ${{ ( !failure() && !cancelled() ) && inputs.batches > 0 }}
# Do not add `-0` to the end, if there's only one batch
name: ${{inputs.test_name}}${{ inputs.batches > 1 && format('-{0}',matrix.batch) || '' }}
env:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}${{ inputs.batches > 1 && format('-{0}',matrix.batch) || '' }}
runs-on: [self-hosted, '${{inputs.runner_type}}']
needs: [PrepareStrategy]
if: ${{ !failure() && !cancelled() && contains(fromJson(inputs.data).jobs_data.jobs_to_do, inputs.test_name) }}
name: ${{inputs.test_name}}${{ fromJson(inputs.data).jobs_data.jobs_params[inputs.test_name].num_batches > 1 && format('-{0}',matrix.batch) || '' }}
env:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}${{ fromJson(inputs.data).jobs_data.jobs_params[inputs.test_name].num_batches > 1 && format('-{0}',matrix.batch) || '' }}
strategy:
fail-fast: false # we always wait for entire matrix
matrix:
# if PrepareStrategy does not have batches, we use 0
batch: ${{ needs.PrepareStrategy.outputs.batches
&& fromJson(needs.PrepareStrategy.outputs.batches)
|| fromJson('[0]')}}
batch: ${{ fromJson(inputs.data).jobs_data.jobs_params[inputs.test_name].batches }}
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
ref: ${{ fromJson(inputs.data).git_ref }}
submodules: ${{inputs.submodules}}
fetch-depth: ${{inputs.checkout_depth}}
filter: tree:0
- name: Set build envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'
CHECK_NAME=${{ inputs.test_name }}
${{inputs.additional_envs}}
${{secrets.secret_envs}}
DOCKER_TAG<<DOCKER_JSON
${{ toJson(fromJson(inputs.data).docker_data.images) }}
DOCKER_JSON
EOF
- name: Common setup
uses: ./.github/actions/common_setup
with:
job_type: test
- name: Download json reports
uses: actions/download-artifact@v3
with:
path: ${{ env.REPORTS_PATH }}
- name: Setup batch
if: ${{ inputs.batches > 1}}
if: ${{ fromJson(inputs.data).jobs_data.jobs_params[inputs.test_name].num_batches > 1 }}
run: |
cat >> "$GITHUB_ENV" << 'EOF'
RUN_BY_HASH_NUM=${{matrix.batch}}
RUN_BY_HASH_TOTAL=${{inputs.batches}}
RUN_BY_HASH_TOTAL=${{ fromJson(inputs.data).jobs_data.jobs_params[inputs.test_name].num_batches }}
EOF
- name: Run test
run: ${{inputs.run_command}}
- name: Pre run
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --pre --job-name '${{inputs.test_name}}'
- name: Run
run: |
if [ -n "${{ inputs.working-directory }}" ]; then
cd "${{ inputs.working-directory }}"
else
cd "$GITHUB_WORKSPACE/tests/ci"
fi
if [ -n "$(echo '${{ inputs.run_command }}' | tr -d '\n')" ]; then
echo "Running command from workflow input"
${{ inputs.run_command }}
else
echo "Running command from job config"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --run --job-name '${{inputs.test_name}}'
fi
- name: Post run
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --post --job-name '${{inputs.test_name}}'
- name: Mark as done
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --mark-success --job-name '${{inputs.test_name}}' --batch ${{matrix.batch}}
- name: Clean
if: always()
uses: ./.github/actions/clean

3
.gitmodules vendored
View File

@ -357,3 +357,6 @@
[submodule "contrib/pocketfft"]
path = contrib/pocketfft
url = https://github.com/mreineck/pocketfft.git
[submodule "contrib/sqids-cpp"]
path = contrib/sqids-cpp
url = https://github.com/sqids/sqids-cpp.git

237
CHANGELOG.md
View File

@ -1,4 +1,5 @@
### Table of Contents
**[ClickHouse release v23.11, 2023-12-06](#2311)**<br/>
**[ClickHouse release v23.10, 2023-11-02](#2310)**<br/>
**[ClickHouse release v23.9, 2023-09-28](#239)**<br/>
**[ClickHouse release v23.8 LTS, 2023-08-31](#238)**<br/>
@ -13,7 +14,217 @@
# 2023 Changelog
### ClickHouse release 23.10, 2023-11-02
### <a id="2311"></a> ClickHouse release 23.11, 2023-12-06
#### Backward Incompatible Change
* The default ClickHouse server configuration file has enabled `access_management` (user manipulation by SQL queries) and `named_collection_control` (manipulation of named collection by SQL queries) for the `default` user by default. This closes [#56482](https://github.com/ClickHouse/ClickHouse/issues/56482). [#56619](https://github.com/ClickHouse/ClickHouse/pull/56619) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Multiple improvements for `RESPECT NULLS`/`IGNORE NULLS` for window functions. If you use them as aggregate functions and store the states of aggregate functions with these modifiers, they might become incompatible. [#57189](https://github.com/ClickHouse/ClickHouse/pull/57189) ([Raúl Marín](https://github.com/Algunenano)).
* Remove optimization `optimize_move_functions_out_of_any`. [#57190](https://github.com/ClickHouse/ClickHouse/pull/57190) ([Raúl Marín](https://github.com/Algunenano)).
* Formatters `%l`/`%k`/`%c` in function `parseDateTime` are now able to parse hours/months without leading zeros, e.g. `select parseDateTime('2023-11-26 8:14', '%F %k:%i')` now works. Set `parsedatetime_parse_without_leading_zeros = 0` to restore the previous behavior which required two digits. Function `formatDateTime` is now also able to print hours/months without leading zeros. This is controlled by setting `formatdatetime_format_without_leading_zeros` but off by default to not break existing use cases. [#55872](https://github.com/ClickHouse/ClickHouse/pull/55872) ([Azat Khuzhin](https://github.com/azat)).
* You can no longer use the aggregate function `avgWeighted` with arguments of type `Decimal`. Workaround: convert arguments to `Float64`. This closes [#43928](https://github.com/ClickHouse/ClickHouse/issues/43928). This closes [#31768](https://github.com/ClickHouse/ClickHouse/issues/31768). This closes [#56435](https://github.com/ClickHouse/ClickHouse/issues/56435). If you have used this function inside materialized views or projections with `Decimal` arguments, contact support@clickhouse.com. Fixed error in aggregate function `sumMap` and made it slower around 1.5..2 times. It does not matter because the function is garbage anyway. This closes [#54955](https://github.com/ClickHouse/ClickHouse/issues/54955). This closes [#53134](https://github.com/ClickHouse/ClickHouse/issues/53134). This closes [#55148](https://github.com/ClickHouse/ClickHouse/issues/55148). Fix a bug in function `groupArraySample` - it used the same random seed in case more than one aggregate state is generated in a query. [#56350](https://github.com/ClickHouse/ClickHouse/pull/56350) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### New Feature
* Added server setting `async_load_databases` for asynchronous loading of databases and tables. Speeds up the server start time. Applies to databases with `Ordinary`, `Atomic` and `Replicated` engines. Their tables load metadata asynchronously. Query to a table increases the priority of the load job and waits for it to be done. Added a new table `system.asynchronous_loader` for introspection. [#49351](https://github.com/ClickHouse/ClickHouse/pull/49351) ([Sergei Trifonov](https://github.com/serxa)).
* Add system table `blob_storage_log`. It allows auditing all the data written to S3 and other object storages. [#52918](https://github.com/ClickHouse/ClickHouse/pull/52918) ([vdimir](https://github.com/vdimir)).
* Use statistics to order prewhere conditions better. [#53240](https://github.com/ClickHouse/ClickHouse/pull/53240) ([Han Fei](https://github.com/hanfei1991)).
* Added support for compression in the Keeper's protocol. It can be enabled on the ClickHouse side by using this flag `use_compression` inside `zookeeper` section. Keep in mind that only ClickHouse Keeper supports compression, while Apache ZooKeeper does not. Resolves [#49507](https://github.com/ClickHouse/ClickHouse/issues/49507). [#54957](https://github.com/ClickHouse/ClickHouse/pull/54957) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Introduce the feature `storage_metadata_write_full_object_key`. If it is set as `true` then metadata files are written with the new format. With that format ClickHouse stores full remote object key in the metadata file which allows better flexibility and optimization. [#55566](https://github.com/ClickHouse/ClickHouse/pull/55566) ([Sema Checherinda](https://github.com/CheSema)).
* Add new settings and syntax to protect named collections' fields from being overridden. This is meant to prevent a malicious user from obtaining unauthorized access to secrets. [#55782](https://github.com/ClickHouse/ClickHouse/pull/55782) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Add `hostname` column to all system log tables - it is useful if you make the system tables replicated, shared, or distributed. [#55894](https://github.com/ClickHouse/ClickHouse/pull/55894) ([Bharat Nallan](https://github.com/bharatnc)).
* Add `CHECK ALL TABLES` query. [#56022](https://github.com/ClickHouse/ClickHouse/pull/56022) ([vdimir](https://github.com/vdimir)).
* Added function `fromDaysSinceYearZero` which is similar to MySQL's `FROM_DAYS`. E.g. `SELECT fromDaysSinceYearZero(739136)` returns `2023-09-08`. [#56088](https://github.com/ClickHouse/ClickHouse/pull/56088) ([Joanna Hulboj](https://github.com/jh0x)).
* Add an external Python tool to view backups and to extract information from them without using ClickHouse. [#56268](https://github.com/ClickHouse/ClickHouse/pull/56268) ([Vitaly Baranov](https://github.com/vitlibar)).
* Implement a new setting called `preferred_optimize_projection_name`. If it is set to a non-empty string, the specified projection would be used if possible instead of choosing from all the candidates. [#56309](https://github.com/ClickHouse/ClickHouse/pull/56309) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Add 4-letter command for yielding/resigning leadership (https://github.com/ClickHouse/ClickHouse/issues/56352). [#56354](https://github.com/ClickHouse/ClickHouse/pull/56354) ([Pradeep Chhetri](https://github.com/chhetripradeep)). [#56620](https://github.com/ClickHouse/ClickHouse/pull/56620) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Added a new SQL function, `arrayRandomSample(arr, k)` which returns a sample of k elements from the input array. Similar functionality could previously be achieved only with less convenient syntax, e.g. `SELECT arrayReduce('groupArraySample(3)', range(10))`. [#56416](https://github.com/ClickHouse/ClickHouse/pull/56416) ([Robert Schulze](https://github.com/rschu1ze)).
* Added support for `Float16` type data to use in `.npy` files. Closes [#56344](https://github.com/ClickHouse/ClickHouse/issues/56344). [#56424](https://github.com/ClickHouse/ClickHouse/pull/56424) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Added a system view `information_schema.statistics` for better compatibility with Tableau Online. [#56425](https://github.com/ClickHouse/ClickHouse/pull/56425) ([Serge Klochkov](https://github.com/slvrtrn)).
* Add `system.symbols` table useful for introspection of the binary. [#56548](https://github.com/ClickHouse/ClickHouse/pull/56548) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Configurable dashboards. Queries for charts are now loaded using a query, which by default uses a new `system.dashboards` table. [#56771](https://github.com/ClickHouse/ClickHouse/pull/56771) ([Sergei Trifonov](https://github.com/serxa)).
* Introduce `fileCluster` table function - it is useful if you mount a shared filesystem (NFS and similar) into the `user_files` directory. [#56868](https://github.com/ClickHouse/ClickHouse/pull/56868) ([Andrey Zvonov](https://github.com/zvonand)).
* Add `_size` virtual column with file size in bytes to `s3/file/hdfs/url/azureBlobStorage` engines. [#57126](https://github.com/ClickHouse/ClickHouse/pull/57126) ([Kruglov Pavel](https://github.com/Avogar)).
* Expose the number of errors for each error code occurred on a server since last restart from the Prometheus endpoint. [#57209](https://github.com/ClickHouse/ClickHouse/pull/57209) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* ClickHouse keeper reports its running availability zone at `/keeper/availability-zone` path. This can be configured via `<availability_zone><value>us-west-1a</value></availability_zone>`. [#56715](https://github.com/ClickHouse/ClickHouse/pull/56715) ([Jianfei Hu](https://github.com/incfly)).
* Make ALTER materialized_view MODIFY QUERY non experimental and deprecate `allow_experimental_alter_materialized_view_structure` setting. Fixes [#15206](https://github.com/ClickHouse/ClickHouse/issues/15206). [#57311](https://github.com/ClickHouse/ClickHouse/pull/57311) ([alesapin](https://github.com/alesapin)).
* Setting `join_algorithm` respects specified order [#51745](https://github.com/ClickHouse/ClickHouse/pull/51745) ([vdimir](https://github.com/vdimir)).
* Add support for the [well-known Protobuf types](https://protobuf.dev/reference/protobuf/google.protobuf/) in the Protobuf format. [#56741](https://github.com/ClickHouse/ClickHouse/pull/56741) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
#### Performance Improvement
* Adaptive timeouts for interacting with S3. The first attempt is made with low send and receive timeouts. [#56314](https://github.com/ClickHouse/ClickHouse/pull/56314) ([Sema Checherinda](https://github.com/CheSema)).
* Increase the default value of `max_concurrent_queries` from 100 to 1000. This makes sense when there is a large number of connecting clients, which are slowly sending or receiving data, so the server is not limited by CPU, or when the number of CPU cores is larger than 100. Also, enable the concurrency control by default, and set the desired number of query processing threads in total as twice the number of CPU cores. It improves performance in scenarios with a very large number of concurrent queries. [#46927](https://github.com/ClickHouse/ClickHouse/pull/46927) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Support parallel evaluation of window functions. Fixes [#34688](https://github.com/ClickHouse/ClickHouse/issues/34688). [#39631](https://github.com/ClickHouse/ClickHouse/pull/39631) ([Dmitry Novik](https://github.com/novikd)).
* `Numbers` table engine (of the `system.numbers` table) now analyzes the condition to generate the needed subset of data, like table's index. [#50909](https://github.com/ClickHouse/ClickHouse/pull/50909) ([JackyWoo](https://github.com/JackyWoo)).
* Improved the performance of filtering by `IN (...)` condition for `Merge` table engine. [#54905](https://github.com/ClickHouse/ClickHouse/pull/54905) ([Nikita Taranov](https://github.com/nickitat)).
* An improvement which takes place when the filesystem cache is full and there are big reads. [#55158](https://github.com/ClickHouse/ClickHouse/pull/55158) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add ability to disable checksums for S3 to avoid excessive pass over the file (this is controlled by the setting `s3_disable_checksum`). [#55559](https://github.com/ClickHouse/ClickHouse/pull/55559) ([Azat Khuzhin](https://github.com/azat)).
* Now we read synchronously from remote tables when data is in page cache (like we do for local tables). It is faster, it doesn't require synchronisation inside the thread pool, and doesn't hesitate to do `seek`-s on local FS, and reduces CPU wait. [#55841](https://github.com/ClickHouse/ClickHouse/pull/55841) ([Nikita Taranov](https://github.com/nickitat)).
* Optimization for getting value from `map`, `arrayElement`. It will bring about 30% speedup. - reduce the reserved memory - reduce the `resize` call. [#55957](https://github.com/ClickHouse/ClickHouse/pull/55957) ([lgbo](https://github.com/lgbo-ustc)).
* Optimization of multi-stage filtering with AVX-512. The performance experiments of the OnTime dataset on the ICX device (Intel Xeon Platinum 8380 CPU, 80 cores, 160 threads) show that this change could bring the improvements of 7.4%, 5.9%, 4.7%, 3.0%, and 4.6% to the QPS of the query Q2, Q3, Q4, Q5 and Q6 respectively while having no impact on others. [#56079](https://github.com/ClickHouse/ClickHouse/pull/56079) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* Limit the number of threads busy inside the query profiler. If there are more - they will skip profiling. [#56105](https://github.com/ClickHouse/ClickHouse/pull/56105) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Decrease the amount of virtual function calls in window functions. [#56120](https://github.com/ClickHouse/ClickHouse/pull/56120) ([Maksim Kita](https://github.com/kitaisreal)).
* Allow recursive Tuple field pruning in ORC data format to speed up scaning. [#56122](https://github.com/ClickHouse/ClickHouse/pull/56122) ([李扬](https://github.com/taiyang-li)).
* Trivial count optimization for `Npy` data format: queries like `select count() from 'data.npy'` will work much more fast because of caching the results. [#56304](https://github.com/ClickHouse/ClickHouse/pull/56304) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Queries with aggregation and a large number of streams will use less amount of memory during the plan's construction. [#57074](https://github.com/ClickHouse/ClickHouse/pull/57074) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve performance of executing queries for use cases with many users and highly concurrent queries (>2000 QPS) by optimizing the access to ProcessList. [#57106](https://github.com/ClickHouse/ClickHouse/pull/57106) ([Andrej Hoos](https://github.com/adikus)).
* Trivial improvement on array join, reuse some intermediate results. [#57183](https://github.com/ClickHouse/ClickHouse/pull/57183) ([李扬](https://github.com/taiyang-li)).
* There are cases when stack unwinding was slow. Not anymore. [#57221](https://github.com/ClickHouse/ClickHouse/pull/57221) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Now we use default read pool for reading from external storage when `max_streams = 1`. It is beneficial when read prefetches are enabled. [#57334](https://github.com/ClickHouse/ClickHouse/pull/57334) ([Nikita Taranov](https://github.com/nickitat)).
* Keeper improvement: improve memory-usage during startup by delaying log preprocessing. [#55660](https://github.com/ClickHouse/ClickHouse/pull/55660) ([Antonio Andelic](https://github.com/antonio2368)).
* Improved performance of glob matching for `File` and `HDFS` storages. [#56141](https://github.com/ClickHouse/ClickHouse/pull/56141) ([Andrey Zvonov](https://github.com/zvonand)).
* Posting lists in experimental full text indexes are now compressed which reduces their size by 10-30%. [#56226](https://github.com/ClickHouse/ClickHouse/pull/56226) ([Harry Lee](https://github.com/HarryLeeIBM)).
* Parallelise `BackupEntriesCollector` in backups. [#56312](https://github.com/ClickHouse/ClickHouse/pull/56312) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Improvement
* Add a new `MergeTree` setting `add_implicit_sign_column_constraint_for_collapsing_engine` (disabled by default). When enabled, it adds an implicit CHECK constraint for `CollapsingMergeTree` tables that restricts the value of the `Sign` column to be only -1 or 1. [#56701](https://github.com/ClickHouse/ClickHouse/issues/56701). [#56986](https://github.com/ClickHouse/ClickHouse/pull/56986) ([Kevin Mingtarja](https://github.com/kevinmingtarja)).
* Enable adding new disk to storage configuration without restart. [#56367](https://github.com/ClickHouse/ClickHouse/pull/56367) ([Duc Canh Le](https://github.com/canhld94)).
* Support creating and materializing index in the same alter query, also support "modify TTL" and "materialize TTL" in the same query. Closes [#55651](https://github.com/ClickHouse/ClickHouse/issues/55651). [#56331](https://github.com/ClickHouse/ClickHouse/pull/56331) ([flynn](https://github.com/ucasfl)).
* Add a new table function named `fuzzJSON` with rows containing perturbed versions of the source JSON string with random variations. [#56490](https://github.com/ClickHouse/ClickHouse/pull/56490) ([Julia Kartseva](https://github.com/jkartseva)).
* Engine `Merge` filters the records according to the row policies of the underlying tables, so you don't have to create another row policy on a `Merge` table. [#50209](https://github.com/ClickHouse/ClickHouse/pull/50209) ([Ilya Golshtein](https://github.com/ilejn)).
* Add a setting `max_execution_time_leaf` to limit the execution time on shard for distributed query, and `timeout_overflow_mode_leaf` to control the behaviour if timeout happens. [#51823](https://github.com/ClickHouse/ClickHouse/pull/51823) ([Duc Canh Le](https://github.com/canhld94)).
* Add ClickHouse setting to disable tunneling for HTTPS requests over HTTP proxy. [#55033](https://github.com/ClickHouse/ClickHouse/pull/55033) ([Arthur Passos](https://github.com/arthurpassos)).
* Set `background_fetches_pool_size` to 16, background_schedule_pool_size to 512 that is better for production usage with frequent small insertions. [#54327](https://github.com/ClickHouse/ClickHouse/pull/54327) ([Denny Crane](https://github.com/den-crane)).
* While read data from a csv format file, and at end of line is `\r` , which not followed by `\n`, then we will enconter the exception as follows `Cannot parse CSV format: found \r (CR) not followed by \n (LF). Line must end by \n (LF) or \r\n (CR LF) or \n\r.` In clickhouse, the csv end of line must be `\n` or `\r\n` or `\n\r`, so the `\r` must be followed by `\n`, but in some suitation, the csv input data is abnormal, like above, `\r` is at end of line. [#54340](https://github.com/ClickHouse/ClickHouse/pull/54340) ([KevinyhZou](https://github.com/KevinyhZou)).
* Update Arrow library to release-13.0.0 that supports new encodings. Closes [#44505](https://github.com/ClickHouse/ClickHouse/issues/44505). [#54800](https://github.com/ClickHouse/ClickHouse/pull/54800) ([Kruglov Pavel](https://github.com/Avogar)).
* Improve performance of ON CLUSTER queries by removing heavy system calls to get all network interfaces when looking for local ip address in the DDL entry hosts list. [#54909](https://github.com/ClickHouse/ClickHouse/pull/54909) ([Duc Canh Le](https://github.com/canhld94)).
* Fixed accounting of memory allocated before attaching a thread to a query or a user. [#56089](https://github.com/ClickHouse/ClickHouse/pull/56089) ([Nikita Taranov](https://github.com/nickitat)).
* Add support for `LARGE_LIST` in Apache Arrow formats. [#56118](https://github.com/ClickHouse/ClickHouse/pull/56118) ([edef](https://github.com/edef1c)).
* Allow manual compaction of `EmbeddedRocksDB` via `OPTIMIZE` query. [#56225](https://github.com/ClickHouse/ClickHouse/pull/56225) ([Azat Khuzhin](https://github.com/azat)).
* Add ability to specify BlockBasedTableOptions for `EmbeddedRocksDB` tables. [#56264](https://github.com/ClickHouse/ClickHouse/pull/56264) ([Azat Khuzhin](https://github.com/azat)).
* `SHOW COLUMNS` now displays MySQL's equivalent data type name when the connection was made through the MySQL protocol. Previously, this was the case when setting `use_mysql_types_in_show_columns = 1`. The setting is retained but made obsolete. [#56277](https://github.com/ClickHouse/ClickHouse/pull/56277) ([Robert Schulze](https://github.com/rschu1ze)).
* Fixed possible `The local set of parts of table doesn't look like the set of parts in ZooKeeper` error if server was restarted just after `TRUNCATE` or `DROP PARTITION`. [#56282](https://github.com/ClickHouse/ClickHouse/pull/56282) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fixed handling of non-const query strings in functions `formatQuery`/ `formatQuerySingleLine`. Also added `OrNull` variants of both functions that return a NULL when a query cannot be parsed instead of throwing an exception. [#56327](https://github.com/ClickHouse/ClickHouse/pull/56327) ([Robert Schulze](https://github.com/rschu1ze)).
* Allow backup of materialized view with dropped inner table instead of failing the backup. [#56387](https://github.com/ClickHouse/ClickHouse/pull/56387) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Queries to `system.replicas` initiate requests to ZooKeeper when certain columns are queried. When there are thousands of tables these requests might produce a considerable load on ZooKeeper. If there are multiple simultaneous queries to `system.replicas` they do same requests multiple times. The change is to "deduplicate" requests from concurrent queries. [#56420](https://github.com/ClickHouse/ClickHouse/pull/56420) ([Alexander Gololobov](https://github.com/davenger)).
* Fix translation to MySQL compatible query for querying external databases. [#56456](https://github.com/ClickHouse/ClickHouse/pull/56456) ([flynn](https://github.com/ucasfl)).
* Add support for backing up and restoring tables using `KeeperMap` engine. [#56460](https://github.com/ClickHouse/ClickHouse/pull/56460) ([Antonio Andelic](https://github.com/antonio2368)).
* 404 response for CompleteMultipartUpload has to be rechecked. Operation could be done on server even if client got timeout or other network errors. The next retry of CompleteMultipartUpload receives 404 response. If the object key exists that operation is considered as successful. [#56475](https://github.com/ClickHouse/ClickHouse/pull/56475) ([Sema Checherinda](https://github.com/CheSema)).
* Enable the HTTP OPTIONS method by default - it simplifies requesting ClickHouse from a web browser. [#56483](https://github.com/ClickHouse/ClickHouse/pull/56483) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The value for `dns_max_consecutive_failures` was changed by mistake in [#46550](https://github.com/ClickHouse/ClickHouse/issues/46550) - this is reverted and adjusted to a better value. Also, increased the HTTP keep-alive timeout to a reasonable value from production. [#56485](https://github.com/ClickHouse/ClickHouse/pull/56485) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Load base backups lazily (a base backup won't be loaded until it's needed). Also add some log message and profile events for backups. [#56516](https://github.com/ClickHouse/ClickHouse/pull/56516) ([Vitaly Baranov](https://github.com/vitlibar)).
* Setting `query_cache_store_results_of_queries_with_nondeterministic_functions` (with values `false` or `true`) was marked obsolete. It was replaced by setting `query_cache_nondeterministic_function_handling`, a three-valued enum that controls how the query cache handles queries with non-deterministic functions: a) throw an exception (default behavior), b) save the non-deterministic query result regardless, or c) ignore, i.e. don't throw an exception and don't cache the result. [#56519](https://github.com/ClickHouse/ClickHouse/pull/56519) ([Robert Schulze](https://github.com/rschu1ze)).
* Rewrite equality with `is null` check in JOIN ON section. Experimental *Analyzer only*. [#56538](https://github.com/ClickHouse/ClickHouse/pull/56538) ([vdimir](https://github.com/vdimir)).
* Function`concat` now supports arbitrary argument types (instead of only String and FixedString arguments). This makes it behave more similar to MySQL `concat` implementation. For example, `SELECT concat('ab', 42)` now returns `ab42`. [#56540](https://github.com/ClickHouse/ClickHouse/pull/56540) ([Serge Klochkov](https://github.com/slvrtrn)).
* Allow getting cache configuration from 'named_collection' section in config or from SQL created named collections. [#56541](https://github.com/ClickHouse/ClickHouse/pull/56541) ([Kseniia Sumarokova](https://github.com/kssenii)).
* PostgreSQL database engine: Make the removal of outdated tables less aggressive with unsuccessful postgres connection. [#56609](https://github.com/ClickHouse/ClickHouse/pull/56609) ([jsc0218](https://github.com/jsc0218)).
* It took too much time to connnect to PG when URL is not right, so the relevant query stucks there and get cancelled. [#56648](https://github.com/ClickHouse/ClickHouse/pull/56648) ([jsc0218](https://github.com/jsc0218)).
* Keeper improvement: disable compressed logs by default in Keeper. [#56763](https://github.com/ClickHouse/ClickHouse/pull/56763) ([Antonio Andelic](https://github.com/antonio2368)).
* Add config setting `wait_dictionaries_load_at_startup`. [#56782](https://github.com/ClickHouse/ClickHouse/pull/56782) ([Vitaly Baranov](https://github.com/vitlibar)).
* There was a potential vulnerability in previous ClickHouse versions: if a user has connected and unsuccessfully tried to authenticate with the "interserver secret" method, the server didn't terminate the connection immediately but continued to receive and ignore the leftover packets from the client. While these packets are ignored, they are still parsed, and if they use a compression method with another known vulnerability, it will lead to exploitation of it without authentication. This issue was found with [ClickHouse Bug Bounty Program](https://github.com/ClickHouse/ClickHouse/issues/38986) by https://twitter.com/malacupa. [#56794](https://github.com/ClickHouse/ClickHouse/pull/56794) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fetching a part waits when that part is fully committed on remote replica. It is better not send part in PreActive state. In case of zero copy this is mandatory restriction. [#56808](https://github.com/ClickHouse/ClickHouse/pull/56808) ([Sema Checherinda](https://github.com/CheSema)).
* Fix possible postgresql logical replication conversion error when using experimental `MaterializedPostgreSQL`. [#53721](https://github.com/ClickHouse/ClickHouse/pull/53721) ([takakawa](https://github.com/takakawa)).
* Implement user-level setting `alter_move_to_space_execute_async` which allow to execute queries `ALTER TABLE ... MOVE PARTITION|PART TO DISK|VOLUME` asynchronously. The size of pool for background executions is controlled by `background_move_pool_size`. Default behavior is synchronous execution. Fixes [#47643](https://github.com/ClickHouse/ClickHouse/issues/47643). [#56809](https://github.com/ClickHouse/ClickHouse/pull/56809) ([alesapin](https://github.com/alesapin)).
* Able to filter by engine when scanning system.tables, avoid unnecessary (potentially time-consuming) connection. [#56813](https://github.com/ClickHouse/ClickHouse/pull/56813) ([jsc0218](https://github.com/jsc0218)).
* Show `total_bytes` and `total_rows` in system tables for RocksDB storage. [#56816](https://github.com/ClickHouse/ClickHouse/pull/56816) ([Aleksandr Musorin](https://github.com/AVMusorin)).
* Allow basic commands in ALTER for TEMPORARY tables. [#56892](https://github.com/ClickHouse/ClickHouse/pull/56892) ([Sergey](https://github.com/icuken)).
* LZ4 compression. Buffer compressed block in a rare case when out buffer capacity is not enough for writing compressed block directly to out's buffer. [#56938](https://github.com/ClickHouse/ClickHouse/pull/56938) ([Sema Checherinda](https://github.com/CheSema)).
* Add metrics for the number of queued jobs, which is useful for the IO thread pool. [#56958](https://github.com/ClickHouse/ClickHouse/pull/56958) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add a setting for PostgreSQL table engine setting in the config file. Added a check for the setting Added documentation around the additional setting. [#56959](https://github.com/ClickHouse/ClickHouse/pull/56959) ([Peignon Melvyn](https://github.com/melvynator)).
* Function `concat` can now be called with a single argument, e.g., `SELECT concat('abc')`. This makes its behavior more consistent with MySQL's concat implementation. [#57000](https://github.com/ClickHouse/ClickHouse/pull/57000) ([Serge Klochkov](https://github.com/slvrtrn)).
* Signs all `x-amz-*` headers as required by AWS S3 docs. [#57001](https://github.com/ClickHouse/ClickHouse/pull/57001) ([Arthur Passos](https://github.com/arthurpassos)).
* Function `fromDaysSinceYearZero` (alias: `FROM_DAYS`) can now be used with unsigned and signed integer types (previously, it had to be an unsigned integer). This improve compatibility with 3rd party tools such as Tableau Online. [#57002](https://github.com/ClickHouse/ClickHouse/pull/57002) ([Serge Klochkov](https://github.com/slvrtrn)).
* Add `system.s3queue_log` to default config. [#57036](https://github.com/ClickHouse/ClickHouse/pull/57036) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Change the default for `wait_dictionaries_load_at_startup` to true, and use this setting only if `dictionaries_lazy_load` is false. [#57133](https://github.com/ClickHouse/ClickHouse/pull/57133) ([Vitaly Baranov](https://github.com/vitlibar)).
* Check dictionary source type on creation even if `dictionaries_lazy_load` is enabled. [#57134](https://github.com/ClickHouse/ClickHouse/pull/57134) ([Vitaly Baranov](https://github.com/vitlibar)).
* Plan-level optimizations can now be enabled/disabled individually. Previously, it was only possible to disable them all. The setting which previously did that (`query_plan_enable_optimizations`) is retained and can still be used to disable all optimizations. [#57152](https://github.com/ClickHouse/ClickHouse/pull/57152) ([Robert Schulze](https://github.com/rschu1ze)).
* The server's exit code will correspond to the exception code. For example, if the server cannot start due to memory limit, it will exit with the code 241 = MEMORY_LIMIT_EXCEEDED. In previous versions, the exit code for exceptions was always 70 = Poco::Util::ExitCode::EXIT_SOFTWARE. [#57153](https://github.com/ClickHouse/ClickHouse/pull/57153) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Do not demangle and symbolize stack frames from `functional` C++ header. [#57201](https://github.com/ClickHouse/ClickHouse/pull/57201) ([Mike Kot](https://github.com/myrrc)).
* HTTP server page `/dashboard` now supports charts with multiple lines. [#57236](https://github.com/ClickHouse/ClickHouse/pull/57236) ([Sergei Trifonov](https://github.com/serxa)).
* The `max_memory_usage_in_client` command line option supports a string value with a suffix (K, M, G, etc). Closes [#56879](https://github.com/ClickHouse/ClickHouse/issues/56879). [#57273](https://github.com/ClickHouse/ClickHouse/pull/57273) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Bumped Intel QPL (used by codec `DEFLATE_QPL`) from v1.2.0 to v1.3.1 . Also fixed a bug in case of BOF (Block On Fault) = 0, changed to handle page faults by falling back to SW path. [#57291](https://github.com/ClickHouse/ClickHouse/pull/57291) ([jasperzhu](https://github.com/jinjunzh)).
* Increase default `replicated_deduplication_window` of MergeTree settings from 100 to 1k. [#57335](https://github.com/ClickHouse/ClickHouse/pull/57335) ([sichenzhao](https://github.com/sichenzhao)).
* Stop using `INCONSISTENT_METADATA_FOR_BACKUP` that much. If possible prefer to continue scanning instead of stopping and starting the scanning for backup from the beginning. [#57385](https://github.com/ClickHouse/ClickHouse/pull/57385) ([Vitaly Baranov](https://github.com/vitlibar)).
#### Build/Testing/Packaging Improvement
* Add SQLLogic test. [#56078](https://github.com/ClickHouse/ClickHouse/pull/56078) ([Han Fei](https://github.com/hanfei1991)).
* Make `clickhouse-local` and `clickhouse-client` available under short names (`ch`, `chl`, `chc`) for usability. [#56634](https://github.com/ClickHouse/ClickHouse/pull/56634) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Optimized build size further by removing unused code from external libraries. [#56786](https://github.com/ClickHouse/ClickHouse/pull/56786) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add automatic check that there are no large translation units. [#56559](https://github.com/ClickHouse/ClickHouse/pull/56559) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Lower the size of the single-binary distribution. This closes [#55181](https://github.com/ClickHouse/ClickHouse/issues/55181). [#56617](https://github.com/ClickHouse/ClickHouse/pull/56617) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Information about the sizes of every translation unit and binary file after each build will be sent to the CI database in ClickHouse Cloud. This closes [#56107](https://github.com/ClickHouse/ClickHouse/issues/56107). [#56636](https://github.com/ClickHouse/ClickHouse/pull/56636) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Certain files of "Apache Arrow" library (which we use only for non-essential things like parsing the arrow format) were rebuilt all the time regardless of the build cache. This is fixed. [#56657](https://github.com/ClickHouse/ClickHouse/pull/56657) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Avoid recompiling translation units depending on the autogenerated source file about version. [#56660](https://github.com/ClickHouse/ClickHouse/pull/56660) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Tracing data of the linker invocations will be sent to the CI database in ClickHouse Cloud. [#56725](https://github.com/ClickHouse/ClickHouse/pull/56725) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Use DWARF 5 debug symbols for the clickhouse binary (was DWARF 4 previously). [#56770](https://github.com/ClickHouse/ClickHouse/pull/56770) ([Michael Kolupaev](https://github.com/al13n321)).
* Add a new build option `SANITIZE_COVERAGE`. If it is enabled, the code is instrumented to track the coverage. The collected information is available inside ClickHouse with: (1) a new function `coverage` that returns an array of unique addresses in the code found after the previous coverage reset; (2) `SYSTEM RESET COVERAGE` query that resets the accumulated data. This allows us to compare the coverage of different tests, including differential code coverage. Continuation of [#20539](https://github.com/ClickHouse/ClickHouse/issues/20539). [#56102](https://github.com/ClickHouse/ClickHouse/pull/56102) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Some of the stack frames might not be resolved when collecting stacks. In such cases the raw address might be helpful. [#56267](https://github.com/ClickHouse/ClickHouse/pull/56267) ([Alexander Gololobov](https://github.com/davenger)).
* Add an option to disable `libssh`. [#56333](https://github.com/ClickHouse/ClickHouse/pull/56333) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Enable temporary_data_in_cache in S3 tests in CI. [#48425](https://github.com/ClickHouse/ClickHouse/pull/48425) ([vdimir](https://github.com/vdimir)).
* Set the max memory usage for clickhouse-client (`1G`) in the CI. [#56873](https://github.com/ClickHouse/ClickHouse/pull/56873) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Fix exerimental Analyzer - insertion from select with subquery referencing insertion table should process only insertion block. [#50857](https://github.com/ClickHouse/ClickHouse/pull/50857) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Fix a bug in `str_to_map` function. [#56423](https://github.com/ClickHouse/ClickHouse/pull/56423) ([Arthur Passos](https://github.com/arthurpassos)).
* Keeper `reconfig`: add timeout before yielding/taking leadership [#53481](https://github.com/ClickHouse/ClickHouse/pull/53481) ([Mike Kot](https://github.com/myrrc)).
* Fix incorrect header in grace hash join and filter pushdown [#53922](https://github.com/ClickHouse/ClickHouse/pull/53922) ([vdimir](https://github.com/vdimir)).
* Select from system tables when table based on table function. [#55540](https://github.com/ClickHouse/ClickHouse/pull/55540) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* RFC: Fix "Cannot find column X in source stream" for Distributed queries with LIMIT BY [#55836](https://github.com/ClickHouse/ClickHouse/pull/55836) ([Azat Khuzhin](https://github.com/azat)).
* Fix 'Cannot read from file:' while running client in a background [#55976](https://github.com/ClickHouse/ClickHouse/pull/55976) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix clickhouse-local exit on bad send_logs_level setting [#55994](https://github.com/ClickHouse/ClickHouse/pull/55994) ([Kruglov Pavel](https://github.com/Avogar)).
* Bug fix explain ast with parameterized view [#56004](https://github.com/ClickHouse/ClickHouse/pull/56004) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix a crash during table loading on startup [#56232](https://github.com/ClickHouse/ClickHouse/pull/56232) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ClickHouse-sourced dictionaries with an explicit query [#56236](https://github.com/ClickHouse/ClickHouse/pull/56236) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix segfault in signal handler for Keeper [#56266](https://github.com/ClickHouse/ClickHouse/pull/56266) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix incomplete query result for UNION in view() function. [#56274](https://github.com/ClickHouse/ClickHouse/pull/56274) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix inconsistency of "cast('0' as DateTime64(3))" and "cast('0' as Nullable(DateTime64(3)))" [#56286](https://github.com/ClickHouse/ClickHouse/pull/56286) ([李扬](https://github.com/taiyang-li)).
* Fix rare race condition related to Memory allocation failure [#56303](https://github.com/ClickHouse/ClickHouse/pull/56303) ([alesapin](https://github.com/alesapin)).
* Fix restore from backup with `flatten_nested` and `data_type_default_nullable` [#56306](https://github.com/ClickHouse/ClickHouse/pull/56306) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix crash in case of adding a column with type Object(JSON) [#56307](https://github.com/ClickHouse/ClickHouse/pull/56307) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix crash in filterPushDown [#56380](https://github.com/ClickHouse/ClickHouse/pull/56380) ([vdimir](https://github.com/vdimir)).
* Fix restore from backup with mat view and dropped source table [#56383](https://github.com/ClickHouse/ClickHouse/pull/56383) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix segfault during Kerberos initialization [#56401](https://github.com/ClickHouse/ClickHouse/pull/56401) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix buffer overflow in T64 [#56434](https://github.com/ClickHouse/ClickHouse/pull/56434) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix nullable primary key in final (2) [#56452](https://github.com/ClickHouse/ClickHouse/pull/56452) ([Amos Bird](https://github.com/amosbird)).
* Fix ON CLUSTER queries without database on initial node [#56484](https://github.com/ClickHouse/ClickHouse/pull/56484) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix startup failure due to TTL dependency [#56489](https://github.com/ClickHouse/ClickHouse/pull/56489) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ALTER COMMENT queries ON CLUSTER [#56491](https://github.com/ClickHouse/ClickHouse/pull/56491) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ALTER COLUMN with ALIAS [#56493](https://github.com/ClickHouse/ClickHouse/pull/56493) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix empty NAMED COLLECTIONs [#56494](https://github.com/ClickHouse/ClickHouse/pull/56494) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix two cases of projection analysis. [#56502](https://github.com/ClickHouse/ClickHouse/pull/56502) ([Amos Bird](https://github.com/amosbird)).
* Fix handling of aliases in query cache [#56545](https://github.com/ClickHouse/ClickHouse/pull/56545) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix conversion from `Nullable(Enum)` to `Nullable(String)` [#56644](https://github.com/ClickHouse/ClickHouse/pull/56644) ([Nikolay Degterinsky](https://github.com/evillique)).
* More reliable log handling in Keeper [#56670](https://github.com/ClickHouse/ClickHouse/pull/56670) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix configuration merge for nodes with substitution attributes [#56694](https://github.com/ClickHouse/ClickHouse/pull/56694) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Fix duplicate usage of table function input(). [#56695](https://github.com/ClickHouse/ClickHouse/pull/56695) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix: RabbitMQ OpenSSL dynamic loading issue [#56703](https://github.com/ClickHouse/ClickHouse/pull/56703) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix crash in GCD codec in case when zeros present in data [#56704](https://github.com/ClickHouse/ClickHouse/pull/56704) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix 'mutex lock failed: Invalid argument' in clickhouse-local during insert into function [#56710](https://github.com/ClickHouse/ClickHouse/pull/56710) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix Date text parsing in optimistic path [#56765](https://github.com/ClickHouse/ClickHouse/pull/56765) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix crash in FPC codec [#56795](https://github.com/ClickHouse/ClickHouse/pull/56795) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* DatabaseReplicated: fix DDL query timeout after recovering a replica [#56796](https://github.com/ClickHouse/ClickHouse/pull/56796) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix incorrect nullable columns reporting in MySQL binary protocol [#56799](https://github.com/ClickHouse/ClickHouse/pull/56799) ([Serge Klochkov](https://github.com/slvrtrn)).
* Support Iceberg metadata files for metastore tables [#56810](https://github.com/ClickHouse/ClickHouse/pull/56810) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix TSAN report under transform [#56817](https://github.com/ClickHouse/ClickHouse/pull/56817) ([Raúl Marín](https://github.com/Algunenano)).
* Fix SET query and SETTINGS formatting [#56825](https://github.com/ClickHouse/ClickHouse/pull/56825) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix failure to start due to table dependency in joinGet [#56828](https://github.com/ClickHouse/ClickHouse/pull/56828) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix flattening existing Nested columns during ADD COLUMN [#56830](https://github.com/ClickHouse/ClickHouse/pull/56830) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix allow cr end of line for csv [#56901](https://github.com/ClickHouse/ClickHouse/pull/56901) ([KevinyhZou](https://github.com/KevinyhZou)).
* Fix `tryBase64Decode` with invalid input [#56913](https://github.com/ClickHouse/ClickHouse/pull/56913) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix generating deep nested columns in CapnProto/Protobuf schemas [#56941](https://github.com/ClickHouse/ClickHouse/pull/56941) ([Kruglov Pavel](https://github.com/Avogar)).
* Prevent incompatible ALTER of projection columns [#56948](https://github.com/ClickHouse/ClickHouse/pull/56948) ([Amos Bird](https://github.com/amosbird)).
* Fix sqlite file path validation [#56984](https://github.com/ClickHouse/ClickHouse/pull/56984) ([San](https://github.com/santrancisco)).
* S3Queue: fix metadata reference increment [#56990](https://github.com/ClickHouse/ClickHouse/pull/56990) ([Kseniia Sumarokova](https://github.com/kssenii)).
* S3Queue minor fix [#56999](https://github.com/ClickHouse/ClickHouse/pull/56999) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix file path validation for DatabaseFileSystem [#57029](https://github.com/ClickHouse/ClickHouse/pull/57029) ([San](https://github.com/santrancisco)).
* Fix `fuzzBits` with `ARRAY JOIN` [#57033](https://github.com/ClickHouse/ClickHouse/pull/57033) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix Nullptr dereference in partial merge join with joined_subquery_re… [#57048](https://github.com/ClickHouse/ClickHouse/pull/57048) ([vdimir](https://github.com/vdimir)).
* Fix race condition in RemoteSource [#57052](https://github.com/ClickHouse/ClickHouse/pull/57052) ([Raúl Marín](https://github.com/Algunenano)).
* Implement `bitHammingDistance` for big integers [#57073](https://github.com/ClickHouse/ClickHouse/pull/57073) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* S3-style links bug fix [#57075](https://github.com/ClickHouse/ClickHouse/pull/57075) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix JSON_QUERY function with multiple numeric paths [#57096](https://github.com/ClickHouse/ClickHouse/pull/57096) ([KevinyhZou](https://github.com/KevinyhZou)).
* Fix buffer overflow in Gorilla codec [#57107](https://github.com/ClickHouse/ClickHouse/pull/57107) ([Nikolay Degterinsky](https://github.com/evillique)).
* Close interserver connection on any exception before authentication [#57142](https://github.com/ClickHouse/ClickHouse/pull/57142) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix segfault after ALTER UPDATE with Nullable MATERIALIZED column [#57147](https://github.com/ClickHouse/ClickHouse/pull/57147) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix incorrect JOIN plan optimization with partially materialized normal projection [#57196](https://github.com/ClickHouse/ClickHouse/pull/57196) ([Amos Bird](https://github.com/amosbird)).
* Ignore comments when comparing column descriptions [#57259](https://github.com/ClickHouse/ClickHouse/pull/57259) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix `ReadonlyReplica` metric for all cases [#57267](https://github.com/ClickHouse/ClickHouse/pull/57267) ([Antonio Andelic](https://github.com/antonio2368)).
* Background merges correctly use temporary data storage in the cache [#57275](https://github.com/ClickHouse/ClickHouse/pull/57275) ([vdimir](https://github.com/vdimir)).
* Keeper fix for changelog and snapshots [#57299](https://github.com/ClickHouse/ClickHouse/pull/57299) ([Antonio Andelic](https://github.com/antonio2368)).
* Ignore finished ON CLUSTER tasks if hostname changed [#57339](https://github.com/ClickHouse/ClickHouse/pull/57339) ([Alexander Tokmakov](https://github.com/tavplubix)).
* MergeTree mutations reuse source part index granularity [#57352](https://github.com/ClickHouse/ClickHouse/pull/57352) ([Maksim Kita](https://github.com/kitaisreal)).
* FS cache: add a limit for background download [#57424](https://github.com/ClickHouse/ClickHouse/pull/57424) ([Kseniia Sumarokova](https://github.com/kssenii)).
### <a id="2310"></a> ClickHouse release 23.10, 2023-11-02
#### Backward Incompatible Change
* There is no longer an option to automatically remove broken data parts. This closes [#55174](https://github.com/ClickHouse/ClickHouse/issues/55174). [#55184](https://github.com/ClickHouse/ClickHouse/pull/55184) ([Alexey Milovidov](https://github.com/alexey-milovidov)). [#55557](https://github.com/ClickHouse/ClickHouse/pull/55557) ([Jihyuk Bok](https://github.com/tomahawk28)).
@ -39,7 +250,7 @@
* Allow to drop cache for Protobuf format with `SYSTEM DROP SCHEMA FORMAT CACHE [FOR Protobuf]`. [#55064](https://github.com/ClickHouse/ClickHouse/pull/55064) ([Aleksandr Musorin](https://github.com/AVMusorin)).
* Add external HTTP Basic authenticator. [#55199](https://github.com/ClickHouse/ClickHouse/pull/55199) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Added function `byteSwap` which reverses the bytes of unsigned integers. This is particularly useful for reversing values of types which are represented as unsigned integers internally such as IPv4. [#55211](https://github.com/ClickHouse/ClickHouse/pull/55211) ([Priyansh Agrawal](https://github.com/Priyansh121096)).
* Added function `formatQuery()` which returns a formatted version (possibly spanning multiple lines) of a SQL query string. Also added function `formatQuerySingleLine()` which does the same but the returned string will not contain linebreaks. [#55239](https://github.com/ClickHouse/ClickHouse/pull/55239) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Added function `formatQuery` which returns a formatted version (possibly spanning multiple lines) of a SQL query string. Also added function `formatQuerySingleLine` which does the same but the returned string will not contain linebreaks. [#55239](https://github.com/ClickHouse/ClickHouse/pull/55239) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Added `DWARF` input format that reads debug symbols from an ELF executable/library/object file. [#55450](https://github.com/ClickHouse/ClickHouse/pull/55450) ([Michael Kolupaev](https://github.com/al13n321)).
* Allow to save unparsed records and errors in RabbitMQ, NATS and FileLog engines. Add virtual columns `_error` and `_raw_message`(for NATS and RabbitMQ), `_raw_record` (for FileLog) that are filled when ClickHouse fails to parse new record. The behaviour is controlled under storage settings `nats_handle_error_mode` for NATS, `rabbitmq_handle_error_mode` for RabbitMQ, `handle_error_mode` for FileLog similar to `kafka_handle_error_mode`. If it's set to `default`, en exception will be thrown when ClickHouse fails to parse a record, if it's set to `stream`, erorr and raw record will be saved into virtual columns. Closes [#36035](https://github.com/ClickHouse/ClickHouse/issues/36035). [#55477](https://github.com/ClickHouse/ClickHouse/pull/55477) ([Kruglov Pavel](https://github.com/Avogar)).
* Keeper client improvement: add `get_all_children_number command` that returns number of all children nodes under a specific path. [#55485](https://github.com/ClickHouse/ClickHouse/pull/55485) ([guoxiaolong](https://github.com/guoxiaolongzte)).
@ -74,11 +285,11 @@
* Reduced memory consumption during loading of hierarchical dictionaries. [#55838](https://github.com/ClickHouse/ClickHouse/pull/55838) ([Nikita Taranov](https://github.com/nickitat)).
* All dictionaries support setting `dictionary_use_async_executor`. [#55839](https://github.com/ClickHouse/ClickHouse/pull/55839) ([vdimir](https://github.com/vdimir)).
* Prevent excesive memory usage when deserializing AggregateFunctionTopKGenericData. [#55947](https://github.com/ClickHouse/ClickHouse/pull/55947) ([Raúl Marín](https://github.com/Algunenano)).
* On a Keeper with lots of watches AsyncMetrics threads can consume 100% of CPU for noticable time in `DB::KeeperStorage::getSessionsWithWatchesCount()`. The fix is to avoid traversing heavy `watches` and `list_watches` sets. [#56054](https://github.com/ClickHouse/ClickHouse/pull/56054) ([Alexander Gololobov](https://github.com/davenger)).
* Add setting `optimize_trivial_approximate_count_query` to use `count()` approximation for storage EmbeddedRocksDB. Enable trivial count for StorageJoin. [#55806](https://github.com/ClickHouse/ClickHouse/pull/55806) ([Duc Canh Le](https://github.com/canhld94)).
* On a Keeper with lots of watches AsyncMetrics threads can consume 100% of CPU for noticable time in `DB::KeeperStorage::getSessionsWithWatchesCount`. The fix is to avoid traversing heavy `watches` and `list_watches` sets. [#56054](https://github.com/ClickHouse/ClickHouse/pull/56054) ([Alexander Gololobov](https://github.com/davenger)).
* Add setting `optimize_trivial_approximate_count_query` to use `count` approximation for storage EmbeddedRocksDB. Enable trivial count for StorageJoin. [#55806](https://github.com/ClickHouse/ClickHouse/pull/55806) ([Duc Canh Le](https://github.com/canhld94)).
#### Improvement
* Functions `toDayOfWeek()` (MySQL alias: `DAYOFWEEK()`), `toYearWeek()` (`YEARWEEK()`) and `toWeek()` (`WEEK()`) now supports `String` arguments. This makes its behavior consistent with MySQL's behavior. [#55589](https://github.com/ClickHouse/ClickHouse/pull/55589) ([Robert Schulze](https://github.com/rschu1ze)).
* Functions `toDayOfWeek` (MySQL alias: `DAYOFWEEK`), `toYearWeek` (`YEARWEEK`) and `toWeek` (`WEEK`) now supports `String` arguments. This makes its behavior consistent with MySQL's behavior. [#55589](https://github.com/ClickHouse/ClickHouse/pull/55589) ([Robert Schulze](https://github.com/rschu1ze)).
* Introduced setting `date_time_overflow_behavior` with possible values `ignore`, `throw`, `saturate` that controls the overflow behavior when converting from Date, Date32, DateTime64, Integer or Float to Date, Date32, DateTime or DateTime64. [#55696](https://github.com/ClickHouse/ClickHouse/pull/55696) ([Andrey Zvonov](https://github.com/zvonand)).
* Implement query parameters support for `ALTER TABLE ... ACTION PARTITION [ID] {parameter_name:ParameterType}`. Merges [#49516](https://github.com/ClickHouse/ClickHouse/issues/49516). Closes [#49449](https://github.com/ClickHouse/ClickHouse/issues/49449). [#55604](https://github.com/ClickHouse/ClickHouse/pull/55604) ([alesapin](https://github.com/alesapin)).
* Print processor ids in a prettier manner in EXPLAIN. [#48852](https://github.com/ClickHouse/ClickHouse/pull/48852) ([Vlad Seliverstov](https://github.com/behebot)).
@ -112,7 +323,7 @@
* Functions `(add|subtract)(Year|Quarter|Month|Week|Day|Hour|Minute|Second|Millisecond|Microsecond|Nanosecond)` now support string-encoded date arguments, e.g. `SELECT addDays('2023-10-22', 1)`. This increases compatibility with MySQL and is needed by Tableau Online. [#55869](https://github.com/ClickHouse/ClickHouse/pull/55869) ([Robert Schulze](https://github.com/rschu1ze)).
* The setting `apply_deleted_mask` when disabled allows to read rows that where marked as deleted by lightweight DELETE queries. This is useful for debugging. [#55952](https://github.com/ClickHouse/ClickHouse/pull/55952) ([Alexander Gololobov](https://github.com/davenger)).
* Allow skipping `null` values when serailizing Tuple to json objects, which makes it possible to keep compatiability with Spark's `to_json` function, which is also useful for gluten. [#55956](https://github.com/ClickHouse/ClickHouse/pull/55956) ([李扬](https://github.com/taiyang-li)).
* Functions `(add|sub)Date()` now support string-encoded date arguments, e.g. `SELECT addDate('2023-10-22 11:12:13', INTERVAL 5 MINUTE)`. The same support for string-encoded date arguments is added to the plus and minus operators, e.g. `SELECT '2023-10-23' + INTERVAL 1 DAY`. This increases compatibility with MySQL and is needed by Tableau Online. [#55960](https://github.com/ClickHouse/ClickHouse/pull/55960) ([Robert Schulze](https://github.com/rschu1ze)).
* Functions `(add|sub)Date` now support string-encoded date arguments, e.g. `SELECT addDate('2023-10-22 11:12:13', INTERVAL 5 MINUTE)`. The same support for string-encoded date arguments is added to the plus and minus operators, e.g. `SELECT '2023-10-23' + INTERVAL 1 DAY`. This increases compatibility with MySQL and is needed by Tableau Online. [#55960](https://github.com/ClickHouse/ClickHouse/pull/55960) ([Robert Schulze](https://github.com/rschu1ze)).
* Allow unquoted strings with CR (`\r`) in CSV format. Closes [#39930](https://github.com/ClickHouse/ClickHouse/issues/39930). [#56046](https://github.com/ClickHouse/ClickHouse/pull/56046) ([Kruglov Pavel](https://github.com/Avogar)).
* Allow to run `clickhouse-keeper` using embedded config. [#56086](https://github.com/ClickHouse/ClickHouse/pull/56086) ([Maksim Kita](https://github.com/kitaisreal)).
* Set limit of the maximum configuration value for `queued.min.messages` to avoid problem with start fetching data with Kafka. [#56121](https://github.com/ClickHouse/ClickHouse/pull/56121) ([Stas Morozov](https://github.com/r3b-fish)).
@ -133,7 +344,7 @@
* Fixed bug of `match` function (regex) with pattern containing alternation produces incorrect key condition. Closes #53222. [#54696](https://github.com/ClickHouse/ClickHouse/pull/54696) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Fix 'Cannot find column' in read-in-order optimization with ARRAY JOIN [#51746](https://github.com/ClickHouse/ClickHouse/pull/51746) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Support missed experimental `Object(Nullable(json))` subcolumns in query. [#54052](https://github.com/ClickHouse/ClickHouse/pull/54052) ([zps](https://github.com/VanDarkholme7)).
* Re-add fix for `accurateCastOrNull()` [#54629](https://github.com/ClickHouse/ClickHouse/pull/54629) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Re-add fix for `accurateCastOrNull` [#54629](https://github.com/ClickHouse/ClickHouse/pull/54629) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Fix detecting `DEFAULT` for columns of a Distributed table created without AS [#55060](https://github.com/ClickHouse/ClickHouse/pull/55060) ([Vitaly Baranov](https://github.com/vitlibar)).
* Proper cleanup in case of exception in ctor of ShellCommandSource [#55103](https://github.com/ClickHouse/ClickHouse/pull/55103) ([Alexander Gololobov](https://github.com/davenger)).
* Fix deadlock in LDAP assigned role update [#55119](https://github.com/ClickHouse/ClickHouse/pull/55119) ([Julian Maicher](https://github.com/jmaicher)).
@ -191,7 +402,7 @@
* Add error handler to odbc-bridge [#56185](https://github.com/ClickHouse/ClickHouse/pull/56185) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
### ClickHouse release 23.9, 2023-09-28
### <a id="239"></a> ClickHouse release 23.9, 2023-09-28
#### Backward Incompatible Change
* Remove the `status_info` configuration option and dictionaries status from the default Prometheus handler. [#54090](https://github.com/ClickHouse/ClickHouse/pull/54090) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
@ -213,7 +424,7 @@
* Add function `decodeHTMLComponent`. [#54097](https://github.com/ClickHouse/ClickHouse/pull/54097) ([Bharat Nallan](https://github.com/bharatnc)).
* Added `peak_threads_usage` to query_log table. [#54335](https://github.com/ClickHouse/ClickHouse/pull/54335) ([Alexey Gerasimchuck](https://github.com/Demilivor)).
* Add `SHOW FUNCTIONS` support to clickhouse-client. [#54337](https://github.com/ClickHouse/ClickHouse/pull/54337) ([Julia Kartseva](https://github.com/wat-ze-hex)).
* Added function `toDaysSinceYearZero` with alias `TO_DAYS` (for compatibility with MySQL) which returns the number of days passed since `0001-01-01` (in Proleptic Gregorian Calendar). [#54479](https://github.com/ClickHouse/ClickHouse/pull/54479) ([Robert Schulze](https://github.com/rschu1ze)). Function `toDaysSinceYearZero()` now supports arguments of type `DateTime` and `DateTime64`. [#54856](https://github.com/ClickHouse/ClickHouse/pull/54856) ([Serge Klochkov](https://github.com/slvrtrn)).
* Added function `toDaysSinceYearZero` with alias `TO_DAYS` (for compatibility with MySQL) which returns the number of days passed since `0001-01-01` (in Proleptic Gregorian Calendar). [#54479](https://github.com/ClickHouse/ClickHouse/pull/54479) ([Robert Schulze](https://github.com/rschu1ze)). Function `toDaysSinceYearZero` now supports arguments of type `DateTime` and `DateTime64`. [#54856](https://github.com/ClickHouse/ClickHouse/pull/54856) ([Serge Klochkov](https://github.com/slvrtrn)).
* Added functions `YYYYMMDDtoDate`, `YYYYMMDDtoDate32`, `YYYYMMDDhhmmssToDateTime` and `YYYYMMDDhhmmssToDateTime64`. They convert a date or date with time encoded as integer (e.g. 20230911) into a native date or date with time. As such, they provide the opposite functionality of existing functions `YYYYMMDDToDate`, `YYYYMMDDToDateTime`, `YYYYMMDDhhmmddToDateTime`, `YYYYMMDDhhmmddToDateTime64`. [#54509](https://github.com/ClickHouse/ClickHouse/pull/54509) ([Quanfa Fu](https://github.com/dentiscalprum)) ([Robert Schulze](https://github.com/rschu1ze)).
* Add several string distance functions, including `byteHammingDistance`, `editDistance`. [#54935](https://github.com/ClickHouse/ClickHouse/pull/54935) ([flynn](https://github.com/ucasfl)).
* Allow specifying the expiration date and, optionally, the time for user credentials with `VALID UNTIL datetime` clause. [#51261](https://github.com/ClickHouse/ClickHouse/pull/51261) ([Nikolay Degterinsky](https://github.com/evillique)).
@ -229,7 +440,7 @@
* An optimization to rewrite `COUNT(DISTINCT ...)` and various `uniq` variants to `count` if it is selected from a subquery with GROUP BY. [#52082](https://github.com/ClickHouse/ClickHouse/pull/52082) [#52645](https://github.com/ClickHouse/ClickHouse/pull/52645) ([JackyWoo](https://github.com/JackyWoo)).
* Remove manual calls to `mmap/mremap/munmap` and delegate all this work to `jemalloc` - and it slightly improves performance. [#52792](https://github.com/ClickHouse/ClickHouse/pull/52792) ([Nikita Taranov](https://github.com/nickitat)).
* Fixed high in CPU consumption when working with NATS. [#54399](https://github.com/ClickHouse/ClickHouse/pull/54399) ([Vasilev Pyotr](https://github.com/vahpetr)).
* Since we use separate instructions for executing `toString()` with datetime argument, it is possible to improve performance a bit for non-datetime arguments and have some parts of the code cleaner. Follows up [#53680](https://github.com/ClickHouse/ClickHouse/issues/53680). [#54443](https://github.com/ClickHouse/ClickHouse/pull/54443) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Since we use separate instructions for executing `toString` with datetime argument, it is possible to improve performance a bit for non-datetime arguments and have some parts of the code cleaner. Follows up [#53680](https://github.com/ClickHouse/ClickHouse/issues/53680). [#54443](https://github.com/ClickHouse/ClickHouse/pull/54443) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Instead of serializing json elements into a `std::stringstream`, this PR try to put the serialization result into `ColumnString` direclty. [#54613](https://github.com/ClickHouse/ClickHouse/pull/54613) ([lgbo](https://github.com/lgbo-ustc)).
* Enable ORDER BY optimization for reading data in corresponding order from a MergeTree table in case that the table is behind a view. [#54628](https://github.com/ClickHouse/ClickHouse/pull/54628) ([Vitaly Baranov](https://github.com/vitlibar)).
* Improve JSON SQL functions by reusing `GeneratorJSONPath` and removing several shared pointers. [#54735](https://github.com/ClickHouse/ClickHouse/pull/54735) ([lgbo](https://github.com/lgbo-ustc)).
@ -479,7 +690,7 @@
* The `domainRFC` function now supports IPv6 in square brackets. [#53506](https://github.com/ClickHouse/ClickHouse/pull/53506) ([Chen768959](https://github.com/Chen768959)).
* Use longer timeout for S3 CopyObject requests, which are used in backups. [#53533](https://github.com/ClickHouse/ClickHouse/pull/53533) ([Michael Kolupaev](https://github.com/al13n321)).
* Added server setting `aggregate_function_group_array_max_element_size`. This setting is used to limit array size for `groupArray` function at serialization. The default value is `16777215`. [#53550](https://github.com/ClickHouse/ClickHouse/pull/53550) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* `SCHEMA()` was added as alias for `DATABASE()` to improve MySQL compatibility. [#53587](https://github.com/ClickHouse/ClickHouse/pull/53587) ([Daniël van Eeden](https://github.com/dveeden)).
* `SCHEMA` was added as alias for `DATABASE` to improve MySQL compatibility. [#53587](https://github.com/ClickHouse/ClickHouse/pull/53587) ([Daniël van Eeden](https://github.com/dveeden)).
* Add asynchronous metrics about tables in the system database. For example, `TotalBytesOfMergeTreeTablesSystem`. This closes [#53603](https://github.com/ClickHouse/ClickHouse/issues/53603). [#53604](https://github.com/ClickHouse/ClickHouse/pull/53604) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* SQL editor in the Play UI and Dashboard will not use Grammarly. [#53614](https://github.com/ClickHouse/ClickHouse/pull/53614) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* As expert-level settings, it is now possible to (1) configure the size_ratio (i.e. the relative size of the protected queue) of the [index] mark/uncompressed caches, (2) configure the cache policy of the index mark and index uncompressed caches. [#53657](https://github.com/ClickHouse/ClickHouse/pull/53657) ([Robert Schulze](https://github.com/rschu1ze)).
@ -741,7 +952,7 @@
* Disable expression templates for time intervals [#52335](https://github.com/ClickHouse/ClickHouse/pull/52335) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix `apply_snapshot` in Keeper [#52358](https://github.com/ClickHouse/ClickHouse/pull/52358) ([Antonio Andelic](https://github.com/antonio2368)).
* Update build-osx.md [#52377](https://github.com/ClickHouse/ClickHouse/pull/52377) ([AlexBykovski](https://github.com/AlexBykovski)).
* Fix `countSubstrings()` hang with empty needle and a column haystack [#52409](https://github.com/ClickHouse/ClickHouse/pull/52409) ([Sergei Trifonov](https://github.com/serxa)).
* Fix `countSubstrings` hang with empty needle and a column haystack [#52409](https://github.com/ClickHouse/ClickHouse/pull/52409) ([Sergei Trifonov](https://github.com/serxa)).
* Fix normal projection with merge table [#52432](https://github.com/ClickHouse/ClickHouse/pull/52432) ([Amos Bird](https://github.com/amosbird)).
* Fix possible double-free in Aggregator [#52439](https://github.com/ClickHouse/ClickHouse/pull/52439) ([Nikita Taranov](https://github.com/nickitat)).
* Fixed inserting into Buffer engine [#52440](https://github.com/ClickHouse/ClickHouse/pull/52440) ([Vasily Nemkov](https://github.com/Enmk)).
@ -1585,7 +1796,7 @@
* A couple of segfaults have been reported around `c-ares`. They were introduced in my previous pull requests. I have fixed them with the help of Alexander Tokmakov. [#45629](https://github.com/ClickHouse/ClickHouse/pull/45629) ([Arthur Passos](https://github.com/arthurpassos)).
* Fix key description when encountering duplicate primary keys. This can happen in projections. See [#45590](https://github.com/ClickHouse/ClickHouse/issues/45590) for details. [#45686](https://github.com/ClickHouse/ClickHouse/pull/45686) ([Amos Bird](https://github.com/amosbird)).
* Set compression method and level for backup Closes [#45690](https://github.com/ClickHouse/ClickHouse/issues/45690). [#45737](https://github.com/ClickHouse/ClickHouse/pull/45737) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Should use `select_query_typed.limitByOffset()` instead of `select_query_typed.limitOffset()`. [#45817](https://github.com/ClickHouse/ClickHouse/pull/45817) ([刘陶峰](https://github.com/taofengliu)).
* Should use `select_query_typed.limitByOffset` instead of `select_query_typed.limitOffset`. [#45817](https://github.com/ClickHouse/ClickHouse/pull/45817) ([刘陶峰](https://github.com/taofengliu)).
* When use experimental analyzer, queries like `SELECT number FROM numbers(100) LIMIT 10 OFFSET 10;` get wrong results (empty result for this sql). That is caused by an unnecessary offset step added by planner. [#45822](https://github.com/ClickHouse/ClickHouse/pull/45822) ([刘陶峰](https://github.com/taofengliu)).
* Backward compatibility - allow implicit narrowing conversion from UInt64 to IPv4 - required for "INSERT ... VALUES ..." expression. [#45865](https://github.com/ClickHouse/ClickHouse/pull/45865) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Bugfix IPv6 parser for mixed ip4 address with missed first octet (like `::.1.2.3`). [#45871](https://github.com/ClickHouse/ClickHouse/pull/45871) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).

1
README.md
View File

@ -35,6 +35,7 @@ curl https://clickhouse.com/ | sh
* [**ClickHouse Meetup in Berlin**](https://www.meetup.com/clickhouse-berlin-user-group/events/296488501/) - Nov 30
* [**ClickHouse Meetup in NYC**](https://www.meetup.com/clickhouse-new-york-user-group/events/296488779/) - Dec 11
* [**ClickHouse Meetup in Sydney**](https://www.meetup.com/clickhouse-sydney-user-group/events/297638812/) - Dec 12
* [**ClickHouse Meetup in Boston**](https://www.meetup.com/clickhouse-boston-user-group/events/296488840/) - Dec 12
Also, keep an eye out for upcoming meetups around the world. Somewhere else you want us to be? Please feel free to reach out to tyler <at> clickhouse <dot> com.

1
SECURITY.md
View File

@ -13,6 +13,7 @@ The following versions of ClickHouse server are currently being supported with s
| Version | Supported |
|:-|:-|
| 23.11 | ✔️ |
| 23.10 | ✔️ |
| 23.9 | ✔️ |
| 23.8 | ✔️ |

1
base/glibc-compatibility/glibc-compatibility.c
View File

@ -30,7 +30,6 @@ int __gai_sigqueue(int sig, const union sigval val, pid_t caller_pid)
}
#include <sys/select.h>
#include <stdlib.h>
#include <features.h>

1
base/poco/Foundation/CMakeLists.txt
View File

@ -55,7 +55,6 @@ set (SRCS
src/DigestStream.cpp
src/DirectoryIterator.cpp
src/DirectoryIteratorStrategy.cpp
src/DirectoryWatcher.cpp
src/Environment.cpp
src/Error.cpp
src/ErrorHandler.cpp

228
base/poco/Foundation/include/Poco/DirectoryWatcher.h
View File

@ -1,228 +0,0 @@
//
// DirectoryWatcher.h
//
// Library: Foundation
// Package: Filesystem
// Module: DirectoryWatcher
//
// Definition of the DirectoryWatcher class.
//
// Copyright (c) 2012, Applied Informatics Software Engineering GmbH.
// and Contributors.
//
// SPDX-License-Identifier: BSL-1.0
//
#ifndef Foundation_DirectoryWatcher_INCLUDED
#define Foundation_DirectoryWatcher_INCLUDED
#include "Poco/Foundation.h"
#ifndef POCO_NO_INOTIFY
# include "Poco/AtomicCounter.h"
# include "Poco/BasicEvent.h"
# include "Poco/File.h"
# include "Poco/Runnable.h"
# include "Poco/Thread.h"
namespace Poco
{
class DirectoryWatcherStrategy;
class Foundation_API DirectoryWatcher : protected Runnable
/// This class is used to get notifications about changes
/// to the filesystem, more specifically, to a specific
/// directory. Changes to a directory are reported via
/// events.
///
/// A thread will be created that watches the specified
/// directory for changes. Events are reported in the context
/// of this thread.
///
/// Note that changes to files in subdirectories of the watched
/// directory are not reported. Separate DirectoryWatcher objects
/// must be created for these directories if they should be watched.
///
/// Changes to file attributes are not reported.
///
/// On Windows, this class is implemented using FindFirstChangeNotification()/FindNextChangeNotification().
/// On Linux, this class is implemented using inotify.
/// On FreeBSD and Darwin (Mac OS X, iOS), this class uses kevent/kqueue.
/// On all other platforms, the watched directory is periodically scanned
/// for changes. This can negatively affect performance if done too often.
/// Therefore, the interval in which scans are done can be specified in
/// the constructor. Note that periodic scanning will also be done on FreeBSD
/// and Darwin if events for changes to files (DW_ITEM_MODIFIED) are enabled.
///
/// DW_ITEM_MOVED_FROM and DW_ITEM_MOVED_TO events will only be reported
/// on Linux. On other platforms, a file rename or move operation
/// will be reported via a DW_ITEM_REMOVED and a DW_ITEM_ADDED event.
/// The order of these two events is not defined.
///
/// An event mask can be specified to enable only certain events.
{
public:
enum DirectoryEventType
{
DW_ITEM_ADDED = 1,
/// A new item has been created and added to the directory.
DW_ITEM_REMOVED = 2,
/// An item has been removed from the directory.
DW_ITEM_MODIFIED = 4,
/// An item has been modified.
DW_ITEM_MOVED_FROM = 8,
/// An item has been renamed or moved. This event delivers the old name.
DW_ITEM_MOVED_TO = 16
/// An item has been renamed or moved. This event delivers the new name.
};
enum DirectoryEventMask
{
DW_FILTER_ENABLE_ALL = 31,
/// Enables all event types.
DW_FILTER_DISABLE_ALL = 0
/// Disables all event types.
};
enum
{
DW_DEFAULT_SCAN_INTERVAL = 5 /// Default scan interval for platforms that don't provide a native notification mechanism.
};
struct DirectoryEvent
{
DirectoryEvent(const File & f, DirectoryEventType ev) : item(f), event(ev) { }
const File & item; /// The directory or file that has been changed.
DirectoryEventType event; /// The kind of event.
};
BasicEvent<const DirectoryEvent> itemAdded;
/// Fired when a file or directory has been created or added to the directory.
BasicEvent<const DirectoryEvent> itemRemoved;
/// Fired when a file or directory has been removed from the directory.
BasicEvent<const DirectoryEvent> itemModified;
/// Fired when a file or directory has been modified.
BasicEvent<const DirectoryEvent> itemMovedFrom;
/// Fired when a file or directory has been renamed. This event delivers the old name.
BasicEvent<const DirectoryEvent> itemMovedTo;
/// Fired when a file or directory has been moved. This event delivers the new name.
BasicEvent<const Exception> scanError;
/// Fired when an error occurs while scanning for changes.
DirectoryWatcher(const std::string & path, int eventMask = DW_FILTER_ENABLE_ALL, int scanInterval = DW_DEFAULT_SCAN_INTERVAL);
/// Creates a DirectoryWatcher for the directory given in path.
/// To enable only specific events, an eventMask can be specified by
/// OR-ing the desired event IDs (e.g., DW_ITEM_ADDED | DW_ITEM_MODIFIED).
/// On platforms where no native filesystem notifications are available,
/// scanInterval specifies the interval in seconds between scans
/// of the directory.
DirectoryWatcher(const File & directory, int eventMask = DW_FILTER_ENABLE_ALL, int scanInterval = DW_DEFAULT_SCAN_INTERVAL);
/// Creates a DirectoryWatcher for the specified directory
/// To enable only specific events, an eventMask can be specified by
/// OR-ing the desired event IDs (e.g., DW_ITEM_ADDED | DW_ITEM_MODIFIED).
/// On platforms where no native filesystem notifications are available,
/// scanInterval specifies the interval in seconds between scans
/// of the directory.
~DirectoryWatcher();
/// Destroys the DirectoryWatcher.
void suspendEvents();
/// Suspends sending of events. Can be called multiple times, but every
/// call to suspendEvent() must be matched by a call to resumeEvents().
void resumeEvents();
/// Resumes events, after they have been suspended with a call to suspendEvents().
bool eventsSuspended() const;
/// Returns true iff events are suspended.
int eventMask() const;
/// Returns the value of the eventMask passed to the constructor.
int scanInterval() const;
/// Returns the scan interval in seconds.
const File & directory() const;
/// Returns the directory being watched.
bool supportsMoveEvents() const;
/// Returns true iff the platform supports DW_ITEM_MOVED_FROM/itemMovedFrom and
/// DW_ITEM_MOVED_TO/itemMovedTo events.
protected:
void init();
void stop();
void run();
private:
DirectoryWatcher();
DirectoryWatcher(const DirectoryWatcher &);
DirectoryWatcher & operator=(const DirectoryWatcher &);
Thread _thread;
File _directory;
int _eventMask;
AtomicCounter _eventsSuspended;
int _scanInterval;
DirectoryWatcherStrategy * _pStrategy;
};
//
// inlines
//
inline bool DirectoryWatcher::eventsSuspended() const
{
return _eventsSuspended.value() > 0;
}
inline int DirectoryWatcher::eventMask() const
{
return _eventMask;
}
inline int DirectoryWatcher::scanInterval() const
{
return _scanInterval;
}
inline const File & DirectoryWatcher::directory() const
{
return _directory;
}
} // namespace Poco
#endif // POCO_NO_INOTIFY
#endif // Foundation_DirectoryWatcher_INCLUDED

602
base/poco/Foundation/src/DirectoryWatcher.cpp
View File

@ -1,602 +0,0 @@
//
// DirectoryWatcher.cpp
//
// Library: Foundation
// Package: Filesystem
// Module: DirectoryWatcher
//
// Copyright (c) 2012, Applied Informatics Software Engineering GmbH.
// and Contributors.
//
// SPDX-License-Identifier: BSL-1.0
//
#include "Poco/DirectoryWatcher.h"
#ifndef POCO_NO_INOTIFY
#include "Poco/Path.h"
#include "Poco/Glob.h"
#include "Poco/DirectoryIterator.h"
#include "Poco/Event.h"
#include "Poco/Exception.h"
#include "Poco/Buffer.h"
#if POCO_OS == POCO_OS_LINUX || POCO_OS == POCO_OS_ANDROID
#include <sys/inotify.h>
#include <sys/select.h>
#include <unistd.h>
#elif POCO_OS == POCO_OS_MAC_OS_X || POCO_OS == POCO_OS_FREE_BSD
#include <fcntl.h>
#include <sys/types.h>
#include <sys/event.h>
#include <sys/time.h>
#include <unistd.h>
#if (POCO_OS == POCO_OS_FREE_BSD) && !defined(O_EVTONLY)
#define O_EVTONLY 0x8000
#endif
#endif
#include <algorithm>
#include <atomic>
#include <map>
namespace Poco {
class DirectoryWatcherStrategy
{
public:
DirectoryWatcherStrategy(DirectoryWatcher& owner):
_owner(owner)
{
}
virtual ~DirectoryWatcherStrategy()
{
}
DirectoryWatcher& owner()
{
return _owner;
}
virtual void run() = 0;
virtual void stop() = 0;
virtual bool supportsMoveEvents() const = 0;
protected:
struct ItemInfo
{
ItemInfo():
size(0)
{
}
ItemInfo(const ItemInfo& other):
path(other.path),
size(other.size),
lastModified(other.lastModified)
{
}
explicit ItemInfo(const File& f):
path(f.path()),
size(f.isFile() ? f.getSize() : 0),
lastModified(f.getLastModified())
{
}
std::string path;
File::FileSize size;
Timestamp lastModified;
};
typedef std::map<std::string, ItemInfo> ItemInfoMap;
void scan(ItemInfoMap& entries)
{
DirectoryIterator it(owner().directory());
DirectoryIterator end;
while (it != end)
{
entries[it.path().getFileName()] = ItemInfo(*it);
++it;
}
}
void compare(ItemInfoMap& oldEntries, ItemInfoMap& newEntries)
{
for (ItemInfoMap::iterator itn = newEntries.begin(); itn != newEntries.end(); ++itn)
{
ItemInfoMap::iterator ito = oldEntries.find(itn->first);
if (ito != oldEntries.end())
{
if ((owner().eventMask() & DirectoryWatcher::DW_ITEM_MODIFIED) && !owner().eventsSuspended())
{
if (itn->second.size != ito->second.size || itn->second.lastModified != ito->second.lastModified)
{
Poco::File f(itn->second.path);
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_MODIFIED);
owner().itemModified(&owner(), ev);
}
}
oldEntries.erase(ito);
}
else if ((owner().eventMask() & DirectoryWatcher::DW_ITEM_ADDED) && !owner().eventsSuspended())
{
Poco::File f(itn->second.path);
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_ADDED);
owner().itemAdded(&owner(), ev);
}
}
if ((owner().eventMask() & DirectoryWatcher::DW_ITEM_REMOVED) && !owner().eventsSuspended())
{
for (ItemInfoMap::iterator it = oldEntries.begin(); it != oldEntries.end(); ++it)
{
Poco::File f(it->second.path);
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_REMOVED);
owner().itemRemoved(&owner(), ev);
}
}
}
private:
DirectoryWatcherStrategy();
DirectoryWatcherStrategy(const DirectoryWatcherStrategy&);
DirectoryWatcherStrategy& operator = (const DirectoryWatcherStrategy&);
DirectoryWatcher& _owner;
};
#if POCO_OS == POCO_OS_WINDOWS_NT
class WindowsDirectoryWatcherStrategy: public DirectoryWatcherStrategy
{
public:
WindowsDirectoryWatcherStrategy(DirectoryWatcher& owner):
DirectoryWatcherStrategy(owner)
{
_hStopped = CreateEventW(NULL, FALSE, FALSE, NULL);
if (!_hStopped)
throw SystemException("cannot create event");
}
~WindowsDirectoryWatcherStrategy()
{
CloseHandle(_hStopped);
}
void run()
{
ItemInfoMap entries;
scan(entries);
DWORD filter = FILE_NOTIFY_CHANGE_FILE_NAME | FILE_NOTIFY_CHANGE_DIR_NAME;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_MODIFIED)
filter |= FILE_NOTIFY_CHANGE_SIZE | FILE_NOTIFY_CHANGE_LAST_WRITE;
std::string path(owner().directory().path());
HANDLE hChange = FindFirstChangeNotificationA(path.c_str(), FALSE, filter);
if (hChange == INVALID_HANDLE_VALUE)
{
try
{
FileImpl::handleLastErrorImpl(path);
}
catch (Poco::Exception& exc)
{
owner().scanError(&owner(), exc);
}
return;
}
bool stopped = false;
while (!stopped)
{
try
{
HANDLE h[2];
h[0] = _hStopped;
h[1] = hChange;
switch (WaitForMultipleObjects(2, h, FALSE, INFINITE))
{
case WAIT_OBJECT_0:
stopped = true;
break;
case WAIT_OBJECT_0 + 1:
{
ItemInfoMap newEntries;
scan(newEntries);
compare(entries, newEntries);
std::swap(entries, newEntries);
if (FindNextChangeNotification(hChange) == FALSE)
{
FileImpl::handleLastErrorImpl(path);
}
}
break;
default:
throw SystemException("failed to wait for directory changes");
}
}
catch (Poco::Exception& exc)
{
owner().scanError(&owner(), exc);
}
}
FindCloseChangeNotification(hChange);
}
void stop()
{
SetEvent(_hStopped);
}
bool supportsMoveEvents() const
{
return false;
}
private:
HANDLE _hStopped;
};
#elif POCO_OS == POCO_OS_LINUX || POCO_OS == POCO_OS_ANDROID
class LinuxDirectoryWatcherStrategy: public DirectoryWatcherStrategy
{
public:
LinuxDirectoryWatcherStrategy(DirectoryWatcher& owner):
DirectoryWatcherStrategy(owner),
_fd(-1),
_stopped(false)
{
_fd = inotify_init();
if (_fd == -1) throw Poco::IOException("cannot initialize inotify", errno);
}
~LinuxDirectoryWatcherStrategy()
{
close(_fd);
}
void run()
{
int mask = 0;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_ADDED)
mask |= IN_CREATE;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_REMOVED)
mask |= IN_DELETE;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_MODIFIED)
mask |= IN_MODIFY;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_MOVED_FROM)
mask |= IN_MOVED_FROM;
if (owner().eventMask() & DirectoryWatcher::DW_ITEM_MOVED_TO)
mask |= IN_MOVED_TO;
int wd = inotify_add_watch(_fd, owner().directory().path().c_str(), mask);
if (wd == -1)
{
try
{
FileImpl::handleLastErrorImpl(owner().directory().path());
}
catch (Poco::Exception& exc)
{
owner().scanError(&owner(), exc);
}
}
Poco::Buffer<char> buffer(4096);
while (!_stopped.load(std::memory_order_relaxed))
{
fd_set fds;
FD_ZERO(&fds);
FD_SET(_fd, &fds);
struct timeval tv;
tv.tv_sec = 0;
tv.tv_usec = 200000;
if (select(_fd + 1, &fds, NULL, NULL, &tv) == 1)
{
int n = read(_fd, buffer.begin(), buffer.size());
int i = 0;
if (n > 0)
{
while (n > 0)
{
struct inotify_event* event = reinterpret_cast<struct inotify_event*>(buffer.begin() + i);
if (event->len > 0)
{
if (!owner().eventsSuspended())
{
Poco::Path p(owner().directory().path());
p.makeDirectory();
p.setFileName(event->name);
Poco::File f(p.toString());
if ((event->mask & IN_CREATE) && (owner().eventMask() & DirectoryWatcher::DW_ITEM_ADDED))
{
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_ADDED);
owner().itemAdded(&owner(), ev);
}
if ((event->mask & IN_DELETE) && (owner().eventMask() & DirectoryWatcher::DW_ITEM_REMOVED))
{
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_REMOVED);
owner().itemRemoved(&owner(), ev);
}
if ((event->mask & IN_MODIFY) && (owner().eventMask() & DirectoryWatcher::DW_ITEM_MODIFIED))
{
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_MODIFIED);
owner().itemModified(&owner(), ev);
}
if ((event->mask & IN_MOVED_FROM) && (owner().eventMask() & DirectoryWatcher::DW_ITEM_MOVED_FROM))
{
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_MOVED_FROM);
owner().itemMovedFrom(&owner(), ev);
}
if ((event->mask & IN_MOVED_TO) && (owner().eventMask() & DirectoryWatcher::DW_ITEM_MOVED_TO))
{
DirectoryWatcher::DirectoryEvent ev(f, DirectoryWatcher::DW_ITEM_MOVED_TO);
owner().itemMovedTo(&owner(), ev);
}
}
}
i += sizeof(inotify_event) + event->len;
n -= sizeof(inotify_event) + event->len;
}
}
}
}
}
void stop()
{
_stopped.store(true, std::memory_order_relaxed);
}
bool supportsMoveEvents() const
{
return true;
}
private:
int _fd;
std::atomic<bool> _stopped;
};
#elif POCO_OS == POCO_OS_MAC_OS_X || POCO_OS == POCO_OS_FREE_BSD
class BSDDirectoryWatcherStrategy: public DirectoryWatcherStrategy
{
public:
BSDDirectoryWatcherStrategy(DirectoryWatcher& owner):
DirectoryWatcherStrategy(owner),
_queueFD(-1),
_dirFD(-1),
_stopped(false)
{
_dirFD = open(owner.directory().path().c_str(), O_EVTONLY);
if (_dirFD < 0) throw Poco::FileNotFoundException(owner.directory().path());
_queueFD = kqueue();
if (_queueFD < 0)
{
close(_dirFD);
throw Poco::SystemException("Cannot create kqueue", errno);
}
}
~BSDDirectoryWatcherStrategy()
{
close(_dirFD);
close(_queueFD);
}
void run()
{
Poco::Timestamp lastScan;
ItemInfoMap entries;
scan(entries);
while (!_stopped.load(std::memory_order_relaxed))
{
struct timespec timeout;
timeout.tv_sec = 0;
timeout.tv_nsec = 200000000;
unsigned eventFilter = NOTE_WRITE;
struct kevent event;
struct kevent eventData;
EV_SET(&event, _dirFD, EVFILT_VNODE, EV_ADD | EV_CLEAR, eventFilter, 0, 0);
int nEvents = kevent(_queueFD, &event, 1, &eventData, 1, &timeout);
if (nEvents < 0 || eventData.flags == EV_ERROR)
{
try
{
FileImpl::handleLastErrorImpl(owner().directory().path());
}
catch (Poco::Exception& exc)
{
owner().scanError(&owner(), exc);
}
}
else if (nEvents > 0 || ((owner().eventMask() & DirectoryWatcher::DW_ITEM_MODIFIED) && lastScan.isElapsed(owner().scanInterval()*1000000)))
{
ItemInfoMap newEntries;
scan(newEntries);
compare(entries, newEntries);
std::swap(entries, newEntries);
lastScan.update();
}
}
}
void stop()
{
_stopped.store(true, std::memory_order_relaxed);
}
bool supportsMoveEvents() const
{
return false;
}
private:
int _queueFD;
int _dirFD;
std::atomic<bool> _stopped;
};
#else
class PollingDirectoryWatcherStrategy: public DirectoryWatcherStrategy
{
public:
PollingDirectoryWatcherStrategy(DirectoryWatcher& owner):
DirectoryWatcherStrategy(owner)
{
}
~PollingDirectoryWatcherStrategy()
{
}
void run()
{
ItemInfoMap entries;
scan(entries);
while (!_stopped.tryWait(1000*owner().scanInterval()))
{
try
{
ItemInfoMap newEntries;
scan(newEntries);
compare(entries, newEntries);
std::swap(entries, newEntries);
}
catch (Poco::Exception& exc)
{
owner().scanError(&owner(), exc);
}
}
}
void stop()
{
_stopped.set();
}
bool supportsMoveEvents() const
{
return false;
}
private:
Poco::Event _stopped;
};
#endif
DirectoryWatcher::DirectoryWatcher(const std::string& path, int eventMask, int scanInterval):
_directory(path),
_eventMask(eventMask),
_scanInterval(scanInterval)
{
init();
}
DirectoryWatcher::DirectoryWatcher(const Poco::File& directory, int eventMask, int scanInterval):
_directory(directory),
_eventMask(eventMask),
_scanInterval(scanInterval)
{
init();
}
DirectoryWatcher::~DirectoryWatcher()
{
try
{
stop();
delete _pStrategy;
}
catch (...)
{
poco_unexpected();
}
}
void DirectoryWatcher::suspendEvents()
{
poco_assert (_eventsSuspended > 0);
_eventsSuspended--;
}
void DirectoryWatcher::resumeEvents()
{
_eventsSuspended++;
}
void DirectoryWatcher::init()
{
if (!_directory.exists())
throw Poco::FileNotFoundException(_directory.path());
if (!_directory.isDirectory())
throw Poco::InvalidArgumentException("not a directory", _directory.path());
#if POCO_OS == POCO_OS_WINDOWS_NT
_pStrategy = new WindowsDirectoryWatcherStrategy(*this);
#elif POCO_OS == POCO_OS_LINUX || POCO_OS == POCO_OS_ANDROID
_pStrategy = new LinuxDirectoryWatcherStrategy(*this);
#elif POCO_OS == POCO_OS_MAC_OS_X || POCO_OS == POCO_OS_FREE_BSD
_pStrategy = new BSDDirectoryWatcherStrategy(*this);
#else
_pStrategy = new PollingDirectoryWatcherStrategy(*this);
#endif
_thread.start(*this);
}
void DirectoryWatcher::run()
{
_pStrategy->run();
}
void DirectoryWatcher::stop()
{
_pStrategy->stop();
_thread.join();
}
bool DirectoryWatcher::supportsMoveEvents() const
{
return _pStrategy->supportsMoveEvents();
}
} // namespace Poco
#endif // POCO_NO_INOTIFY

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54480)
SET(VERSION_REVISION 54481)
SET(VERSION_MAJOR 23)
SET(VERSION_MINOR 11)
SET(VERSION_MINOR 12)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 13adae0e42fd48de600486fc5d4b64d39f80c43e)
SET(VERSION_DESCRIBE v23.11.1.1-testing)
SET(VERSION_STRING 23.11.1.1)
SET(VERSION_GITHASH 05bc8ef1e02b9c7332f08091775b255d191341bf)
SET(VERSION_DESCRIBE v23.12.1.1-testing)
SET(VERSION_STRING 23.12.1.1)
# end of autochange

16
cmake/target.cmake
View File

@ -42,10 +42,8 @@ if (CMAKE_CROSSCOMPILING)
if (ARCH_AARCH64)
# FIXME: broken dependencies
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_SENTRY OFF CACHE INTERNAL "")
elseif (ARCH_PPC64LE)
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_SENTRY OFF CACHE INTERNAL "")
elseif (ARCH_RISCV64)
# RISC-V support is preliminary
set (GLIBC_COMPATIBILITY OFF CACHE INTERNAL "")
@ -73,19 +71,5 @@ if (CMAKE_CROSSCOMPILING)
message (FATAL_ERROR "Trying to cross-compile to unsupported system: ${CMAKE_SYSTEM_NAME}!")
endif ()
if (USE_MUSL)
# use of undeclared identifier 'PTHREAD_RECURSIVE_MUTEX_INITIALIZER_NP'
set (ENABLE_SENTRY OFF CACHE INTERNAL "")
set (ENABLE_ODBC OFF CACHE INTERNAL "")
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_HDFS OFF CACHE INTERNAL "")
set (ENABLE_EMBEDDED_COMPILER OFF CACHE INTERNAL "")
# use of drand48_data
set (ENABLE_AZURE_BLOB_STORAGE OFF CACHE INTERNAL "")
endif ()
# Don't know why but CXX_STANDARD doesn't work for cross-compilation
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++20")
message (STATUS "Cross-compiling for target: ${CMAKE_CXX_COMPILE_TARGET}")
endif ()

3
contrib/CMakeLists.txt vendored
View File

@ -135,9 +135,9 @@ add_contrib (libuv-cmake libuv)
add_contrib (liburing-cmake liburing)
add_contrib (amqpcpp-cmake AMQP-CPP) # requires: libuv
add_contrib (cassandra-cmake cassandra) # requires: libuv
if (NOT OS_DARWIN)
add_contrib (curl-cmake curl)
add_contrib (azure-cmake azure) # requires: curl
if (NOT OS_DARWIN)
add_contrib (sentry-native-cmake sentry-native) # requires: curl
endif()
add_contrib (fmtlib-cmake fmtlib)
@ -156,6 +156,7 @@ add_contrib (nuraft-cmake NuRaft)
add_contrib (fast_float-cmake fast_float)
add_contrib (datasketches-cpp-cmake datasketches-cpp)
add_contrib (incbin-cmake incbin)
add_contrib (sqids-cpp-cmake sqids-cpp)
option(ENABLE_NLP "Enable NLP functions support" ${ENABLE_LIBRARIES})
if (ENABLE_NLP)

2
contrib/azure vendored

@ -1 +1 @@
Subproject commit 096049bf24fffafcaccc132b9367694532716731
Subproject commit 352ff0a61cb319ac1cc38c4058443ddf70147530

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

@ -10,7 +10,7 @@ set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/curl")
set (SRCS
"${LIBRARY_DIR}/lib/altsvc.c"
"${LIBRARY_DIR}/lib/amigaos.c"
"${LIBRARY_DIR}/lib/asyn-thread.c"
"${LIBRARY_DIR}/lib/asyn-ares.c"
"${LIBRARY_DIR}/lib/base64.c"
"${LIBRARY_DIR}/lib/bufq.c"
"${LIBRARY_DIR}/lib/bufref.c"
@ -165,13 +165,14 @@ target_compile_definitions (_curl PRIVATE
libcurl_EXPORTS
OS="${CMAKE_SYSTEM_NAME}"
)
target_include_directories (_curl SYSTEM PUBLIC
"${LIBRARY_DIR}/include"
"${LIBRARY_DIR}/lib"
. # curl_config.h
)
target_link_libraries (_curl PRIVATE OpenSSL::SSL)
target_link_libraries (_curl PRIVATE OpenSSL::SSL ch_contrib::c-ares)
# The library is large - avoid bloat (XXX: is it?)
if (OMIT_HEAVY_DEBUG_SYMBOLS)

1
contrib/curl-cmake/curl_config.h
View File

@ -50,3 +50,4 @@
#define ENABLE_IPV6
#define USE_OPENSSL
#define USE_THREADS_POSIX
#define USE_ARES

2
contrib/libhdfs3 vendored

@ -1 +1 @@
Subproject commit bdcb91354b1c05b21e73043a112a6f1e3b013497
Subproject commit b9598e6016720a7c088bfe85ce1fa0410f9d2103

5
contrib/libhdfs3-cmake/CMakeLists.txt
View File

@ -26,6 +26,11 @@ ADD_DEFINITIONS(-D__STDC_FORMAT_MACROS)
ADD_DEFINITIONS(-D_GNU_SOURCE)
ADD_DEFINITIONS(-D_GLIBCXX_USE_NANOSLEEP)
ADD_DEFINITIONS(-DHAVE_NANOSLEEP)
if (USE_MUSL)
ADD_DEFINITIONS(-DSTRERROR_R_RETURN_INT)
endif ()
set(HAVE_STEADY_CLOCK 1)
set(HAVE_NESTED_EXCEPTION 1)
SET(HAVE_BOOST_CHRONO 0)

2
contrib/librdkafka vendored

@ -1 +1 @@
Subproject commit 6f3b483426a8c8ec950e27e446bec175cf8b553f
Subproject commit 2d2aab6f5b79db1cfca15d7bf0dee75d00d82082

4
contrib/libxml2-cmake/linux_x86_64/include/libxml/xmlversion.h
View File

@ -270,7 +270,7 @@ XMLPUBFUN void XMLCALL xmlCheckVersion(int version);
*
* Whether iconv support is available
*/
#if 1
#if 0
#define LIBXML_ICONV_ENABLED
#endif
@ -499,5 +499,3 @@ XMLPUBFUN void XMLCALL xmlCheckVersion(int version);
}
#endif /* __cplusplus */
#endif

2
contrib/llvm-project vendored

@ -1 +1 @@
Subproject commit e7b8befca85c8b847614432dba250c22d35fbae0
Subproject commit 1834e42289c58402c804a87be4d489892b88f3ec

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

@ -117,7 +117,7 @@ endif()
add_definitions(-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX)
if (OS_LINUX OR OS_FREEBSD)
if ((OS_LINUX OR OS_FREEBSD) AND NOT USE_MUSL)
add_definitions(-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX)
endif()

2
contrib/sentry-native vendored

@ -1 +1 @@
Subproject commit ae10fb8c224c3f41571446e1ed7fd57b9e5e366b
Subproject commit bc359f86cbf0f73f6fd4b6bfb4ede0c1f8c9400f

3
contrib/sentry-native-cmake/CMakeLists.txt
View File

@ -13,6 +13,7 @@ set (SRC_DIR "${ClickHouse_SOURCE_DIR}/contrib/sentry-native")
set (SRCS
${SRC_DIR}/vendor/mpack.c
${SRC_DIR}/vendor/stb_sprintf.c
${SRC_DIR}/src/sentry_alloc.c
${SRC_DIR}/src/sentry_backend.c
${SRC_DIR}/src/sentry_core.c
@ -21,6 +22,7 @@ set (SRCS
${SRC_DIR}/src/sentry_json.c
${SRC_DIR}/src/sentry_logger.c
${SRC_DIR}/src/sentry_options.c
${SRC_DIR}/src/sentry_os.c
${SRC_DIR}/src/sentry_random.c
${SRC_DIR}/src/sentry_ratelimiter.c
${SRC_DIR}/src/sentry_scope.c
@ -29,6 +31,7 @@ set (SRCS
${SRC_DIR}/src/sentry_string.c
${SRC_DIR}/src/sentry_sync.c
${SRC_DIR}/src/sentry_transport.c
${SRC_DIR}/src/sentry_tracing.c
${SRC_DIR}/src/sentry_utils.c
${SRC_DIR}/src/sentry_uuid.c
${SRC_DIR}/src/sentry_value.c

1
contrib/sqids-cpp vendored Submodule

@ -0,0 +1 @@
Subproject commit 3756e537d4d48cc0dd4176801fe19f99601439b0

14
contrib/sqids-cpp-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,14 @@
option(ENABLE_SQIDS "Enable sqids support" ${ENABLE_LIBRARIES})
if ((NOT ENABLE_SQIDS))
message (STATUS "Not using sqids")
return()
endif()
set (SQIDS_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/sqids-cpp")
set (SQIDS_INCLUDE_DIR "${SQIDS_SOURCE_DIR}/include")
add_library(_sqids INTERFACE)
target_include_directories(_sqids SYSTEM INTERFACE ${SQIDS_INCLUDE_DIR})
add_library(ch_contrib::sqids ALIAS _sqids)
target_compile_definitions(_sqids INTERFACE ENABLE_SQIDS)

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

@ -1,7 +1,7 @@
option (ENABLE_ODBC "Enable ODBC library" ${ENABLE_LIBRARIES})
if (NOT OS_LINUX)
if (NOT OS_LINUX OR USE_MUSL)
if (ENABLE_ODBC)
message(STATUS "ODBC is only supported on Linux")
message(STATUS "ODBC is only supported on Linux with dynamic linking")
endif()
set (ENABLE_ODBC OFF CACHE INTERNAL "")
endif ()

5
docker/images.json
View File

@ -125,6 +125,7 @@
"docker/test/server-jepsen",
"docker/test/sqllogic",
"docker/test/sqltest",
"docker/test/clickbench",
"docker/test/stateless"
]
},
@ -145,6 +146,10 @@
"name": "clickhouse/server-jepsen-test",
"dependent": []
},
"docker/test/clickbench": {
"name": "clickhouse/clickbench",
"dependent": []
},
"docker/test/install/deb": {
"name": "clickhouse/install-deb-test",
"dependent": []

25
docker/keeper/Dockerfile
View File

@ -34,8 +34,9 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.10.5.20"
ARG VERSION="23.11.2.11"
ARG PACKAGES="clickhouse-keeper"
ARG DIRECT_DOWNLOAD_URLS=""
# user/group precreated explicitly with fixed uid/gid on purpose.
# It is especially important for rootless containers: in that case entrypoint
@ -47,15 +48,27 @@ ARG PACKAGES="clickhouse-keeper"
ARG TARGETARCH
RUN arch=${TARGETARCH:-amd64} \
&& for package in ${PACKAGES}; do \
( \
&& cd /tmp && rm -f /tmp/*tgz && rm -f /tmp/*tgz.sha512 |: \
&& if [ -n "${DIRECT_DOWNLOAD_URLS}" ]; then \
echo "installing from provided urls with tgz packages: ${DIRECT_DOWNLOAD_URLS}" \
&& for url in $DIRECT_DOWNLOAD_URLS; do \
echo "Get ${url}" \
&& wget -c -q "$url" \
; done \
else \
for package in ${PACKAGES}; do \
cd /tmp \
&& echo "Get ${REPOSITORY}/${package}-${VERSION}-${arch}.tgz" \
&& wget -c -q "${REPOSITORY}/${package}-${VERSION}-${arch}.tgz" \
&& wget -c -q "${REPOSITORY}/${package}-${VERSION}-${arch}.tgz.sha512" \
&& sed 's:/output/:/tmp/:' < "${package}-${VERSION}-${arch}.tgz.sha512" | sha512sum -c \
&& tar xvzf "${package}-${VERSION}-${arch}.tgz" --strip-components=1 -C / \
) \
; done \
fi \
&& cat *.tgz.sha512 | sha512sum -c \
&& for file in *.tgz; do \
if [ -f "$file" ]; then \
echo "Unpacking $file"; \
tar xvzf "$file" --strip-components=1 -C /; \
fi \
; done \
&& rm /tmp/*.tgz /install -r \
&& addgroup -S -g 101 clickhouse \

1
docker/packager/binary/Dockerfile
View File

@ -49,6 +49,7 @@ RUN curl https://sh.rustup.rs -sSf | bash -s -- -y && \
chmod 777 -R /rust && \
rustup toolchain install nightly-2023-07-04 && \
rustup default nightly-2023-07-04 && \
rustup toolchain remove stable && \
rustup component add rust-src && \
rustup target add x86_64-unknown-linux-gnu && \
rustup target add aarch64-unknown-linux-gnu && \

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

@ -149,7 +149,7 @@ then
mkdir -p "$PERF_OUTPUT"
cp -r ../tests/performance "$PERF_OUTPUT"
cp -r ../tests/config/top_level_domains "$PERF_OUTPUT"
cp -r ../docker/test/performance-comparison/config "$PERF_OUTPUT" ||:
cp -r ../tests/performance/scripts/config "$PERF_OUTPUT" ||:
for SRC in /output/clickhouse*; do
# Copy all clickhouse* files except packages and bridges
[[ "$SRC" != *.* ]] && [[ "$SRC" != *-bridge ]] && \
@ -160,7 +160,7 @@ then
ln -sf clickhouse "$PERF_OUTPUT"/clickhouse-keeper
fi
cp -r ../docker/test/performance-comparison "$PERF_OUTPUT"/scripts ||:
cp -r ../tests/performance/scripts "$PERF_OUTPUT"/scripts ||:
prepare_combined_output "$PERF_OUTPUT"
# We have to know the revision that corresponds to this binary build.

9
docker/packager/packager
View File

@ -145,6 +145,7 @@ def parse_env_variables(
RISCV_SUFFIX = "-riscv64"
S390X_SUFFIX = "-s390x"
AMD64_COMPAT_SUFFIX = "-amd64-compat"
AMD64_MUSL_SUFFIX = "-amd64-musl"
result = []
result.append("OUTPUT_DIR=/output")
@ -163,6 +164,7 @@ def parse_env_variables(
is_cross_s390x = compiler.endswith(S390X_SUFFIX)
is_cross_freebsd = compiler.endswith(FREEBSD_SUFFIX)
is_amd64_compat = compiler.endswith(AMD64_COMPAT_SUFFIX)
is_amd64_musl = compiler.endswith(AMD64_MUSL_SUFFIX)
if is_cross_darwin:
cc = compiler[: -len(DARWIN_SUFFIX)]
@ -232,6 +234,12 @@ def parse_env_variables(
cc = compiler[: -len(AMD64_COMPAT_SUFFIX)]
result.append("DEB_ARCH=amd64")
cmake_flags.append("-DNO_SSE3_OR_HIGHER=1")
elif is_amd64_musl:
cc = compiler[: -len(AMD64_MUSL_SUFFIX)]
result.append("DEB_ARCH=amd64")
cmake_flags.append(
"-DCMAKE_TOOLCHAIN_FILE=/build/cmake/linux/toolchain-x86_64-musl.cmake"
)
else:
cc = compiler
result.append("DEB_ARCH=amd64")
@ -396,6 +404,7 @@ def parse_args() -> argparse.Namespace:
"clang-17-riscv64",
"clang-17-s390x",
"clang-17-amd64-compat",
"clang-17-amd64-musl",
"clang-17-freebsd",
),
default="clang-17",

28
docker/server/Dockerfile.alpine
View File

@ -32,8 +32,9 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.10.5.20"
ARG VERSION="23.11.2.11"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
ARG DIRECT_DOWNLOAD_URLS=""
# user/group precreated explicitly with fixed uid/gid on purpose.
# It is especially important for rootless containers: in that case entrypoint
@ -43,15 +44,26 @@ ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# The same uid / gid (101) is used both for alpine and ubuntu.
RUN arch=${TARGETARCH:-amd64} \
&& for package in ${PACKAGES}; do \
( \
cd /tmp \
&& echo "Get ${REPOSITORY}/${package}-${VERSION}-${arch}.tgz" \
&& cd /tmp \
&& if [ -n "${DIRECT_DOWNLOAD_URLS}" ]; then \
echo "installing from provided urls with tgz packages: ${DIRECT_DOWNLOAD_URLS}" \
&& for url in $DIRECT_DOWNLOAD_URLS; do \
echo "Get ${url}" \
&& wget -c -q "$url" \
; done \
else \
for package in ${PACKAGES}; do \
echo "Get ${REPOSITORY}/${package}-${VERSION}-${arch}.tgz" \
&& wget -c -q "${REPOSITORY}/${package}-${VERSION}-${arch}.tgz" \
&& wget -c -q "${REPOSITORY}/${package}-${VERSION}-${arch}.tgz.sha512" \
&& sed 's:/output/:/tmp/:' < "${package}-${VERSION}-${arch}.tgz.sha512" | sha512sum -c \
&& tar xvzf "${package}-${VERSION}-${arch}.tgz" --strip-components=1 -C / \
) \
; done \
fi \
&& cat *.tgz.sha512 | sed 's:/output/:/tmp/:' | sha512sum -c \
&& for file in *.tgz; do \
if [ -f "$file" ]; then \
echo "Unpacking $file"; \
tar xvzf "$file" --strip-components=1 -C /; \
fi \
; done \
&& rm /tmp/*.tgz /install -r \
&& addgroup -S -g 101 clickhouse \

17
docker/server/Dockerfile.ubuntu
View File

@ -30,13 +30,14 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
ARG VERSION="23.10.5.20"
ARG VERSION="23.11.2.11"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# set non-empty deb_location_url url to create a docker image
# from debs created by CI build, for example:
# docker build . --network host --build-arg version="21.4.1.6282" --build-arg deb_location_url="https://..." -t ...
ARG deb_location_url=""
ARG DIRECT_DOWNLOAD_URLS=""
# set non-empty single_binary_location_url to create docker image
# from a single binary url (useful for non-standard builds - with sanitizers, for arm64).
@ -44,6 +45,18 @@ ARG single_binary_location_url=""
ARG TARGETARCH
# install from direct URL
RUN if [ -n "${DIRECT_DOWNLOAD_URLS}" ]; then \
echo "installing from custom predefined urls with deb packages: ${DIRECT_DOWNLOAD_URLS}" \
&& rm -rf /tmp/clickhouse_debs \
&& mkdir -p /tmp/clickhouse_debs \
&& for url in $DIRECT_DOWNLOAD_URLS; do \
wget --progress=bar:force:noscroll "$url" -P /tmp/clickhouse_debs || exit 1 \
; done \
&& dpkg -i /tmp/clickhouse_debs/*.deb \
&& rm -rf /tmp/* ; \
fi
# install from a web location with deb packages
RUN arch="${TARGETARCH:-amd64}" \
&& if [ -n "${deb_location_url}" ]; then \
@ -83,7 +96,7 @@ RUN if ! clickhouse local -q "SELECT ''" > /dev/null 2>&1; then \
&& GNUPGHOME="$GNUPGHOME" gpg --no-default-keyring \
--keyring /usr/share/keyrings/clickhouse-keyring.gpg \
--keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 8919F6BD2B48D754 \
&& rm -r "$GNUPGHOME" \
&& rm -rf "$GNUPGHOME" \
&& chmod +r /usr/share/keyrings/clickhouse-keyring.gpg \
&& echo "${REPOSITORY}" > /etc/apt/sources.list.d/clickhouse.list \
&& echo "installing from repository: ${REPOSITORY}" \

1
docker/test/base/Dockerfile
View File

@ -12,6 +12,7 @@ RUN apt-get update \
ripgrep \
zstd \
locales \
sudo \
--yes --no-install-recommends
# Sanitizer options for services (clickhouse-server)

2
docker/test/base/setup_export_logs.sh
View File

@ -21,7 +21,7 @@ EXTRA_ORDER_BY_COLUMNS=${EXTRA_ORDER_BY_COLUMNS:-"check_name, "}
# trace_log needs more columns for symbolization
EXTRA_COLUMNS_TRACE_LOG="${EXTRA_COLUMNS} symbols Array(LowCardinality(String)), lines Array(LowCardinality(String)), "
EXTRA_COLUMNS_EXPRESSION_TRACE_LOG="${EXTRA_COLUMNS_EXPRESSION}, arrayMap(x -> toLowCardinality(demangle(addressToSymbol(x))), trace) AS symbols, arrayMap(x -> toLowCardinality(addressToLine(x)), trace) AS lines"
EXTRA_COLUMNS_EXPRESSION_TRACE_LOG="${EXTRA_COLUMNS_EXPRESSION}, arrayMap(x -> demangle(addressToSymbol(x)), trace)::Array(LowCardinality(String)) AS symbols, arrayMap(x -> addressToLine(x), trace)::Array(LowCardinality(String)) AS lines"
function __set_connection_args

10
docker/test/clickbench/Dockerfile Normal file
View File

@ -0,0 +1,10 @@
ARG FROM_TAG=latest
FROM clickhouse/test-base:$FROM_TAG
ENV TZ=Europe/Amsterdam
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
COPY *.sh /
COPY *.sql /
CMD ["/bin/bash", "/run.sh"]

112
docker/test/clickbench/create.sql Normal file
View File

@ -0,0 +1,112 @@
ATTACH TABLE hits UUID 'c449dfbf-ba06-4d13-abec-8396559eb955'
(
WatchID BIGINT NOT NULL,
JavaEnable SMALLINT NOT NULL,
Title TEXT NOT NULL,
GoodEvent SMALLINT NOT NULL,
EventTime TIMESTAMP NOT NULL,
EventDate Date NOT NULL,
CounterID INTEGER NOT NULL,
ClientIP INTEGER NOT NULL,
RegionID INTEGER NOT NULL,
UserID BIGINT NOT NULL,
CounterClass SMALLINT NOT NULL,
OS SMALLINT NOT NULL,
UserAgent SMALLINT NOT NULL,
URL TEXT NOT NULL,
Referer TEXT NOT NULL,
IsRefresh SMALLINT NOT NULL,
RefererCategoryID SMALLINT NOT NULL,
RefererRegionID INTEGER NOT NULL,
URLCategoryID SMALLINT NOT NULL,
URLRegionID INTEGER NOT NULL,
ResolutionWidth SMALLINT NOT NULL,
ResolutionHeight SMALLINT NOT NULL,
ResolutionDepth SMALLINT NOT NULL,
FlashMajor SMALLINT NOT NULL,
FlashMinor SMALLINT NOT NULL,
FlashMinor2 TEXT NOT NULL,
NetMajor SMALLINT NOT NULL,
NetMinor SMALLINT NOT NULL,
UserAgentMajor SMALLINT NOT NULL,
UserAgentMinor VARCHAR(255) NOT NULL,
CookieEnable SMALLINT NOT NULL,
JavascriptEnable SMALLINT NOT NULL,
IsMobile SMALLINT NOT NULL,
MobilePhone SMALLINT NOT NULL,
MobilePhoneModel TEXT NOT NULL,
Params TEXT NOT NULL,
IPNetworkID INTEGER NOT NULL,
TraficSourceID SMALLINT NOT NULL,
SearchEngineID SMALLINT NOT NULL,
SearchPhrase TEXT NOT NULL,
AdvEngineID SMALLINT NOT NULL,
IsArtifical SMALLINT NOT NULL,
WindowClientWidth SMALLINT NOT NULL,
WindowClientHeight SMALLINT NOT NULL,
ClientTimeZone SMALLINT NOT NULL,
ClientEventTime TIMESTAMP NOT NULL,
SilverlightVersion1 SMALLINT NOT NULL,
SilverlightVersion2 SMALLINT NOT NULL,
SilverlightVersion3 INTEGER NOT NULL,
SilverlightVersion4 SMALLINT NOT NULL,
PageCharset TEXT NOT NULL,
CodeVersion INTEGER NOT NULL,
IsLink SMALLINT NOT NULL,
IsDownload SMALLINT NOT NULL,
IsNotBounce SMALLINT NOT NULL,
FUniqID BIGINT NOT NULL,
OriginalURL TEXT NOT NULL,
HID INTEGER NOT NULL,
IsOldCounter SMALLINT NOT NULL,
IsEvent SMALLINT NOT NULL,
IsParameter SMALLINT NOT NULL,
DontCountHits SMALLINT NOT NULL,
WithHash SMALLINT NOT NULL,
HitColor CHAR NOT NULL,
LocalEventTime TIMESTAMP NOT NULL,
Age SMALLINT NOT NULL,
Sex SMALLINT NOT NULL,
Income SMALLINT NOT NULL,
Interests SMALLINT NOT NULL,
Robotness SMALLINT NOT NULL,
RemoteIP INTEGER NOT NULL,
WindowName INTEGER NOT NULL,
OpenerName INTEGER NOT NULL,
HistoryLength SMALLINT NOT NULL,
BrowserLanguage TEXT NOT NULL,
BrowserCountry TEXT NOT NULL,
SocialNetwork TEXT NOT NULL,
SocialAction TEXT NOT NULL,
HTTPError SMALLINT NOT NULL,
SendTiming INTEGER NOT NULL,
DNSTiming INTEGER NOT NULL,
ConnectTiming INTEGER NOT NULL,
ResponseStartTiming INTEGER NOT NULL,
ResponseEndTiming INTEGER NOT NULL,
FetchTiming INTEGER NOT NULL,
SocialSourceNetworkID SMALLINT NOT NULL,
SocialSourcePage TEXT NOT NULL,
ParamPrice BIGINT NOT NULL,
ParamOrderID TEXT NOT NULL,
ParamCurrency TEXT NOT NULL,
ParamCurrencyID SMALLINT NOT NULL,
OpenstatServiceName TEXT NOT NULL,
OpenstatCampaignID TEXT NOT NULL,
OpenstatAdID TEXT NOT NULL,
OpenstatSourceID TEXT NOT NULL,
UTMSource TEXT NOT NULL,
UTMMedium TEXT NOT NULL,
UTMCampaign TEXT NOT NULL,
UTMContent TEXT NOT NULL,
UTMTerm TEXT NOT NULL,
FromTag TEXT NOT NULL,
HasGCLID SMALLINT NOT NULL,
RefererHash BIGINT NOT NULL,
URLHash BIGINT NOT NULL,
CLID INTEGER NOT NULL,
PRIMARY KEY (CounterID, EventDate, UserID, EventTime, WatchID)
)
ENGINE = MergeTree
SETTINGS disk = disk(type = cache, path = '/dev/shm/clickhouse/', max_size = '16G',
disk = disk(type = web, endpoint = 'https://clickhouse-datasets-web.s3.us-east-1.amazonaws.com/'));

43
docker/test/clickbench/queries.sql Normal file
View File

@ -0,0 +1,43 @@
SELECT COUNT(*) FROM hits;
SELECT COUNT(*) FROM hits WHERE AdvEngineID <> 0;
SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM hits;
SELECT AVG(UserID) FROM hits;
SELECT COUNT(DISTINCT UserID) FROM hits;
SELECT COUNT(DISTINCT SearchPhrase) FROM hits;
SELECT MIN(EventDate), MAX(EventDate) FROM hits;
SELECT AdvEngineID, COUNT(*) FROM hits WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC;
SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM hits GROUP BY RegionID ORDER BY u DESC LIMIT 10;
SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM hits GROUP BY RegionID ORDER BY c DESC LIMIT 10;
SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
SELECT SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT UserID, COUNT(*) FROM hits GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase LIMIT 10;
SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, m, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID FROM hits WHERE UserID = 435090932899640449;
SELECT COUNT(*) FROM hits WHERE URL LIKE '%google%';
SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM hits WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT SearchPhrase, MIN(URL), MIN(Title), COUNT(*) AS c, COUNT(DISTINCT UserID) FROM hits WHERE Title LIKE '%Google%' AND URL NOT LIKE '%.google.%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT * FROM hits WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10;
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10;
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10;
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10;
SELECT CounterID, AVG(length(URL)) AS l, COUNT(*) AS c FROM hits WHERE URL <> '' GROUP BY CounterID HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
SELECT REGEXP_REPLACE(Referer, '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length(Referer)) AS l, COUNT(*) AS c, MIN(Referer) FROM hits WHERE Referer <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
SELECT SUM(ResolutionWidth), SUM(ResolutionWidth + 1), SUM(ResolutionWidth + 2), SUM(ResolutionWidth + 3), SUM(ResolutionWidth + 4), SUM(ResolutionWidth + 5), SUM(ResolutionWidth + 6), SUM(ResolutionWidth + 7), SUM(ResolutionWidth + 8), SUM(ResolutionWidth + 9), SUM(ResolutionWidth + 10), SUM(ResolutionWidth + 11), SUM(ResolutionWidth + 12), SUM(ResolutionWidth + 13), SUM(ResolutionWidth + 14), SUM(ResolutionWidth + 15), SUM(ResolutionWidth + 16), SUM(ResolutionWidth + 17), SUM(ResolutionWidth + 18), SUM(ResolutionWidth + 19), SUM(ResolutionWidth + 20), SUM(ResolutionWidth + 21), SUM(ResolutionWidth + 22), SUM(ResolutionWidth + 23), SUM(ResolutionWidth + 24), SUM(ResolutionWidth + 25), SUM(ResolutionWidth + 26), SUM(ResolutionWidth + 27), SUM(ResolutionWidth + 28), SUM(ResolutionWidth + 29), SUM(ResolutionWidth + 30), SUM(ResolutionWidth + 31), SUM(ResolutionWidth + 32), SUM(ResolutionWidth + 33), SUM(ResolutionWidth + 34), SUM(ResolutionWidth + 35), SUM(ResolutionWidth + 36), SUM(ResolutionWidth + 37), SUM(ResolutionWidth + 38), SUM(ResolutionWidth + 39), SUM(ResolutionWidth + 40), SUM(ResolutionWidth + 41), SUM(ResolutionWidth + 42), SUM(ResolutionWidth + 43), SUM(ResolutionWidth + 44), SUM(ResolutionWidth + 45), SUM(ResolutionWidth + 46), SUM(ResolutionWidth + 47), SUM(ResolutionWidth + 48), SUM(ResolutionWidth + 49), SUM(ResolutionWidth + 50), SUM(ResolutionWidth + 51), SUM(ResolutionWidth + 52), SUM(ResolutionWidth + 53), SUM(ResolutionWidth + 54), SUM(ResolutionWidth + 55), SUM(ResolutionWidth + 56), SUM(ResolutionWidth + 57), SUM(ResolutionWidth + 58), SUM(ResolutionWidth + 59), SUM(ResolutionWidth + 60), SUM(ResolutionWidth + 61), SUM(ResolutionWidth + 62), SUM(ResolutionWidth + 63), SUM(ResolutionWidth + 64), SUM(ResolutionWidth + 65), SUM(ResolutionWidth + 66), SUM(ResolutionWidth + 67), SUM(ResolutionWidth + 68), SUM(ResolutionWidth + 69), SUM(ResolutionWidth + 70), SUM(ResolutionWidth + 71), SUM(ResolutionWidth + 72), SUM(ResolutionWidth + 73), SUM(ResolutionWidth + 74), SUM(ResolutionWidth + 75), SUM(ResolutionWidth + 76), SUM(ResolutionWidth + 77), SUM(ResolutionWidth + 78), SUM(ResolutionWidth + 79), SUM(ResolutionWidth + 80), SUM(ResolutionWidth + 81), SUM(ResolutionWidth + 82), SUM(ResolutionWidth + 83), SUM(ResolutionWidth + 84), SUM(ResolutionWidth + 85), SUM(ResolutionWidth + 86), SUM(ResolutionWidth + 87), SUM(ResolutionWidth + 88), SUM(ResolutionWidth + 89) FROM hits;
SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT URL, COUNT(*) AS c FROM hits GROUP BY URL ORDER BY c DESC LIMIT 10;
SELECT 1, URL, COUNT(*) AS c FROM hits GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
SELECT ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3, COUNT(*) AS c FROM hits GROUP BY ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3 ORDER BY c DESC LIMIT 10;
SELECT URL, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND URL <> '' GROUP BY URL ORDER BY PageViews DESC LIMIT 10;
SELECT Title, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND Title <> '' GROUP BY Title ORDER BY PageViews DESC LIMIT 10;
SELECT URL, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND IsLink <> 0 AND IsDownload = 0 GROUP BY URL ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
SELECT TraficSourceID, SearchEngineID, AdvEngineID, CASE WHEN (SearchEngineID = 0 AND AdvEngineID = 0) THEN Referer ELSE '' END AS Src, URL AS Dst, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 GROUP BY TraficSourceID, SearchEngineID, AdvEngineID, Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
SELECT URLHash, EventDate, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND TraficSourceID IN (-1, 6) AND RefererHash = 3594120000172545465 GROUP BY URLHash, EventDate ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
SELECT WindowClientWidth, WindowClientHeight, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND DontCountHits = 0 AND URLHash = 2868770270353813622 GROUP BY WindowClientWidth, WindowClientHeight ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
SELECT DATE_TRUNC('minute', EventTime) AS M, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-14' AND EventDate <= '2013-07-15' AND IsRefresh = 0 AND DontCountHits = 0 GROUP BY DATE_TRUNC('minute', EventTime) ORDER BY DATE_TRUNC('minute', EventTime) LIMIT 10 OFFSET 1000;

79
docker/test/clickbench/run.sh Executable file
View File

@ -0,0 +1,79 @@
#!/bin/bash
SCRIPT_PID=$!
(sleep 1200 && kill -9 $SCRIPT_PID) &
# shellcheck disable=SC1091
source /setup_export_logs.sh
# fail on errors, verbose and export all env variables
set -e -x -a
dpkg -i package_folder/clickhouse-common-static_*.deb
dpkg -i package_folder/clickhouse-server_*.deb
dpkg -i package_folder/clickhouse-client_*.deb
# A directory for cache
mkdir /dev/shm/clickhouse
chown clickhouse:clickhouse /dev/shm/clickhouse
# Allow introspection functions, needed for sending the logs
echo "
profiles:
default:
allow_introspection_functions: 1
" > /etc/clickhouse-server/users.d/allow_introspection_functions.yaml
# Enable text_log
echo "
text_log:
" > /etc/clickhouse-server/config.d/text_log.yaml
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
clickhouse start
# Wait for the server to start, but not for too long.
for _ in {1..100}
do
clickhouse-client --query "SELECT 1" && break
sleep 1
done
setup_logs_replication
# Load the data
clickhouse-client --time < /create.sql
# Run the queries
set +x
TRIES=3
QUERY_NUM=1
while read -r query; do
echo -n "["
for i in $(seq 1 $TRIES); do
RES=$(clickhouse-client --query_id "q${QUERY_NUM}-${i}" --time --format Null --query "$query" --progress 0 2>&1 ||:)
echo -n "${RES}"
[[ "$i" != "$TRIES" ]] && echo -n ", "
echo "${QUERY_NUM},${i},${RES}" >> /test_output/test_results.tsv
done
echo "],"
QUERY_NUM=$((QUERY_NUM + 1))
done < /queries.sql
set -x
clickhouse-client --query "SELECT total_bytes FROM system.tables WHERE name = 'hits' AND database = 'default'"
clickhouse-client -q "system flush logs" ||:
stop_logs_replication
clickhouse stop
mv /var/log/clickhouse-server/* /test_output/
echo -e "success\tClickBench finished" > /test_output/check_status.tsv

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

@ -16,7 +16,7 @@ export LLVM_VERSION=${LLVM_VERSION:-17}
# it being undefined. Also read it as array so that we can pass an empty list
# of additional variable to cmake properly, and it doesn't generate an extra
# empty parameter.
# Read it as CMAKE_FLAGS to not lose exported FASTTEST_CMAKE_FLAGS on subsequential launch
# Read it as CMAKE_FLAGS to not lose exported FASTTEST_CMAKE_FLAGS on subsequent launch
read -ra CMAKE_FLAGS <<< "${FASTTEST_CMAKE_FLAGS:-}"
# Run only matching tests.
@ -197,7 +197,7 @@ function run_cmake
(
cd "$FASTTEST_BUILD"
cmake "$FASTTEST_SOURCE" -DCMAKE_CXX_COMPILER="clang++-${LLVM_VERSION}" -DCMAKE_C_COMPILER="clang-${LLVM_VERSION}" "${CMAKE_LIBS_CONFIG[@]}" "${CMAKE_FLAGS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/cmake_log.txt"
cmake "$FASTTEST_SOURCE" -DCMAKE_CXX_COMPILER="clang++-${LLVM_VERSION}" -DCMAKE_C_COMPILER="clang-${LLVM_VERSION}" -DCMAKE_TOOLCHAIN_FILE="${FASTTEST_SOURCE}/cmake/linux/toolchain-x86_64-musl.cmake" "${CMAKE_LIBS_CONFIG[@]}" "${CMAKE_FLAGS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/cmake_log.txt"
)
}

2
docker/test/integration/helper_container/Dockerfile
View File

@ -1,7 +1,7 @@
# docker build -t clickhouse/integration-helper .
# Helper docker container to run iptables without sudo
FROM alpine
FROM alpine:3.18
RUN apk add --no-cache -U iproute2 \
&& for bin in iptables iptables-restore iptables-save; \
do ln -sf xtables-nft-multi "/sbin/$bin"; \

2
docker/test/integration/runner/Dockerfile
View File

@ -74,7 +74,7 @@ RUN python3 -m pip install --no-cache-dir \
delta-spark==2.3.0 \
dict2xml \
dicttoxml \
docker \
docker==6.1.3 \
docker-compose==1.29.2 \
grpcio \
grpcio-tools \

14
docker/test/performance-comparison/Dockerfile
View File

@ -39,18 +39,8 @@ RUN apt-get update \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
COPY * /
COPY run.sh /
# Bind everything to one NUMA node, if there's more than one. Theoretically the
# node #0 should be less stable because of system interruptions. We bind
# randomly to node 1 or 0 to gather some statistics on that. We have to bind
# both servers and the tmpfs on which the database is stored. How to do it
# is unclear, but by default tmpfs uses
# 'process allocation policy', not sure which process but hopefully the one that
# writes to it, so just bind the downloader script as well.
# https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
# Double-escaped backslashes are a tribute to the engineering wonder of docker --
# it gives '/bin/sh: 1: [bash,: not found' otherwise.
CMD ["bash", "-c", "node=$((RANDOM % $(numactl --hardware | sed -n 's/^.*available:\\(.*\\)nodes.*$/\\1/p'))); echo Will bind to NUMA node $node; numactl --cpunodebind=$node --membind=$node /entrypoint.sh"]
CMD ["bash", "/run.sh"]
# docker run --network=host --volume <workspace>:/workspace --volume=<output>:/output -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/performance-comparison

18
docker/test/performance-comparison/run.sh Normal file
View File

@ -0,0 +1,18 @@
#!/bin/bash
entry="/usr/share/clickhouse-test/performance/scripts/entrypoint.sh"
[ ! -e "$entry" ] && echo "ERROR: test scripts are not found" && exit 1
# Bind everything to one NUMA node, if there's more than one. Theoretically the
# node #0 should be less stable because of system interruptions. We bind
# randomly to node 1 or 0 to gather some statistics on that. We have to bind
# both servers and the tmpfs on which the database is stored. How to do it
# is unclear, but by default tmpfs uses
# 'process allocation policy', not sure which process but hopefully the one that
# writes to it, so just bind the downloader script as well.
# https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
# Double-escaped backslashes are a tribute to the engineering wonder of docker --
# it gives '/bin/sh: 1: [bash,: not found' otherwise.
node=$(( RANDOM % $(numactl --hardware | sed -n 's/^.*available:\(.*\)nodes.*$/\1/p') ));
echo Will bind to NUMA node $node;
numactl --cpunodebind=$node --membind=$node $entry

5
docker/test/sqllogic/Dockerfile
View File

@ -20,7 +20,8 @@ RUN apt-get update --yes \
RUN pip3 install \
numpy \
pyodbc \
deepdiff
deepdiff \
sqlglot
ARG odbc_repo="https://github.com/ClickHouse/clickhouse-odbc.git"
@ -35,7 +36,7 @@ RUN git clone --recursive ${odbc_repo} \
&& odbcinst -i -s -l -f /clickhouse-odbc/packaging/odbc.ini.sample
ENV TZ=Europe/Amsterdam
ENV MAX_RUN_TIME=900
ENV MAX_RUN_TIME=9000
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
ARG sqllogic_test_repo="https://github.com/gregrahn/sqllogictest.git"

14
docker/test/sqllogic/run.sh
View File

@ -75,6 +75,20 @@ function run_tests()
cat /test_output/statements-test/check_status.tsv >> /test_output/check_status.tsv
cat /test_output/statements-test/test_results.tsv >> /test_output/test_results.tsv
tar -zcvf statements-check.tar.gz statements-test 1>/dev/null
mkdir -p /test_output/complete-test
/clickhouse-tests/sqllogic/runner.py \
--log-file /test_output/runner-complete-test.log \
--log-level info \
complete-test \
--input-dir /sqllogictest \
--out-dir /test_output/complete-test \
2>&1 \
| ts '%Y-%m-%d %H:%M:%S'
cat /test_output/complete-test/check_status.tsv >> /test_output/check_status.tsv
cat /test_output/complete-test/test_results.tsv >> /test_output/test_results.tsv
tar -zcvf complete-check.tar.gz complete-test 1>/dev/null
fi
}

18
docker/test/stateful/run.sh
View File

@ -24,6 +24,22 @@ azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
cache_policy=""
if [ $(( $(date +%-d) % 2 )) -eq 1 ]; then
cache_policy="SLRU"
else
cache_policy="LRU"
fi
echo "Using cache policy: $cache_policy"
if [ "$cache_policy" = "SLRU" ]; then
sudo cat /etc/clickhouse-server/config.d/storage_conf.xml \
| sed "s|<cache_policy>LRU</cache_policy>|<cache_policy>SLRU</cache_policy>|" \
> /etc/clickhouse-server/config.d/storage_conf.xml.tmp
mv /etc/clickhouse-server/config.d/storage_conf.xml.tmp /etc/clickhouse-server/config.d/storage_conf.xml
fi
function start()
{
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
@ -135,7 +151,7 @@ function run_tests()
set +e
if [[ -n "$USE_PARALLEL_REPLICAS" ]] && [[ "$USE_PARALLEL_REPLICAS" -eq 1 ]]; then
clickhouse-test --client="clickhouse-client --use_hedged_requests=0 --allow_experimental_parallel_reading_from_replicas=1 --parallel_replicas_for_non_replicated_merge_tree=1 \
clickhouse-test --client="clickhouse-client --allow_experimental_parallel_reading_from_replicas=1 --parallel_replicas_for_non_replicated_merge_tree=1 \
--max_parallel_replicas=100 --cluster_for_parallel_replicas='parallel_replicas'" \
-j 2 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --no-parallel-replicas --hung-check --print-time "${ADDITIONAL_OPTIONS[@]}" \
"$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt

4
docker/test/stateful/s3downloader
View File

@ -30,7 +30,7 @@ def build_url(base_url, dataset):
return os.path.join(base_url, dataset, "partitions", AVAILABLE_DATASETS[dataset])
def dowload_with_progress(url, path):
def download_with_progress(url, path):
logging.info("Downloading from %s to temp path %s", url, path)
for i in range(RETRIES_COUNT):
try:
@ -110,7 +110,7 @@ if __name__ == "__main__":
temp_archive_path = _get_temp_file_name()
try:
download_url_for_dataset = build_url(args.url_prefix, dataset)
dowload_with_progress(download_url_for_dataset, temp_archive_path)
download_with_progress(download_url_for_dataset, temp_archive_path)
unpack_to_clickhouse_directory(temp_archive_path, args.clickhouse_data_path)
except Exception as ex:
logging.info("Some exception occured %s", str(ex))

17
docker/test/stateless/run.sh
View File

@ -19,10 +19,14 @@ dpkg -i package_folder/clickhouse-common-static-dbg_*.deb
dpkg -i package_folder/clickhouse-server_*.deb
dpkg -i package_folder/clickhouse-client_*.deb
echo "$BUGFIX_VALIDATE_CHECK"
# Check that the tools are available under short names
if [[ -z "$BUGFIX_VALIDATE_CHECK" ]]; then
ch --query "SELECT 1" || exit 1
chl --query "SELECT 1" || exit 1
chc --version || exit 1
fi
ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
@ -46,6 +50,16 @@ fi
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
if [[ -n "$BUGFIX_VALIDATE_CHECK" ]] && [[ "$BUGFIX_VALIDATE_CHECK" -eq 1 ]]; then
sudo cat /etc/clickhouse-server/config.d/zookeeper.xml \
| sed "/<use_compression>1<\/use_compression>/d" \
> /etc/clickhouse-server/config.d/zookeeper.xml.tmp
sudo mv /etc/clickhouse-server/config.d/zookeeper.xml.tmp /etc/clickhouse-server/config.d/zookeeper.xml
# it contains some new settings, but we can safely remove it
rm /etc/clickhouse-server/users.d/s3_cache_new.xml
fi
# For flaky check we also enable thread fuzzer
if [ "$NUM_TRIES" -gt "1" ]; then
export THREAD_FUZZER_CPU_TIME_PERIOD_US=1000
@ -286,9 +300,6 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server2.log ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server2.log > /test_output/clickhouse-server2.log.zst ||:
# FIXME: remove once only github actions will be left
rm /var/log/clickhouse-server/clickhouse-server1.log
rm /var/log/clickhouse-server/clickhouse-server2.log
mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
mv /var/log/clickhouse-server/stderr2.log /test_output/ ||:
tar -chf /test_output/coordination1.tar /var/lib/clickhouse1/coordination ||:

31
docker/test/stress/run.sh
View File

@ -65,9 +65,27 @@ chmod 777 -R /var/lib/clickhouse
clickhouse-client --query "ATTACH DATABASE IF NOT EXISTS datasets ENGINE = Ordinary"
clickhouse-client --query "CREATE DATABASE IF NOT EXISTS test"
stop
mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.initial.log
# Randomize cache policies.
cache_policy=""
if [ $(( $(date +%-d) % 2 )) -eq 1 ]; then
cache_policy="SLRU"
else
cache_policy="LRU"
fi
echo "Using cache policy: $cache_policy"
if [ "$cache_policy" = "SLRU" ]; then
sudo cat /etc/clickhouse-server/config.d/storage_conf.xml \
| sed "s|<cache_policy>LRU</cache_policy>|<cache_policy>SLRU</cache_policy>|" \
> /etc/clickhouse-server/config.d/storage_conf.xml.tmp
mv /etc/clickhouse-server/config.d/storage_conf.xml.tmp /etc/clickhouse-server/config.d/storage_conf.xml
fi
start
clickhouse-client --query "SHOW TABLES FROM datasets"
@ -191,6 +209,19 @@ sudo cat /etc/clickhouse-server/config.d/logger_trace.xml \
> /etc/clickhouse-server/config.d/logger_trace.xml.tmp
mv /etc/clickhouse-server/config.d/logger_trace.xml.tmp /etc/clickhouse-server/config.d/logger_trace.xml
if [ "$cache_policy" = "SLRU" ]; then
sudo cat /etc/clickhouse-server/config.d/storage_conf.xml \
| sed "s|<cache_policy>LRU</cache_policy>|<cache_policy>SLRU</cache_policy>|" \
> /etc/clickhouse-server/config.d/storage_conf.xml.tmp
mv /etc/clickhouse-server/config.d/storage_conf.xml.tmp /etc/clickhouse-server/config.d/storage_conf.xml
fi
# Randomize async_load_databases
if [ $(( $(date +%-d) % 2 )) -eq 1 ]; then
sudo echo "<clickhouse><async_load_databases>true</async_load_databases></clickhouse>" \
> /etc/clickhouse-server/config.d/enable_async_load_databases.xml
fi
start
stress --hung-check --drop-databases --output-folder test_output --skip-func-tests "$SKIP_TESTS_OPTION" --global-time-limit 1200 \

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

@ -23,6 +23,7 @@ echo "Check submodules" | ts
./check-submodules |& tee /test_output/submodules_output.txt
echo "Check shell scripts with shellcheck" | ts
./shellcheck-run.sh |& tee /test_output/shellcheck_output.txt
/process_style_check_result.py || echo -e "failure\tCannot parse results" > /test_output/check_status.tsv
echo "Check help for changelog generator works" | ts
cd ../changelog || exit 1

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

@ -77,8 +77,10 @@ remove_keeper_config "create_if_not_exists" "[01]"
# it contains some new settings, but we can safely remove it
rm /etc/clickhouse-server/config.d/merge_tree.xml
rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
rm /etc/clickhouse-server/config.d/zero_copy_destructive_operations.xml
rm /etc/clickhouse-server/users.d/nonconst_timezone.xml
rm /etc/clickhouse-server/users.d/s3_cache_new.xml
rm /etc/clickhouse-server/users.d/replicated_ddl_entry.xml
start
stop
@ -114,8 +116,10 @@ sudo chgrp clickhouse /etc/clickhouse-server/config.d/s3_storage_policy_by_defau
# it contains some new settings, but we can safely remove it
rm /etc/clickhouse-server/config.d/merge_tree.xml
rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
rm /etc/clickhouse-server/config.d/zero_copy_destructive_operations.xml
rm /etc/clickhouse-server/users.d/nonconst_timezone.xml
rm /etc/clickhouse-server/users.d/s3_cache_new.xml
rm /etc/clickhouse-server/users.d/replicated_ddl_entry.xml
start

525
docs/changelogs/v23.11.1.2711-stable.md Normal file
View File

@ -0,0 +1,525 @@
---
sidebar_position: 1
sidebar_label: 2023
---
# 2023 Changelog
### ClickHouse release v23.11.1.2711-stable (05bc8ef1e02) FIXME as compared to v23.10.1.1976-stable (13adae0e42f)
#### Backward Incompatible Change
* Formatters `%l`/`%k`/`%c` in function `parseDateTime()` are now able to parse hours/months without leading zeros, e.g. `select parseDateTime('2023-11-26 8:14', '%F %k:%i')` now works. Set `parsedatetime_parse_without_leading_zeros = 0` to restore the previous behavior which required two digits. Function `formatDateTime` is now also able to print hours/months without leading zeros. This is controlled by setting `formatdatetime_format_without_leading_zeros` but off by default to not break existing use cases. [#55872](https://github.com/ClickHouse/ClickHouse/pull/55872) ([Azat Khuzhin](https://github.com/azat)).
* You can no longer use the aggregate function `avgWeighted` with arguments of type `Decimal`. Workaround: convert arguments to `Float64`. This closes [#43928](https://github.com/ClickHouse/ClickHouse/issues/43928). This closes [#31768](https://github.com/ClickHouse/ClickHouse/issues/31768). This closes [#56435](https://github.com/ClickHouse/ClickHouse/issues/56435). If you have used this function inside materialized views or projections with `Decimal` arguments, contact support@clickhouse.com. Fixed error in aggregate function `sumMap` and made it slower around 1.5..2 times. It does not matter because the function is garbage anyway. This closes [#54955](https://github.com/ClickHouse/ClickHouse/issues/54955). This closes [#53134](https://github.com/ClickHouse/ClickHouse/issues/53134). This closes [#55148](https://github.com/ClickHouse/ClickHouse/issues/55148). Fix a bug in function `groupArraySample` - it used the same random seed in case more than one aggregate state is generated in a query. [#56350](https://github.com/ClickHouse/ClickHouse/pull/56350) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The default ClickHouse server configuration file has enabled `access_management` (user manipulation by SQL queries) and `named_collection_control` (manipulation of named collection by SQL queries) for the `default` user by default. This closes [#56482](https://github.com/ClickHouse/ClickHouse/issues/56482). [#56619](https://github.com/ClickHouse/ClickHouse/pull/56619) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Multiple improvements for RESPECT/IGNORE NULLS. [#57189](https://github.com/ClickHouse/ClickHouse/pull/57189) ([Raúl Marín](https://github.com/Algunenano)).
* Remove optimization optimize_move_functions_out_of_any. [#57190](https://github.com/ClickHouse/ClickHouse/pull/57190) ([Raúl Marín](https://github.com/Algunenano)).
#### New Feature
* Added server setting `async_load_databases` for asynchronous loading of databases and tables. Speeds up the server start time. Applies to databases with Ordinary, Atomic and Replicated engines. Their tables load metadata asynchronously. Query to a table increases the priority of the load job and waits for it to be done. Added table `system.async_loader`. [#49351](https://github.com/ClickHouse/ClickHouse/pull/49351) ([Sergei Trifonov](https://github.com/serxa)).
* 1. Add function `extractPlainRanges` to `KeyCondition`. 2. Add some useful functions to `Range` 3. Add `PlainRanges` who represent a serious of ranges that ordered and no overlapping. 4. Add `NumbersRangedSource` who can accurately return user selected numbers. [#50909](https://github.com/ClickHouse/ClickHouse/pull/50909) ([JackyWoo](https://github.com/JackyWoo)).
* Add system table `blob_storage_log`. [#52918](https://github.com/ClickHouse/ClickHouse/pull/52918) ([vdimir](https://github.com/vdimir)).
* Use statistic to order prewhere conditions better. [#53240](https://github.com/ClickHouse/ClickHouse/pull/53240) ([Han Fei](https://github.com/hanfei1991)).
* Added a new aggregation function `groupArraySorted(n)(value)` which returns an array with the n first values from a field value sorted by itself. [#53562](https://github.com/ClickHouse/ClickHouse/pull/53562) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Added support for compression in keeper protocol. Can be enabled on clickhouse by using this flag `use_compression` inside `zookeeper`. resolves [#49507](https://github.com/ClickHouse/ClickHouse/issues/49507). [#54957](https://github.com/ClickHouse/ClickHouse/pull/54957) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Add ClickHouse setting to disable tunneling for HTTPS requests over HTTP proxy. [#55033](https://github.com/ClickHouse/ClickHouse/pull/55033) ([Arthur Passos](https://github.com/arthurpassos)).
* Introduce the feature `storage_metadata_write_full_object_key`. If it is set as `true` then metadata files are written with new format VERSION_FULL_OBJECT_KEY. With that format CH stores full remote object key in the metadata file. [#55566](https://github.com/ClickHouse/ClickHouse/pull/55566) ([Sema Checherinda](https://github.com/CheSema)).
* Add new settings and syntax to protect named collections' fields from being overridden. This is meant to prevent a malicious user from obtaining unauthorized access to secrets. [#55782](https://github.com/ClickHouse/ClickHouse/pull/55782) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Add `hostname` column to all system log tables;. [#55894](https://github.com/ClickHouse/ClickHouse/pull/55894) ([Bharat Nallan](https://github.com/bharatnc)).
* Add `CHECK ALL TABLES` query. [#56022](https://github.com/ClickHouse/ClickHouse/pull/56022) ([vdimir](https://github.com/vdimir)).
* Added function `fromDaysSinceYearZero()` which is similar to MySQL's `FROM_DAYS`. E.g. `SELECT fromDaysSinceYearZero(739136)` returns `2023-09-08`. [#56088](https://github.com/ClickHouse/ClickHouse/pull/56088) ([Joanna Hulboj](https://github.com/jh0x)).
* Implemented series period detect method using FFT in pocketFFT lib. [#56171](https://github.com/ClickHouse/ClickHouse/pull/56171) ([Bhavna Jindal](https://github.com/bhavnajindal)).
* Add an external Python tool to view backups and to extract information from them without using ClickHouse. [#56268](https://github.com/ClickHouse/ClickHouse/pull/56268) ([Vitaly Baranov](https://github.com/vitlibar)).
* ... [#56275](https://github.com/ClickHouse/ClickHouse/pull/56275) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* This pull request implements new setting called `preferred_projection_name`. If it is set to a non-empty string, the specified projection would be used if possible. [#56309](https://github.com/ClickHouse/ClickHouse/pull/56309) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* S3 adaptive timeout means that first attempt made with low send and receive timeouts. [#56314](https://github.com/ClickHouse/ClickHouse/pull/56314) ([Sema Checherinda](https://github.com/CheSema)).
* Add 4-letter command for yielding/resigning leadership (https://github.com/ClickHouse/ClickHouse/issues/56352). [#56354](https://github.com/ClickHouse/ClickHouse/pull/56354) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Added a new SQL function, "arrayRandomSample(arr, k)" which returns a sample of k elements from the input array. Similar functionality could previously be achieved only with less convenient syntax, e.g. "SELECT arrayReduce('groupArraySample(3)', range(10))". [#56416](https://github.com/ClickHouse/ClickHouse/pull/56416) ([Robert Schulze](https://github.com/rschu1ze)).
* Added support for `float16` type data to use in `.npy` files. Closes [#56344](https://github.com/ClickHouse/ClickHouse/issues/56344). [#56424](https://github.com/ClickHouse/ClickHouse/pull/56424) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Added system view `information_schema.statistics` for better compatibility with Tableau Online. [#56425](https://github.com/ClickHouse/ClickHouse/pull/56425) ([Serge Klochkov](https://github.com/slvrtrn)).
* Add function `getClientHTTPHeader` for fetching values header values set in the HTTP request. [#56488](https://github.com/ClickHouse/ClickHouse/pull/56488) ([凌涛](https://github.com/lingtaolf)).
* Add a new table function named `fuzzJSON` with rows containing perturbed versions of the source JSON string with random variations. [#56490](https://github.com/ClickHouse/ClickHouse/pull/56490) ([Julia Kartseva](https://github.com/jkartseva)).
* Add `system.symbols` table useful for introspection of the binary. [#56548](https://github.com/ClickHouse/ClickHouse/pull/56548) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add 4-letter command for yielding/resigning leadership. [#56620](https://github.com/ClickHouse/ClickHouse/pull/56620) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Configurable dashboards. Queries for charts are now loaded using a query, which by default uses a new `system.dashboards` table. [#56771](https://github.com/ClickHouse/ClickHouse/pull/56771) ([Sergei Trifonov](https://github.com/serxa)).
* Introduce `fileCluster` table function. [#56868](https://github.com/ClickHouse/ClickHouse/pull/56868) ([Andrey Zvonov](https://github.com/zvonand)).
* Add `_size` virtual column with file size in bytes to `s3/file/hdfs/url/azureBlobStorage` engines. [#57126](https://github.com/ClickHouse/ClickHouse/pull/57126) ([Kruglov Pavel](https://github.com/Avogar)).
* Expose the number of errors occurred on a server since last restart from the Prometheus endpoint. [#57209](https://github.com/ClickHouse/ClickHouse/pull/57209) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Added a new SQL function `sqid` to generate Sqids (https://sqids.org/), example: `SELECT sqid(125, 126)`. [#57442](https://github.com/ClickHouse/ClickHouse/pull/57442) ([awakeljw](https://github.com/awakeljw)).
#### Performance Improvement
* Support window functions parallel evaluation. Fixes [#34688](https://github.com/ClickHouse/ClickHouse/issues/34688). [#39631](https://github.com/ClickHouse/ClickHouse/pull/39631) ([Dmitry Novik](https://github.com/novikd)).
* Increase the default value of `max_concurrent_queries` from 100 to 1000. This makes sense when there is a large number of connecting clients, which are slowly sending or receiving data, so the server is not limited by CPU, or when the number of CPU cores is larger than 100. Also, enable the concurrency control by default, and set the desired number of query processing threads in total as twice the number of CPU cores. It improves performance in scenarios with a very large number of concurrent queries. [#46927](https://github.com/ClickHouse/ClickHouse/pull/46927) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fixed filtering by `IN(...)` condition for `Merge` table engine. [#54905](https://github.com/ClickHouse/ClickHouse/pull/54905) ([Nikita Taranov](https://github.com/nickitat)).
* An improvement which takes place when cache is full and there are big reads. [#55158](https://github.com/ClickHouse/ClickHouse/pull/55158) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add ability to disable checksums for S3 to avoid excessive input file read (this new behavior could be enabled with `s3_disable_checksum=true`). [#55559](https://github.com/ClickHouse/ClickHouse/pull/55559) ([Azat Khuzhin](https://github.com/azat)).
* Now we read synchronously from remote tables when data is in page cache (like we do for local tables). It is faster, doesn't require synchronisation inside thread pool, doesn't hesitate to do `seek`-s on local fs and reduces cpu wait. [#55841](https://github.com/ClickHouse/ClickHouse/pull/55841) ([Nikita Taranov](https://github.com/nickitat)).
* ... This PR follows [#55929](https://github.com/ClickHouse/ClickHouse/issues/55929), it will bring about 30% speedup. - reduce the reserved memory - reduce the `resize` call. [#55957](https://github.com/ClickHouse/ClickHouse/pull/55957) ([lgbo](https://github.com/lgbo-ustc)).
* The performance experiments of **OnTime** on the ICX device (Intel Xeon Platinum 8380 CPU, 80 cores, 160 threads) show that this change could bring the improvements of **7.4%, 5.9%, 4.7%, 3.0%, and 4.6%** to the QPS of the query Q2, Q3, Q4, Q5 and Q6 respectively while having no impact on others. [#56079](https://github.com/ClickHouse/ClickHouse/pull/56079) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* Limit the number of threads busy inside the query profiler. If there are more - they will skip profiling. [#56105](https://github.com/ClickHouse/ClickHouse/pull/56105) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* WindowTransform decrease amount of virtual function calls. [#56120](https://github.com/ClickHouse/ClickHouse/pull/56120) ([Maksim Kita](https://github.com/kitaisreal)).
* Allow recursive tuple field pruning in ORC to speed up scaning. [#56122](https://github.com/ClickHouse/ClickHouse/pull/56122) ([李扬](https://github.com/taiyang-li)).
* This pull request provides countRows support for Npy data format. Now with setting `optimize_count_from_files=1` queries like `select count() from file(data.npy)` will work much more fast because of caching the results. [#56304](https://github.com/ClickHouse/ClickHouse/pull/56304) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Queries with aggregation and a large number of streams will use less amount of memory during the plan's construction. [#57074](https://github.com/ClickHouse/ClickHouse/pull/57074) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve performance of executing queries for use cases with many users. [#57106](https://github.com/ClickHouse/ClickHouse/pull/57106) ([Andrej Hoos](https://github.com/adikus)).
* Trivial improvement on array join, reuse some intermediate results. [#57183](https://github.com/ClickHouse/ClickHouse/pull/57183) ([李扬](https://github.com/taiyang-li)).
* There are cases when stack unwinding was slow. [#57221](https://github.com/ClickHouse/ClickHouse/pull/57221) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Now we use default read pool for reading from external storage when `max_streams = 1`. It is beneficial when read prefetches are enabled. [#57334](https://github.com/ClickHouse/ClickHouse/pull/57334) ([Nikita Taranov](https://github.com/nickitat)).
#### Improvement
* Engine `Merge` filters the records according to the row policies of the underlying tables. [#50209](https://github.com/ClickHouse/ClickHouse/pull/50209) ([Ilya Golshtein](https://github.com/ilejn)).
* Add a setting `max_execution_time_leaf` to limit the execution time on shard for distributed query, and `timeout_overflow_mode_leaf` to control the behaviour if timeout happens. [#51823](https://github.com/ClickHouse/ClickHouse/pull/51823) ([Duc Canh Le](https://github.com/canhld94)).
* Fix possible postgresql logical replication conversion_error when using MaterializedPostgreSQL. [#53721](https://github.com/ClickHouse/ClickHouse/pull/53721) ([takakawa](https://github.com/takakawa)).
* Set `background_fetches_pool_size` to 16, background_schedule_pool_size to 512 that is better for production usage with frequent small insertions. [#54327](https://github.com/ClickHouse/ClickHouse/pull/54327) ([Denny Crane](https://github.com/den-crane)).
* While read data from a csv format file, and at end of line is'\r' , which not followed by '\n', then we will enconter the exception as below ``` Cannot parse CSV format: found \r (CR) not followed by \n (LF). Line must end by \n (LF) or \r\n (CR LF) or \n\r.: ``` In clickhouse, the csv end of line must be \n or \r\n or \n\r, so the \r must be followed by \n , but in some suitation, the csv input data is abnormal, like above, \r is at end of line. [#54340](https://github.com/ClickHouse/ClickHouse/pull/54340) ([KevinyhZou](https://github.com/KevinyhZou)).
* Update arrow library to release-13.0.0 that supports new encodings. Closes [#44505](https://github.com/ClickHouse/ClickHouse/issues/44505). [#54800](https://github.com/ClickHouse/ClickHouse/pull/54800) ([Kruglov Pavel](https://github.com/Avogar)).
* Improve performance of ON CLUSTER queries by removing heavy system calls to get all network interfaces when looking for local ip address in the DDL entry hosts list. [#54909](https://github.com/ClickHouse/ClickHouse/pull/54909) ([Duc Canh Le](https://github.com/canhld94)).
* Keeper improvement: improve memory-usage during startup by delaying log preprocessing. [#55660](https://github.com/ClickHouse/ClickHouse/pull/55660) ([Antonio Andelic](https://github.com/antonio2368)).
* Fixed accounting of memory allocated before attaching thread to a query or a user. [#56089](https://github.com/ClickHouse/ClickHouse/pull/56089) ([Nikita Taranov](https://github.com/nickitat)).
* ClickHouse keeper reports its running availability zone at `/keeper/availability-zone` path, when running on AWS environment. [#56104](https://github.com/ClickHouse/ClickHouse/pull/56104) ([Jianfei Hu](https://github.com/incfly)).
* Add support for LARGE_LIST with Arrow. [#56118](https://github.com/ClickHouse/ClickHouse/pull/56118) ([edef](https://github.com/edef1c)).
* Improved performance of glob matching for `file` and `hdfs` storages. [#56141](https://github.com/ClickHouse/ClickHouse/pull/56141) ([Andrey Zvonov](https://github.com/zvonand)).
* Allow manual compaction of `EmbeddedRocksDB` via `OPTIMIZE` query. [#56225](https://github.com/ClickHouse/ClickHouse/pull/56225) ([Azat Khuzhin](https://github.com/azat)).
* Posting lists in inverted indexes are now compressed which reduces their size by 10-30%. [#56226](https://github.com/ClickHouse/ClickHouse/pull/56226) ([Harry Lee](https://github.com/HarryLeeIBM)).
* Add ability to specify BlockBasedTableOptions for EmbeddedRocksDB. [#56264](https://github.com/ClickHouse/ClickHouse/pull/56264) ([Azat Khuzhin](https://github.com/azat)).
* `SHOW COLUMNS` now displays MySQL's equivalent data type name when the connection was made through the MySQL protocol. Previously, this was the case when setting `use_mysql_types_in_show_columns = 1`. The setting is retained but made obsolete. [#56277](https://github.com/ClickHouse/ClickHouse/pull/56277) ([Robert Schulze](https://github.com/rschu1ze)).
* Fixed possible `The local set of parts of table doesn't look like the set of parts in ZooKeeper` error if server was restarted just after `TRUNCATE` or `DROP PARTITION`. [#56282](https://github.com/ClickHouse/ClickHouse/pull/56282) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Parallelise `BackupEntriesCollector`. [#56312](https://github.com/ClickHouse/ClickHouse/pull/56312) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fixed handling of non-const query strings in functions `formatQuery()`/ `formatQuerySingleLine()`. Also added `OrNull` variants of both functions that return a NULL when a query cannot be parsed instead of throwing an exception. [#56327](https://github.com/ClickHouse/ClickHouse/pull/56327) ([Robert Schulze](https://github.com/rschu1ze)).
* Support create and materialized index in the same alter query, also support modity TTL and materialize TTL in the same query. Closes [#55651](https://github.com/ClickHouse/ClickHouse/issues/55651). [#56331](https://github.com/ClickHouse/ClickHouse/pull/56331) ([flynn](https://github.com/ucasfl)).
* Enable adding new disk to storage configuration without restart. [#56367](https://github.com/ClickHouse/ClickHouse/pull/56367) ([Duc Canh Le](https://github.com/canhld94)).
* Allow backup of materialized view with dropped inner table instead of failing the backup. [#56387](https://github.com/ClickHouse/ClickHouse/pull/56387) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Queries to `system.replicas` initiate requests to ZooKeeper when certain columns are queried. When there are thousands of tables these requests might produce a considerable load on ZooKeeper. If there are multiple simultaneous queries to `system.replicas` they do same requests multiple times. The change is to "deduplicate" requests from concurrent queries. [#56420](https://github.com/ClickHouse/ClickHouse/pull/56420) ([Alexander Gololobov](https://github.com/davenger)).
* Add transition from reading key to reading quoted key when double quotes are found. [#56423](https://github.com/ClickHouse/ClickHouse/pull/56423) ([Arthur Passos](https://github.com/arthurpassos)).
* Fix transfer query to MySQL compatible query. [#56456](https://github.com/ClickHouse/ClickHouse/pull/56456) ([flynn](https://github.com/ucasfl)).
* Add support for backing up and restoring tables using KeeperMap engine. [#56460](https://github.com/ClickHouse/ClickHouse/pull/56460) ([Antonio Andelic](https://github.com/antonio2368)).
* 404 response for CompleteMultipartUpload has to be rechecked. Operation could be done on server even if client got timeout or other network errors. The next retry of CompleteMultipartUpload receives 404 response. If the object key exists that operation is considered as successful. [#56475](https://github.com/ClickHouse/ClickHouse/pull/56475) ([Sema Checherinda](https://github.com/CheSema)).
* Enable the HTTP OPTIONS method by default - it simplifies requesting ClickHouse from a web browser. [#56483](https://github.com/ClickHouse/ClickHouse/pull/56483) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The value for `dns_max_consecutive_failures` was changed by mistake in [#46550](https://github.com/ClickHouse/ClickHouse/issues/46550) - this is reverted and adjusted to a better value. Also, increased the HTTP keep-alive timeout to a reasonable value from production. [#56485](https://github.com/ClickHouse/ClickHouse/pull/56485) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Load base backups lazily (a base backup won't be loaded until it's needed). Also add some log message and profile events for backups. [#56516](https://github.com/ClickHouse/ClickHouse/pull/56516) ([Vitaly Baranov](https://github.com/vitlibar)).
* Setting `query_cache_store_results_of_queries_with_nondeterministic_functions` (with values `false` or `true`) was marked obsolete. It was replaced by setting `query_cache_nondeterministic_function_handling`, a three-valued enum that controls how the query cache handles queries with non-deterministic functions: a) throw an exception (default behavior), b) save the non-deterministic query result regardless, or c) ignore, i.e. don't throw an exception and don't cache the result. [#56519](https://github.com/ClickHouse/ClickHouse/pull/56519) ([Robert Schulze](https://github.com/rschu1ze)).
* Rewrite equality with `is null` check in JOIN ON section. *Analyzer only*. [#56538](https://github.com/ClickHouse/ClickHouse/pull/56538) ([vdimir](https://github.com/vdimir)).
* Function`concat` now supports arbitrary argument types (instead of only String and FixedString arguments). This makes it behave more similar to MySQL `concat` implementation. For example, `SELECT concat('ab', 42)` now returns `ab42`. [#56540](https://github.com/ClickHouse/ClickHouse/pull/56540) ([Serge Klochkov](https://github.com/slvrtrn)).
* Allow getting cache configuration from 'named_collection' section in config or from sql created named collection. [#56541](https://github.com/ClickHouse/ClickHouse/pull/56541) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update `query_masking_rules` when reloading the config ([#56449](https://github.com/ClickHouse/ClickHouse/issues/56449)). [#56573](https://github.com/ClickHouse/ClickHouse/pull/56573) ([Mikhail Koviazin](https://github.com/mkmkme)).
* Make removeoutdatedtables() less aggressive with unsuccessful postgres connection. [#56609](https://github.com/ClickHouse/ClickHouse/pull/56609) ([jsc0218](https://github.com/jsc0218)).
* Currenting setting takes too much time to connnect to PG when URL is not right, so the relevant query stucks there and get cancelled. [#56648](https://github.com/ClickHouse/ClickHouse/pull/56648) ([jsc0218](https://github.com/jsc0218)).
* ClickHouse keeper reports its running availability zone at `/keeper/availability-zone` path. This can be configured via `<availability_zone><value>us-west-1a</value></availability_zone>`. [#56715](https://github.com/ClickHouse/ClickHouse/pull/56715) ([Jianfei Hu](https://github.com/incfly)).
* Do not allow tables on different replicas have different aggregate functions in SimpleAggregateFunction columns. [#56724](https://github.com/ClickHouse/ClickHouse/pull/56724) ([Duc Canh Le](https://github.com/canhld94)).
* Add support for the [well-known Protobuf types](https://protobuf.dev/reference/protobuf/google.protobuf/) in the Protobuf format. [#56741](https://github.com/ClickHouse/ClickHouse/pull/56741) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Keeper improvement: disable compressed logs by default in Keeper. [#56763](https://github.com/ClickHouse/ClickHouse/pull/56763) ([Antonio Andelic](https://github.com/antonio2368)).
* Add config setting `wait_dictionaries_load_at_startup`:. [#56782](https://github.com/ClickHouse/ClickHouse/pull/56782) ([Vitaly Baranov](https://github.com/vitlibar)).
* There was a potential vulnerability in previous ClickHouse versions: if a user has connected and unsuccessfully tried to authenticate with the "interserver secret" method, the server didn't terminate the connection immediately but continued to receive and ignore the leftover packets from the client. While these packets are ignored, they are still parsed, and if they use a compression method with another known vulnerability, it will lead to exploitation of it without authentication. This issue was found with [ClickHouse Bug Bounty Program](https://github.com/ClickHouse/ClickHouse/issues/38986) by https://twitter.com/malacupa. [#56794](https://github.com/ClickHouse/ClickHouse/pull/56794) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fetching a part waits when that part is fully committed on remote replica. It is better not send part in PreActive state. In case of zero copy this is mandatory restriction. [#56808](https://github.com/ClickHouse/ClickHouse/pull/56808) ([Sema Checherinda](https://github.com/CheSema)).
* Implement user-level setting `alter_move_to_space_execute_async` which allow to execute queries `ALTER TABLE ... MOVE PARTITION|PART TO DISK|VOLUME` asynchronously. The size of pool for background executions is controlled by `background_move_pool_size`. Default behavior is synchronous execution. Fixes [#47643](https://github.com/ClickHouse/ClickHouse/issues/47643). [#56809](https://github.com/ClickHouse/ClickHouse/pull/56809) ([alesapin](https://github.com/alesapin)).
* Able to filter by engine when scanning system.tables, avoid unnecessary (potentially time-consuming) connection. [#56813](https://github.com/ClickHouse/ClickHouse/pull/56813) ([jsc0218](https://github.com/jsc0218)).
* Show `total_bytes` and `total_rows` in system tables for RocksDB storage. [#56816](https://github.com/ClickHouse/ClickHouse/pull/56816) ([Aleksandr Musorin](https://github.com/AVMusorin)).
* Allow basic commands in ALTER for TEMPORARY tables. [#56892](https://github.com/ClickHouse/ClickHouse/pull/56892) ([Sergey](https://github.com/icuken)).
* Lz4 compression. Buffer compressed block in a rare case when out buffer capacity is not enough for writing compressed block directly to out's buffer. [#56938](https://github.com/ClickHouse/ClickHouse/pull/56938) ([Sema Checherinda](https://github.com/CheSema)).
* Add metrics for the number of queued jobs, which is useful for the IO thread pool. [#56958](https://github.com/ClickHouse/ClickHouse/pull/56958) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add a setting for PostgreSQL table engine setting in the config file Added a check for the setting Added documentation around the additional setting. [#56959](https://github.com/ClickHouse/ClickHouse/pull/56959) ([Peignon Melvyn](https://github.com/melvynator)).
* Run interpreter with `only_analyze` flag in getsampleblock method. [#56972](https://github.com/ClickHouse/ClickHouse/pull/56972) ([Mikhail Artemenko](https://github.com/Michicosun)).
* Add a new `MergeTree` setting `add_implicit_sign_column_constraint_for_collapsing_engine` (disabled by default). When enabled, it adds an implicit CHECK constraint for `CollapsingMergeTree` tables that restricts the value of the `Sign` column to be only -1 or 1. [#56701](https://github.com/ClickHouse/ClickHouse/issues/56701). [#56986](https://github.com/ClickHouse/ClickHouse/pull/56986) ([Kevin Mingtarja](https://github.com/kevinmingtarja)).
* Function `concat()` can now be called with a single argument, e.g., `SELECT concat('abc')`. This makes its behavior more consistent with MySQL's concat implementation. [#57000](https://github.com/ClickHouse/ClickHouse/pull/57000) ([Serge Klochkov](https://github.com/slvrtrn)).
* Signs all `x-amz-*` headers as required by AWS S3 docs. [#57001](https://github.com/ClickHouse/ClickHouse/pull/57001) ([Arthur Passos](https://github.com/arthurpassos)).
* Function `fromDaysSinceYearZero` (alias: `FROM_DAYS`) can now be used with unsigned and signed integer types (previously, it had to be an unsigned integer). This improve compatibility with 3rd party tools such as Tableau Online. [#57002](https://github.com/ClickHouse/ClickHouse/pull/57002) ([Serge Klochkov](https://github.com/slvrtrn)).
* Add system.s3queue_log to default config. [#57036](https://github.com/ClickHouse/ClickHouse/pull/57036) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Change the default for `wait_dictionaries_load_at_startup` to true, and use this setting only if `dictionaries_lazy_load` is false. [#57133](https://github.com/ClickHouse/ClickHouse/pull/57133) ([Vitaly Baranov](https://github.com/vitlibar)).
* Check dictionary source type on creation even if `dictionaries_lazy_load` is enabled. [#57134](https://github.com/ClickHouse/ClickHouse/pull/57134) ([Vitaly Baranov](https://github.com/vitlibar)).
* Plan-level optimizations can now be enabled/disabled individually. Previously, it was only possible to disable them all. The setting which previously did that (`query_plan_enable_optimizations`) is retained and can still be used to disable all optimizations. [#57152](https://github.com/ClickHouse/ClickHouse/pull/57152) ([Robert Schulze](https://github.com/rschu1ze)).
* The server's exit code will correspond to the exception code. For example, if the server cannot start due to memory limit, it will exit with the code 241 = MEMORY_LIMIT_EXCEEDED. In previous versions, the exit code for exceptions was always 70 = Poco::Util::ExitCode::EXIT_SOFTWARE. [#57153](https://github.com/ClickHouse/ClickHouse/pull/57153) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Do not demangle and symbolize stack frames from __functional c++ header. [#57201](https://github.com/ClickHouse/ClickHouse/pull/57201) ([Mike Kot](https://github.com/myrrc)).
* It is now possible to refer to ALIAS column in index (non-primary-key) definitions (issue [#55650](https://github.com/ClickHouse/ClickHouse/issues/55650)). Example: `CREATE TABLE tab(col UInt32, col_alias ALIAS col + 1, INDEX idx (col_alias) TYPE minmax) ENGINE = MergeTree ORDER BY col;`. [#57220](https://github.com/ClickHouse/ClickHouse/pull/57220) ([flynn](https://github.com/ucasfl)).
* HTTP server page `/dashboard` now supports charts with multiple lines. [#57236](https://github.com/ClickHouse/ClickHouse/pull/57236) ([Sergei Trifonov](https://github.com/serxa)).
* This pr gives possibility to use suffixes (K, M, G, T, E) along with the amount of memory to be used. Closes [#56879](https://github.com/ClickHouse/ClickHouse/issues/56879). [#57273](https://github.com/ClickHouse/ClickHouse/pull/57273) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Bumped Intel QPL (used by codec `DEFLATE_QPL`) from v1.2.0 to v1.3.1 . Also fixed a bug in case of BOF (Block On Fault) = 0, changed to handle page faults by falling back to SW path. [#57291](https://github.com/ClickHouse/ClickHouse/pull/57291) ([jasperzhu](https://github.com/jinjunzh)).
* Make alter materialized view non experimental and deprecate `allow_experimental_alter_materialized_view_structure` setting. Fixes [#15206](https://github.com/ClickHouse/ClickHouse/issues/15206). [#57311](https://github.com/ClickHouse/ClickHouse/pull/57311) ([alesapin](https://github.com/alesapin)).
* Increase default `replicated_deduplication_window` of MergeTree settings from 100 to 1k. [#57335](https://github.com/ClickHouse/ClickHouse/pull/57335) ([sichenzhao](https://github.com/sichenzhao)).
* Stop using `INCONSISTENT_METADATA_FOR_BACKUP` that much. If possible prefer to continue scanning instead of stopping and starting the scanning for backup from the beginning. [#57385](https://github.com/ClickHouse/ClickHouse/pull/57385) ([Vitaly Baranov](https://github.com/vitlibar)).
* Introduce the limit for the maximum number of table projections (default 25). [#57491](https://github.com/ClickHouse/ClickHouse/pull/57491) ([Julia Kartseva](https://github.com/jkartseva)).
* Enable `async_block_ids_cache` by default for `async_inserts` deduplication. [#57513](https://github.com/ClickHouse/ClickHouse/pull/57513) ([alesapin](https://github.com/alesapin)).
#### Build/Testing/Packaging Improvement
* Enable temporary_data_in_cache in s3 tests in CI. [#48425](https://github.com/ClickHouse/ClickHouse/pull/48425) ([vdimir](https://github.com/vdimir)).
* Run sqllogic test. [#56078](https://github.com/ClickHouse/ClickHouse/pull/56078) ([Han Fei](https://github.com/hanfei1991)).
* Add a new build option `SANITIZE_COVERAGE`. If it is enabled, the code is instrumented to track the coverage. The collected information is available inside ClickHouse with: (1) a new function `coverage` that returns an array of unique addresses in the code found after the previous coverage reset; (2) `SYSTEM RESET COVERAGE` query that resets the accumulated data. This allows us to compare the coverage of different tests, including differential code coverage. Continuation of [#20539](https://github.com/ClickHouse/ClickHouse/issues/20539). [#56102](https://github.com/ClickHouse/ClickHouse/pull/56102) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* In [#54043](https://github.com/ClickHouse/ClickHouse/issues/54043) the setup plan started to appear in the logs. It should be only in the `runner_get_all_tests.log` only. As well, send the failed infrastructure event to CI db. [#56214](https://github.com/ClickHouse/ClickHouse/pull/56214) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Some of the stack frames might not be resolved when collecting stacks. In such cases the raw address might be helpful. [#56267](https://github.com/ClickHouse/ClickHouse/pull/56267) ([Alexander Gololobov](https://github.com/davenger)).
* Add an option to disable libssh. [#56333](https://github.com/ClickHouse/ClickHouse/pull/56333) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add automatic check that there are no large translation units. [#56559](https://github.com/ClickHouse/ClickHouse/pull/56559) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Lower the size of the single-binary distribution. This closes [#55181](https://github.com/ClickHouse/ClickHouse/issues/55181). [#56617](https://github.com/ClickHouse/ClickHouse/pull/56617) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Make `clickhouse-local` and `clickhouse-client` available under short names (`ch`, `chl`, `chc`) for usability. [#56634](https://github.com/ClickHouse/ClickHouse/pull/56634) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Information about the sizes of every translation unit and binary file after each build will be sent to the CI database in ClickHouse Cloud. This closes [#56107](https://github.com/ClickHouse/ClickHouse/issues/56107). [#56636](https://github.com/ClickHouse/ClickHouse/pull/56636) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Certain files of "Apache Arrow" library (which we use only for non-essential things like parsing the arrow format) were rebuilt all the time regardless of the build cache. This is fixed. [#56657](https://github.com/ClickHouse/ClickHouse/pull/56657) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Avoid recompiling translation units depending on the autogenerated source file about version. [#56660](https://github.com/ClickHouse/ClickHouse/pull/56660) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Do not fetch changed submodules in the builder container. [#56689](https://github.com/ClickHouse/ClickHouse/pull/56689) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Tracing data of the linker invocations will be sent to the CI database in ClickHouse Cloud. [#56725](https://github.com/ClickHouse/ClickHouse/pull/56725) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Use DWARF 5 debug symbols for the clickhouse binary (was DWARF 4 previously). [#56770](https://github.com/ClickHouse/ClickHouse/pull/56770) ([Michael Kolupaev](https://github.com/al13n321)).
* Optimized build size further by removing unused code from external libraries. [#56786](https://github.com/ClickHouse/ClickHouse/pull/56786) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Set memory usage for client (`1G`) to address problems like this: https://s3.amazonaws.com/clickhouse-test-reports/0/f1bf3f1fc39f520871ec878d815e515e12fd3e7b/fuzzer_astfuzzertsan/report.html. [#56873](https://github.com/ClickHouse/ClickHouse/pull/56873) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* There was an attempt to have the proper listing in [#44311](https://github.com/ClickHouse/ClickHouse/issues/44311), but the fix itself was in the wrong place, so it's still broken. See an [example](https://github.com/ClickHouse/ClickHouse/actions/runs/6897342568/job/18781001022#step:8:25). [#56989](https://github.com/ClickHouse/ClickHouse/pull/56989) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fixed the memory leak in integration test of postgres dictionary. The case of network partition is not correctly handled at the time of the repo pulled years ago. [#57231](https://github.com/ClickHouse/ClickHouse/pull/57231) ([jsc0218](https://github.com/jsc0218)).
* Fix a test filename typo. [#57272](https://github.com/ClickHouse/ClickHouse/pull/57272) ([jsc0218](https://github.com/jsc0218)).
* Fix issue caught in https://github.com/docker-library/official-images/pull/15846. [#57571](https://github.com/ClickHouse/ClickHouse/pull/57571) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Fix analyzer - insertion from select with subquery referencing insertion table should process only insertion block. [#50857](https://github.com/ClickHouse/ClickHouse/pull/50857) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Setting JoinAlgorithm respect specified order [#51745](https://github.com/ClickHouse/ClickHouse/pull/51745) ([vdimir](https://github.com/vdimir)).
* Keeper `reconfig`: add timeout before yielding/taking leadership [#53481](https://github.com/ClickHouse/ClickHouse/pull/53481) ([Mike Kot](https://github.com/myrrc)).
* Fix incorrect header in grace hash join and filter pushdown [#53922](https://github.com/ClickHouse/ClickHouse/pull/53922) ([vdimir](https://github.com/vdimir)).
* Select from system tables when table based on table function. [#55540](https://github.com/ClickHouse/ClickHouse/pull/55540) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* RFC: Fix "Cannot find column X in source stream" for Distributed queries with LIMIT BY [#55836](https://github.com/ClickHouse/ClickHouse/pull/55836) ([Azat Khuzhin](https://github.com/azat)).
* Fix 'Cannot read from file:' while running client in a background [#55976](https://github.com/ClickHouse/ClickHouse/pull/55976) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix clickhouse-local exit on bad send_logs_level setting [#55994](https://github.com/ClickHouse/ClickHouse/pull/55994) ([Kruglov Pavel](https://github.com/Avogar)).
* Bug fix explain ast with parameterized view [#56004](https://github.com/ClickHouse/ClickHouse/pull/56004) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix a crash during table loading on startup [#56232](https://github.com/ClickHouse/ClickHouse/pull/56232) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ClickHouse-sourced dictionaries with an explicit query [#56236](https://github.com/ClickHouse/ClickHouse/pull/56236) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix segfault in signal handler for Keeper [#56266](https://github.com/ClickHouse/ClickHouse/pull/56266) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix incomplete query result for UNION in view() function. [#56274](https://github.com/ClickHouse/ClickHouse/pull/56274) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix inconsistency of "cast('0' as DateTime64(3))" and "cast('0' as Nullable(DateTime64(3)))" [#56286](https://github.com/ClickHouse/ClickHouse/pull/56286) ([李扬](https://github.com/taiyang-li)).
* Fix rare race condition related to Memory allocation failure [#56303](https://github.com/ClickHouse/ClickHouse/pull/56303) ([alesapin](https://github.com/alesapin)).
* Fix restore from backup with `flatten_nested` and `data_type_default_nullable` [#56306](https://github.com/ClickHouse/ClickHouse/pull/56306) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix crash in case of adding a column with type Object(JSON) [#56307](https://github.com/ClickHouse/ClickHouse/pull/56307) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix crash in filterPushDown [#56380](https://github.com/ClickHouse/ClickHouse/pull/56380) ([vdimir](https://github.com/vdimir)).
* Fix restore from backup with mat view and dropped source table [#56383](https://github.com/ClickHouse/ClickHouse/pull/56383) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix segfault during Kerberos initialization [#56401](https://github.com/ClickHouse/ClickHouse/pull/56401) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix buffer overflow in T64 [#56434](https://github.com/ClickHouse/ClickHouse/pull/56434) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix nullable primary key in final (2) [#56452](https://github.com/ClickHouse/ClickHouse/pull/56452) ([Amos Bird](https://github.com/amosbird)).
* Fix ON CLUSTER queries without database on initial node [#56484](https://github.com/ClickHouse/ClickHouse/pull/56484) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix startup failure due to TTL dependency [#56489](https://github.com/ClickHouse/ClickHouse/pull/56489) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ALTER COMMENT queries ON CLUSTER [#56491](https://github.com/ClickHouse/ClickHouse/pull/56491) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ALTER COLUMN with ALIAS [#56493](https://github.com/ClickHouse/ClickHouse/pull/56493) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix empty NAMED COLLECTIONs [#56494](https://github.com/ClickHouse/ClickHouse/pull/56494) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix two cases of projection analysis. [#56502](https://github.com/ClickHouse/ClickHouse/pull/56502) ([Amos Bird](https://github.com/amosbird)).
* Fix handling of aliases in query cache [#56545](https://github.com/ClickHouse/ClickHouse/pull/56545) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix conversion from `Nullable(Enum)` to `Nullable(String)` [#56644](https://github.com/ClickHouse/ClickHouse/pull/56644) ([Nikolay Degterinsky](https://github.com/evillique)).
* More reliable log handling in Keeper [#56670](https://github.com/ClickHouse/ClickHouse/pull/56670) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix configuration merge for nodes with substitution attributes [#56694](https://github.com/ClickHouse/ClickHouse/pull/56694) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Fix duplicate usage of table function input(). [#56695](https://github.com/ClickHouse/ClickHouse/pull/56695) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix: RabbitMQ OpenSSL dynamic loading issue [#56703](https://github.com/ClickHouse/ClickHouse/pull/56703) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix crash in GCD codec in case when zeros present in data [#56704](https://github.com/ClickHouse/ClickHouse/pull/56704) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix 'mutex lock failed: Invalid argument' in clickhouse-local during insert into function [#56710](https://github.com/ClickHouse/ClickHouse/pull/56710) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix Date text parsing in optimistic path [#56765](https://github.com/ClickHouse/ClickHouse/pull/56765) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix crash in FPC codec [#56795](https://github.com/ClickHouse/ClickHouse/pull/56795) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* DatabaseReplicated: fix DDL query timeout after recovering a replica [#56796](https://github.com/ClickHouse/ClickHouse/pull/56796) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix incorrect nullable columns reporting in MySQL binary protocol [#56799](https://github.com/ClickHouse/ClickHouse/pull/56799) ([Serge Klochkov](https://github.com/slvrtrn)).
* Support Iceberg metadata files for metastore tables [#56810](https://github.com/ClickHouse/ClickHouse/pull/56810) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix TSAN report under transform [#56817](https://github.com/ClickHouse/ClickHouse/pull/56817) ([Raúl Marín](https://github.com/Algunenano)).
* Fix SET query and SETTINGS formatting [#56825](https://github.com/ClickHouse/ClickHouse/pull/56825) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix failure to start due to table dependency in joinGet [#56828](https://github.com/ClickHouse/ClickHouse/pull/56828) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix flattening existing Nested columns during ADD COLUMN [#56830](https://github.com/ClickHouse/ClickHouse/pull/56830) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix allow cr end of line for csv [#56901](https://github.com/ClickHouse/ClickHouse/pull/56901) ([KevinyhZou](https://github.com/KevinyhZou)).
* Fix `tryBase64Decode()` with invalid input [#56913](https://github.com/ClickHouse/ClickHouse/pull/56913) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix generating deep nested columns in CapnProto/Protobuf schemas [#56941](https://github.com/ClickHouse/ClickHouse/pull/56941) ([Kruglov Pavel](https://github.com/Avogar)).
* Prevent incompatible ALTER of projection columns [#56948](https://github.com/ClickHouse/ClickHouse/pull/56948) ([Amos Bird](https://github.com/amosbird)).
* Fix sqlite file path validation [#56984](https://github.com/ClickHouse/ClickHouse/pull/56984) ([San](https://github.com/santrancisco)).
* S3Queue: fix metadata reference increment [#56990](https://github.com/ClickHouse/ClickHouse/pull/56990) ([Kseniia Sumarokova](https://github.com/kssenii)).
* S3Queue minor fix [#56999](https://github.com/ClickHouse/ClickHouse/pull/56999) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix file path validation for DatabaseFileSystem [#57029](https://github.com/ClickHouse/ClickHouse/pull/57029) ([San](https://github.com/santrancisco)).
* Fix `fuzzBits` with `ARRAY JOIN` [#57033](https://github.com/ClickHouse/ClickHouse/pull/57033) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix Nullptr dereference in partial merge join with joined_subquery_re… [#57048](https://github.com/ClickHouse/ClickHouse/pull/57048) ([vdimir](https://github.com/vdimir)).
* Fix race condition in RemoteSource [#57052](https://github.com/ClickHouse/ClickHouse/pull/57052) ([Raúl Marín](https://github.com/Algunenano)).
* Implement `bitHammingDistance` for big integers [#57073](https://github.com/ClickHouse/ClickHouse/pull/57073) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* S3-style links bug fix [#57075](https://github.com/ClickHouse/ClickHouse/pull/57075) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix JSON_QUERY function with multiple numeric paths [#57096](https://github.com/ClickHouse/ClickHouse/pull/57096) ([KevinyhZou](https://github.com/KevinyhZou)).
* Fix buffer overflow in Gorilla codec [#57107](https://github.com/ClickHouse/ClickHouse/pull/57107) ([Nikolay Degterinsky](https://github.com/evillique)).
* Close interserver connection on any exception before authentication [#57142](https://github.com/ClickHouse/ClickHouse/pull/57142) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix segfault after ALTER UPDATE with Nullable MATERIALIZED column [#57147](https://github.com/ClickHouse/ClickHouse/pull/57147) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix incorrect JOIN plan optimization with partially materialized normal projection [#57196](https://github.com/ClickHouse/ClickHouse/pull/57196) ([Amos Bird](https://github.com/amosbird)).
* Ignore comments when comparing column descriptions [#57259](https://github.com/ClickHouse/ClickHouse/pull/57259) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix `ReadonlyReplica` metric for all cases [#57267](https://github.com/ClickHouse/ClickHouse/pull/57267) ([Antonio Andelic](https://github.com/antonio2368)).
* Background merges correctly use temporary data storage in the cache [#57275](https://github.com/ClickHouse/ClickHouse/pull/57275) ([vdimir](https://github.com/vdimir)).
* Keeper fix for changelog and snapshots [#57299](https://github.com/ClickHouse/ClickHouse/pull/57299) ([Antonio Andelic](https://github.com/antonio2368)).
* Ignore finished ON CLUSTER tasks if hostname changed [#57339](https://github.com/ClickHouse/ClickHouse/pull/57339) ([Alexander Tokmakov](https://github.com/tavplubix)).
* MergeTree mutations reuse source part index granularity [#57352](https://github.com/ClickHouse/ClickHouse/pull/57352) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix function jsonMergePatch for partially const columns [#57379](https://github.com/ClickHouse/ClickHouse/pull/57379) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix ubsan error in `Arena` [#57407](https://github.com/ClickHouse/ClickHouse/pull/57407) ([Nikita Taranov](https://github.com/nickitat)).
* fs cache: add limit for background download [#57424](https://github.com/ClickHouse/ClickHouse/pull/57424) ([Kseniia Sumarokova](https://github.com/kssenii)).
* bugfix: correctly parse SYSTEM STOP LISTEN TCP SECURE [#57483](https://github.com/ClickHouse/ClickHouse/pull/57483) ([joelynch](https://github.com/joelynch)).
#### NO CL ENTRY
* NO CL ENTRY: 'Revert "Add function `arrayRandomSample()`"'. [#56399](https://github.com/ClickHouse/ClickHouse/pull/56399) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Update README.md'. [#56549](https://github.com/ClickHouse/ClickHouse/pull/56549) ([Tyler Hannan](https://github.com/tylerhannan)).
* NO CL ENTRY: 'Revert "FunctionSleep exception message fix"'. [#56591](https://github.com/ClickHouse/ClickHouse/pull/56591) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Inserting only non-duplicate chunks in MV"'. [#56598](https://github.com/ClickHouse/ClickHouse/pull/56598) ([Maksim Kita](https://github.com/kitaisreal)).
* NO CL ENTRY: 'Add new header for README with updated logo'. [#56607](https://github.com/ClickHouse/ClickHouse/pull/56607) ([Justin de Guzman](https://github.com/justindeguzman)).
* NO CL ENTRY: 'Revert "Add /keeper/availability-zone node to allow server load balancing within AZ."'. [#56610](https://github.com/ClickHouse/ClickHouse/pull/56610) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Add 4-letter command for yielding/resigning leadership"'. [#56611](https://github.com/ClickHouse/ClickHouse/pull/56611) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'fix(docs): correct default value for output_format_parquet_compression_method to 'lz4''. [#56614](https://github.com/ClickHouse/ClickHouse/pull/56614) ([james-seymour-cubiko](https://github.com/james-seymour-cubiko)).
* NO CL ENTRY: 'Update except.md'. [#56651](https://github.com/ClickHouse/ClickHouse/pull/56651) ([rondo_1895](https://github.com/yangguang1991)).
* NO CL ENTRY: 'Revert "Add a setting max_execution_time_leaf to limit the execution time on shard for distributed query"'. [#56702](https://github.com/ClickHouse/ClickHouse/pull/56702) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Better except for SSL authentication failure"'. [#56844](https://github.com/ClickHouse/ClickHouse/pull/56844) ([Antonio Andelic](https://github.com/antonio2368)).
* NO CL ENTRY: 'Revert "s3 adaptive timeouts"'. [#56992](https://github.com/ClickHouse/ClickHouse/pull/56992) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Revert "s3 adaptive timeouts""'. [#56994](https://github.com/ClickHouse/ClickHouse/pull/56994) ([Sema Checherinda](https://github.com/CheSema)).
* NO CL ENTRY: 'Revert "Resubmit 01600_parts_types_metrics test (possibly without flakiness)"'. [#57163](https://github.com/ClickHouse/ClickHouse/pull/57163) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Mark select() as harmful function"'. [#57195](https://github.com/ClickHouse/ClickHouse/pull/57195) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Update Sentry"'. [#57229](https://github.com/ClickHouse/ClickHouse/pull/57229) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Add debugging info for 01600_parts_types_metrics on failures"'. [#57232](https://github.com/ClickHouse/ClickHouse/pull/57232) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Update date-time-functions.md"'. [#57329](https://github.com/ClickHouse/ClickHouse/pull/57329) ([Denny Crane](https://github.com/den-crane)).
* NO CL ENTRY: 'Revert "add function getClientHTTPHeader"'. [#57510](https://github.com/ClickHouse/ClickHouse/pull/57510) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Add `sqid()` function"'. [#57511](https://github.com/ClickHouse/ClickHouse/pull/57511) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Add new aggregation function groupArraySorted()"'. [#57519](https://github.com/ClickHouse/ClickHouse/pull/57519) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Implemented series period detect method using pocketfft lib"'. [#57536](https://github.com/ClickHouse/ClickHouse/pull/57536) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* NO CL ENTRY: 'Revert "Support use alias column in indices"'. [#57537](https://github.com/ClickHouse/ClickHouse/pull/57537) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Remove useless "install" from CMake (step 1) [#36589](https://github.com/ClickHouse/ClickHouse/pull/36589) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Analyzer support 'is not distinct from' in join on section [#54068](https://github.com/ClickHouse/ClickHouse/pull/54068) ([vdimir](https://github.com/vdimir)).
* Refactor merge join transform [#55007](https://github.com/ClickHouse/ClickHouse/pull/55007) ([Alex Cheng](https://github.com/Alex-Cheng)).
* Add function jaccardIndex back with better performance [#55126](https://github.com/ClickHouse/ClickHouse/pull/55126) ([vdimir](https://github.com/vdimir)).
* Use more thread pools in BACKUP/RESTORE to avoid its hanging in tests [#55216](https://github.com/ClickHouse/ClickHouse/pull/55216) ([Vitaly Baranov](https://github.com/vitlibar)).
* Parallel replicas: progress bar [#55574](https://github.com/ClickHouse/ClickHouse/pull/55574) ([Igor Nikonov](https://github.com/devcrafter)).
* Analyzer: Fix result type after IfConstantConditionPass [#55951](https://github.com/ClickHouse/ClickHouse/pull/55951) ([Dmitry Novik](https://github.com/novikd)).
* RemoteSource: remove unnecessary flag [#55980](https://github.com/ClickHouse/ClickHouse/pull/55980) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix `REPLICA_ALREADY_EXISTS` for ReplicatedMergeTree [#56000](https://github.com/ClickHouse/ClickHouse/pull/56000) ([Nikolay Degterinsky](https://github.com/evillique)).
* Rework [#52159](https://github.com/ClickHouse/ClickHouse/issues/52159) to avoid coredump generation [#56039](https://github.com/ClickHouse/ClickHouse/pull/56039) ([Raúl Marín](https://github.com/Algunenano)).
* Bump gRPC to v1.47.5 [#56059](https://github.com/ClickHouse/ClickHouse/pull/56059) ([Robert Schulze](https://github.com/rschu1ze)).
* See what happens if we use less different docker images in integration tests [#56082](https://github.com/ClickHouse/ClickHouse/pull/56082) ([Raúl Marín](https://github.com/Algunenano)).
* Add missing zookeeper retries in StorageReplicatedMergeTree::backupData [#56131](https://github.com/ClickHouse/ClickHouse/pull/56131) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Better process broken parts on table start for replicated tables [#56142](https://github.com/ClickHouse/ClickHouse/pull/56142) ([alesapin](https://github.com/alesapin)).
* Add more details to "Data after merge is not byte-identical to data on another replicas" [#56164](https://github.com/ClickHouse/ClickHouse/pull/56164) ([Azat Khuzhin](https://github.com/azat)).
* Revert "Revert "Fix output/input of Arrow dictionary column"" [#56167](https://github.com/ClickHouse/ClickHouse/pull/56167) ([Kruglov Pavel](https://github.com/Avogar)).
* Add a log message for DatabaseReplicated [#56215](https://github.com/ClickHouse/ClickHouse/pull/56215) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Correct aggregate function cross tab accessors to be endianness-independent. [#56223](https://github.com/ClickHouse/ClickHouse/pull/56223) ([Austin Kothig](https://github.com/kothiga)).
* Fix client suggestions for user without grants [#56234](https://github.com/ClickHouse/ClickHouse/pull/56234) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix link to failed check report in status commit [#56243](https://github.com/ClickHouse/ClickHouse/pull/56243) ([vdimir](https://github.com/vdimir)).
* Analyzer: fix 01019_alter_materialized_view_consistent [#56246](https://github.com/ClickHouse/ClickHouse/pull/56246) ([vdimir](https://github.com/vdimir)).
* Properly process aliases for aggregation-by-partition optimization. [#56254](https://github.com/ClickHouse/ClickHouse/pull/56254) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* deltalake: Do not raise errors when processing add and remove actions [#56260](https://github.com/ClickHouse/ClickHouse/pull/56260) ([joelynch](https://github.com/joelynch)).
* Fix rare logical error in Replicated database [#56272](https://github.com/ClickHouse/ClickHouse/pull/56272) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Update version_date.tsv and changelogs after v23.10.1.1976-stable [#56278](https://github.com/ClickHouse/ClickHouse/pull/56278) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Add assertion that `SizePredictor` is set if `preferred_block_size_bytes` is set [#56302](https://github.com/ClickHouse/ClickHouse/pull/56302) ([Nikita Taranov](https://github.com/nickitat)).
* Implement digest helpers for different objects [#56305](https://github.com/ClickHouse/ClickHouse/pull/56305) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Removed stale events from README [#56311](https://github.com/ClickHouse/ClickHouse/pull/56311) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix more tests with analyzer. [#56315](https://github.com/ClickHouse/ClickHouse/pull/56315) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Change some exception codes [#56316](https://github.com/ClickHouse/ClickHouse/pull/56316) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix using table shared id during backup and improve logs. [#56339](https://github.com/ClickHouse/ClickHouse/pull/56339) ([Vitaly Baranov](https://github.com/vitlibar)).
* Print info while decompressing the binary [#56360](https://github.com/ClickHouse/ClickHouse/pull/56360) ([Antonio Andelic](https://github.com/antonio2368)).
* remove unstable test test_heavy_insert_select_check_memory [#56369](https://github.com/ClickHouse/ClickHouse/pull/56369) ([Sema Checherinda](https://github.com/CheSema)).
* Update test_storage_s3_queue/test.py [#56370](https://github.com/ClickHouse/ClickHouse/pull/56370) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update 02735_system_zookeeper_connection.sql [#56374](https://github.com/ClickHouse/ClickHouse/pull/56374) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Cleanup convenience functions in IDataType [#56375](https://github.com/ClickHouse/ClickHouse/pull/56375) ([Robert Schulze](https://github.com/rschu1ze)).
* Update test_storage_s3_queue [#56376](https://github.com/ClickHouse/ClickHouse/pull/56376) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Minor improvements for S3Queue [#56377](https://github.com/ClickHouse/ClickHouse/pull/56377) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add obsolete setting back [#56382](https://github.com/ClickHouse/ClickHouse/pull/56382) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Rewrite jobs to use callable workflow [#56385](https://github.com/ClickHouse/ClickHouse/pull/56385) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Update stress.py [#56388](https://github.com/ClickHouse/ClickHouse/pull/56388) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix rocksdb with analyzer. [#56391](https://github.com/ClickHouse/ClickHouse/pull/56391) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Option to check particular file with utils/check-style/check-doc-aspell [#56394](https://github.com/ClickHouse/ClickHouse/pull/56394) ([vdimir](https://github.com/vdimir)).
* Add a metric for suspicious parts in ZooKeeper [#56395](https://github.com/ClickHouse/ClickHouse/pull/56395) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix 02404_memory_bound_merging with analyzer. [#56419](https://github.com/ClickHouse/ClickHouse/pull/56419) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* move storage_metadata_write_full_object_key setting to the server scope [#56421](https://github.com/ClickHouse/ClickHouse/pull/56421) ([Sema Checherinda](https://github.com/CheSema)).
* Make autoscaling more responsive [#56422](https://github.com/ClickHouse/ClickHouse/pull/56422) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix `test_attach_without_fetching` [#56429](https://github.com/ClickHouse/ClickHouse/pull/56429) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Use `pcg` + `randomSeed()` instead of `std::mt19937`/`std::random_device` [#56430](https://github.com/ClickHouse/ClickHouse/pull/56430) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix test `02725_database_hdfs.sh` [#56457](https://github.com/ClickHouse/ClickHouse/pull/56457) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update the AMI receipt [#56459](https://github.com/ClickHouse/ClickHouse/pull/56459) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Make IMergeTreeDataPart::getState() inlinable [#56461](https://github.com/ClickHouse/ClickHouse/pull/56461) ([Alexander Gololobov](https://github.com/davenger)).
* Update version_date.tsv and changelogs after v23.10.2.13-stable [#56467](https://github.com/ClickHouse/ClickHouse/pull/56467) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.9.4.11-stable [#56468](https://github.com/ClickHouse/ClickHouse/pull/56468) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.8.6.16-lts [#56469](https://github.com/ClickHouse/ClickHouse/pull/56469) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.3.16.7-lts [#56470](https://github.com/ClickHouse/ClickHouse/pull/56470) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Disable randomization of allow_experimental_block_number_column flag [#56474](https://github.com/ClickHouse/ClickHouse/pull/56474) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Parallel clone sparse/shallow submodules [#56479](https://github.com/ClickHouse/ClickHouse/pull/56479) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix default port for Replicated database cluster [#56486](https://github.com/ClickHouse/ClickHouse/pull/56486) ([Nikolay Degterinsky](https://github.com/evillique)).
* Updated compression to LZ4 [#56497](https://github.com/ClickHouse/ClickHouse/pull/56497) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Analyzer remove unused projection columns [#56499](https://github.com/ClickHouse/ClickHouse/pull/56499) ([Maksim Kita](https://github.com/kitaisreal)).
* FunctionSleep exception message fix [#56500](https://github.com/ClickHouse/ClickHouse/pull/56500) ([Maksim Kita](https://github.com/kitaisreal)).
* Continue rewriting workflows to reusable tests [#56501](https://github.com/ClickHouse/ClickHouse/pull/56501) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Analyzer special functions projection names fix [#56514](https://github.com/ClickHouse/ClickHouse/pull/56514) ([Maksim Kita](https://github.com/kitaisreal)).
* CTE invalid query analysis add test [#56517](https://github.com/ClickHouse/ClickHouse/pull/56517) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix compilation of BackupsWorker.cpp [#56518](https://github.com/ClickHouse/ClickHouse/pull/56518) ([Vitaly Baranov](https://github.com/vitlibar)).
* Analyzer MoveFunctionsOutOfAnyPass refactoring [#56520](https://github.com/ClickHouse/ClickHouse/pull/56520) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer support EXPLAIN ESTIMATE [#56522](https://github.com/ClickHouse/ClickHouse/pull/56522) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer log used row policies [#56531](https://github.com/ClickHouse/ClickHouse/pull/56531) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer ORDER BY read in order query plan add test [#56532](https://github.com/ClickHouse/ClickHouse/pull/56532) ([Maksim Kita](https://github.com/kitaisreal)).
* ReplicatedMergeTree: check shutdown flags in retry loops [#56533](https://github.com/ClickHouse/ClickHouse/pull/56533) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix race between REPLACE_RANGE and GET_PART (set actual part name when fetching) [#56536](https://github.com/ClickHouse/ClickHouse/pull/56536) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Bump gRPC to v1.54.3 [#56543](https://github.com/ClickHouse/ClickHouse/pull/56543) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix flaky LDAP integration tests [#56544](https://github.com/ClickHouse/ClickHouse/pull/56544) ([Julian Maicher](https://github.com/jmaicher)).
* Remove useless using [#56546](https://github.com/ClickHouse/ClickHouse/pull/56546) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Better warning message [#56547](https://github.com/ClickHouse/ClickHouse/pull/56547) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Allow `chassert` to guide the static analyzer [#56552](https://github.com/ClickHouse/ClickHouse/pull/56552) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove C++ templates [#56556](https://github.com/ClickHouse/ClickHouse/pull/56556) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix `test_keeper_four_word_command/test.py::test_cmd_crst` [#56570](https://github.com/ClickHouse/ClickHouse/pull/56570) ([Antonio Andelic](https://github.com/antonio2368)).
* Delete unnecessary file from tests [#56572](https://github.com/ClickHouse/ClickHouse/pull/56572) ([vdimir](https://github.com/vdimir)).
* Analyzer: fix logical error with set in array join [#56587](https://github.com/ClickHouse/ClickHouse/pull/56587) ([vdimir](https://github.com/vdimir)).
* hide VERSION_INLINE_DATA under feature flag [#56594](https://github.com/ClickHouse/ClickHouse/pull/56594) ([Sema Checherinda](https://github.com/CheSema)).
* Fix 02554_fix_grouping_sets_predicate_push_down with analyzer. [#56595](https://github.com/ClickHouse/ClickHouse/pull/56595) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Add "FunctionSleep exception message fix" again [#56597](https://github.com/ClickHouse/ClickHouse/pull/56597) ([Raúl Marín](https://github.com/Algunenano)).
* Update version_date.tsv and changelogs after v23.10.3.5-stable [#56606](https://github.com/ClickHouse/ClickHouse/pull/56606) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Remove bad test [#56612](https://github.com/ClickHouse/ClickHouse/pull/56612) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Symbolize `trace_log` for exporting [#56613](https://github.com/ClickHouse/ClickHouse/pull/56613) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add indices to exported system logs [#56615](https://github.com/ClickHouse/ClickHouse/pull/56615) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove dependencies [#56616](https://github.com/ClickHouse/ClickHouse/pull/56616) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* WIP: Add test describing MV deduplication issues [#56621](https://github.com/ClickHouse/ClickHouse/pull/56621) ([Jordi Villar](https://github.com/jrdi)).
* Add test for ROW POLICY ON CLUSTER [#56623](https://github.com/ClickHouse/ClickHouse/pull/56623) ([Nikolay Degterinsky](https://github.com/evillique)).
* Enable --secure flag for clickhouse-client for hostnames pointing to clickhouse cloud [#56638](https://github.com/ClickHouse/ClickHouse/pull/56638) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Continue with work from [#56621](https://github.com/ClickHouse/ClickHouse/issues/56621) [#56641](https://github.com/ClickHouse/ClickHouse/pull/56641) ([Jordi Villar](https://github.com/jrdi)).
* Switch to SSL port for clickhouse-client for hostnames pointing to clickhouse cloud [#56649](https://github.com/ClickHouse/ClickHouse/pull/56649) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Remove garbage from libssh [#56654](https://github.com/ClickHouse/ClickHouse/pull/56654) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Delete a file [#56655](https://github.com/ClickHouse/ClickHouse/pull/56655) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Delete a file (2) [#56656](https://github.com/ClickHouse/ClickHouse/pull/56656) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove some entries from `analyzer_tech_debt.txt` [#56658](https://github.com/ClickHouse/ClickHouse/pull/56658) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Miscellaneous [#56662](https://github.com/ClickHouse/ClickHouse/pull/56662) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Bump gRPC to v1.55.4 and protobuf to v22.5 [#56664](https://github.com/ClickHouse/ClickHouse/pull/56664) ([Robert Schulze](https://github.com/rschu1ze)).
* Small refactoring of AST hash calculation (follow-up to [#56545](https://github.com/ClickHouse/ClickHouse/issues/56545)) [#56665](https://github.com/ClickHouse/ClickHouse/pull/56665) ([Robert Schulze](https://github.com/rschu1ze)).
* Analyzer: filtering by virtual columns for StorageS3 [#56668](https://github.com/ClickHouse/ClickHouse/pull/56668) ([vdimir](https://github.com/vdimir)).
* Add back flaky tests to analyzer_tech_debt.txt [#56669](https://github.com/ClickHouse/ClickHouse/pull/56669) ([Raúl Marín](https://github.com/Algunenano)).
* gRPC: remove build dependency on systemd [#56671](https://github.com/ClickHouse/ClickHouse/pull/56671) ([Raúl Marín](https://github.com/Algunenano)).
* Remove unused code [#56677](https://github.com/ClickHouse/ClickHouse/pull/56677) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix missing argument for style_check.py in master workflow [#56691](https://github.com/ClickHouse/ClickHouse/pull/56691) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix unexpected parts handling [#56693](https://github.com/ClickHouse/ClickHouse/pull/56693) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Revert "Revert "Add a setting max_execution_time_leaf to limit the execution time on shard for distributed query"" [#56707](https://github.com/ClickHouse/ClickHouse/pull/56707) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix use_structure_from_insertion_table_in_table_functions with new Analyzer [#56708](https://github.com/ClickHouse/ClickHouse/pull/56708) ([Kruglov Pavel](https://github.com/Avogar)).
* Disable settings randomisation for `02896_memory_accounting_for_user.sh` [#56709](https://github.com/ClickHouse/ClickHouse/pull/56709) ([Nikita Taranov](https://github.com/nickitat)).
* Light autogenerated file [#56720](https://github.com/ClickHouse/ClickHouse/pull/56720) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Less CMake checks [#56721](https://github.com/ClickHouse/ClickHouse/pull/56721) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove orphan header files [#56722](https://github.com/ClickHouse/ClickHouse/pull/56722) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Try to fix hang in 01104_distributed_numbers_test [#56764](https://github.com/ClickHouse/ClickHouse/pull/56764) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Test RabbitMQ with secure connection [#56767](https://github.com/ClickHouse/ClickHouse/pull/56767) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix flaky test_replicated_merge_tree_encryption_codec. [#56768](https://github.com/ClickHouse/ClickHouse/pull/56768) ([Vitaly Baranov](https://github.com/vitlibar)).
* fix typo in ClickHouseDictionarySource [#56776](https://github.com/ClickHouse/ClickHouse/pull/56776) ([Mikhail Koviazin](https://github.com/mkmkme)).
* Fix pygithub [#56778](https://github.com/ClickHouse/ClickHouse/pull/56778) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add test for avoided recursion [#56785](https://github.com/ClickHouse/ClickHouse/pull/56785) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix randomization of Keeper configs in stress tests [#56788](https://github.com/ClickHouse/ClickHouse/pull/56788) ([Antonio Andelic](https://github.com/antonio2368)).
* Try fix `No user in current context, it's a bug` [#56789](https://github.com/ClickHouse/ClickHouse/pull/56789) ([Antonio Andelic](https://github.com/antonio2368)).
* Update avg_weighted.xml [#56797](https://github.com/ClickHouse/ClickHouse/pull/56797) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Better except for SSL authentication failure [#56811](https://github.com/ClickHouse/ClickHouse/pull/56811) ([Nikolay Degterinsky](https://github.com/evillique)).
* More stable `test_keeper_reconfig_replace_leader` [#56835](https://github.com/ClickHouse/ClickHouse/pull/56835) ([Antonio Andelic](https://github.com/antonio2368)).
* Add cancellation hook for moving background operation [#56846](https://github.com/ClickHouse/ClickHouse/pull/56846) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Updated comment in universal.sh [#56852](https://github.com/ClickHouse/ClickHouse/pull/56852) ([Robert Schulze](https://github.com/rschu1ze)).
* Bump gRPC to v1.59 and protobuf to v24.4 [#56853](https://github.com/ClickHouse/ClickHouse/pull/56853) ([Robert Schulze](https://github.com/rschu1ze)).
* Better exception messages [#56854](https://github.com/ClickHouse/ClickHouse/pull/56854) ([Antonio Andelic](https://github.com/antonio2368)).
* Sparse checkout: Use `--remote` for `git submodule update` [#56857](https://github.com/ClickHouse/ClickHouse/pull/56857) ([Aleksandr Musorin](https://github.com/AVMusorin)).
* Fix `test_keeper_broken_logs` [#56858](https://github.com/ClickHouse/ClickHouse/pull/56858) ([Antonio Andelic](https://github.com/antonio2368)).
* CMake: Small cleanup in cpu_features.cmake [#56861](https://github.com/ClickHouse/ClickHouse/pull/56861) ([Robert Schulze](https://github.com/rschu1ze)).
* Planner support transactions [#56867](https://github.com/ClickHouse/ClickHouse/pull/56867) ([Maksim Kita](https://github.com/kitaisreal)).
* Improve diagnostics in test 02908_many_requests_to_system_replicas [#56869](https://github.com/ClickHouse/ClickHouse/pull/56869) ([Alexander Gololobov](https://github.com/davenger)).
* Update 01052_window_view_proc_tumble_to_now.sh [#56870](https://github.com/ClickHouse/ClickHouse/pull/56870) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Call cache check a bit more often [#56872](https://github.com/ClickHouse/ClickHouse/pull/56872) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update test_storage_s3_queue/test.py [#56874](https://github.com/ClickHouse/ClickHouse/pull/56874) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix perf tests report when there are no tests [#56881](https://github.com/ClickHouse/ClickHouse/pull/56881) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Remove ctest [#56894](https://github.com/ClickHouse/ClickHouse/pull/56894) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Simpler CMake [#56898](https://github.com/ClickHouse/ClickHouse/pull/56898) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* test for [#56790](https://github.com/ClickHouse/ClickHouse/issues/56790) [#56899](https://github.com/ClickHouse/ClickHouse/pull/56899) ([Denny Crane](https://github.com/den-crane)).
* Allow delegate disk to handle retries for createDirectories [#56905](https://github.com/ClickHouse/ClickHouse/pull/56905) ([Alexander Gololobov](https://github.com/davenger)).
* Update version_date.tsv and changelogs after v23.10.4.25-stable [#56906](https://github.com/ClickHouse/ClickHouse/pull/56906) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.3.17.13-lts [#56907](https://github.com/ClickHouse/ClickHouse/pull/56907) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.8.7.24-lts [#56908](https://github.com/ClickHouse/ClickHouse/pull/56908) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.9.5.29-stable [#56909](https://github.com/ClickHouse/ClickHouse/pull/56909) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Remove outdated instructions [#56911](https://github.com/ClickHouse/ClickHouse/pull/56911) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Avoid dependencies with no fixed versions [#56914](https://github.com/ClickHouse/ClickHouse/pull/56914) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix race on zk_log initialization [#56915](https://github.com/ClickHouse/ClickHouse/pull/56915) ([Alexander Gololobov](https://github.com/davenger)).
* Check what will happen if I remove some lines [#56916](https://github.com/ClickHouse/ClickHouse/pull/56916) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Update fasttest [#56919](https://github.com/ClickHouse/ClickHouse/pull/56919) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Make some tests independent of macro settings [#56927](https://github.com/ClickHouse/ClickHouse/pull/56927) ([Raúl Marín](https://github.com/Algunenano)).
* Fix flaky 02494_query_cache_events [#56935](https://github.com/ClickHouse/ClickHouse/pull/56935) ([Robert Schulze](https://github.com/rschu1ze)).
* Add CachedReadBufferReadFromCache{Hits,Misses} profile events [#56936](https://github.com/ClickHouse/ClickHouse/pull/56936) ([Jordi Villar](https://github.com/jrdi)).
* Send fatal logs by default in clickhouse-local [#56956](https://github.com/ClickHouse/ClickHouse/pull/56956) ([Nikolay Degterinsky](https://github.com/evillique)).
* Resubmit: Better except for SSL authentication [#56957](https://github.com/ClickHouse/ClickHouse/pull/56957) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix `test_keeper_auth` [#56960](https://github.com/ClickHouse/ClickHouse/pull/56960) ([Antonio Andelic](https://github.com/antonio2368)).
* Fewer concurrent requests in 02908_many_requests_to_system_replicas [#56968](https://github.com/ClickHouse/ClickHouse/pull/56968) ([Alexander Gololobov](https://github.com/davenger)).
* Own CMake for GRPC [#56971](https://github.com/ClickHouse/ClickHouse/pull/56971) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix build in Backups/BackupIO_S3.cpp [#56974](https://github.com/ClickHouse/ClickHouse/pull/56974) ([Robert Schulze](https://github.com/rschu1ze)).
* Add exclude for tryBase64Decode to backward compat test (follow-up to [#56913](https://github.com/ClickHouse/ClickHouse/issues/56913)) [#56975](https://github.com/ClickHouse/ClickHouse/pull/56975) ([Robert Schulze](https://github.com/rschu1ze)).
* Prefer sccache to ccache by default [#56980](https://github.com/ClickHouse/ClickHouse/pull/56980) ([Igor Nikonov](https://github.com/devcrafter)).
* update 02003_memory_limit_in_client.sh [#56981](https://github.com/ClickHouse/ClickHouse/pull/56981) ([Bharat Nallan](https://github.com/bharatnc)).
* Make check for the limited cmake dependencies the part of sparse checkout [#56991](https://github.com/ClickHouse/ClickHouse/pull/56991) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix flaky and slow tests. [#56993](https://github.com/ClickHouse/ClickHouse/pull/56993) ([Amos Bird](https://github.com/amosbird)).
* Fix dropping tables in test_create_or_drop_tables_during_backup [#57007](https://github.com/ClickHouse/ClickHouse/pull/57007) ([Vitaly Baranov](https://github.com/vitlibar)).
* Enable Analyzer in Stress and Fuzz tests [#57008](https://github.com/ClickHouse/ClickHouse/pull/57008) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Run CI for PRs with missing documentation [#57018](https://github.com/ClickHouse/ClickHouse/pull/57018) ([Michael Kolupaev](https://github.com/al13n321)).
* test_s3_engine_heavy_write_check_mem: turn test off [#57025](https://github.com/ClickHouse/ClickHouse/pull/57025) ([Sema Checherinda](https://github.com/CheSema)).
* NamedCollections: make exception message more informative. [#57031](https://github.com/ClickHouse/ClickHouse/pull/57031) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Avoid returning biggest resolution when fpr > 0.283 [#57034](https://github.com/ClickHouse/ClickHouse/pull/57034) ([Jordi Villar](https://github.com/jrdi)).
* Fix: suppress TSAN in RabbitMQ test [#57040](https://github.com/ClickHouse/ClickHouse/pull/57040) ([Igor Nikonov](https://github.com/devcrafter)).
* Small Keeper fixes [#57047](https://github.com/ClickHouse/ClickHouse/pull/57047) ([Antonio Andelic](https://github.com/antonio2368)).
* Parallel replicas: cleanup, narrow dependency [#57054](https://github.com/ClickHouse/ClickHouse/pull/57054) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix gRPC build on macOS [#57061](https://github.com/ClickHouse/ClickHouse/pull/57061) ([Robert Schulze](https://github.com/rschu1ze)).
* Better comment for ITransformingStep::transformPipeline [#57062](https://github.com/ClickHouse/ClickHouse/pull/57062) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix `Duplicate set` for StorageSet with analyzer. [#57063](https://github.com/ClickHouse/ClickHouse/pull/57063) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Better metadata path [#57083](https://github.com/ClickHouse/ClickHouse/pull/57083) ([Nikolay Degterinsky](https://github.com/evillique)).
* Analyzer fuzzer 3 (aggregate_functions_null_for_empty for projections) [#57099](https://github.com/ClickHouse/ClickHouse/pull/57099) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Update numbers.md [#57100](https://github.com/ClickHouse/ClickHouse/pull/57100) ([konruvikt](https://github.com/konruvikt)).
* Fix FunctionNode::toASTImpl [#57102](https://github.com/ClickHouse/ClickHouse/pull/57102) ([vdimir](https://github.com/vdimir)).
* Analyzer fuzzer 5 [#57103](https://github.com/ClickHouse/ClickHouse/pull/57103) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Cancel PipelineExecutor properly in case of exception in spawnThreads [#57104](https://github.com/ClickHouse/ClickHouse/pull/57104) ([Kruglov Pavel](https://github.com/Avogar)).
* Allow HashedDictionary/FunctionsConversion as large TU [#57108](https://github.com/ClickHouse/ClickHouse/pull/57108) ([Azat Khuzhin](https://github.com/azat)).
* Disable checksums for builds with fuzzer [#57122](https://github.com/ClickHouse/ClickHouse/pull/57122) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Analyzer: Fix logical error in LogicalExpressionOptimizerVisitor [#57123](https://github.com/ClickHouse/ClickHouse/pull/57123) ([vdimir](https://github.com/vdimir)).
* Split HashedDictionary CU [#57124](https://github.com/ClickHouse/ClickHouse/pull/57124) ([Azat Khuzhin](https://github.com/azat)).
* Cancel executor in ~CreatingSetsTransform [#57125](https://github.com/ClickHouse/ClickHouse/pull/57125) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix system.*_log in artifacts on CI [#57128](https://github.com/ClickHouse/ClickHouse/pull/57128) ([Azat Khuzhin](https://github.com/azat)).
* Fix something in ReplicatedMergeTree [#57129](https://github.com/ClickHouse/ClickHouse/pull/57129) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Do not symbolize traces for debug/sanitizer builds for sending to cloud [#57130](https://github.com/ClickHouse/ClickHouse/pull/57130) ([Azat Khuzhin](https://github.com/azat)).
* Resubmit 01600_parts_types_metrics test (possibly without flakiness) [#57131](https://github.com/ClickHouse/ClickHouse/pull/57131) ([Azat Khuzhin](https://github.com/azat)).
* Follow up to [#56541](https://github.com/ClickHouse/ClickHouse/issues/56541) [#57141](https://github.com/ClickHouse/ClickHouse/pull/57141) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Allow to disable reorder-functions-after-sorting optimization [#57144](https://github.com/ClickHouse/ClickHouse/pull/57144) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix bad test `00002_log_and_exception_messages_formatting` [#57145](https://github.com/ClickHouse/ClickHouse/pull/57145) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix test test_replicated_merge_tree_encryption_codec/test.py::test_different_keys [#57146](https://github.com/ClickHouse/ClickHouse/pull/57146) ([Vitaly Baranov](https://github.com/vitlibar)).
* Remove partial results from build matrix for stress tests [#57150](https://github.com/ClickHouse/ClickHouse/pull/57150) ([Azat Khuzhin](https://github.com/azat)).
* Minor changes in test_check_table [#57154](https://github.com/ClickHouse/ClickHouse/pull/57154) ([vdimir](https://github.com/vdimir)).
* Fix 02903_rmt_retriable_merge_exception flakiness for replicated database [#57155](https://github.com/ClickHouse/ClickHouse/pull/57155) ([Azat Khuzhin](https://github.com/azat)).
* Mark select() as harmful function [#57156](https://github.com/ClickHouse/ClickHouse/pull/57156) ([Igor Nikonov](https://github.com/devcrafter)).
* Improve the cherry-pick PR description [#57167](https://github.com/ClickHouse/ClickHouse/pull/57167) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add debugging info for 01600_parts_types_metrics on failures [#57170](https://github.com/ClickHouse/ClickHouse/pull/57170) ([Azat Khuzhin](https://github.com/azat)).
* Tiny improvement security [#57171](https://github.com/ClickHouse/ClickHouse/pull/57171) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Update blob_storage_log.md [#57187](https://github.com/ClickHouse/ClickHouse/pull/57187) ([vdimir](https://github.com/vdimir)).
* [RFC] Set log_comment to the file name while processing files in client [#57191](https://github.com/ClickHouse/ClickHouse/pull/57191) ([Azat Khuzhin](https://github.com/azat)).
* Add test for [#5323](https://github.com/ClickHouse/ClickHouse/issues/5323) [#57192](https://github.com/ClickHouse/ClickHouse/pull/57192) ([Raúl Marín](https://github.com/Algunenano)).
* Analyzer fuzzer 6 (arrayJoin) [#57198](https://github.com/ClickHouse/ClickHouse/pull/57198) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Add test for [#47366](https://github.com/ClickHouse/ClickHouse/issues/47366) [#57200](https://github.com/ClickHouse/ClickHouse/pull/57200) ([Raúl Marín](https://github.com/Algunenano)).
* Add test for [#51321](https://github.com/ClickHouse/ClickHouse/issues/51321) [#57202](https://github.com/ClickHouse/ClickHouse/pull/57202) ([Raúl Marín](https://github.com/Algunenano)).
* Fix possible crash (in Rust) of fuzzy finder in client [#57204](https://github.com/ClickHouse/ClickHouse/pull/57204) ([Azat Khuzhin](https://github.com/azat)).
* fix zero-copy locks leaking [#57205](https://github.com/ClickHouse/ClickHouse/pull/57205) ([Sema Checherinda](https://github.com/CheSema)).
* Fix test_distributed_storage_configuration flakiness [#57206](https://github.com/ClickHouse/ClickHouse/pull/57206) ([Azat Khuzhin](https://github.com/azat)).
* Update Sentry [#57222](https://github.com/ClickHouse/ClickHouse/pull/57222) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Update version_date.tsv and changelogs after v23.10.5.20-stable [#57223](https://github.com/ClickHouse/ClickHouse/pull/57223) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.9.6.20-stable [#57224](https://github.com/ClickHouse/ClickHouse/pull/57224) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.3.18.15-lts [#57225](https://github.com/ClickHouse/ClickHouse/pull/57225) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.8.8.20-lts [#57226](https://github.com/ClickHouse/ClickHouse/pull/57226) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Change cursor style for overwrite mode (INS) to blinking in client [#57227](https://github.com/ClickHouse/ClickHouse/pull/57227) ([Azat Khuzhin](https://github.com/azat)).
* Remove test `01280_ttl_where_group_by` [#57230](https://github.com/ClickHouse/ClickHouse/pull/57230) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix docs [#57234](https://github.com/ClickHouse/ClickHouse/pull/57234) ([Nikolay Degterinsky](https://github.com/evillique)).
* Remove addBatchSinglePlaceFromInterval [#57258](https://github.com/ClickHouse/ClickHouse/pull/57258) ([Raúl Marín](https://github.com/Algunenano)).
* Add some additional groups to CI [#57260](https://github.com/ClickHouse/ClickHouse/pull/57260) ([alesapin](https://github.com/alesapin)).
* Analyzer: fix result type of aggregate function with NULL [#57265](https://github.com/ClickHouse/ClickHouse/pull/57265) ([vdimir](https://github.com/vdimir)).
* Ignore memory exception in Keeper asio workers [#57268](https://github.com/ClickHouse/ClickHouse/pull/57268) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix code reports [#57301](https://github.com/ClickHouse/ClickHouse/pull/57301) ([Raúl Marín](https://github.com/Algunenano)).
* Follow up recommendations from [#57167](https://github.com/ClickHouse/ClickHouse/issues/57167) [#57302](https://github.com/ClickHouse/ClickHouse/pull/57302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add back flaky tests to analyzer_tech_debt.txt [#57307](https://github.com/ClickHouse/ClickHouse/pull/57307) ([Raúl Marín](https://github.com/Algunenano)).
* Lower level for annoying S3 log [#57312](https://github.com/ClickHouse/ClickHouse/pull/57312) ([Antonio Andelic](https://github.com/antonio2368)).
* Add regression test for skim (Rust) crash on pasting certain input [#57313](https://github.com/ClickHouse/ClickHouse/pull/57313) ([Azat Khuzhin](https://github.com/azat)).
* Remove unused Strings from MergeTreeData [#57318](https://github.com/ClickHouse/ClickHouse/pull/57318) ([Mikhail Koviazin](https://github.com/mkmkme)).
* Address 02668_ulid_decoding flakiness [#57320](https://github.com/ClickHouse/ClickHouse/pull/57320) ([Raúl Marín](https://github.com/Algunenano)).
* DiskWeb fix [#57322](https://github.com/ClickHouse/ClickHouse/pull/57322) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update README.md [#57325](https://github.com/ClickHouse/ClickHouse/pull/57325) ([Tyler Hannan](https://github.com/tylerhannan)).
* Add information about new _size virtual column in file/s3/url/hdfs/azure table functions [#57328](https://github.com/ClickHouse/ClickHouse/pull/57328) ([Kruglov Pavel](https://github.com/Avogar)).
* Follow-up to [#56490](https://github.com/ClickHouse/ClickHouse/issues/56490): Fix build with `cmake -DENABLE_LIBRARIES=0` [#57330](https://github.com/ClickHouse/ClickHouse/pull/57330) ([Robert Schulze](https://github.com/rschu1ze)).
* Mark a setting obsolete [#57336](https://github.com/ClickHouse/ClickHouse/pull/57336) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Always renew ZK client in `WithRetries` [#57357](https://github.com/ClickHouse/ClickHouse/pull/57357) ([Antonio Andelic](https://github.com/antonio2368)).
* Shutdown disks after tables [#57358](https://github.com/ClickHouse/ClickHouse/pull/57358) ([Alexander Gololobov](https://github.com/davenger)).
* Update DDLTask.cpp [#57369](https://github.com/ClickHouse/ClickHouse/pull/57369) ([Alexander Tokmakov](https://github.com/tavplubix)).
* verbose exception messages for StorageFuzzJSON [#57372](https://github.com/ClickHouse/ClickHouse/pull/57372) ([Julia Kartseva](https://github.com/jkartseva)).
* Initialize only required disks in clickhouse-disks [#57387](https://github.com/ClickHouse/ClickHouse/pull/57387) ([Nikolay Degterinsky](https://github.com/evillique)).
* Allow wildcards in directories for partitioned write with File storage [#57391](https://github.com/ClickHouse/ClickHouse/pull/57391) ([Nikolay Degterinsky](https://github.com/evillique)).
* Add tests for 43202 [#57404](https://github.com/ClickHouse/ClickHouse/pull/57404) ([Raúl Marín](https://github.com/Algunenano)).
* Consider whole check failure in bugfix validate check as an error [#57413](https://github.com/ClickHouse/ClickHouse/pull/57413) ([vdimir](https://github.com/vdimir)).
* Change type of s3_cache in test_encrypted_disk [#57416](https://github.com/ClickHouse/ClickHouse/pull/57416) ([vdimir](https://github.com/vdimir)).
* Add extra debug information on replication consistency errors [#57419](https://github.com/ClickHouse/ClickHouse/pull/57419) ([Raúl Marín](https://github.com/Algunenano)).
* Don't print server revision in client on connect [#57435](https://github.com/ClickHouse/ClickHouse/pull/57435) ([Nikita Taranov](https://github.com/nickitat)).
* Adding Sydney Meetup [#57457](https://github.com/ClickHouse/ClickHouse/pull/57457) ([Tyler Hannan](https://github.com/tylerhannan)).
* Fix adjusting log_comment in case of multiple files passed [#57464](https://github.com/ClickHouse/ClickHouse/pull/57464) ([Azat Khuzhin](https://github.com/azat)).
* Fix flaky test 02697_stop_reading_on_first_cancel.sh [#57481](https://github.com/ClickHouse/ClickHouse/pull/57481) ([Raúl Marín](https://github.com/Algunenano)).
* Tiny refactoring around cache [#57482](https://github.com/ClickHouse/ClickHouse/pull/57482) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Decrease default value for `filesystem_prefetch_min_bytes_for_single_read_task` [#57489](https://github.com/ClickHouse/ClickHouse/pull/57489) ([Nikita Taranov](https://github.com/nickitat)).
* Remove bad test [#57494](https://github.com/ClickHouse/ClickHouse/pull/57494) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add changelog for 23.11 [#57517](https://github.com/ClickHouse/ClickHouse/pull/57517) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Simple cleanup in distributed (while dealing with parallel replicas) [#57518](https://github.com/ClickHouse/ClickHouse/pull/57518) ([Igor Nikonov](https://github.com/devcrafter)).
* Remove a feature. [#57521](https://github.com/ClickHouse/ClickHouse/pull/57521) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* `S3Queue` is production ready [#57548](https://github.com/ClickHouse/ClickHouse/pull/57548) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Revert "Merge pull request [#56724](https://github.com/ClickHouse/ClickHouse/issues/56724) from canhld94/ch_replicated_column_mismatch" [#57576](https://github.com/ClickHouse/ClickHouse/pull/57576) ([Alexey Milovidov](https://github.com/alexey-milovidov)).

22
docs/changelogs/v23.11.2.11-stable.md Normal file
View File

@ -0,0 +1,22 @@
---
sidebar_position: 1
sidebar_label: 2023
---
# 2023 Changelog
### ClickHouse release v23.11.2.11-stable (6e5411358c8) FIXME as compared to v23.11.1.2711-stable (05bc8ef1e02)
#### Improvement
* Backported in [#57661](https://github.com/ClickHouse/ClickHouse/issues/57661): Handle sigabrt case when getting PostgreSQl table structure with empty array. [#57618](https://github.com/ClickHouse/ClickHouse/pull/57618) ([Mike Kot (Михаил Кот)](https://github.com/myrrc)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Ignore ON CLUSTER clause in grant/revoke queries for management of replicated access entities. [#57538](https://github.com/ClickHouse/ClickHouse/pull/57538) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Fix SIGSEGV for aggregation of sparse columns with any() RESPECT NULL [#57710](https://github.com/ClickHouse/ClickHouse/pull/57710) ([Azat Khuzhin](https://github.com/azat)).
* Fix bug window functions: revert [#39631](https://github.com/ClickHouse/ClickHouse/issues/39631) [#57766](https://github.com/ClickHouse/ClickHouse/pull/57766) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Pin alpine version of integration tests helper container [#57669](https://github.com/ClickHouse/ClickHouse/pull/57669) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).

8
docs/en/development/build-cross-osx.md
View File

@ -28,18 +28,20 @@ sudo apt-get install clang-17
Let’s remember the path where we install `cctools` as ${CCTOOLS}
``` bash
mkdir ~/cctools
export CCTOOLS=$(cd ~/cctools && pwd)
mkdir ${CCTOOLS}
cd ${CCTOOLS}
git clone --depth=1 https://github.com/tpoechtrager/apple-libtapi.git
git clone https://github.com/tpoechtrager/apple-libtapi.git
cd apple-libtapi
git checkout 15dfc2a8c9a2a89d06ff227560a69f5265b692f9
INSTALLPREFIX=${CCTOOLS} ./build.sh
./install.sh
cd ..
git clone --depth=1 https://github.com/tpoechtrager/cctools-port.git
git clone https://github.com/tpoechtrager/cctools-port.git
cd cctools-port/cctools
git checkout 2a3e1c2a6ff54a30f898b70cfb9ba1692a55fad7
./configure --prefix=$(readlink -f ${CCTOOLS}) --with-libtapi=$(readlink -f ${CCTOOLS}) --target=x86_64-apple-darwin
make install
```

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

@ -3,7 +3,7 @@ slug: /en/development/build-osx
sidebar_position: 65
sidebar_label: Build on macOS
title: How to Build ClickHouse on macOS
description: How to build ClickHouse on macOS
description: How to build ClickHouse on macOS for macOS
---
:::info You don't have to build ClickHouse yourself!

44
docs/en/development/developer-instruction.md
View File

@ -7,42 +7,39 @@ description: Prerequisites and an overview of how to build ClickHouse
# Getting Started Guide for Building ClickHouse
The building of ClickHouse is supported on Linux, FreeBSD and macOS.
ClickHouse can be build on Linux, FreeBSD and macOS. If you use Windows, you can still build ClickHouse in a virtual machine running Linux, e.g. [VirtualBox](https://www.virtualbox.org/) with Ubuntu.
If you use Windows, you need to create a virtual machine with Ubuntu. To start working with a virtual machine please install VirtualBox. You can download Ubuntu from the website: https://www.ubuntu.com/#download. Please create a virtual machine from the downloaded image (you should reserve at least 4GB of RAM for it). To run a command-line terminal in Ubuntu, please locate a program containing the word “terminal” in its name (gnome-terminal, konsole etc.) or just press Ctrl+Alt+T.
ClickHouse cannot work or build on a 32-bit system. You should acquire access to a 64-bit system and you can continue reading.
ClickHouse requires a 64-bit system to compile and run, 32-bit systems do not work.
## Creating a Repository on GitHub {#creating-a-repository-on-github}
To start working with ClickHouse repository you will need a GitHub account.
To start developing for ClickHouse you will need a [GitHub](https://www.virtualbox.org/) account. Please also generate a SSH key locally (if you don't have one already) and upload the public key to GitHub as this is a prerequisite for contributing patches.
You probably already have one, but if you do not, please register at https://github.com. In case you do not have SSH keys, you should generate them and then upload them on GitHub. It is required for sending over your patches. It is also possible to use the same SSH keys that you use with any other SSH servers - probably you already have those.
Next, create a fork of the [ClickHouse repository](https://github.com/ClickHouse/ClickHouse/) in your personal account by clicking the "fork" button in the upper right corner.
Create a fork of ClickHouse repository. To do that please click on the “fork” button in the upper right corner at https://github.com/ClickHouse/ClickHouse. It will fork your own copy of ClickHouse/ClickHouse to your account.
To contribute, e.g. a fix for an issue or a feature, please commit your changes to a branch in your fork, then create a "pull request" with the changes to the main repository.
The development process consists of first committing the intended changes into your fork of ClickHouse and then creating a “pull request” for these changes to be accepted into the main repository (ClickHouse/ClickHouse).
To work with Git repositories, please install `git`. To do that in Ubuntu you would run in the command line terminal:
For working with Git repositories, please install `git`. In Ubuntu run these commands in a terminal:
```sh
sudo apt update
sudo apt install git
```
A brief manual on using Git can be found [here](https://education.github.com/git-cheat-sheet-education.pdf).
For a detailed manual on Git see [here](https://git-scm.com/book/en/v2).
A cheatsheet for using Git can be found [here](https://education.github.com/git-cheat-sheet-education.pdf). The detailed manual for Git is [here](https://git-scm.com/book/en/v2).
## Cloning a Repository to Your Development Machine {#cloning-a-repository-to-your-development-machine}
Next, you need to download the source files onto your working machine. This is called “to clone a repository” because it creates a local copy of the repository on your working machine.
Run in your terminal:
First, download the source files to your working machine, i.e. clone the repository:
```sh
git clone git@github.com:your_github_username/ClickHouse.git # replace placeholder with your GitHub user name
cd ClickHouse
```
This command will create a directory `ClickHouse/` containing the source code of ClickHouse. If you specify a custom checkout directory (after the URL), it is important that this path does not contain whitespaces as it may lead to problems with the build system.
This command creates a directory `ClickHouse/` containing the source code of ClickHouse. If you specify a custom checkout directory after the URL but it is important that this path does not contain whitespaces as it may lead to problems with the build later on.
To make library dependencies available for the build, the ClickHouse repository uses Git submodules, i.e. references to external repositories. These are not checked out by default. To do so, you can either
The ClickHouse repository uses Git submodules, i.e. references to external repositories (usually 3rd party libraries used by ClickHouse). These are not checked out by default. To do so, you can either
- run `git clone` with option `--recurse-submodules`,
@ -52,7 +49,7 @@ To make library dependencies available for the build, the ClickHouse repository
You can check the Git status with the command: `git submodule status`.
If you get the following error message:
If you get the following error message
Permission denied (publickey).
fatal: Could not read from remote repository.
@ -60,7 +57,7 @@ If you get the following error message:
Please make sure you have the correct access rights
and the repository exists.
It generally means that the SSH keys for connecting to GitHub are missing. These keys are normally located in `~/.ssh`. For SSH keys to be accepted you need to upload them in the settings section of GitHub UI.
it generally means that the SSH keys for connecting to GitHub are missing. These keys are normally located in `~/.ssh`. For SSH keys to be accepted you need to upload them in GitHub's settings.
You can also clone the repository via https protocol:
@ -74,12 +71,17 @@ You can also add original ClickHouse repo address to your local repository to pu
After successfully running this command you will be able to pull updates from the main ClickHouse repo by running `git pull upstream master`.
:::note
Instructions below assume you are building on Linux. If you are cross-compiling or building on macOS, please also check for operating system and architecture specific guides, such as building [on macOS for macOS](build-osx.md), [on Linux for macOS](build-cross-osx.md), [on Linux for Linux/RISC-V](build-cross-riscv.md) and so on.
:::
## Build System {#build-system}
ClickHouse uses CMake and Ninja for building.
CMake - a meta-build system that can generate Ninja files (build tasks).
Ninja - a smaller build system with a focus on the speed used to execute those cmake generated tasks.
- CMake - a meta-build system that can generate Ninja files (build tasks).
- Ninja - a smaller build system with a focus on the speed used to execute those cmake generated tasks.
To install on Ubuntu, Debian or Mint run `sudo apt install cmake ninja-build`.

9
docs/en/engines/table-engines/integrations/s3queue.md
View File

@ -4,16 +4,9 @@ sidebar_position: 181
sidebar_label: S3Queue
---
# [experimental] S3Queue Table Engine
# S3Queue Table Engine
This engine provides integration with [Amazon S3](https://aws.amazon.com/s3/) ecosystem and allows streaming import. This engine is similar to the [Kafka](../../../engines/table-engines/integrations/kafka.md), [RabbitMQ](../../../engines/table-engines/integrations/rabbitmq.md) engines, but provides S3-specific features.
:::note
This table engine is experimental. To use it, set `allow_experimental_s3queue` to 1 by using the `SET` command:
```sql
SET allow_experimental_s3queue=1
```
:::
## Create Table {#creating-a-table}
``` sql

5
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -520,7 +520,7 @@ Indexes of type `set` can be utilized by all functions. The other index types ar
| [empty](/docs/en/sql-reference/functions/array-functions#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ | ✗ |
| [notEmpty](/docs/en/sql-reference/functions/array-functions#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ | ✗ |
| [has](/docs/en/sql-reference/functions/array-functions#function-has) | ✗ | ✗ | ✔ | ✔ | ✔ | ✔ |
| [hasAny](/docs/en/sql-reference/functions/array-functions#function-hasAny) | ✗ | ✗ | ✗ | ✗ | ✔ | ✗ |
| [hasAny](/docs/en/sql-reference/functions/array-functions#function-hasAny) | ✗ | ✗ | ✔ | ✔ | ✔ | ✗ |
| [hasAll](/docs/en/sql-reference/functions/array-functions#function-hasAll) | ✗ | ✗ | ✗ | ✗ | ✔ | ✗ |
| hasToken | ✗ | ✗ | ✗ | ✔ | ✗ | ✔ |
| hasTokenOrNull | ✗ | ✗ | ✗ | ✔ | ✗ | ✔ |
@ -865,10 +865,10 @@ Tags:
- `disk` — a disk within a volume.
- `max_data_part_size_bytes` — the maximum size of a part that can be stored on any of the volume’s disks. If the a size of a merged part estimated to be bigger than `max_data_part_size_bytes` then this part will be written to a next volume. Basically this feature allows to keep new/small parts on a hot (SSD) volume and move them to a cold (HDD) volume when they reach large size. Do not use this setting if your policy has only one volume.
- `move_factor` — when the amount of available space gets lower than this factor, data automatically starts to move on the next volume if any (by default, 0.1). ClickHouse sorts existing parts by size from largest to smallest (in descending order) and selects parts with the total size that is sufficient to meet the `move_factor` condition. If the total size of all parts is insufficient, all parts will be moved.
- `prefer_not_to_merge` — Disables merging of data parts on this volume. When this setting is enabled, merging data on this volume is not allowed. This allows controlling how ClickHouse works with slow disks.
- `perform_ttl_move_on_insert` — Disables TTL move on data part INSERT. By default (if enabled) if we insert a data part that already expired by the TTL move rule it immediately goes to a volume/disk declared in move rule. This can significantly slowdown insert in case if destination volume/disk is slow (e.g. S3). If disabled then already expired data part is written into a default volume and then right after moved to TTL volume.
- `load_balancing` - Policy for disk balancing, `round_robin` or `least_used`.
- `least_used_ttl_ms` - Configure timeout (in milliseconds) for the updating available space on all disks (`0` - update always, `-1` - never update, default is `60000`). Note, if the disk can be used by ClickHouse only and is not subject to a online filesystem resize/shrink you can use `-1`, in all other cases it is not recommended, since eventually it will lead to incorrect space distribution.
- `prefer_not_to_merge` — You should not use this setting. Disables merging of data parts on this volume (this is harmful and leads to performance degradation). When this setting is enabled (don't do it), merging data on this volume is not allowed (which is bad). This allows (but you don't need it) controlling (if you want to control something, you're making a mistake) how ClickHouse works with slow disks (but ClickHouse knows better, so please don't use this setting).
Configuration examples:
@ -905,7 +905,6 @@ Configuration examples:
</main>
<external>
<disk>external</disk>
<prefer_not_to_merge>true</prefer_not_to_merge>
</external>
</volumes>
</small_jbod_with_external_no_merges>

49
docs/en/engines/table-engines/mergetree-family/replacingmergetree.md
View File

@ -25,7 +25,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
[ORDER BY expr]
[PRIMARY KEY expr]
[SAMPLE BY expr]
[SETTINGS name=value, clean_deleted_rows=value, ...]
[SETTINGS name=value, ...]
```
For a description of request parameters, see [statement description](../../../sql-reference/statements/create/table.md).
@ -88,53 +88,6 @@ SELECT * FROM mySecondReplacingMT FINAL;
└─────┴─────────┴─────────────────────┘
```
### is_deleted
`is_deleted` — Name of a column used during a merge to determine whether the data in this row represents the state or is to be deleted; `1` is a “deleted“ row, `0` is a “state“ row.
Column data type — `UInt8`.
:::note
`is_deleted` can only be enabled when `ver` is used.
The row is deleted when `OPTIMIZE ... FINAL CLEANUP` or `OPTIMIZE ... FINAL` is used, or if the engine setting `clean_deleted_rows` has been set to `Always`.
No matter the operation on the data, the version must be increased. If two inserted rows have the same version number, the last inserted row is the one kept.
:::
Example:
```sql
-- with ver and is_deleted
CREATE OR REPLACE TABLE myThirdReplacingMT
(
`key` Int64,
`someCol` String,
`eventTime` DateTime,
`is_deleted` UInt8
)
ENGINE = ReplacingMergeTree(eventTime, is_deleted)
ORDER BY key;
INSERT INTO myThirdReplacingMT Values (1, 'first', '2020-01-01 01:01:01', 0);
INSERT INTO myThirdReplacingMT Values (1, 'first', '2020-01-01 01:01:01', 1);
select * from myThirdReplacingMT final;
0 rows in set. Elapsed: 0.003 sec.
-- delete rows with is_deleted
OPTIMIZE TABLE myThirdReplacingMT FINAL CLEANUP;
INSERT INTO myThirdReplacingMT Values (1, 'first', '2020-01-01 00:00:00', 0);
select * from myThirdReplacingMT final;
┌─key─┬─someCol─┬───────────eventTime─┬─is_deleted─┐
│ 1 │ first │ 2020-01-01 00:00:00 │ 0 │
└─────┴─────────┴─────────────────────┴────────────┘
```
## Query clauses
When creating a `ReplacingMergeTree` table the same [clauses](../../../engines/table-engines/mergetree-family/mergetree.md) are required, as when creating a `MergeTree` table.

26
docs/en/engines/table-engines/special/distributed.md
View File

@ -1,13 +1,16 @@
---
slug: /en/engines/table-engines/special/distributed
sidebar_label: "Distributed"
sidebar_position: 10
sidebar_label: Distributed
slug: /en/engines/table-engines/special/distributed
---
# Distributed Table Engine
Tables with Distributed engine do not store any data of their own, but allow distributed query processing on multiple servers.
Reading is automatically parallelized. During a read, the table indexes on remote servers are used, if there are any.
:::warning
To create a distributed table engine in the cloud, you can use the [remote and remoteSecure](../../../sql-reference/table-functions/remote) table functions. The `Distributed(...)` syntax cannot be used in ClickHouse Cloud.
:::
Tables with Distributed engine do not store any data of their own, but allow distributed query processing on multiple servers. Reading is automatically parallelized. During a read, the table indexes on remote servers are used, if there are any.
## Creating a Table {#distributed-creating-a-table}
@ -22,6 +25,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
```
### From a Table {#distributed-from-a-table}
When the `Distributed` table is pointing to a table on the current server you can adopt that table's schema:
``` sql
@ -48,7 +52,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] AS [db2.]name2
Specifying the `sharding_key` is necessary for the following:
- For `INSERTs` into a distributed table (as the table engine needs the `sharding_key` to determine how to split the data). However, if `insert_distributed_one_random_shard` setting is enabled, then `INSERTs` do not need the sharding key
- For `INSERTs` into a distributed table (as the table engine needs the `sharding_key` to determine how to split the data). However, if `insert_distributed_one_random_shard` setting is enabled, then `INSERTs` do not need the sharding key.
- For use with `optimize_skip_unused_shards` as the `sharding_key` is necessary to determine what shards should be queried
#### policy_name
@ -122,9 +126,7 @@ SETTINGS
fsync_directories=0;
```
Data will be read from all servers in the `logs` cluster, from the `default.hits` table located on every server in the cluster.
Data is not only read but is partially processed on the remote servers (to the extent that this is possible).
For example, for a query with `GROUP BY`, data will be aggregated on remote servers, and the intermediate states of aggregate functions will be sent to the requestor server. Then data will be further aggregated.
Data will be read from all servers in the `logs` cluster, from the `default.hits` table located on every server in the cluster. Data is not only read but is partially processed on the remote servers (to the extent that this is possible). For example, for a query with `GROUP BY`, data will be aggregated on remote servers, and the intermediate states of aggregate functions will be sent to the requestor server. Then data will be further aggregated.
Instead of the database name, you can use a constant expression that returns a string. For example: `currentDatabase()`.
@ -183,9 +185,7 @@ Clusters are configured in the [server configuration file](../../../operations/c
</remote_servers>
```
Here a cluster is defined with the name `logs` that consists of two shards, each of which contains two replicas.
Shards refer to the servers that contain different parts of the data (in order to read all the data, you must access all the shards).
Replicas are duplicating servers (in order to read all the data, you can access the data on any one of the replicas).
Here a cluster is defined with the name `logs` that consists of two shards, each of which contains two replicas. Shards refer to the servers that contain different parts of the data (in order to read all the data, you must access all the shards). Replicas are duplicating servers (in order to read all the data, you can access the data on any one of the replicas).
Cluster names must not contain dots.
@ -198,9 +198,7 @@ The parameters `host`, `port`, and optionally `user`, `password`, `secure`, `com
- `secure` - Whether to use a secure SSL/TLS connection. Usually also requires specifying the port (the default secure port is `9440`). The server should listen on `<tcp_port_secure>9440</tcp_port_secure>` and be configured with correct certificates.
- `compression` - Use data compression. Default value: `true`.
When specifying replicas, one of the available replicas will be selected for each of the shards when reading. You can configure the algorithm for load balancing (the preference for which replica to access) – see the [load_balancing](../../../operations/settings/settings.md#settings-load_balancing) setting.
If the connection with the server is not established, there will be an attempt to connect with a short timeout. If the connection failed, the next replica will be selected, and so on for all the replicas. If the connection attempt failed for all the replicas, the attempt will be repeated the same way, several times.
This works in favour of resiliency, but does not provide complete fault tolerance: a remote server might accept the connection, but might not work, or work poorly.
When specifying replicas, one of the available replicas will be selected for each of the shards when reading. You can configure the algorithm for load balancing (the preference for which replica to access) – see the [load_balancing](../../../operations/settings/settings.md#settings-load_balancing) setting. If the connection with the server is not established, there will be an attempt to connect with a short timeout. If the connection failed, the next replica will be selected, and so on for all the replicas. If the connection attempt failed for all the replicas, the attempt will be repeated the same way, several times. This works in favour of resiliency, but does not provide complete fault tolerance: a remote server might accept the connection, but might not work, or work poorly.
You can specify just one of the shards (in this case, query processing should be called remote, rather than distributed) or up to any number of shards. In each shard, you can specify from one to any number of replicas. You can specify a different number of replicas for each shard.

4
docs/en/getting-started/install.md
View File

@ -56,7 +56,7 @@ On Linux, macOS and FreeBSD:
./clickhouse client
ClickHouse client version 23.2.1.1501 (official build).
Connecting to localhost:9000 as user default.
Connected to ClickHouse server version 23.2.1 revision 54461.
Connected to ClickHouse server version 23.2.1.
local-host :)
```
@ -81,7 +81,7 @@ It is recommended to use official pre-compiled `deb` packages for Debian or Ubun
sudo apt-get install -y apt-transport-https ca-certificates dirmngr
GNUPGHOME=$(mktemp -d)
sudo GNUPGHOME="$GNUPGHOME" gpg --no-default-keyring --keyring /usr/share/keyrings/clickhouse-keyring.gpg --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 8919F6BD2B48D754
sudo rm -r "$GNUPGHOME"
sudo rm -rf "$GNUPGHOME"
sudo chmod +r /usr/share/keyrings/clickhouse-keyring.gpg
echo "deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb stable main" | sudo tee \

2
docs/en/interfaces/cli.md
View File

@ -16,7 +16,7 @@ ClickHouse provides a native command-line client: `clickhouse-client`. The clien
$ clickhouse-client
ClickHouse client version 20.13.1.5273 (official build).
Connecting to localhost:9000 as user default.
Connected to ClickHouse server version 20.13.1 revision 54442.
Connected to ClickHouse server version 20.13.1.
:)
```

1
docs/en/interfaces/formats.md
View File

@ -478,6 +478,7 @@ The CSV format supports the output of totals and extremes the same way as `TabSe
- [input_format_csv_allow_whitespace_or_tab_as_delimiter](/docs/en/operations/settings/settings-formats.md/# input_format_csv_allow_whitespace_or_tab_as_delimiter) - Allow to use whitespace or tab as field delimiter in CSV strings. Default value - `false`.
- [input_format_csv_allow_variable_number_of_columns](/docs/en/operations/settings/settings-formats.md/#input_format_csv_allow_variable_number_of_columns) - allow variable number of columns in CSV format, ignore extra columns and use default values on missing columns. Default value - `false`.
- [input_format_csv_use_default_on_bad_values](/docs/en/operations/settings/settings-formats.md/#input_format_csv_use_default_on_bad_values) - Allow to set default value to column when CSV field deserialization failed on bad value. Default value - `false`.
- [input_format_csv_try_infer_numbers_from_strings](/docs/en/operations/settings/settings-formats.md/#input_format_csv_try_infer_numbers_from_strings) - Try to infer numbers from string fields while schema inference. Default value - `false`.
## CSVWithNames {#csvwithnames}

120
docs/en/interfaces/schema-inference.md
View File

@ -834,6 +834,27 @@ $$)
└──────────────┴───────────────┘
```
#### CSV settings {#csv-settings}
##### input_format_csv_try_infer_numbers_from_strings
Enabling this setting allows inferring numbers from string values.
This setting is disabled by default.
**Example:**
```sql
SET input_format_json_try_infer_numbers_from_strings = 1;
DESC format(CSV, '"42","42.42"');
```
```reponse
┌─name─┬─type──────────────┬─default_type─┬─default_expression─┬─comment─┬─codec_expression─┬─ttl_expression─┐
│ c1 │ Nullable(Int64) │ │ │ │ │ │
│ c2 │ Nullable(Float64) │ │ │ │ │ │
└──────┴───────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
```
### TSV/TSKV {#tsv-tskv}
In TSV/TSKV formats ClickHouse extracts column value from the row according to tabular delimiters and then parses extracted value using
@ -1846,3 +1867,102 @@ DESC format(JSONAsString, '{"x" : 42, "y" : "Hello, World!"}') SETTINGS allow_ex
│ json │ Object('json') │ │ │ │ │ │
└──────┴────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
```
## Schema inference modes {#schema-inference-modes}
Schema inference from the set of data files can work in 2 different modes: `default` and `union`.
The mode is controlled by the setting `schema_inference_mode`.
### Default mode {#default-schema-inference-mode}
In default mode, ClickHouse assumes that all files have the same schema and tries to infer the schema by reading files one by one until it succeeds.
Example:
Let's say we have 3 files `data1.jsonl`, `data2.jsonl` and `data3.jsonl` with the next content:
`data1.jsonl`:
```json
{"field1" : 1, "field2" : null}
{"field1" : 2, "field2" : null}
{"field1" : 3, "field2" : null}
```
`data2.jsonl`:
```json
{"field1" : 4, "field2" : "Data4"}
{"field1" : 5, "field2" : "Data5"}
{"field1" : 6, "field2" : "Data5"}
```
`data3.jsonl`:
```json
{"field1" : 7, "field2" : "Data7", "field3" : [1, 2, 3]}
{"field1" : 8, "field2" : "Data8", "field3" : [4, 5, 6]}
{"field1" : 9, "field2" : "Data9", "field3" : [7, 8, 9]}
```
Let's try to use schema inference on these 3 files:
```sql
:) DESCRIBE file('data{1,2,3}.jsonl') SETTINGS schema_inference_mode='default'
```
Result:
```text
┌─name───┬─type─────────────┐
│ field1 │ Nullable(Int64) │
│ field2 │ Nullable(String) │
└────────┴──────────────────┘
```
As we can see, we don't have `field3` from file `data3.jsonl`.
It happens because ClickHouse first tried to infer schema from file `data1.jsonl`, failed because of only nulls for field `field2`,
and then tried to infer schema from `data2.jsonl` and succeeded, so data from file `data3.jsonl` wasn't read.
### Union mode {#default-schema-inference-mode}
In union mode, ClickHouse assumes that files can have different schemas, so it infer schemas of all files and then union them to the common schema.
Let's say we have 3 files `data1.jsonl`, `data2.jsonl` and `data3.jsonl` with the next content:
`data1.jsonl`:
```json
{"field1" : 1}
{"field1" : 2}
{"field1" : 3}
```
`data2.jsonl`:
```json
{"field2" : "Data4"}
{"field2" : "Data5"}
{"field2" : "Data5"}
```
`data3.jsonl`:
```json
{"field3" : [1, 2, 3]}
{"field3" : [4, 5, 6]}
{"field3" : [7, 8, 9]}
```
Let's try to use schema inference on these 3 files:
```sql
:) DESCRIBE file('data{1,2,3}.jsonl') SETTINGS schema_inference_mode='union'
```
Result:
```text
┌─name───┬─type───────────────────┐
│ field1 │ Nullable(Int64) │
│ field2 │ Nullable(String) │
│ field3 │ Array(Nullable(Int64)) │
└────────┴────────────────────────┘
```
As we can see, we have all fields from all files.
Note:
- As some of the files may not contain some columns from the resulting schema, union mode is supported only for formats that support reading subset of columns (like JSONEachRow, Parquet, TSVWithNames, etc) and won't work for other formats (like CSV, TSV, JSONCompactEachRow, etc).
- If ClickHouse cannot infer the schema from one of the files, the exception will be thrown.
- If you have a lot of files, reading schema from all of them can take a lot of time.

2
docs/en/operations/backup.md
View File

@ -406,7 +406,7 @@ RESTORE TABLE data AS data_restored FROM Disk('s3_plain', 'cloud_backup');
:::note
But keep in mind that:
- This disk should not be used for `MergeTree` itself, only for `BACKUP`/`RESTORE`
- If your tables are backed by S3 storage, it doesn't use `CopyObject` calls to copy parts to the destination bucket, instead, it downloads and uploads them, which is very inefficient. Prefer to use `BACKUP ... TO S3(<endpoint>)` syntax for this use-case.
- If your tables are backed by S3 storage and types of the disks are different, it doesn't use `CopyObject` calls to copy parts to the destination bucket, instead, it downloads and uploads them, which is very inefficient. Prefer to use `BACKUP ... TO S3(<endpoint>)` syntax for this use-case.
:::
## Alternatives

21
docs/en/operations/monitoring.md
View File

@ -15,6 +15,27 @@ You can monitor:
- Utilization of hardware resources.
- ClickHouse server metrics.
## Built-in observability dashboard
<img width="400" alt="Screenshot 2023-11-12 at 6 08 58 PM" src="https://github.com/ClickHouse/ClickHouse/assets/3936029/2bd10011-4a47-4b94-b836-d44557c7fdc1" />
ClickHouse comes with a built-in observability dashboard feature which can be accessed by `$HOST:$PORT/dashboard` (requires user and password) that shows the following metrics:
- Queries/second
- CPU usage (cores)
- Queries running
- Merges running
- Selected bytes/second
- IO wait
- CPU wait
- OS CPU Usage (userspace)
- OS CPU Usage (kernel)
- Read from disk
- Read from filesystem
- Memory (tracked)
- Inserted rows/second
- Total MergeTree parts
- Max parts for partition
## Resource Utilization {#resource-utilization}
ClickHouse also monitors the state of hardware resources by itself such as:

72
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -473,6 +473,39 @@ The value 0 means that you can delete all tables without any restrictions.
<max_table_size_to_drop>0</max_table_size_to_drop>
```
## max\_database\_num\_to\_warn {#max-database-num-to-warn}
If the number of attached databases exceeds the specified value, clickhouse server will add warning messages to `system.warnings` table.
Default value: 1000
**Example**
``` xml
<max_database_num_to_warn>50</max_database_num_to_warn>
```
## max\_table\_num\_to\_warn {#max-table-num-to-warn}
If the number of attached tables exceeds the specified value, clickhouse server will add warning messages to `system.warnings` table.
Default value: 5000
**Example**
``` xml
<max_table_num_to_warn>400</max_table_num_to_warn>
```
## max\_part\_num\_to\_warn {#max-part-num-to-warn}
If the number of active parts exceeds the specified value, clickhouse server will add warning messages to `system.warnings` table.
Default value: 100000
**Example**
``` xml
<max_part_num_to_warn>400</max_part_num_to_warn>
```
## max_temporary_data_on_disk_size
The maximum amount of storage that could be used for external aggregation, joins or sorting.
@ -1646,6 +1679,45 @@ Default value: `0.5`.
## async_load_databases {#async_load_databases}
Asynchronous loading of databases and tables.
If `true` all non-system databases with `Ordinary`, `Atomic` and `Replicated` engine will be loaded asynchronously after the ClickHouse server start up. See `system.asynchronous_loader` table, `tables_loader_background_pool_size` and `tables_loader_foreground_pool_size` server settings. Any query that tries to access a table, that is not yet loaded, will wait for exactly this table to be started up. If load job fails, query will rethrow an error (instead of shutting down the whole server in case of `async_load_databases = false`). The table that is waited for by at least one query will be loaded with higher priority. DDL queries on a database will wait for exactly that database to be started up.
If `false`, all databases are loaded when the server starts.
The default is `false`.
**Example**
``` xml
<async_load_databases>true</async_load_databases>
```
## tables_loader_foreground_pool_size {#tables_loader_foreground_pool_size}
Sets the number of threads performing load jobs in foreground pool. The foreground pool is used for loading table synchronously before server start listening on a port and for loading tables that are waited for. Foreground pool has higher priority than background pool. It means that no job starts in background pool while there are jobs running in foreground pool.
Possible values:
- Any positive integer.
- Zero. Use all available CPUs.
Default value: 0.
## tables_loader_background_pool_size {#tables_loader_background_pool_size}
Sets the number of threads performing asynchronous load jobs in background pool. The background pool is used for loading tables asynchronously after server start in case there are no queries waiting for the table. It could be beneficial to keep low number of threads in background pool if there are a lot of tables. It will reserve CPU resources for concurrent query execution.
Possible values:
- Any positive integer.
- Zero. Use all available CPUs.
Default value: 0.
## merge_tree {#merge_tree}

12
docs/en/operations/settings/merge-tree-settings.md
View File

@ -149,7 +149,7 @@ Possible values:
- Any positive integer.
- 0 (disable deduplication)
Default value: 100.
Default value: 1000.
The `Insert` command creates one or more blocks (parts). For [insert deduplication](../../engines/table-engines/mergetree-family/replication.md), when writing into replicated tables, ClickHouse writes the hash sums of the created parts into ClickHouse Keeper. Hash sums are stored only for the most recent `replicated_deduplication_window` blocks. The oldest hash sums are removed from ClickHouse Keeper.
A large number of `replicated_deduplication_window` slows down `Inserts` because it needs to compare more entries.
@ -852,16 +852,6 @@ If the file name for column is too long (more than `max_file_name_length` bytes)
The maximal length of the file name to keep it as is without hashing. Takes effect only if setting `replace_long_file_name_to_hash` is enabled. The value of this setting does not include the length of file extension. So, it is recommended to set it below the maximum filename length (usually 255 bytes) with some gap to avoid filesystem errors. Default value: 127.
## clean_deleted_rows
Enable/disable automatic deletion of rows flagged as `is_deleted` when perform `OPTIMIZE ... FINAL` on a table using the ReplacingMergeTree engine. When disabled, the `CLEANUP` keyword has to be added to the `OPTIMIZE ... FINAL` to have the same behaviour.
Possible values:
- `Always` or `Never`.
Default value: `Never`
## allow_experimental_block_number_column
Persists virtual column `_block_number` on merges.

7
docs/en/operations/settings/settings-formats.md
View File

@ -1130,6 +1130,13 @@ Result
a 0 1971-01-01
```
## input_format_csv_try_infer_numbers_from_strings {#input_format_csv_try_infer_numbers_from_strings}
If enabled, during schema inference ClickHouse will try to infer numbers from string fields.
It can be useful if CSV data contains quoted UInt64 numbers.
Disabled by default.
## Values format settings {#values-format-settings}
### input_format_values_interpret_expressions {#input_format_values_interpret_expressions}

13
docs/en/operations/settings/settings.md
View File

@ -2647,7 +2647,7 @@ Default value: 0.
## input_format_parallel_parsing {#input-format-parallel-parsing}
Enables or disables order-preserving parallel parsing of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TKSV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Enables or disables order-preserving parallel parsing of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TSKV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Possible values:
@ -2658,7 +2658,7 @@ Default value: `1`.
## output_format_parallel_formatting {#output-format-parallel-formatting}
Enables or disables parallel formatting of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TKSV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Enables or disables parallel formatting of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TSKV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Possible values:
@ -4349,6 +4349,8 @@ Default value: `1GiB`.
## Schema Inference settings
See [schema inference](../../interfaces/schema-inference.md#schema-inference-modes) documentation for more details.
### schema_inference_use_cache_for_file {schema_inference_use_cache_for_file}
Enable schemas cache for schema inference in `file` table function.
@ -4390,6 +4392,13 @@ Possible values:
Default value: 2.
### schema_inference_mode {schema_inference_mode}
The mode of schema inference. Possible values: `default` and `union`.
See [schema inference modes](../../interfaces/schema-inference.md#schema-inference-modes) section for more details.
Default value: `default`.
## compatibility {#compatibility}
The `compatibility` setting causes ClickHouse to use the default settings of a previous version of ClickHouse, where the previous version is provided as the setting.

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

@ -13,6 +13,7 @@ ClickHouse does not delete data from the table automatically. See [Introduction]
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — The date when the async insert happened.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the async insert finished execution.
- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — The date and time when the async insert finished execution with microseconds precision.
@ -42,6 +43,7 @@ SELECT * FROM system.asynchronous_insert_log LIMIT 1 \G;
Result:
``` text
hostname: clickhouse.eu-central1.internal
event_date: 2023-06-08
event_time: 2023-06-08 10:08:53
event_time_microseconds: 2023-06-08 10:08:53.199516

54
docs/en/operations/system-tables/asynchronous_loader.md Normal file
View File

@ -0,0 +1,54 @@
---
slug: /en/operations/system-tables/asynchronous_loader
---
# asynchronous_loader
Contains information and status for recent asynchronous jobs (e.g. for tables loading). The table contains a row for every job. There is a tool for visualizing information from this table `utils/async_loader_graph`.
Example:
``` sql
SELECT *
FROM system.asynchronous_loader
FORMAT Vertical
LIMIT 1
```
``` text
```
Columns:
- `job` (`String`) - Job name (may be not unique).
- `job_id` (`UInt64`) - Unique ID of the job.
- `dependencies` (`Array(UInt64)`) - List of IDs of jobs that should be done before this job.
- `dependencies_left` (`UInt64`) - Current number of dependencies left to be done.
- `status` (`Enum`) - Current load status of a job:
`PENDING`: Load job is not started yet.
`OK`: Load job executed and was successful.
`FAILED`: Load job executed and failed.
`CANCELED`: Load job is not going to be executed due to removal or dependency failure.
A pending job might be in one of the following states:
- `is_executing` (`UInt8`) - The job is currently being executed by a worker.
- `is_blocked` (`UInt8`) - The job waits for its dependencies to be done.
- `is_ready` (`UInt8`) - The job is ready to be executed and waits for a worker.
- `elapsed` (`Float64`) - Seconds elapsed since start of execution. Zero if job is not started. Total execution time if job finished.
Every job has a pool associated with it and is started in this pool. Each pool has a constant priority and a mutable maximum number of workers. Higher priority (lower `priority` value) jobs are run first. No job with lower priority is started while there is at least one higher priority job ready or executing. Job priority can be elevated (but cannot be lowered) by prioritizing it. For example jobs for a table loading and startup will be prioritized if incoming query required this table. It is possible prioritize a job during its execution, but job is not moved from its `execution_pool` to newly assigned `pool`. The job uses `pool` for creating new jobs to avoid priority inversion. Already started jobs are not preempted by higher priority jobs and always run to completion after start.
- `pool_id` (`UInt64`) - ID of a pool currently assigned to the job.
- `pool` (`String`) - Name of `pool_id` pool.
- `priority` (`Int64`) - Priority of `pool_id` pool.
- `execution_pool_id` (`UInt64`) - ID of a pool the job is executed in. Equals initially assigned pool before execution starts.
- `execution_pool` (`String`) - Name of `execution_pool_id` pool.
- `execution_priority` (`Int64`) - Priority of `execution_pool_id` pool.
- `ready_seqno` (`Nullable(UInt64)`) - Not null for ready jobs. Worker pulls the next job to be executed from a ready queue of its pool. If there are multiple ready jobs, then job with the lowest value of `ready_seqno` is picked.
- `waiters` (`UInt64`) - The number of threads waiting on this job.
- `exception` (`Nullable(String)`) - Not null for failed and canceled jobs. Holds error message raised during query execution or error leading to cancelling of this job along with dependency failure chain of job names.
Time instants during job lifetime:
- `schedule_time` (`DateTime64`) - Time when job was created and scheduled to be executed (usually with all its dependencies).
- `enqueue_time` (`Nullable(DateTime64)`) - Time when job became ready and was enqueued into a ready queue of it's pool. Null if the job is not ready yet.
- `start_time` (`Nullable(DateTime64)`) - Time when worker dequeues the job from ready queue and start its execution. Null if the job is not started yet.
- `finish_time` (`Nullable(DateTime64)`) - Time when job execution is finished. Null if the job is not finished yet.

38
docs/en/operations/system-tables/asynchronous_metric_log.md
View File

@ -7,6 +7,7 @@ Contains the historical values for `system.asynchronous_metrics`, which are save
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time.
- `name` ([String](../../sql-reference/data-types/string.md)) — Metric name.
@ -15,22 +16,33 @@ Columns:
**Example**
``` sql
SELECT * FROM system.asynchronous_metric_log LIMIT 10
SELECT * FROM system.asynchronous_metric_log LIMIT 3 \G
```
``` text
┌─event_date─┬──────────event_time─┬─name─────────────────────────────────────┬─────value─┐
│ 2020-09-05 │ 2020-09-05 15:56:30 │ CPUFrequencyMHz_0 │ 2120.9 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pmuzzy │ 743 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pdirty │ 26288 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.run_intervals │ 0 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.num_runs │ 0 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.retained │ 60694528 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.mapped │ 303161344 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.resident │ 260931584 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.metadata │ 12079488 │
│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.allocated │ 133756128 │
└────────────┴─────────────────────┴──────────────────────────────────────────┴───────────┘
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-11-14
event_time: 2023-11-14 14:39:07
metric: AsynchronousHeavyMetricsCalculationTimeSpent
value: 0.001
Row 2:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-11-14
event_time: 2023-11-14 14:39:08
metric: AsynchronousHeavyMetricsCalculationTimeSpent
value: 0
Row 3:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-11-14
event_time: 2023-11-14 14:39:09
metric: AsynchronousHeavyMetricsCalculationTimeSpent
value: 0
```
**See Also**

5
docs/en/operations/system-tables/backup_log.md
View File

@ -7,6 +7,7 @@ Contains logging entries with the information about `BACKUP` and `RESTORE` opera
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Date of the entry.
- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Time of the entry with microseconds precision.
- `id` ([String](../../sql-reference/data-types/string.md)) — Identifier of the backup or restore operation.
@ -45,6 +46,7 @@ SELECT * FROM system.backup_log WHERE id = 'e5b74ecb-f6f1-426a-80be-872f90043885
```response
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-08-19
event_time_microseconds: 2023-08-19 11:05:21.998566
id: e5b74ecb-f6f1-426a-80be-872f90043885
@ -63,6 +65,7 @@ bytes_read: 0
Row 2:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-08-19
event_time_microseconds: 2023-08-19 11:08:56.916192
id: e5b74ecb-f6f1-426a-80be-872f90043885
@ -93,6 +96,7 @@ SELECT * FROM system.backup_log WHERE id = 'cdf1f731-52ef-42da-bc65-2e1bfcd4ce90
```response
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-08-19
event_time_microseconds: 2023-08-19 11:09:19.718077
id: cdf1f731-52ef-42da-bc65-2e1bfcd4ce90
@ -111,6 +115,7 @@ bytes_read: 0
Row 2:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2023-08-19
event_time_microseconds: 2023-08-19 11:09:29.334234
id: cdf1f731-52ef-42da-bc65-2e1bfcd4ce90

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

@ -7,6 +7,7 @@ Contains information about stack traces for fatal errors. The table does not exi
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([DateTime](../../sql-reference/data-types/datetime.md)) — Date of the event.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Time of the event.
- `timestamp_ns` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Timestamp of the event with nanoseconds.
@ -32,6 +33,7 @@ Result (not full):
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2020-10-14
event_time: 2020-10-14 15:47:40
timestamp_ns: 1602679660271312710

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

@ -6,6 +6,7 @@ slug: /en/operations/system-tables/metric_log
Contains history of metrics values from tables `system.metrics` and `system.events`, periodically flushed to disk.
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time.
- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Event time with microseconds resolution.
@ -19,6 +20,7 @@ SELECT * FROM system.metric_log LIMIT 1 FORMAT Vertical;
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2020-09-05
event_time: 2020-09-05 16:22:33
event_time_microseconds: 2020-09-05 16:22:33.196807

40
docs/en/operations/system-tables/metrics.md
View File

@ -45,6 +45,22 @@ Number of threads in the Aggregator thread pool.
Number of threads in the Aggregator thread pool running a task.
### TablesLoaderForegroundThreads
Number of threads in the async loader foreground thread pool.
### TablesLoaderForegroundThreadsActive
Number of threads in the async loader foreground thread pool running a task.
### TablesLoaderBackgroundThreads
Number of threads in the async loader background thread pool.
### TablesLoaderBackgroundThreadsActive
Number of threads in the async loader background thread pool running a task.
### AsyncInsertCacheSize
Number of async insert hash id in cache
@ -197,14 +213,6 @@ Number of threads in the DatabaseOnDisk thread pool.
Number of threads in the DatabaseOnDisk thread pool running a task.
### DatabaseOrdinaryThreads
Number of threads in the Ordinary database thread pool.
### DatabaseOrdinaryThreadsActive
Number of threads in the Ordinary database thread pool running a task.
### DelayedInserts
Number of INSERT queries that are throttled due to high number of active data parts for partition in a MergeTree table.
@ -625,14 +633,6 @@ Number of connections that are sending data for external tables to remote server
Number of connections that are sending data for scalars to remote servers.
### StartupSystemTablesThreads
Number of threads in the StartupSystemTables thread pool.
### StartupSystemTablesThreadsActive
Number of threads in the StartupSystemTables thread pool running a task.
### StorageBufferBytes
Number of bytes in buffers of Buffer tables
@ -677,14 +677,6 @@ Number of threads in the system.replicas thread pool running a task.
Number of connections to TCP server (clients with native interface), also included server-server distributed query connections
### TablesLoaderThreads
Number of threads in the tables loader thread pool.
### TablesLoaderThreadsActive
Number of threads in the tables loader thread pool running a task.
### TablesToDropQueueSize
Number of dropped tables, that are waiting for background data removal.

9
docs/en/operations/system-tables/opentelemetry_span_log.md
View File

@ -8,28 +8,19 @@ Contains information about [trace spans](https://opentracing.io/docs/overview/sp
Columns:
- `trace_id` ([UUID](../../sql-reference/data-types/uuid.md)) — ID of the trace for executed query.
- `span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the `trace span`.
- `parent_span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the parent `trace span`.
- `operation_name` ([String](../../sql-reference/data-types/string.md)) — The name of the operation.
- `kind` ([Enum8](../../sql-reference/data-types/enum.md)) — The [SpanKind](https://opentelemetry.io/docs/reference/specification/trace/api/#spankind) of the span.
- `INTERNAL` — Indicates that the span represents an internal operation within an application.
- `SERVER` — Indicates that the span covers server-side handling of a synchronous RPC or other remote request.
- `CLIENT` — Indicates that the span describes a request to some remote service.
- `PRODUCER` — Indicates that the span describes the initiators of an asynchronous request. This parent span will often end before the corresponding child CONSUMER span, possibly even before the child span starts.
- `CONSUMER` - Indicates that the span describes a child of an asynchronous PRODUCER request.
- `start_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The start time of the `trace span` (in microseconds).
- `finish_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The finish time of the `trace span` (in microseconds).
- `finish_date` ([Date](../../sql-reference/data-types/date.md)) — The finish date of the `trace span`.
- `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — [Attribute](https://opentelemetry.io/docs/go/instrumentation/#attributes) names depending on the `trace span`. They are filled in according to the recommendations in the [OpenTelemetry](https://opentelemetry.io/) standard.
- `attribute.values` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Attribute values depending on the `trace span`. They are filled in according to the recommendations in the `OpenTelemetry` standard.
**Example**

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

@ -9,6 +9,7 @@ This table contains information about events that occurred with [data parts](../
The `system.part_log` table contains the following columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `query_id` ([String](../../sql-reference/data-types/string.md)) — Identifier of the `INSERT` query that created this data part.
- `event_type` ([Enum8](../../sql-reference/data-types/enum.md)) — Type of the event that occurred with the data part. Can have one of the following values:
- `NewPart` — Inserting of a new data part.
@ -56,6 +57,7 @@ SELECT * FROM system.part_log LIMIT 1 FORMAT Vertical;
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
query_id: 983ad9c7-28d5-4ae1-844e-603116b7de31
event_type: NewPart
merge_reason: NotAMerge

1
docs/en/operations/system-tables/processors_profile_log.md
View File

@ -4,6 +4,7 @@ This table contains profiling on processors level (that you can find in [`EXPLAI
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — The date when the event happened.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the event happened.
- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — The date and time with microseconds precision when the event happened.

4
docs/en/operations/system-tables/query_log.md
View File

@ -34,6 +34,7 @@ You can use the [log_formatted_queries](../../operations/settings/settings.md#se
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `type` ([Enum8](../../sql-reference/data-types/enum.md)) — Type of an event that occurred when executing the query. Values:
- `'QueryStart' = 1` — Successful start of query execution.
- `'QueryFinish' = 2` — Successful end of query execution.
@ -127,6 +128,7 @@ SELECT * FROM system.query_log WHERE type = 'QueryFinish' ORDER BY query_start_t
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
type: QueryFinish
event_date: 2021-11-03
event_time: 2021-11-03 16:13:54
@ -167,7 +169,7 @@ initial_query_start_time: 2021-11-03 16:13:54
initial_query_start_time_microseconds: 2021-11-03 16:13:54.952325
interface: 1
os_user: sevirov
client_hostname: clickhouse.ru-central1.internal
client_hostname: clickhouse.eu-central1.internal
client_name: ClickHouse
client_revision: 54449
client_version_major: 21

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

@ -18,6 +18,7 @@ You can use the [log_queries_probability](../../operations/settings/settings.md#
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — The date when the thread has finished execution of the query.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the thread has finished execution of the query.
- `event_time_microsecinds` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the thread has finished execution of the query with microseconds precision.
@ -74,6 +75,7 @@ Columns:
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2020-09-11
event_time: 2020-09-11 10:08:17
event_time_microseconds: 2020-09-11 10:08:17.134042

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

@ -18,6 +18,7 @@ You can use the [log_queries_probability](../../operations/settings/settings.md#
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — The date when the last event of the view happened.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the view finished execution.
- `event_time_microseconds` ([DateTime](../../sql-reference/data-types/datetime.md)) — The date and time when the view finished execution with microseconds precision.
@ -59,6 +60,7 @@ Result:
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2021-06-22
event_time: 2021-06-22 13:23:07
event_time_microseconds: 2021-06-22 13:23:07.738221

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

@ -7,6 +7,7 @@ Contains information about all successful and failed login and logout events.
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `type` ([Enum8](../../sql-reference/data-types/enum.md)) — Login/logout result. Possible values:
- `LoginFailure` — Login error.
- `LoginSuccess` — Successful login.
@ -57,6 +58,7 @@ Result:
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
type: LoginSuccess
auth_id: 45e6bd83-b4aa-4a23-85e6-bd83b4aa1a23
session_id:

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

@ -17,7 +17,7 @@ Columns:
- `UNKNOWN`
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
- `prefer_not_to_merge` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Value of the `prefer_not_to_merge` setting. When this setting is enabled, merging data on this volume is not allowed. This allows controlling how ClickHouse works with slow disks.
- `prefer_not_to_merge` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Value of the `prefer_not_to_merge` setting. Should be always false. When this setting is enabled, you did a mistake.
- `perform_ttl_move_on_insert` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Value of the `perform_ttl_move_on_insert` setting. — Disables TTL move on data part INSERT. By default if we insert a data part that already expired by the TTL move rule it immediately goes to a volume/disk declared in move rule. This can significantly slowdown insert in case if destination volume/disk is slow (e.g. S3).
- `load_balancing` ([Enum8](../../sql-reference/data-types/enum.md)) — Policy for disk balancing. Can have one of the following values:
- `ROUND_ROBIN`

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

@ -7,6 +7,7 @@ Contains logging entries. The logging level which goes to this table can be limi
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` (Date) — Date of the entry.
- `event_time` (DateTime) — Time of the entry.
- `event_time_microseconds` (DateTime) — Time of the entry with microseconds precision.
@ -39,6 +40,7 @@ SELECT * FROM system.text_log LIMIT 1 \G
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2020-09-10
event_time: 2020-09-10 11:23:07
event_time_microseconds: 2020-09-10 11:23:07.871397

15
docs/en/operations/system-tables/trace_log.md
View File

@ -12,37 +12,27 @@ To analyze logs, use the `addressToLine`, `addressToLineWithInlines`, `addressTo
Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Date of sampling moment.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Timestamp of the sampling moment.
- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Timestamp of the sampling moment with microseconds precision.
- `timestamp_ns` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Timestamp of the sampling moment in nanoseconds.
- `revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — ClickHouse server build revision.
When connecting to the server by `clickhouse-client`, you see the string similar to `Connected to ClickHouse server version 19.18.1 revision 54429.`. This field contains the `revision`, but not the `version` of a server.
When connecting to the server by `clickhouse-client`, you see the string similar to `Connected to ClickHouse server version 19.18.1.`. This field contains the `revision`, but not the `version` of a server.
- `trace_type` ([Enum8](../../sql-reference/data-types/enum.md)) — Trace type:
- `Real` represents collecting stack traces by wall-clock time.
- `CPU` represents collecting stack traces by CPU time.
- `Memory` represents collecting allocations and deallocations when memory allocation exceeds the subsequent watermark.
- `MemorySample` represents collecting random allocations and deallocations.
- `MemoryPeak` represents collecting updates of peak memory usage.
- `ProfileEvent` represents collecting of increments of profile events.
- `thread_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Thread identifier.
- `query_id` ([String](../../sql-reference/data-types/string.md)) — Query identifier that can be used to get details about a query that was running from the [query_log](#system_tables-query_log) system table.
- `trace` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — Stack trace at the moment of sampling. Each element is a virtual memory address inside ClickHouse server process.
- `size` ([Int64](../../sql-reference/data-types/int-uint.md)) - For trace types `Memory`, `MemorySample` or `MemoryPeak` is the amount of memory allocated, for other trace types is 0.
- `event` ([LowCardinality(String)](../../sql-reference/data-types/lowcardinality.md)) - For trace type `ProfileEvent` is the name of updated profile event, for other trace types is an empty string.
- `increment` ([UInt64](../../sql-reference/data-types/int-uint.md)) - For trace type `ProfileEvent` is the amount of increment of profile event, for other trace types is 0.
**Example**
@ -54,6 +44,7 @@ SELECT * FROM system.trace_log LIMIT 1 \G
``` text
Row 1:
──────
hostname: clickhouse.eu-central1.internal
event_date: 2020-09-10
event_time: 2020-09-10 11:23:09
event_time_microseconds: 2020-09-10 11:23:09.872924

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