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

Merge remote-tracking branch 'origin/master' into attaching_parts

Browse Source
This commit is contained in:
Кирилл Гарбар 2024-08-08 18:28:09 +03:00
commit c83e444315
4750 changed files with 117484 additions and 53669 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.clang-tidy
View File

@ -27,6 +27,8 @@ Checks: [
'-bugprone-not-null-terminated-result',
'-bugprone-reserved-identifier', # useful but too slow, TODO retry when https://reviews.llvm.org/rG1c282052624f9d0bd273bde0b47b30c96699c6c7 is merged
'-bugprone-unchecked-optional-access',
'-bugprone-crtp-constructor-accessibility',
'-bugprone-suspicious-stringview-data-usage',
'-cert-dcl16-c',
'-cert-dcl37-c',
@ -36,8 +38,8 @@ Checks: [
'-cert-msc51-cpp',
'-cert-oop54-cpp',
'-cert-oop57-cpp',
'-cert-err33-c', # Misreports on clang-19: it warns about all functions containing 'remove' in the name, not only about the standard library.
'-clang-analyzer-optin.core.EnumCastOutOfRange', # https://github.com/abseil/abseil-cpp/issues/1667
'-clang-analyzer-optin.performance.Padding',
'-clang-analyzer-unix.Malloc',
@ -100,6 +102,7 @@ Checks: [
'-modernize-use-emplace',
'-modernize-use-nodiscard',
'-modernize-use-trailing-return-type',
'-modernize-use-designated-initializers',
'-performance-enum-size',
'-performance-inefficient-string-concatenation',

4
.editorconfig
View File

@ -19,3 +19,7 @@ charset = utf-8
indent_style = space
indent_size = 4
trim_trailing_whitespace = true
# Some SQL results have trailing whitespace which is removed by IDEs
[tests/queries/**.reference]
trim_trailing_whitespace = false

3
.git-blame-ignore-revs
View File

@ -13,3 +13,6 @@
# dbms/ → src/
# (though it is unlikely that you will see it in blame)
06446b4f08a142d6f1bc30664c47ded88ab51782
# Applied Black formatter for Python code
e6f5a3f98b21ba99cf274a9833797889e020a2b3

1
.gitattributes vendored
View File

@ -2,3 +2,4 @@ contrib/* linguist-vendored
*.h linguist-language=C++
tests/queries/0_stateless/data_json/* binary
tests/queries/0_stateless/*.reference -crlf
src/Core/SettingsChangesHistory.cpp merge=union

10
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -6,6 +6,7 @@ tests/ci/cancel_and_rerun_workflow_lambda/app.py
-->
### Changelog category (leave one):
- New Feature
- Experimental Feature
- Improvement
- Performance Improvement
- Backward Incompatible Change
@ -48,21 +49,18 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] <!---ci_include_stateful--> Allow: Stateful tests
- [ ] <!---ci_include_integration--> Allow: Integration Tests
- [ ] <!---ci_include_performance--> Allow: Performance tests
- [ ] <!---ci_set_non_required--> Allow: All NOT Required Checks
- [ ] <!---ci_set_builds--> Allow: All Builds
- [ ] <!---batch_0_1--> Allow: batch 1, 2 for multi-batch jobs
- [ ] <!---batch_2_3--> Allow: batch 3, 4, 5, 6 for multi-batch jobs
---
- [ ] <!---ci_exclude_style--> Exclude: Style check
- [ ] <!---ci_exclude_fast--> Exclude: Fast test
- [ ] <!---ci_exclude_integration--> Exclude: Integration Tests
- [ ] <!---ci_exclude_stateless--> Exclude: Stateless tests
- [ ] <!---ci_exclude_stateful--> Exclude: Stateful tests
- [ ] <!---ci_exclude_performance--> Exclude: Performance tests
- [ ] <!---ci_exclude_asan--> Exclude: All with ASAN
- [ ] <!---ci_exclude_aarch64--> Exclude: All with Aarch64
- [ ] <!---ci_exclude_tsan|msan|ubsan|coverage--> Exclude: All with TSAN, MSAN, UBSAN, Coverage
- [ ] <!---ci_exclude_aarch64|release|debug--> Exclude: All with aarch64, release, debug
---
- [ ] <!---do_not_test--> Do not test
- [ ] <!---woolen_wolfdog--> Woolen Wolfdog
- [ ] <!---upload_all--> Upload binaries for special builds
- [ ] <!---no_merge_commit--> Disable merge-commit
- [ ] <!---no_ci_cache--> Disable CI cache

1
.github/actionlint.yml vendored
View File

@ -7,3 +7,4 @@ self-hosted-runner:
- stress-tester
- style-checker
- style-checker-aarch64
- release-maker

21
.github/actions/check_workflow/action.yml vendored Normal file
View File

@ -0,0 +1,21 @@
name: CheckWorkflowResults
description: Check overall workflow status and post error to slack if any
inputs:
needs:
description: github needs context as a json string
required: true
type: string
runs:
using: "composite"
steps:
- name: Check Workflow
shell: bash
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ inputs.needs }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

45
.github/workflows/auto_release.yml vendored
View File

@ -1,45 +0,0 @@
name: AutoRelease
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
concurrency:
group: auto-release
on: # yamllint disable-line rule:truthy
# schedule:
# - cron: '0 10-16 * * 1-5'
workflow_dispatch:
jobs:
CherryPick:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
# https://docs.github.com/en/actions/learn-github-actions/workflow-commands-for-github-actions#multiline-strings
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/cherry_pick
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
REPO_OWNER=ClickHouse
REPO_NAME=ClickHouse
REPO_TEAM=core
EOF
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Auto-release
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 auto_release.py --release-after-days=3
- 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"

79
.github/workflows/backport_branches.yml vendored
View File

@ -36,10 +36,6 @@ jobs:
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: |
@ -62,7 +58,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:
@ -70,7 +66,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check (amd64)
test_name: Compatibility check (release)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckAarch64:
@ -159,33 +155,24 @@ jobs:
############################################################################################
##################################### BUILD REPORTER #######################################
############################################################################################
BuilderReport:
Builds_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() }}
needs:
- RunConfig
- BuilderDebAarch64
- BuilderDebAsan
- BuilderDebDebug
- BuilderDebRelease
- BuilderDebTsan
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
BuilderSpecialReport:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() }}
needs:
- RunConfig
- BuilderBinDarwin
- BuilderBinDarwinAarch64
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
needs: [RunConfig, BuilderDebAarch64, BuilderDebAsan, BuilderDebDebug, BuilderDebRelease, BuilderDebTsan, BuilderBinDarwin, BuilderBinDarwinAarch64]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Download reports
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --pre --job-name Builds
- name: Builds report
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 ./build_report_check.py --reports package_release package_aarch64 package_asan package_tsan package_debug binary_darwin binary_darwin_aarch64
- name: Set status
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --post --job-name Builds
############################################################################################
#################################### INSTALL PACKAGES ######################################
############################################################################################
@ -194,7 +181,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (amd64)
test_name: Install packages (release)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
@ -204,7 +191,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (arm64)
test_name: Install packages (aarch64)
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
@ -254,10 +241,10 @@ jobs:
runner_type: stress-tester
data: ${{ needs.RunConfig.outputs.data }}
FinishCheck:
if: ${{ !failure() && !cancelled() }}
if: ${{ !cancelled() }}
needs:
- BuilderReport
- BuilderSpecialReport
- RunConfig
- Builds_Report
- FunctionalStatelessTestAsan
- FunctionalStatefulTestDebug
- StressTestTsan
@ -271,7 +258,23 @@ jobs:
with:
clear-repository: true
- name: Finish label
if: ${{ !failure() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
# update mergeable check
python3 merge_pr.py --set-ci-status
# update overall ci report
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
python3 merge_pr.py
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

202
.github/workflows/create_release.yml vendored Normal file
View File

@ -0,0 +1,202 @@
name: CreateRelease
concurrency:
group: release
'on':
workflow_dispatch:
inputs:
ref:
description: 'Git reference (branch or commit sha) from which to create the release'
required: true
type: string
type:
description: 'The type of release: "new" for a new release or "patch" for a patch release'
required: true
type: choice
options:
- patch
- new
only-repo:
description: 'Run only repos updates including docker (repo-recovery, tests)'
required: false
default: false
type: boolean
dry-run:
description: 'Dry run'
required: false
default: false
type: boolean
jobs:
CreateRelease:
env:
GH_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
runs-on: [self-hosted, release-maker]
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Prepare Release Info
shell: bash
run: |
if [ ${{ inputs.only-repo }} == "true" ]; then
git tag -l ${{ inputs.ref }} || { echo "With only-repo option ref must be a valid release tag"; exit 1; }
fi
python3 ./tests/ci/create_release.py --prepare-release-info \
--ref ${{ inputs.ref }} --release-type ${{ inputs.type }} \
${{ inputs.dry-run == true && '--dry-run' || '' }} \
${{ inputs.only-repo == true && '--skip-tag-check' || '' }}
echo "::group::Release Info"
python3 -m json.tool /tmp/release_info.json
echo "::endgroup::"
release_tag=$(jq -r '.release_tag' /tmp/release_info.json)
commit_sha=$(jq -r '.commit_sha' /tmp/release_info.json)
is_latest=$(jq -r '.latest' /tmp/release_info.json)
echo "Release Tag: $release_tag"
echo "RELEASE_TAG=$release_tag" >> "$GITHUB_ENV"
echo "COMMIT_SHA=$commit_sha" >> "$GITHUB_ENV"
if [ "$is_latest" == "true" ]; then
echo "DOCKER_TAG_TYPE=release-latest" >> "$GITHUB_ENV"
else
echo "DOCKER_TAG_TYPE=release" >> "$GITHUB_ENV"
fi
- name: Download All Release Artifacts
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --download-packages ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Push Git Tag for the Release
if: ${{ ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --push-release-tag ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Push New Release Branch
if: ${{ inputs.type == 'new' && ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --push-new-release-branch ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Bump CH Version and Update Contributors' List
if: ${{ ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --create-bump-version-pr ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Bump Docker versions, Changelog, Security
if: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --set-progress-started --progress "update changelog, docker version, security"
git checkout master # in case WF started from feature branch
echo "List versions"
./utils/list-versions/list-versions.sh > ./utils/list-versions/version_date.tsv
echo "Update docker version"
./utils/list-versions/update-docker-version.sh
echo "Generate ChangeLog"
export CI=1
docker run -u "${UID}:${GID}" -e PYTHONUNBUFFERED=1 -e CI=1 --network=host \
--volume=".:/wd" --workdir="/wd" \
clickhouse/style-test \
./tests/ci/changelog.py -v --debug-helpers \
--jobs=5 \
--output="./docs/changelogs/${{ env.RELEASE_TAG }}.md" ${{ env.RELEASE_TAG }}
git add ./docs/changelogs/${{ env.RELEASE_TAG }}.md
echo "Generate Security"
python3 ./utils/security-generator/generate_security.py > SECURITY.md
git diff HEAD
- name: Create ChangeLog PR
if: ${{ inputs.type == 'patch' && ! inputs.dry-run && ! inputs.only-repo }}
uses: peter-evans/create-pull-request@v6
with:
author: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
token: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
committer: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
commit-message: Update version_date.tsv and changelogs after ${{ env.RELEASE_TAG }}
branch: auto/${{ env.RELEASE_TAG }}
base: master
assignees: ${{ github.event.sender.login }} # assign the PR to the tag pusher
delete-branch: true
title: Update version_date.tsv and changelog after ${{ env.RELEASE_TAG }}
labels: do not test
body: |
Update version_date.tsv and changelogs after ${{ env.RELEASE_TAG }}
### Changelog category (leave one):
- Not for changelog (changelog entry is not required)
- name: Complete previous steps and Restore git state
if: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --set-progress-completed
git reset --hard HEAD
git checkout "$GITHUB_REF_NAME"
- name: Create GH Release
if: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --create-gh-release ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Export TGZ Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --export-tgz ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Test TGZ Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --test-tgz ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Export RPM Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --export-rpm ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Test RPM Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --test-rpm ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Export Debian Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --export-debian ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Test Debian Packages
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
python3 ./tests/ci/artifactory.py --test-debian ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Docker clickhouse/clickhouse-server building
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
cd "./tests/ci"
python3 ./create_release.py --set-progress-started --progress "docker server release"
export CHECK_NAME="Docker server image"
python3 docker_server.py --tag-type ${{ env.DOCKER_TAG_TYPE }} --version ${{ env.RELEASE_TAG }} --check-name "$CHECK_NAME" --sha ${{ env.COMMIT_SHA }} ${{ ! inputs.dry-run && '--push' || '' }}
python3 ./create_release.py --set-progress-completed
- name: Docker clickhouse/clickhouse-keeper building
if: ${{ inputs.type == 'patch' }}
shell: bash
run: |
cd "./tests/ci"
python3 ./create_release.py --set-progress-started --progress "docker keeper release"
export CHECK_NAME="Docker keeper image"
python3 docker_server.py --tag-type ${{ env.DOCKER_TAG_TYPE }} --version ${{ env.RELEASE_TAG }} --check-name "$CHECK_NAME" --sha ${{ env.COMMIT_SHA }} ${{ ! inputs.dry-run && '--push' || '' }}
python3 ./create_release.py --set-progress-completed
- name: Update release info. Merge created PRs
shell: bash
run: |
python3 ./tests/ci/create_release.py --merge-prs ${{ inputs.dry-run == true && '--dry-run' || '' }}
- name: Set current Release progress to Completed with OK
shell: bash
run: |
# dummy stage to finalize release info with "progress: completed; status: OK"
python3 ./tests/ci/create_release.py --set-progress-started --progress "completed"
python3 ./tests/ci/create_release.py --set-progress-completed
- name: Post Slack Message
if: ${{ !cancelled() }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --post-status ${{ inputs.dry-run == true && '--dry-run' || '' }}

0
.github/workflows/reusable_docker.yml → .github/workflows/docker_test_images.yml vendored
View File

70
.github/workflows/jepsen.yml vendored
View File

@ -9,19 +9,65 @@ on: # yamllint disable-line rule:truthy
- cron: '0 */6 * * *'
workflow_dispatch:
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: PrepareRunConfig
id: runconfig
run: |
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --workflow "$GITHUB_WORKFLOW" --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"
KeeperJepsenRelease:
uses: ./.github/workflows/reusable_simple_job.yml
needs: [RunConfig]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Jepsen keeper check
runner_type: style-checker
report_required: true
test_name: ClickHouse Keeper Jepsen
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 jepsen_check.py keeper
# ServerJepsenRelease:
# uses: ./.github/workflows/reusable_simple_job.yml
# with:
# test_name: Jepsen server check
# runner_type: style-checker
# run_command: |
# cd "$REPO_COPY/tests/ci"
# python3 jepsen_check.py server
ServerJepsenRelease:
if: false # skip for server
needs: [RunConfig]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse Server Jepsen
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 jepsen_check.py server
CheckWorkflow:
if: ${{ !cancelled() }}
needs: [RunConfig, ServerJepsenRelease, KeeperJepsenRelease]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat >> "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

90
.github/workflows/master.yml vendored
View File

@ -33,10 +33,6 @@ jobs:
# 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: |
@ -58,7 +54,7 @@ jobs:
# BuildDockers:
# needs: [RunConfig]
# if: ${{ !failure() && !cancelled() }}
# uses: ./.github/workflows/reusable_docker.yml
# uses: ./.github/workflows/docker_test_images.yml
# with:
# data: ${{ needs.RunConfig.outputs.data }}
# StyleCheck:
@ -97,75 +93,37 @@ jobs:
with:
stage: Builds_2
data: ${{ needs.RunConfig.outputs.data }}
Tests_2:
Tests_2_ww:
needs: [RunConfig, Builds_2]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2_ww') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_2_ww
data: ${{ needs.RunConfig.outputs.data }}
Tests_2:
# Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
needs: [RunConfig, Builds_1]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_2
data: ${{ needs.RunConfig.outputs.data }}
# stage for jobs that do not prohibit merge
Tests_3:
# Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
needs: [RunConfig, Builds_1, Builds_2]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_3
data: ${{ needs.RunConfig.outputs.data }}
################################# Reports #################################
# Reports should be run even if Builds_1/2 failed - put them separately in wf (not in Tests_1/2)
Builds_1_Report:
# Reports should run even if Builds_1/2 fail - run them separately, not in Tests_1/2/3
Builds_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
needs: [RunConfig, Builds_1]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
Builds_2_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
needs: [RunConfig, Builds_2]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
MarkReleaseReady:
if: ${{ !failure() && !cancelled() }}
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
needs: [RunConfig, Builds_1, Builds_2]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Debug
run: |
echo need with different filters
cat << 'EOF'
${{ toJSON(needs) }}
${{ toJSON(needs.*.result) }}
no failures ${{ !contains(needs.*.result, 'failure') }}
no skips ${{ !contains(needs.*.result, 'skipped') }}
no both ${{ !(contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
EOF
- name: Not ready
# fail the job to be able to restart it
if: ${{ contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure') }}
run: exit 1
- name: Check out repository code
if: ${{ ! (contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
uses: ClickHouse/checkout@v1
- name: Mark Commit Release Ready
if: ${{ ! (contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Builds
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
FinishCheck:
if: ${{ !cancelled() }}
needs: [RunConfig, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2, Tests_3]
needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
@ -173,4 +131,12 @@ jobs:
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

32
.github/workflows/merge_queue.yml vendored
View File

@ -30,10 +30,6 @@ jobs:
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: |
@ -51,7 +47,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
@ -96,20 +92,28 @@ jobs:
stage: Tests_1
data: ${{ needs.RunConfig.outputs.data }}
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !failure() && !cancelled() }}
CheckReadyForMerge:
if: ${{ !cancelled() }}
# Test_2 or Test_3 must not have jobs required for Mergeable check
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Tests_1]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check sync status
- name: Check and set merge status
if: ${{ needs.StyleCheck.result == 'success' }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
cd "$GITHUB_WORKSPACE/tests/ci"
python3 sync_pr.py --status
- name: Finish label
python3 merge_pr.py --set-ci-status
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

17
.github/workflows/nightly.yml vendored
View File

@ -40,7 +40,22 @@ jobs:
} >> "$GITHUB_OUTPUT"
BuildDockers:
needs: [RunConfig]
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: "${{ needs.RunConfig.outputs.data }}"
set_latest: true
CheckWorkflow:
if: ${{ !cancelled() }}
needs: [RunConfig, BuildDockers]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

74
.github/workflows/pull_request.yml vendored
View File

@ -48,10 +48,6 @@ jobs:
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: |
@ -72,7 +68,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
@ -126,46 +122,44 @@ jobs:
with:
stage: Builds_2
data: ${{ needs.RunConfig.outputs.data }}
# stage for running non-required checks without being blocked by required checks (Test_1) if corresponding settings is selected
Tests_2_ww:
needs: [RunConfig, Builds_1]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2_ww') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_2_ww
data: ${{ needs.RunConfig.outputs.data }}
Tests_2:
needs: [RunConfig, Builds_2]
needs: [RunConfig, Builds_1, Tests_1]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_2
data: ${{ needs.RunConfig.outputs.data }}
# stage for jobs that do not prohibit merge
Tests_3:
needs: [RunConfig, Builds_1, Tests_1, Builds_2, Tests_2]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_3
data: ${{ needs.RunConfig.outputs.data }}
################################# Reports #################################
# Reports should by run even if Builds_1/2 fail, so put them separately in wf (not in Tests_1/2)
Builds_1_Report:
# Reports should run even if Builds_1/2 fail - run them separately (not in Tests_1/2/3)
Builds_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
needs: [RunConfig, StyleCheck, Builds_1]
if: ${{ !cancelled()
&& needs.RunConfig.result == 'success'
&& needs.StyleCheck.result != 'failure'
&& needs.FastTest.result != 'failure'
&& needs.BuildDockers.result != 'failure'
&& contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
Builds_2_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
needs: [RunConfig, StyleCheck, Builds_2]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
test_name: Builds
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
CheckReadyForMerge:
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2]
if: ${{ !cancelled() }}
# Test_2 or Test_3 do not have the jobs required for Mergeable check,
# however, set them as "needs" to get all checks results before the automatic merge occurs.
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
@ -173,15 +167,24 @@ jobs:
with:
filter: tree:0
- name: Check and set merge status
if: ${{ needs.StyleCheck.result == 'success' }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 merge_pr.py --set-ci-status
- name: Check Workflow results
uses: ./.github/actions/check_workflow
with:
needs: ${{ toJson(needs) }}
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2, Tests_3]
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
@ -191,7 +194,7 @@ jobs:
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
#############################################################################################
###################################### JEPSEN TESTS #########################################
@ -204,8 +207,7 @@ jobs:
concurrency:
group: jepsen
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse Keeper Jepsen') }}
# jepsen needs binary_release build which is in Builds_2
needs: [RunConfig, Builds_2]
needs: [RunConfig, Builds_1]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse Keeper Jepsen

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

@ -1,69 +0,0 @@
name: PublishedReleaseCI
# - Gets artifacts from S3
# - Sends it to JFROG Artifactory
# - Adds them to the release assets
on: # yamllint disable-line rule:truthy
release:
types:
- published
workflow_dispatch:
inputs:
tag:
description: 'Release tag'
required: true
type: string
jobs:
ReleasePublish:
runs-on: [self-hosted, style-checker]
steps:
- name: Set tag from input
if: github.event_name == 'workflow_dispatch'
run: |
echo "GITHUB_TAG=${{ github.event.inputs.tag }}" >> "$GITHUB_ENV"
- name: Set tag from REF
if: github.event_name == 'release'
run: |
echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
- name: Deploy packages and assets
run: |
curl --silent --data '' --no-buffer \
'${{ secrets.PACKAGES_RELEASE_URL }}/release/'"${GITHUB_TAG}"'?binary=binary_darwin&binary=binary_darwin_aarch64&sync=true'
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
runs-on: [self-hosted, style-checker]
steps:
- name: Set tag from input
if: github.event_name == 'workflow_dispatch'
run: |
echo "GITHUB_TAG=${{ github.event.inputs.tag }}" >> "$GITHUB_ENV"
- name: Set tag from REF
if: github.event_name == 'release'
run: |
echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # otherwise we will have no version info
filter: tree:0
ref: ${{ env.GITHUB_TAG }}
- name: Check docker clickhouse/clickhouse-server building
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
export CHECK_NAME="Docker server image"
python3 docker_server.py --release-type auto --version "$GITHUB_TAG" --check-name "$CHECK_NAME" --push
- name: Check docker clickhouse/clickhouse-keeper building
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
export CHECK_NAME="Docker keeper image"
python3 docker_server.py --release-type auto --version "$GITHUB_TAG" --check-name "$CHECK_NAME" --push
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"

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

@ -33,10 +33,6 @@ jobs:
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: |
@ -57,7 +53,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:
@ -65,7 +61,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Compatibility check (amd64)
test_name: Compatibility check (release)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckAarch64:
@ -176,35 +172,24 @@ jobs:
############################################################################################
##################################### BUILD REPORTER #######################################
############################################################################################
BuilderReport:
Builds_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() }}
needs:
- RunConfig
- BuilderDebRelease
- BuilderDebAarch64
- BuilderDebAsan
- BuilderDebTsan
- BuilderDebUBsan
- BuilderDebMsan
- BuilderDebDebug
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
BuilderSpecialReport:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() }}
needs:
- RunConfig
- BuilderBinDarwin
- BuilderBinDarwinAarch64
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64, BuilderDebAsan, BuilderDebUBsan, BuilderDebMsan, BuilderDebTsan, BuilderDebDebug, BuilderBinDarwin, BuilderBinDarwinAarch64]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Download reports
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --pre --job-name Builds
- name: Builds report
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 ./build_report_check.py --reports package_release package_aarch64 package_asan package_msan package_ubsan package_tsan package_debug binary_darwin binary_darwin_aarch64
- name: Set status
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --post --job-name Builds
MarkReleaseReady:
if: ${{ !failure() && !cancelled() }}
needs:
@ -244,7 +229,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (amd64)
test_name: Install packages (release)
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
@ -254,7 +239,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Install packages (arm64)
test_name: Install packages (aarch64)
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
@ -456,12 +441,12 @@ jobs:
runner_type: stress-tester
data: ${{ needs.RunConfig.outputs.data }}
FinishCheck:
if: ${{ !failure() && !cancelled() }}
if: ${{ !cancelled() }}
needs:
- RunConfig
- DockerServerImage
- DockerKeeperImage
- BuilderReport
- BuilderSpecialReport
- Builds_Report
- MarkReleaseReady
- FunctionalStatelessTestDebug
- FunctionalStatelessTestRelease
@ -494,6 +479,16 @@ jobs:
with:
clear-repository: true
- name: Finish label
if: ${{ !failure() }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
# update overall ci report
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
- name: Check Workflow results
if: ${{ !cancelled() }}
run: |
export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
${{ toJson(needs) }}
EOF
python3 ./tests/ci/ci_buddy.py --check-wf-status

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

@ -102,6 +102,8 @@ jobs:
--job-name '${{inputs.test_name}}' \
--run \
--run-command '''${{inputs.run_command}}'''
# shellcheck disable=SC2319
echo "JOB_EXIT_CODE=$?" >> "$GITHUB_ENV"
- name: Post run
if: ${{ !cancelled() }}
run: |

73
.github/workflows/tags_stable.yml vendored
View File

@ -1,73 +0,0 @@
name: TagsStableWorkflow
# - Gets artifacts from S3
# - Sends it to JFROG Artifactory
# - Adds them to the release assets
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
push:
tags:
- 'v*-prestable'
- 'v*-stable'
- 'v*-lts'
workflow_dispatch:
inputs:
tag:
description: 'Test tag'
required: true
type: string
jobs:
UpdateVersions:
runs-on: [self-hosted, style-checker]
steps:
- name: Set test tag
if: github.event_name == 'workflow_dispatch'
run: |
echo "GITHUB_TAG=${{ github.event.inputs.tag }}" >> "$GITHUB_ENV"
- name: Get tag name
if: github.event_name != 'workflow_dispatch'
run: |
echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
ref: master
fetch-depth: 0
filter: tree:0
- name: Update versions, docker version, changelog, security
env:
GITHUB_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
run: |
./utils/list-versions/list-versions.sh > ./utils/list-versions/version_date.tsv
./utils/list-versions/update-docker-version.sh
GID=$(id -g "${UID}")
docker run -u "${UID}:${GID}" -e PYTHONUNBUFFERED=1 \
--volume="${GITHUB_WORKSPACE}:/ClickHouse" clickhouse/style-test \
/ClickHouse/utils/changelog/changelog.py -v --debug-helpers \
--gh-user-or-token="$GITHUB_TOKEN" --jobs=5 \
--output="/ClickHouse/docs/changelogs/${GITHUB_TAG}.md" "${GITHUB_TAG}"
git add "./docs/changelogs/${GITHUB_TAG}.md"
python3 ./utils/security-generator/generate_security.py > SECURITY.md
git diff HEAD
- name: Create Pull Request
uses: peter-evans/create-pull-request@v6
with:
author: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
token: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
committer: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
commit-message: Update version_date.tsv and changelogs after ${{ env.GITHUB_TAG }}
branch: auto/${{ env.GITHUB_TAG }}
assignees: ${{ github.event.sender.login }} # assign the PR to the tag pusher
delete-branch: true
title: Update version_date.tsv and changelogs after ${{ env.GITHUB_TAG }}
labels: do not test
body: |
Update version_date.tsv and changelogs after ${{ env.GITHUB_TAG }}
### Changelog category (leave one):
- Not for changelog (changelog entry is not required)

11
.gitmodules vendored
View File

@ -91,13 +91,13 @@
[submodule "contrib/aws"]
path = contrib/aws
url = https://github.com/ClickHouse/aws-sdk-cpp
[submodule "aws-c-event-stream"]
[submodule "contrib/aws-c-event-stream"]
path = contrib/aws-c-event-stream
url = https://github.com/awslabs/aws-c-event-stream
[submodule "aws-c-common"]
[submodule "contrib/aws-c-common"]
path = contrib/aws-c-common
url = https://github.com/awslabs/aws-c-common.git
[submodule "aws-checksums"]
[submodule "contrib/aws-checksums"]
path = contrib/aws-checksums
url = https://github.com/awslabs/aws-checksums
[submodule "contrib/curl"]
@ -163,7 +163,7 @@
url = https://github.com/xz-mirror/xz
[submodule "contrib/abseil-cpp"]
path = contrib/abseil-cpp
url = https://github.com/abseil/abseil-cpp
url = https://github.com/ClickHouse/abseil-cpp.git
[submodule "contrib/dragonbox"]
path = contrib/dragonbox
url = https://github.com/ClickHouse/dragonbox
@ -372,3 +372,6 @@
[submodule "contrib/double-conversion"]
path = contrib/double-conversion
url = https://github.com/ClickHouse/double-conversion.git
[submodule "contrib/numactl"]
path = contrib/numactl
url = https://github.com/ClickHouse/numactl.git

15
.yamllint
View File

@ -5,13 +5,12 @@ rules:
indentation:
level: warning
indent-sequences: consistent
line-length:
# there are:
# - bash -c "", so this is OK
# - yaml in tests
max: 1000
level: warning
comments:
min-spaces-from-content: 1
document-start:
present: false
document-start: disable
colons: disable
indentation: disable
line-length: disable
trailing-spaces: disable
truthy: disable
new-line-at-end-of-file: disable

332
CHANGELOG.md
View File

@ -1,4 +1,6 @@
### Table of Contents
**[ClickHouse release v24.7, 2024-07-30](#247)**<br/>
**[ClickHouse release v24.6, 2024-07-01](#246)**<br/>
**[ClickHouse release v24.5, 2024-05-30](#245)**<br/>
**[ClickHouse release v24.4, 2024-04-30](#244)**<br/>
**[ClickHouse release v24.3 LTS, 2024-03-26](#243)**<br/>
@ -8,6 +10,336 @@
# 2024 Changelog
### <a id="247"></a> ClickHouse release 24.7, 2024-07-30
#### Backward Incompatible Change
* Forbid `CRATE MATERIALIZED VIEW ... ENGINE Replicated*MergeTree POPULATE AS SELECT ...` with Replicated databases. [#63963](https://github.com/ClickHouse/ClickHouse/pull/63963) ([vdimir](https://github.com/vdimir)).
* `clickhouse-keeper-client` will only accept paths in string literals, such as `ls '/hello/world'`, not bare strings such as `ls /hello/world`. [#65494](https://github.com/ClickHouse/ClickHouse/pull/65494) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Metric `KeeperOutstandingRequets` was renamed to `KeeperOutstandingRequests`. [#66206](https://github.com/ClickHouse/ClickHouse/pull/66206) ([Robert Schulze](https://github.com/rschu1ze)).
* Remove `is_deterministic` field from the `system.functions` table. [#66630](https://github.com/ClickHouse/ClickHouse/pull/66630) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Function `tuple` will now try to construct named tuples in query (controlled by `enable_named_columns_in_function_tuple`). Introduce function `tupleNames` to extract names from tuples. [#54881](https://github.com/ClickHouse/ClickHouse/pull/54881) ([Amos Bird](https://github.com/amosbird)).
* Change how deduplication for Materialized Views works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)).
#### New Feature
* Add `ASOF JOIN` support for `full_sorting_join` algorithm. [#55051](https://github.com/ClickHouse/ClickHouse/pull/55051) ([vdimir](https://github.com/vdimir)).
* Support JWT authentication in `clickhouse-client` (will be available only in ClickHouse Cloud). [#62829](https://github.com/ClickHouse/ClickHouse/pull/62829) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Add SQL functions `changeYear`, `changeMonth`, `changeDay`, `changeHour`, `changeMinute`, `changeSecond`. For example, `SELECT changeMonth(toDate('2024-06-14'), 7)` returns date `2024-07-14`. [#63186](https://github.com/ClickHouse/ClickHouse/pull/63186) ([cucumber95](https://github.com/cucumber95)).
* Introduce startup scripts, which allow the execution of preconfigured queries at the startup stage. [#64889](https://github.com/ClickHouse/ClickHouse/pull/64889) ([pufit](https://github.com/pufit)).
* Support accept_invalid_certificate in client's config in order to allow for client to connect over secure TCP to a server running with self-signed certificate - can be used as a shorthand for corresponding `openSSL` client settings `verificationMode=none` + `invalidCertificateHandler.name=AcceptCertificateHandler`. [#65238](https://github.com/ClickHouse/ClickHouse/pull/65238) ([peacewalker122](https://github.com/peacewalker122)).
* Add system.error_log which contains history of error values from table system.errors, periodically flushed to disk. [#65381](https://github.com/ClickHouse/ClickHouse/pull/65381) ([Pablo Marcos](https://github.com/pamarcos)).
* Add aggregate function `groupConcat`. About the same as `arrayStringConcat( groupArray(column), ',')` Can receive 2 parameters: a string delimiter and the number of elements to be processed. [#65451](https://github.com/ClickHouse/ClickHouse/pull/65451) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Add AzureQueue storage. [#65458](https://github.com/ClickHouse/ClickHouse/pull/65458) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add a new setting to disable/enable writing page index into parquet files. [#65475](https://github.com/ClickHouse/ClickHouse/pull/65475) ([lgbo](https://github.com/lgbo-ustc)).
* Introduce `logger.console_log_level` server config to control the log level to the console (if enabled). [#65559](https://github.com/ClickHouse/ClickHouse/pull/65559) ([Azat Khuzhin](https://github.com/azat)).
* Automatically append a wildcard `*` to the end of a directory path with table function `file`. [#66019](https://github.com/ClickHouse/ClickHouse/pull/66019) ([Zhidong (David) Guo](https://github.com/Gun9niR)).
* Add `--memory-usage` option to client in non-interactive mode. [#66393](https://github.com/ClickHouse/ClickHouse/pull/66393) ([vdimir](https://github.com/vdimir)).
* Make an interactive client for clickhouse-disks, add local disk from the local directory. [#64446](https://github.com/ClickHouse/ClickHouse/pull/64446) ([Daniil Ivanik](https://github.com/divanik)).
* When lightweight delete happens on a table with projection(s), users have choices either throw an exception (by default) or drop the projection [#65594](https://github.com/ClickHouse/ClickHouse/pull/65594) ([jsc0218](https://github.com/jsc0218)).
* Add system tables with main information about all detached tables. [#65400](https://github.com/ClickHouse/ClickHouse/pull/65400) ([Konstantin Morozov](https://github.com/k-morozov)).
#### Experimental Feature
* Change binary serialization of the `Variant` data type: add `compact` mode to avoid writing the same discriminator multiple times for granules with single variant or with only NULL values. Add MergeTree setting `use_compact_variant_discriminators_serialization` that is enabled by default. Note that Variant type is still experimental and backward-incompatible change in serialization is ok. [#62774](https://github.com/ClickHouse/ClickHouse/pull/62774) ([Kruglov Pavel](https://github.com/Avogar)).
* Support on-disk backend storage for clickhouse-keeper. [#56626](https://github.com/ClickHouse/ClickHouse/pull/56626) ([Han Fei](https://github.com/hanfei1991)).
* Refactor JSONExtract functions, support more types including experimental Dynamic type. [#66046](https://github.com/ClickHouse/ClickHouse/pull/66046) ([Kruglov Pavel](https://github.com/Avogar)).
* Support null map subcolumn for `Variant` and `Dynamic` subcolumns. [#66178](https://github.com/ClickHouse/ClickHouse/pull/66178) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix reading `Dynamic` subcolumns from altered `Memory` table. Previously if `max_types` parameter of a Dynamic type was changed in Memory table via alter, further subcolumns reading can return wrong result. [#66066](https://github.com/ClickHouse/ClickHouse/pull/66066) ([Kruglov Pavel](https://github.com/Avogar)).
* Add support for `cluster_for_parallel_replicas` when using custom key parallel replicas. It allows you to use parallel replicas with custom key with MergeTree tables. [#65453](https://github.com/ClickHouse/ClickHouse/pull/65453) ([Antonio Andelic](https://github.com/antonio2368)).
#### Performance Improvement
* Replace int to string algorithm with a faster one (from a modified amdn/itoa to a modified jeaiii/itoa). [#61661](https://github.com/ClickHouse/ClickHouse/pull/61661) ([Raúl Marín](https://github.com/Algunenano)).
* Sizes of hash tables created by join (`parallel_hash` algorithm) are collected and cached now. This information will be used to preallocate space in hash tables for subsequent query executions and save time on hash table resizes. [#64553](https://github.com/ClickHouse/ClickHouse/pull/64553) ([Nikita Taranov](https://github.com/nickitat)).
* Optimized queries with `ORDER BY` primary key and `WHERE` that have a condition with high selectivity by using buffering. It is controlled by setting `read_in_order_use_buffering` (enabled by default) and can increase memory usage of query. [#64607](https://github.com/ClickHouse/ClickHouse/pull/64607) ([Anton Popov](https://github.com/CurtizJ)).
* Improve performance of loading `plain_rewritable` metadata. [#65634](https://github.com/ClickHouse/ClickHouse/pull/65634) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Attaching tables on read-only disks will use fewer resources by not loading outdated parts. [#65635](https://github.com/ClickHouse/ClickHouse/pull/65635) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Support minmax hyperrectangle for Set indices. [#65676](https://github.com/ClickHouse/ClickHouse/pull/65676) ([AntiTopQuark](https://github.com/AntiTopQuark)).
* Unload primary index of outdated parts to reduce total memory usage. [#65852](https://github.com/ClickHouse/ClickHouse/pull/65852) ([Anton Popov](https://github.com/CurtizJ)).
* Functions `replaceRegexpAll` and `replaceRegexpOne` are now significantly faster if the pattern is trivial, i.e. contains no metacharacters, pattern classes, flags, grouping characters etc. (Thanks to Taiyang Li). [#66185](https://github.com/ClickHouse/ClickHouse/pull/66185) ([Robert Schulze](https://github.com/rschu1ze)).
* s3 requests: Reduce retry time for queries, increase retries count for backups. 8.5 minutes and 100 retires for queries, 1.2 hours and 1000 retries for backup restore. [#65232](https://github.com/ClickHouse/ClickHouse/pull/65232) ([Sema Checherinda](https://github.com/CheSema)).
* Support query plan LIMIT optimization. Support LIMIT pushdown for PostgreSQL storage and table function. [#65454](https://github.com/ClickHouse/ClickHouse/pull/65454) ([Maksim Kita](https://github.com/kitaisreal)).
* Improved ZooKeeper load balancing. The current session doesn't expire until the optimal nodes become available despite `fallback_session_lifetime`. Added support for AZ-aware balancing. [#65570](https://github.com/ClickHouse/ClickHouse/pull/65570) ([Alexander Tokmakov](https://github.com/tavplubix)).
* DatabaseCatalog drops tables faster by using up to database_catalog_drop_table_concurrency threads. [#66065](https://github.com/ClickHouse/ClickHouse/pull/66065) ([Sema Checherinda](https://github.com/CheSema)).
#### Improvement
* Improved ZooKeeper load balancing. The current session doesn't expire until the optimal nodes become available despite `fallback_session_lifetime`. Added support for AZ-aware balancing. [#65570](https://github.com/ClickHouse/ClickHouse/pull/65570) ([Alexander Tokmakov](https://github.com/tavplubix)).
* The setting `optimize_trivial_insert_select` is disabled by default. In most cases, it should be beneficial. Nevertheless, if you are seeing slower INSERT SELECT or increased memory usage, you can enable it back or `SET compatibility = '24.6'`. [#58970](https://github.com/ClickHouse/ClickHouse/pull/58970) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Print stacktrace and diagnostic info if `clickhouse-client` or `clickhouse-local` crashes. [#61109](https://github.com/ClickHouse/ClickHouse/pull/61109) ([Alexander Tokmakov](https://github.com/tavplubix)).
* The result of `SHOW INDEX | INDEXES | INDICES | KEYS` was previously sorted by the primary key column names. Since this was unintuitive, the result is now sorted by the position of the primary key columns within the primary key. [#61131](https://github.com/ClickHouse/ClickHouse/pull/61131) ([Robert Schulze](https://github.com/rschu1ze)).
* Change how deduplication for Materialized Views works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)).
* Support reading partitioned data DeltaLake data. Infer DeltaLake schema by reading metadata instead of data. [#63201](https://github.com/ClickHouse/ClickHouse/pull/63201) ([Kseniia Sumarokova](https://github.com/kssenii)).
* In composable protocols TLS layer accepted only `certificateFile` and `privateKeyFile` parameters. https://clickhouse.com/docs/en/operations/settings/composable-protocols. [#63985](https://github.com/ClickHouse/ClickHouse/pull/63985) ([Anton Ivashkin](https://github.com/ianton-ru)).
* Added profile event `SelectQueriesWithPrimaryKeyUsage` which indicates how many SELECT queries use the primary key to evaluate the WHERE clause. [#64492](https://github.com/ClickHouse/ClickHouse/pull/64492) ([0x01f](https://github.com/0xfei)).
* `StorageS3Queue` related fixes and improvements. Deduce a default value of `s3queue_processing_threads_num` according to the number of physical cpu cores on the server (instead of the previous default value as 1). Set default value of `s3queue_loading_retries` to 10. Fix possible vague "Uncaught exception" in exception column of `system.s3queue`. Do not increment retry count on `MEMORY_LIMIT_EXCEEDED` exception. Move files commit to a stage after insertion into table fully finished to avoid files being commited while not inserted. Add settings `s3queue_max_processed_files_before_commit`, `s3queue_max_processed_rows_before_commit`, `s3queue_max_processed_bytes_before_commit`, `s3queue_max_processing_time_sec_before_commit`, to better control commit and flush time. [#65046](https://github.com/ClickHouse/ClickHouse/pull/65046) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Support aliases in parametrized view function (only new analyzer). [#65190](https://github.com/ClickHouse/ClickHouse/pull/65190) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Updated to mask account key in logs in azureBlobStorage. [#65273](https://github.com/ClickHouse/ClickHouse/pull/65273) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Partition pruning for `IN` predicates when filter expression is a part of `PARTITION BY` expression. [#65335](https://github.com/ClickHouse/ClickHouse/pull/65335) ([Eduard Karacharov](https://github.com/korowa)).
* `arrayMin`/`arrayMax` can be applicable to all data types that are comparable. [#65455](https://github.com/ClickHouse/ClickHouse/pull/65455) ([pn](https://github.com/chloro-pn)).
* Improved memory accounting for cgroups v2 to exclude the amount occupied by the page cache. [#65470](https://github.com/ClickHouse/ClickHouse/pull/65470) ([Nikita Taranov](https://github.com/nickitat)).
* Do not create format settings for each row when serializing chunks to insert to EmbeddedRocksDB table. [#65474](https://github.com/ClickHouse/ClickHouse/pull/65474) ([Duc Canh Le](https://github.com/canhld94)).
* Reduce `clickhouse-local` prompt to just `:)`. `getFQDNOrHostName()` takes too long on macOS, and we don't want a hostname in the prompt for `clickhouse-local` anyway. [#65510](https://github.com/ClickHouse/ClickHouse/pull/65510) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Avoid printing a message from jemalloc about per-CPU arenas on low-end virtual machines. [#65532](https://github.com/ClickHouse/ClickHouse/pull/65532) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Disable filesystem cache background download by default. It will be enabled back when we fix the issue with possible "Memory limit exceeded" because memory deallocation is done outside of query context (while buffer is allocated inside of query context) if we use background download threads. Plus we need to add a separate setting to define max size to download for background workers (currently it is limited by max_file_segment_size, which might be too big). [#65534](https://github.com/ClickHouse/ClickHouse/pull/65534) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add new option to config `<config_reload_interval_ms>` which allow to specify how often clickhouse will reload config. [#65545](https://github.com/ClickHouse/ClickHouse/pull/65545) ([alesapin](https://github.com/alesapin)).
* Implement binary encoding for ClickHouse data types and add its specification in docs. Use it in Dynamic binary serialization, allow to use it in RowBinaryWithNamesAndTypes and Native formats under settings. [#65546](https://github.com/ClickHouse/ClickHouse/pull/65546) ([Kruglov Pavel](https://github.com/Avogar)).
* Server settings `compiled_expression_cache_size` and `compiled_expression_cache_elements_size` are now shown in `system.server_settings`. [#65584](https://github.com/ClickHouse/ClickHouse/pull/65584) ([Robert Schulze](https://github.com/rschu1ze)).
* Add support for user identification based on x509 SubjectAltName extension. [#65626](https://github.com/ClickHouse/ClickHouse/pull/65626) ([Anton Kozlov](https://github.com/tonickkozlov)).
* `clickhouse-local` will respect the `max_server_memory_usage` and `max_server_memory_usage_to_ram_ratio` from the configuration file. It will also set the max memory usage to 90% of the system memory by default, like `clickhouse-server` does. [#65697](https://github.com/ClickHouse/ClickHouse/pull/65697) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add a script to backup your files to ClickHouse. [#65699](https://github.com/ClickHouse/ClickHouse/pull/65699) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* PostgreSQL source to support query cancellations. [#65722](https://github.com/ClickHouse/ClickHouse/pull/65722) ([Maksim Kita](https://github.com/kitaisreal)).
* Make `allow_experimental_analyzer` be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Respect cgroup CPU limit in Keeper. [#65819](https://github.com/ClickHouse/ClickHouse/pull/65819) ([Antonio Andelic](https://github.com/antonio2368)).
* Allow to use `concat` function with empty arguments `:) select concat();`. [#65887](https://github.com/ClickHouse/ClickHouse/pull/65887) ([李扬](https://github.com/taiyang-li)).
* Allow controlling named collections in `clickhouse-local`. [#65973](https://github.com/ClickHouse/ClickHouse/pull/65973) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve Azure-related profile events. [#65999](https://github.com/ClickHouse/ClickHouse/pull/65999) ([alesapin](https://github.com/alesapin)).
* Support ORC file read by writer's time zone. [#66025](https://github.com/ClickHouse/ClickHouse/pull/66025) ([kevinyhzou](https://github.com/KevinyhZou)).
* Add settings to control connections to PostgreSQL. The setting `postgresql_connection_attempt_timeout` specifies the value passed to `connect_timeout` parameter of connection URL. The setting `postgresql_connection_pool_retries` specifies the number of retries to establish a connection to the PostgreSQL end-point. [#66232](https://github.com/ClickHouse/ClickHouse/pull/66232) ([Dmitry Novik](https://github.com/novikd)).
* Reduce inaccuracy of `input_wait_elapsed_us`/`elapsed_us` in the `system.processors_profile_log`. [#66239](https://github.com/ClickHouse/ClickHouse/pull/66239) ([Azat Khuzhin](https://github.com/azat)).
* Improve ProfileEvents for the filesystem cache. [#66249](https://github.com/ClickHouse/ClickHouse/pull/66249) ([zhukai](https://github.com/nauu)).
* Add settings to ignore the `ON CLUSTER` clause in queries for named collection management with the replicated storage. [#66288](https://github.com/ClickHouse/ClickHouse/pull/66288) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Function `generateSnowflakeID` now allows to specify a machine ID as a parameter to prevent collisions in large clusters. [#66374](https://github.com/ClickHouse/ClickHouse/pull/66374) ([ZAWA_ll](https://github.com/Zawa-ll)).
* Disable suspending on `Ctrl+Z` in interactive mode. This is a common trap and is not expected behavior for almost all users. I imagine only a few extreme power users could appreciate suspending terminal applications to the background, but I don't know any. [#66511](https://github.com/ClickHouse/ClickHouse/pull/66511) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add option for validating the primary key type in Dictionaries. Without this option for simple layouts any column type will be implicitly converted to UInt64. [#66595](https://github.com/ClickHouse/ClickHouse/pull/66595) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Check cyclic dependencies on CREATE/REPLACE/RENAME/EXCHANGE queries and throw an exception if there is a cyclic dependency. Previously such cyclic dependencies could lead to a deadlock during server startup. Also fix some bugs in dependencies creation. [#65405](https://github.com/ClickHouse/ClickHouse/pull/65405) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix unexpected sizes of `LowCardinality` columns in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
* Fix crash in maxIntersections. [#65689](https://github.com/ClickHouse/ClickHouse/pull/65689) ([Raúl Marín](https://github.com/Algunenano)).
* Fix the `VALID UNTIL` clause in the user definition resetting after a restart. [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix the remaining time column in `SHOW MERGES`. [#66735](https://github.com/ClickHouse/ClickHouse/pull/66735) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* `Query was cancelled` might have been printed twice in clickhouse-client. This behaviour is fixed. [#66005](https://github.com/ClickHouse/ClickHouse/pull/66005) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fixed crash while using `MaterializedMySQL` (which is an unsupported, experimental feature) with TABLE OVERRIDE that maps MySQL NULL field into ClickHouse not NULL field. [#54649](https://github.com/ClickHouse/ClickHouse/pull/54649) ([Filipp Ozinov](https://github.com/bakwc)).
* Fix logical error when `PREWHERE` expression read no columns and table has no adaptive index granularity (very old table). [#59173](https://github.com/ClickHouse/ClickHouse/pull/59173) ([Alexander Gololobov](https://github.com/davenger)).
* Fix bug with the cancellation buffer when canceling a query. [#64478](https://github.com/ClickHouse/ClickHouse/pull/64478) ([Sema Checherinda](https://github.com/CheSema)).
* Fix filling parts columns from metadata (when columns.txt does not exists). [#64757](https://github.com/ClickHouse/ClickHouse/pull/64757) ([Azat Khuzhin](https://github.com/azat)).
* Fix crash for `ALTER TABLE ... ON CLUSTER ... MODIFY SQL SECURITY`. [#64957](https://github.com/ClickHouse/ClickHouse/pull/64957) ([pufit](https://github.com/pufit)).
* Fix crash on destroying AccessControl: add explicit shutdown. [#64993](https://github.com/ClickHouse/ClickHouse/pull/64993) ([Vitaly Baranov](https://github.com/vitlibar)).
* Eliminate injective function in argument of functions `uniq*` recursively. This used to work correctly but was broken in the new analyzer. [#65140](https://github.com/ClickHouse/ClickHouse/pull/65140) ([Duc Canh Le](https://github.com/canhld94)).
* Fix unexpected projection name when query with CTE. [#65267](https://github.com/ClickHouse/ClickHouse/pull/65267) ([wudidapaopao](https://github.com/wudidapaopao)).
* Require `dictGet` privilege when accessing dictionaries via direct query or the `Dictionary` table engine. [#65359](https://github.com/ClickHouse/ClickHouse/pull/65359) ([Joe Lynch](https://github.com/joelynch)).
* Fix user-specific S3 auth with incremental backups. [#65481](https://github.com/ClickHouse/ClickHouse/pull/65481) ([Antonio Andelic](https://github.com/antonio2368)).
* Disable `non-intersecting-parts` optimization for queries with `FINAL` in case of `read-in-order` optimization was enabled. This could lead to an incorrect query result. As a workaround, disable `do_not_merge_across_partitions_select_final` and `split_parts_ranges_into_intersecting_and_non_intersecting_final` before this fix is merged. [#65505](https://github.com/ClickHouse/ClickHouse/pull/65505) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix getting exception `Index out of bound for blob metadata` in case all files from list batch were filtered out. [#65523](https://github.com/ClickHouse/ClickHouse/pull/65523) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix NOT_FOUND_COLUMN_IN_BLOCK for deduplicate merge of projection. [#65573](https://github.com/ClickHouse/ClickHouse/pull/65573) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Fixed bug in MergeJoin. Column in sparse serialisation might be treated as a column of its nested type though the required conversion wasn't performed. [#65632](https://github.com/ClickHouse/ClickHouse/pull/65632) ([Nikita Taranov](https://github.com/nickitat)).
* Fixed a bug that compatibility level '23.4' was not properly applied. [#65737](https://github.com/ClickHouse/ClickHouse/pull/65737) ([cw5121](https://github.com/cw5121)).
* Fix odbc table with nullable fields. [#65738](https://github.com/ClickHouse/ClickHouse/pull/65738) ([Rodolphe Dugé de Bernonville](https://github.com/RodolpheDuge)).
* Fix data race in `TCPHandler`, which could happen on fatal error. [#65744](https://github.com/ClickHouse/ClickHouse/pull/65744) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix invalid exceptions in function `parseDateTime` with `%F` and `%D` placeholders. [#65768](https://github.com/ClickHouse/ClickHouse/pull/65768) ([Antonio Andelic](https://github.com/antonio2368)).
* For queries that read from `PostgreSQL`, cancel the internal `PostgreSQL` query if the ClickHouse query is finished. Otherwise, `ClickHouse` query cannot be canceled until the internal `PostgreSQL` query is finished. [#65771](https://github.com/ClickHouse/ClickHouse/pull/65771) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix a bug in short circuit logic when old analyzer and dictGetOrDefault is used. [#65802](https://github.com/ClickHouse/ClickHouse/pull/65802) ([jsc0218](https://github.com/jsc0218)).
* Fix a bug leads to EmbeddedRocksDB with TTL write corrupted SST files. [#65816](https://github.com/ClickHouse/ClickHouse/pull/65816) ([Duc Canh Le](https://github.com/canhld94)).
* Functions `bitTest`, `bitTestAll`, and `bitTestAny` now return an error if the specified bit index is out-of-bounds [#65818](https://github.com/ClickHouse/ClickHouse/pull/65818) ([Pablo Marcos](https://github.com/pamarcos)).
* Setting `join_any_take_last_row` is supported in any query with hash join. [#65820](https://github.com/ClickHouse/ClickHouse/pull/65820) ([vdimir](https://github.com/vdimir)).
* Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
* Functions `bitShiftLeft` and `bitShitfRight` return an error for out of bounds shift positions [#65838](https://github.com/ClickHouse/ClickHouse/pull/65838) ([Pablo Marcos](https://github.com/pamarcos)).
* Fix growing memory usage in S3Queue. [#65839](https://github.com/ClickHouse/ClickHouse/pull/65839) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix tie handling in `arrayAUC` to match sklearn. [#65840](https://github.com/ClickHouse/ClickHouse/pull/65840) ([gabrielmcg44](https://github.com/gabrielmcg44)).
* Fix possible issues with MySQL server protocol TLS connections. [#65917](https://github.com/ClickHouse/ClickHouse/pull/65917) ([Azat Khuzhin](https://github.com/azat)).
* Fix possible issues with MySQL client protocol TLS connections. [#65938](https://github.com/ClickHouse/ClickHouse/pull/65938) ([Azat Khuzhin](https://github.com/azat)).
* Fix handling of `SSL_ERROR_WANT_READ`/`SSL_ERROR_WANT_WRITE` with zero timeout. [#65941](https://github.com/ClickHouse/ClickHouse/pull/65941) ([Azat Khuzhin](https://github.com/azat)).
* Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
* Column _size in s3 engine and s3 table function denotes the size of a file inside the archive, not a size of the archive itself. [#65993](https://github.com/ClickHouse/ClickHouse/pull/65993) ([Daniil Ivanik](https://github.com/divanik)).
* Fix resolving dynamic subcolumns in analyzer, avoid reading the whole column on dynamic subcolumn reading. [#66004](https://github.com/ClickHouse/ClickHouse/pull/66004) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix config merging for from_env with replace overrides. [#66034](https://github.com/ClickHouse/ClickHouse/pull/66034) ([Azat Khuzhin](https://github.com/azat)).
* Fix a possible hanging in `GRPCServer` during shutdown. [#66061](https://github.com/ClickHouse/ClickHouse/pull/66061) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fixed several cases in function `has` with non-constant `LowCardinality` arguments. [#66088](https://github.com/ClickHouse/ClickHouse/pull/66088) ([Anton Popov](https://github.com/CurtizJ)).
* Fix for `groupArrayIntersect`. It had incorrect behavior in the `merge()` function. Also, fixed behavior in `deserialise()` for numeric and general data. [#66103](https://github.com/ClickHouse/ClickHouse/pull/66103) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
* Disable the `merge-filters` optimization introduced in [#64760](https://github.com/ClickHouse/ClickHouse/issues/64760). It may cause an exception if optimization merges two filter expressions and does not apply a short-circuit evaluation. [#66126](https://github.com/ClickHouse/ClickHouse/pull/66126) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fixed the issue when the server failed to parse Avro files with negative block size arrays encoded, which is now allowed by the Avro specification. [#66130](https://github.com/ClickHouse/ClickHouse/pull/66130) ([Serge Klochkov](https://github.com/slvrtrn)).
* Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
* Fix rare case with missing data in the result of distributed query. [#66174](https://github.com/ClickHouse/ClickHouse/pull/66174) ([vdimir](https://github.com/vdimir)).
* Fix order of parsing metadata fields in StorageDeltaLake. [#66211](https://github.com/ClickHouse/ClickHouse/pull/66211) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Don't throw `TIMEOUT_EXCEEDED` for `none_only_active` mode of `distributed_ddl_output_mode`. [#66218](https://github.com/ClickHouse/ClickHouse/pull/66218) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
* Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix error reporting while copying to S3 or AzureBlobStorage. [#66295](https://github.com/ClickHouse/ClickHouse/pull/66295) ([Vitaly Baranov](https://github.com/vitlibar)).
* Prevent watchdog from keeping descriptors of unlinked (rotated) log files. [#66334](https://github.com/ClickHouse/ClickHouse/pull/66334) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Fix the bug that logicalexpressionoptimizerpass lost logical type of constant. [#66344](https://github.com/ClickHouse/ClickHouse/pull/66344) ([pn](https://github.com/chloro-pn)).
* Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix possible incorrect result for queries joining and filtering table external engine (like PostgreSQL), due to too aggressive filter pushdown. Since now, conditions from where section won't be send to external database in case of outer join with external table. [#66402](https://github.com/ClickHouse/ClickHouse/pull/66402) ([vdimir](https://github.com/vdimir)).
* Added missing column materialization for cross join. [#66413](https://github.com/ClickHouse/ClickHouse/pull/66413) ([lgbo](https://github.com/lgbo-ustc)).
* Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Avoid possible logical error during import from Npy format in case of bad array nesting level, fix testing of other kinds of errors. [#66461](https://github.com/ClickHouse/ClickHouse/pull/66461) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix wrong count() result when there is non-deterministic function in predicate. [#66510](https://github.com/ClickHouse/ClickHouse/pull/66510) ([Duc Canh Le](https://github.com/canhld94)).
* Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix reading of uninitialized memory when hashing empty tuples. [#66562](https://github.com/ClickHouse/ClickHouse/pull/66562) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix removing named collections in local storage. [#66599](https://github.com/ClickHouse/ClickHouse/pull/66599) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Fix `column_length` is not updated in `ColumnTuple::insertManyFrom`. [#66626](https://github.com/ClickHouse/ClickHouse/pull/66626) ([lgbo](https://github.com/lgbo-ustc)).
* Fix `Unknown identifier` and `Column is not under aggregate function` errors for queries with the expression `(column IS NULL).` The bug was triggered by [#65088](https://github.com/ClickHouse/ClickHouse/issues/65088), with the disabled analyzer only. [#66654](https://github.com/ClickHouse/ClickHouse/pull/66654) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix rare case of stuck merge after drop column. [#66707](https://github.com/ClickHouse/ClickHouse/pull/66707) ([Raúl Marín](https://github.com/Algunenano)).
* Fix assertion `isUniqTypes` when insert select from remote sources. [#66722](https://github.com/ClickHouse/ClickHouse/pull/66722) ([Sema Checherinda](https://github.com/CheSema)).
* Fix logical error in PrometheusRequestHandler. [#66621](https://github.com/ClickHouse/ClickHouse/pull/66621) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fix `indexHint` function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
* Fix AST formatting of 'create table b empty as a'. [#64951](https://github.com/ClickHouse/ClickHouse/pull/64951) ([Michael Kolupaev](https://github.com/al13n321)).
### <a id="246"></a> ClickHouse release 24.6, 2024-07-01
#### Backward Incompatible Change
* Enable asynchronous load of databases and tables by default. See the `async_load_databases` in config.xml. While this change is fully compatible, it can introduce a difference in behavior. When `async_load_databases` is false, as in the previous versions, the server will not accept connections until all tables are loaded. When `async_load_databases` is true, as in the new version, the server can accept connections before all the tables are loaded. If a query is made to a table that is not yet loaded, it will wait for the table's loading, which can take considerable time. It can change the behavior of the server if it is part of a large distributed system under a load balancer. In the first case, the load balancer can get a connection refusal and quickly failover to another server. In the second case, the load balancer can connect to a server that is still loading the tables, and the query will have a higher latency. Moreover, if many queries accumulate in the waiting state, it can lead to a "thundering herd" problem when they start processing simultaneously. This can make a difference only for highly loaded distributed backends. You can set the value of `async_load_databases` to false to avoid this problem. [#57695](https://github.com/ClickHouse/ClickHouse/pull/57695) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Setting `replace_long_file_name_to_hash` is enabled by default for `MergeTree` tables. [#64457](https://github.com/ClickHouse/ClickHouse/pull/64457) ([Anton Popov](https://github.com/CurtizJ)). This setting is fully compatible, and no actions needed during upgrade. The new data format is supported from all versions starting from 23.9. After enabling this setting, you can no longer downgrade to a version 23.8 or older.
* Some invalid queries will fail earlier during parsing. Note: disabled the support for inline KQL expressions (the experimental Kusto language) when they are put into a `kql` table function without a string literal, e.g. `kql(garbage | trash)` instead of `kql('garbage | trash')` or `kql($$garbage | trash$$)`. This feature was introduced unintentionally and should not exist. [#61500](https://github.com/ClickHouse/ClickHouse/pull/61500) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Rework parallel processing in `Ordered` mode of storage `S3Queue`. This PR is backward incompatible for Ordered mode if you used settings `s3queue_processing_threads_num` or `s3queue_total_shards_num`. Setting `s3queue_total_shards_num` is deleted, previously it was allowed to use only under `s3queue_allow_experimental_sharded_mode`, which is now deprecated. A new setting is added - `s3queue_buckets`. [#64349](https://github.com/ClickHouse/ClickHouse/pull/64349) ([Kseniia Sumarokova](https://github.com/kssenii)).
* New functions `snowflakeIDToDateTime`, `snowflakeIDToDateTime64`, `dateTimeToSnowflakeID`, and `dateTime64ToSnowflakeID` were added. Unlike the existing functions `snowflakeToDateTime`, `snowflakeToDateTime64`, `dateTimeToSnowflake`, and `dateTime64ToSnowflake`, the new functions are compatible with function `generateSnowflakeID`, i.e. they accept the snowflake IDs generated by `generateSnowflakeID` and produce snowflake IDs of the same type as `generateSnowflakeID` (i.e. `UInt64`). Furthermore, the new functions default to the UNIX epoch (aka. 1970-01-01), just like `generateSnowflakeID`. If necessary, a different epoch, e.g. Twitter's/X's epoch 2010-11-04 aka. 1288834974657 msec since UNIX epoch, can be passed. The old conversion functions are deprecated and will be removed after a transition period: to use them regardless, enable setting `allow_deprecated_snowflake_conversion_functions`. [#64948](https://github.com/ClickHouse/ClickHouse/pull/64948) ([Robert Schulze](https://github.com/rschu1ze)).
#### New Feature
* Allow to store named collections in ClickHouse Keeper. [#64574](https://github.com/ClickHouse/ClickHouse/pull/64574) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Support empty tuples. [#55061](https://github.com/ClickHouse/ClickHouse/pull/55061) ([Amos Bird](https://github.com/amosbird)).
* Add Hilbert Curve encode and decode functions. [#60156](https://github.com/ClickHouse/ClickHouse/pull/60156) ([Artem Mustafin](https://github.com/Artemmm91)).
* Add support for index analysis over `hilbertEncode`. [#64662](https://github.com/ClickHouse/ClickHouse/pull/64662) ([Artem Mustafin](https://github.com/Artemmm91)).
* Added support for reading `LINESTRING` geometry in the WKT format using function `readWKTLineString`. [#62519](https://github.com/ClickHouse/ClickHouse/pull/62519) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Allow to attach parts from a different disk. [#63087](https://github.com/ClickHouse/ClickHouse/pull/63087) ([Unalian](https://github.com/Unalian)).
* Added new SQL functions `generateSnowflakeID` for generating Twitter-style Snowflake IDs. [#63577](https://github.com/ClickHouse/ClickHouse/pull/63577) ([Danila Puzov](https://github.com/kazalika)).
* Added `merge_workload` and `mutation_workload` settings to regulate how resources are utilized and shared between merges, mutations and other workloads. [#64061](https://github.com/ClickHouse/ClickHouse/pull/64061) ([Sergei Trifonov](https://github.com/serxa)).
* Add support for comparing `IPv4` and `IPv6` types using the `=` operator. [#64292](https://github.com/ClickHouse/ClickHouse/pull/64292) ([Francisco J. Jurado Moreno](https://github.com/Beetelbrox)).
* Support decimal arguments in binary math functions (pow, atan2, max2, min2, hypot). [#64582](https://github.com/ClickHouse/ClickHouse/pull/64582) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
* Added SQL functions `parseReadableSize` (along with `OrNull` and `OrZero` variants). [#64742](https://github.com/ClickHouse/ClickHouse/pull/64742) ([Francisco J. Jurado Moreno](https://github.com/Beetelbrox)).
* Add server settings `max_table_num_to_throw` and `max_database_num_to_throw` to limit the number of databases or tables on `CREATE` queries. [#64781](https://github.com/ClickHouse/ClickHouse/pull/64781) ([Xu Jia](https://github.com/XuJia0210)).
* Add `_time` virtual column to file alike storages (s3/file/hdfs/url/azureBlobStorage). [#64947](https://github.com/ClickHouse/ClickHouse/pull/64947) ([Ilya Golshtein](https://github.com/ilejn)).
* Introduced new functions `base64URLEncode`, `base64URLDecode` and `tryBase64URLDecode`. [#64991](https://github.com/ClickHouse/ClickHouse/pull/64991) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
* Add new function `editDistanceUTF8`, which calculates the [edit distance](https://en.wikipedia.org/wiki/Edit_distance) between two UTF8 strings. [#65269](https://github.com/ClickHouse/ClickHouse/pull/65269) ([LiuNeng](https://github.com/liuneng1994)).
* Add `http_response_headers` configuration to support custom response headers in custom HTTP handlers. [#63562](https://github.com/ClickHouse/ClickHouse/pull/63562) ([Grigorii](https://github.com/GSokol)).
* Added a new table function `loop` to support returning query results in an infinite loop. [#63452](https://github.com/ClickHouse/ClickHouse/pull/63452) ([Sariel](https://github.com/sarielwxm)). This is useful for testing.
* Introduced two additional columns in the `system.query_log`: `used_privileges` and `missing_privileges`. `used_privileges` is populated with the privileges that were checked during query execution, and `missing_privileges` contains required privileges that are missing. [#64597](https://github.com/ClickHouse/ClickHouse/pull/64597) ([Alexey Katsman](https://github.com/alexkats)).
* Added a setting `output_format_pretty_display_footer_column_names` which when enabled displays column names at the end of the table for long tables (50 rows by default), with the threshold value for minimum number of rows controlled by `output_format_pretty_display_footer_column_names_min_rows`. [#65144](https://github.com/ClickHouse/ClickHouse/pull/65144) ([Shaun Struwig](https://github.com/Blargian)).
#### Experimental Feature
* Introduce statistics of type "number of distinct values". [#59357](https://github.com/ClickHouse/ClickHouse/pull/59357) ([Han Fei](https://github.com/hanfei1991)).
* Support statistics with ReplicatedMergeTree. [#64934](https://github.com/ClickHouse/ClickHouse/pull/64934) ([Han Fei](https://github.com/hanfei1991)).
* If "replica group" is configured for a `Replicated` database, automatically create a cluster that includes replicas from all groups. [#64312](https://github.com/ClickHouse/ClickHouse/pull/64312) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Add settings `parallel_replicas_custom_key_range_lower` and `parallel_replicas_custom_key_range_upper` to control how parallel replicas with dynamic shards parallelizes queries when using a range filter. [#64604](https://github.com/ClickHouse/ClickHouse/pull/64604) ([josh-hildred](https://github.com/josh-hildred)).
#### Performance Improvement
* Add the ability to reshuffle rows during insert to optimize for size without violating the order set by `PRIMARY KEY`. It's controlled by the setting `optimize_row_order` (off by default). [#63578](https://github.com/ClickHouse/ClickHouse/pull/63578) ([Igor Markelov](https://github.com/ElderlyPassionFruit)).
* Add a native parquet reader, which can read parquet binary to ClickHouse Columns directly. It's controlled by the setting `input_format_parquet_use_native_reader` (disabled by default). [#60361](https://github.com/ClickHouse/ClickHouse/pull/60361) ([ZhiHong Zhang](https://github.com/copperybean)).
* Support partial trivial count optimization when the query filter is able to select exact ranges from merge tree tables. [#60463](https://github.com/ClickHouse/ClickHouse/pull/60463) ([Amos Bird](https://github.com/amosbird)).
* Reduce max memory usage of multithreaded `INSERT`s by collecting chunks of multiple threads in a single transform. [#61047](https://github.com/ClickHouse/ClickHouse/pull/61047) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Reduce the memory usage when using Azure object storage by using fixed memory allocation, avoiding the allocation of an extra buffer. [#63160](https://github.com/ClickHouse/ClickHouse/pull/63160) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Reduce the number of virtual function calls in `ColumnNullable::size`. [#60556](https://github.com/ClickHouse/ClickHouse/pull/60556) ([HappenLee](https://github.com/HappenLee)).
* Speedup `splitByRegexp` when the regular expression argument is a single-character. [#62696](https://github.com/ClickHouse/ClickHouse/pull/62696) ([Robert Schulze](https://github.com/rschu1ze)).
* Speed up aggregation by 8-bit and 16-bit keys by keeping track of the min and max keys used. This allows to reduce the number of cells that need to be verified. [#62746](https://github.com/ClickHouse/ClickHouse/pull/62746) ([Jiebin Sun](https://github.com/jiebinn)).
* Optimize operator IN when the left hand side is `LowCardinality` and the right is a set of constants. [#64060](https://github.com/ClickHouse/ClickHouse/pull/64060) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* Use a thread pool to initialize and destroy hash tables inside `ConcurrentHashJoin`. [#64241](https://github.com/ClickHouse/ClickHouse/pull/64241) ([Nikita Taranov](https://github.com/nickitat)).
* Optimized vertical merges in tables with sparse columns. [#64311](https://github.com/ClickHouse/ClickHouse/pull/64311) ([Anton Popov](https://github.com/CurtizJ)).
* Enabled prefetches of data from remote filesystem during vertical merges. It improves latency of vertical merges in tables with data stored on remote filesystem. [#64314](https://github.com/ClickHouse/ClickHouse/pull/64314) ([Anton Popov](https://github.com/CurtizJ)).
* Reduce redundant calls to `isDefault` of `ColumnSparse::filter` to improve performance. [#64426](https://github.com/ClickHouse/ClickHouse/pull/64426) ([Jiebin Sun](https://github.com/jiebinn)).
* Speedup `find_super_nodes` and `find_big_family` keeper-client commands by making multiple asynchronous getChildren requests. [#64628](https://github.com/ClickHouse/ClickHouse/pull/64628) ([Alexander Gololobov](https://github.com/davenger)).
* Improve function `least`/`greatest` for nullable numberic type arguments. [#64668](https://github.com/ClickHouse/ClickHouse/pull/64668) ([KevinyhZou](https://github.com/KevinyhZou)).
* Allow merging two consequent filtering steps of a query plan. This improves filter-push-down optimization if the filter condition can be pushed down from the parent step. [#64760](https://github.com/ClickHouse/ClickHouse/pull/64760) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Remove bad optimization in the vertical final implementation and re-enable vertical final algorithm by default. [#64783](https://github.com/ClickHouse/ClickHouse/pull/64783) ([Duc Canh Le](https://github.com/canhld94)).
* Remove ALIAS nodes from the filter expression. This slightly improves performance for queries with `PREWHERE` (with the new analyzer). [#64793](https://github.com/ClickHouse/ClickHouse/pull/64793) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Re-enable OpenSSL session caching. [#65111](https://github.com/ClickHouse/ClickHouse/pull/65111) ([Robert Schulze](https://github.com/rschu1ze)).
* Added settings to disable materialization of skip indexes and statistics on inserts (`materialize_skip_indexes_on_insert` and `materialize_statistics_on_insert`). [#64391](https://github.com/ClickHouse/ClickHouse/pull/64391) ([Anton Popov](https://github.com/CurtizJ)).
* Use the allocated memory size to calculate the row group size and reduce the peak memory of the parquet writer in the single-threaded mode. [#64424](https://github.com/ClickHouse/ClickHouse/pull/64424) ([LiuNeng](https://github.com/liuneng1994)).
* Improve the iterator of sparse column to reduce call of `size`. [#64497](https://github.com/ClickHouse/ClickHouse/pull/64497) ([Jiebin Sun](https://github.com/jiebinn)).
* Update condition to use server-side copy for backups to Azure blob storage. [#64518](https://github.com/ClickHouse/ClickHouse/pull/64518) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Optimized memory usage of vertical merges for tables with high number of skip indexes. [#64580](https://github.com/ClickHouse/ClickHouse/pull/64580) ([Anton Popov](https://github.com/CurtizJ)).
#### Improvement
* `SHOW CREATE TABLE` executed on top of system tables will now show the super handy comment unique for each table which will explain why this table is needed. [#63788](https://github.com/ClickHouse/ClickHouse/pull/63788) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* The second argument (scale) of functions `round()`, `roundBankers()`, `floor()`, `ceil()` and `trunc()` can now be non-const. [#64798](https://github.com/ClickHouse/ClickHouse/pull/64798) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
* Hot reload storage policy for `Distributed` tables when adding a new disk. [#58285](https://github.com/ClickHouse/ClickHouse/pull/58285) ([Duc Canh Le](https://github.com/canhld94)).
* Avoid possible deadlock during MergeTree index analysis when scheduling threads in a saturated service. [#59427](https://github.com/ClickHouse/ClickHouse/pull/59427) ([Sean Haynes](https://github.com/seandhaynes)).
* Several minor corner case fixes to S3 proxy support & tunneling. [#63427](https://github.com/ClickHouse/ClickHouse/pull/63427) ([Arthur Passos](https://github.com/arthurpassos)).
* Improve io_uring resubmit visibility. Rename profile event `IOUringSQEsResubmits` -> `IOUringSQEsResubmitsAsync` and add a new one `IOUringSQEsResubmitsSync`. [#63699](https://github.com/ClickHouse/ClickHouse/pull/63699) ([Tomer Shafir](https://github.com/tomershafir)).
* Added a new setting, `metadata_keep_free_space_bytes` to keep free space on the metadata storage disk. [#64128](https://github.com/ClickHouse/ClickHouse/pull/64128) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Add metrics to track the number of directories created and removed by the `plain_rewritable` metadata storage, and the number of entries in the local-to-remote in-memory map. [#64175](https://github.com/ClickHouse/ClickHouse/pull/64175) ([Julia Kartseva](https://github.com/jkartseva)).
* The query cache now considers identical queries with different settings as different. This increases robustness in cases where different settings (e.g. `limit` or `additional_table_filters`) would affect the query result. [#64205](https://github.com/ClickHouse/ClickHouse/pull/64205) ([Robert Schulze](https://github.com/rschu1ze)).
* Support the non standard error code `QpsLimitExceeded` in object storage as a retryable error. [#64225](https://github.com/ClickHouse/ClickHouse/pull/64225) ([Sema Checherinda](https://github.com/CheSema)).
* Forbid converting a MergeTree table to replicated if the zookeeper path for this table already exists. [#64244](https://github.com/ClickHouse/ClickHouse/pull/64244) ([Kirill](https://github.com/kirillgarbar)).
* Added a new setting `input_format_parquet_prefer_block_bytes` to control the average output block bytes, and modified the default value of `input_format_parquet_max_block_size` to 65409. [#64427](https://github.com/ClickHouse/ClickHouse/pull/64427) ([LiuNeng](https://github.com/liuneng1994)).
* Allow proxy to be bypassed for hosts specified in `no_proxy` env variable and ClickHouse proxy configuration. [#63314](https://github.com/ClickHouse/ClickHouse/pull/63314) ([Arthur Passos](https://github.com/arthurpassos)).
* Always start Keeper with sufficient amount of threads in global thread pool. [#64444](https://github.com/ClickHouse/ClickHouse/pull/64444) ([Duc Canh Le](https://github.com/canhld94)).
* Settings from the user's config don't affect merges and mutations for `MergeTree` on top of object storage. [#64456](https://github.com/ClickHouse/ClickHouse/pull/64456) ([alesapin](https://github.com/alesapin)).
* Support the non standard error code `TotalQpsLimitExceeded` in object storage as a retryable error. [#64520](https://github.com/ClickHouse/ClickHouse/pull/64520) ([Sema Checherinda](https://github.com/CheSema)).
* Updated Advanced Dashboard for both open-source and ClickHouse Cloud versions to include a chart for 'Maximum concurrent network connections'. [#64610](https://github.com/ClickHouse/ClickHouse/pull/64610) ([Thom O'Connor](https://github.com/thomoco)).
* Improve progress report on `zeros_mt` and `generateRandom`. [#64804](https://github.com/ClickHouse/ClickHouse/pull/64804) ([Raúl Marín](https://github.com/Algunenano)).
* Add an asynchronous metric `jemalloc.profile.active` to show whether sampling is currently active. This is an activation mechanism in addition to prof.active; both must be active for the calling thread to sample. [#64842](https://github.com/ClickHouse/ClickHouse/pull/64842) ([Unalian](https://github.com/Unalian)).
* Remove mark of `allow_experimental_join_condition` as important. This mark may have prevented distributed queries in a mixed versions cluster from being executed successfully. [#65008](https://github.com/ClickHouse/ClickHouse/pull/65008) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Added server Asynchronous metrics `DiskGetObjectThrottler*` and `DiskGetObjectThrottler*` reflecting request per second rate limit defined with `s3_max_get_rps` and `s3_max_put_rps` disk settings and currently available number of requests that could be sent without hitting throttling limit on the disk. Metrics are defined for every disk that has a configured limit. [#65050](https://github.com/ClickHouse/ClickHouse/pull/65050) ([Sergei Trifonov](https://github.com/serxa)).
* Initialize global trace collector for `Poco::ThreadPool` (needed for Keeper, etc). [#65239](https://github.com/ClickHouse/ClickHouse/pull/65239) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add a validation when creating a user with `bcrypt_hash`. [#65242](https://github.com/ClickHouse/ClickHouse/pull/65242) ([Raúl Marín](https://github.com/Algunenano)).
* Add profile events for number of rows read during/after `PREWHERE`. [#64198](https://github.com/ClickHouse/ClickHouse/pull/64198) ([Nikita Taranov](https://github.com/nickitat)).
* Print query in `EXPLAIN PLAN` with parallel replicas. [#64298](https://github.com/ClickHouse/ClickHouse/pull/64298) ([vdimir](https://github.com/vdimir)).
* Rename `allow_deprecated_functions` to `allow_deprecated_error_prone_window_functions`. [#64358](https://github.com/ClickHouse/ClickHouse/pull/64358) ([Raúl Marín](https://github.com/Algunenano)).
* Respect `max_read_buffer_size` setting for file descriptors as well in the `file` table function. [#64532](https://github.com/ClickHouse/ClickHouse/pull/64532) ([Azat Khuzhin](https://github.com/azat)).
* Disable transactions for unsupported storages even for materialized views. [#64918](https://github.com/ClickHouse/ClickHouse/pull/64918) ([alesapin](https://github.com/alesapin)).
* Forbid `QUALIFY` clause in the old analyzer. The old analyzer ignored `QUALIFY`, so it could lead to unexpected data removal in mutations. [#65356](https://github.com/ClickHouse/ClickHouse/pull/65356) ([Dmitry Novik](https://github.com/novikd)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* A bug in Apache ORC library was fixed: Fixed ORC statistics calculation, when writing, for unsigned types on all platforms and Int8 on ARM. [#64563](https://github.com/ClickHouse/ClickHouse/pull/64563) ([Michael Kolupaev](https://github.com/al13n321)).
* Returned back the behaviour of how ClickHouse works and interprets Tuples in CSV format. This change effectively reverts https://github.com/ClickHouse/ClickHouse/pull/60994 and makes it available only under a few settings: `output_format_csv_serialize_tuple_into_separate_columns`, `input_format_csv_deserialize_separate_columns_into_tuple` and `input_format_csv_try_infer_strings_from_quoted_tuples`. [#65170](https://github.com/ClickHouse/ClickHouse/pull/65170) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix a permission error where a user in a specific situation can escalate their privileges on the default database without necessary grants. [#64769](https://github.com/ClickHouse/ClickHouse/pull/64769) ([pufit](https://github.com/pufit)).
* Fix crash with UniqInjectiveFunctionsEliminationPass and uniqCombined. [#65188](https://github.com/ClickHouse/ClickHouse/pull/65188) ([Raúl Marín](https://github.com/Algunenano)).
* Fix a bug in ClickHouse Keeper that causes digest mismatch during closing session. [#65198](https://github.com/ClickHouse/ClickHouse/pull/65198) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Use correct memory alignment for Distinct combinator. Previously, crash could happen because of invalid memory allocation when the combinator was used. [#65379](https://github.com/ClickHouse/ClickHouse/pull/65379) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix crash with `DISTINCT` and window functions. [#64767](https://github.com/ClickHouse/ClickHouse/pull/64767) ([Igor Nikonov](https://github.com/devcrafter)).
* Fixed 'set' skip index not working with IN and indexHint(). [#62083](https://github.com/ClickHouse/ClickHouse/pull/62083) ([Michael Kolupaev](https://github.com/al13n321)).
* Support executing function during assignment of parameterized view value. [#63502](https://github.com/ClickHouse/ClickHouse/pull/63502) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fixed parquet memory tracking. [#63584](https://github.com/ClickHouse/ClickHouse/pull/63584) ([Michael Kolupaev](https://github.com/al13n321)).
* Fixed reading of columns of type `Tuple(Map(LowCardinality(String), String), ...)`. [#63956](https://github.com/ClickHouse/ClickHouse/pull/63956) ([Anton Popov](https://github.com/CurtizJ)).
* Fix an `Cyclic aliases` error for cyclic aliases of different type (expression and function). [#63993](https://github.com/ClickHouse/ClickHouse/pull/63993) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* This fix will use a proper redefined context with the correct definer for each individual view in the query pipeline. [#64079](https://github.com/ClickHouse/ClickHouse/pull/64079) ([pufit](https://github.com/pufit)).
* Fix analyzer: "Not found column" error is fixed when using INTERPOLATE. [#64096](https://github.com/ClickHouse/ClickHouse/pull/64096) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Fix creating backups to S3 buckets with different credentials from the disk containing the file. [#64153](https://github.com/ClickHouse/ClickHouse/pull/64153) ([Antonio Andelic](https://github.com/antonio2368)).
* The query cache now considers two identical queries against different databases as different. The previous behavior could be used to bypass missing privileges to read from a table. [#64199](https://github.com/ClickHouse/ClickHouse/pull/64199) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix possible abort on uncaught exception in ~WriteBufferFromFileDescriptor in StatusFile. [#64206](https://github.com/ClickHouse/ClickHouse/pull/64206) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix `duplicate alias` error for distributed queries with `ARRAY JOIN`. [#64226](https://github.com/ClickHouse/ClickHouse/pull/64226) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix unexpected accurateCast from string to integer. [#64255](https://github.com/ClickHouse/ClickHouse/pull/64255) ([wudidapaopao](https://github.com/wudidapaopao)).
* Fixed CNF simplification, in case any OR group contains mutually exclusive atoms. [#64256](https://github.com/ClickHouse/ClickHouse/pull/64256) ([Eduard Karacharov](https://github.com/korowa)).
* Fix Query Tree size validation. [#64377](https://github.com/ClickHouse/ClickHouse/pull/64377) ([Dmitry Novik](https://github.com/novikd)).
* Fix `Logical error: Bad cast` for `Buffer` table with `PREWHERE`. [#64388](https://github.com/ClickHouse/ClickHouse/pull/64388) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Prevent recursive logging in `blob_storage_log` when it's stored on object storage. [#64393](https://github.com/ClickHouse/ClickHouse/pull/64393) ([vdimir](https://github.com/vdimir)).
* Fixed `CREATE TABLE AS` queries for tables with default expressions. [#64455](https://github.com/ClickHouse/ClickHouse/pull/64455) ([Anton Popov](https://github.com/CurtizJ)).
* Fixed `optimize_read_in_order` behaviour for ORDER BY ... NULLS FIRST / LAST on tables with nullable keys. [#64483](https://github.com/ClickHouse/ClickHouse/pull/64483) ([Eduard Karacharov](https://github.com/korowa)).
* Fix the `Expression nodes list expected 1 projection names` and `Unknown expression or identifier` errors for queries with aliases to `GLOBAL IN.`. [#64517](https://github.com/ClickHouse/ClickHouse/pull/64517) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix an error `Cannot find column` in distributed queries with constant CTE in the `GROUP BY` key. [#64519](https://github.com/ClickHouse/ClickHouse/pull/64519) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix the crash loop when restoring from backup is blocked by creating an MV with a definer that hasn't been restored yet. [#64595](https://github.com/ClickHouse/ClickHouse/pull/64595) ([pufit](https://github.com/pufit)).
* Fix the output of function `formatDateTimeInJodaSyntax` when a formatter generates an uneven number of characters and the last character is `0`. For example, `SELECT formatDateTimeInJodaSyntax(toDate('2012-05-29'), 'D')` now correctly returns `150` instead of previously `15`. [#64614](https://github.com/ClickHouse/ClickHouse/pull/64614) ([LiuNeng](https://github.com/liuneng1994)).
* Do not rewrite aggregation if `-If` combinator is already used. [#64638](https://github.com/ClickHouse/ClickHouse/pull/64638) ([Dmitry Novik](https://github.com/novikd)).
* Fix type inference for float (in case of small buffer, i.e. `--max_read_buffer_size 1`). [#64641](https://github.com/ClickHouse/ClickHouse/pull/64641) ([Azat Khuzhin](https://github.com/azat)).
* Fix bug which could lead to non-working TTLs with expressions. [#64694](https://github.com/ClickHouse/ClickHouse/pull/64694) ([alesapin](https://github.com/alesapin)).
* Fix removing the `WHERE` and `PREWHERE` expressions, which are always true (for the new analyzer). [#64695](https://github.com/ClickHouse/ClickHouse/pull/64695) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fixed excessive part elimination by token-based text indexes (`ngrambf` , `full_text`) when filtering by result of `startsWith`, `endsWith`, `match`, `multiSearchAny`. [#64720](https://github.com/ClickHouse/ClickHouse/pull/64720) ([Eduard Karacharov](https://github.com/korowa)).
* Fixes incorrect behaviour of ANSI CSI escaping in the `UTF8::computeWidth` function. [#64756](https://github.com/ClickHouse/ClickHouse/pull/64756) ([Shaun Struwig](https://github.com/Blargian)).
* Fix a case of incorrect removal of `ORDER BY` / `LIMIT BY` across subqueries. [#64766](https://github.com/ClickHouse/ClickHouse/pull/64766) ([Raúl Marín](https://github.com/Algunenano)).
* Fix (experimental) unequal join with subqueries for sets which are in the mixed join conditions. [#64775](https://github.com/ClickHouse/ClickHouse/pull/64775) ([lgbo](https://github.com/lgbo-ustc)).
* Fix crash in a local cache over `plain_rewritable` disk. [#64778](https://github.com/ClickHouse/ClickHouse/pull/64778) ([Julia Kartseva](https://github.com/jkartseva)).
* Keeper fix: return correct value for `zk_latest_snapshot_size` in `mntr` command. [#64784](https://github.com/ClickHouse/ClickHouse/pull/64784) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix `Cannot find column` in distributed query with `ARRAY JOIN` by `Nested` column. Fixes [#64755](https://github.com/ClickHouse/ClickHouse/issues/64755). [#64801](https://github.com/ClickHouse/ClickHouse/pull/64801) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix memory leak in slru cache policy. [#64803](https://github.com/ClickHouse/ClickHouse/pull/64803) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fixed possible incorrect memory tracking in several kinds of queries: queries that read any data from S3, queries via http protocol, asynchronous inserts. [#64844](https://github.com/ClickHouse/ClickHouse/pull/64844) ([Anton Popov](https://github.com/CurtizJ)).
* Fix the `Block structure mismatch` error for queries reading with `PREWHERE` from the materialized view when the materialized view has columns of different types than the source table. Fixes [#64611](https://github.com/ClickHouse/ClickHouse/issues/64611). [#64855](https://github.com/ClickHouse/ClickHouse/pull/64855) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix rare crash when table has TTL with subquery + database replicated + parallel replicas + analyzer. It's really rare, but please don't use TTLs with subqueries. [#64858](https://github.com/ClickHouse/ClickHouse/pull/64858) ([alesapin](https://github.com/alesapin)).
* Fix duplicating `Delete` events in `blob_storage_log` in case of large batch to delete. [#64924](https://github.com/ClickHouse/ClickHouse/pull/64924) ([vdimir](https://github.com/vdimir)).
* Fixed `Session moved to another server` error from [Zoo]Keeper that might happen after server startup when the config has includes from [Zoo]Keeper. [#64986](https://github.com/ClickHouse/ClickHouse/pull/64986) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix `ALTER MODIFY COMMENT` query that was broken for parameterized VIEWs in https://github.com/ClickHouse/ClickHouse/pull/54211. [#65031](https://github.com/ClickHouse/ClickHouse/pull/65031) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix `host_id` in DatabaseReplicated when `cluster_secure_connection` parameter is enabled. Previously all the connections within the cluster created by DatabaseReplicated were not secure, even if the parameter was enabled. [#65054](https://github.com/ClickHouse/ClickHouse/pull/65054) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fixing the `Not-ready Set` error after the `PREWHERE` optimization for StorageMerge. [#65057](https://github.com/ClickHouse/ClickHouse/pull/65057) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Avoid writing to finalized buffer in File-like storages. [#65063](https://github.com/ClickHouse/ClickHouse/pull/65063) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix possible infinite query duration in case of cyclic aliases. Fixes [#64849](https://github.com/ClickHouse/ClickHouse/issues/64849). [#65081](https://github.com/ClickHouse/ClickHouse/pull/65081) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix the `Unknown expression identifier` error for remote queries with `INTERPOLATE (alias)` (new analyzer). Fixes [#64636](https://github.com/ClickHouse/ClickHouse/issues/64636). [#65090](https://github.com/ClickHouse/ClickHouse/pull/65090) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix pushing arithmetic operations out of aggregation. In the new analyzer, optimization was applied only once. [#65104](https://github.com/ClickHouse/ClickHouse/pull/65104) ([Dmitry Novik](https://github.com/novikd)).
* Fix aggregate function name rewriting in the new analyzer. [#65110](https://github.com/ClickHouse/ClickHouse/pull/65110) ([Dmitry Novik](https://github.com/novikd)).
* Respond with 5xx instead of 200 OK in case of receive timeout while reading (parts of) the request body from the client socket. [#65118](https://github.com/ClickHouse/ClickHouse/pull/65118) ([Julian Maicher](https://github.com/jmaicher)).
* Fix possible crash for hedged requests. [#65206](https://github.com/ClickHouse/ClickHouse/pull/65206) ([Azat Khuzhin](https://github.com/azat)).
* Fix the bug in Hashed and Hashed_Array dictionary short circuit evaluation, which may read uninitialized number, leading to various errors. [#65256](https://github.com/ClickHouse/ClickHouse/pull/65256) ([jsc0218](https://github.com/jsc0218)).
* This PR ensures that the type of the constant(IN operator's second parameter) is always visible during the IN operator's type conversion process. Otherwise, losing type information may cause some conversions to fail, such as the conversion from DateTime to Date. This fixes ([#64487](https://github.com/ClickHouse/ClickHouse/issues/64487)). [#65315](https://github.com/ClickHouse/ClickHouse/pull/65315) ([pn](https://github.com/chloro-pn)).
#### Build/Testing/Packaging Improvement
* Add support for LLVM XRay. [#64592](https://github.com/ClickHouse/ClickHouse/pull/64592) [#64837](https://github.com/ClickHouse/ClickHouse/pull/64837) ([Tomer Shafir](https://github.com/tomershafir)).
* Unite s3/hdfs/azure storage implementations into a single class working with IObjectStorage. Same for *Cluster, data lakes and Queue storages. [#59767](https://github.com/ClickHouse/ClickHouse/pull/59767) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Refactor data part writer to remove dependencies on MergeTreeData and DataPart. [#63620](https://github.com/ClickHouse/ClickHouse/pull/63620) ([Alexander Gololobov](https://github.com/davenger)).
* Refactor `KeyCondition` and key analysis to improve PartitionPruner and trivial count optimization. This is separated from [#60463](https://github.com/ClickHouse/ClickHouse/issues/60463) . [#61459](https://github.com/ClickHouse/ClickHouse/pull/61459) ([Amos Bird](https://github.com/amosbird)).
* Introduce assertions to verify all functions are called with columns of the right size. [#63723](https://github.com/ClickHouse/ClickHouse/pull/63723) ([Raúl Marín](https://github.com/Algunenano)).
* Make `network` service be required when using the `rc` init script to start the ClickHouse server daemon. [#60650](https://github.com/ClickHouse/ClickHouse/pull/60650) ([Chun-Sheng, Li](https://github.com/peter279k)).
* Reduce the size of some slow tests. [#64387](https://github.com/ClickHouse/ClickHouse/pull/64387) [#64452](https://github.com/ClickHouse/ClickHouse/pull/64452) ([Raúl Marín](https://github.com/Algunenano)).
* Replay ZooKeeper logs using keeper-bench. [#62481](https://github.com/ClickHouse/ClickHouse/pull/62481) ([Antonio Andelic](https://github.com/antonio2368)).
### <a id="245"></a> ClickHouse release 24.5, 2024-05-30
#### Backward Incompatible Change

9
CMakeLists.txt
View File

@ -319,7 +319,6 @@ endif()
# Disable floating-point expression contraction in order to get consistent floating point calculation results across platforms
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ffp-contract=off")
# Our built-in unwinder only supports DWARF version up to 4.
set (DEBUG_INFO_FLAGS "-g")
# Disable omit frame pointer compiler optimization using -fno-omit-frame-pointer
@ -333,15 +332,15 @@ endif()
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${COMPILER_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${COMPILER_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_RELWITHDEBINFO "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
if (OS_DARWIN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
@ -399,7 +398,7 @@ option (ENABLE_GWP_ASAN "Enable Gwp-Asan" ON)
# but GWP-ASan also wants to use mmap frequently,
# and due to a large number of memory mappings,
# it does not work together well.
if ((NOT OS_LINUX AND NOT OS_ANDROID) OR (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG"))
if ((NOT OS_LINUX AND NOT OS_ANDROID) OR (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") OR SANITIZE)
set(ENABLE_GWP_ASAN OFF)
endif ()

12
README.md
View File

@ -34,21 +34,13 @@ curl https://clickhouse.com/ | sh
Every month we get together with the community (users, contributors, customers, those interested in learning more about ClickHouse) to discuss what is coming in the latest release. If you are interested in sharing what you've built on ClickHouse, let us know.
* [v24.5 Community Call](https://clickhouse.com/company/events/v24-5-community-release-call) - May 30
* [v24.8 Community Call](https://clickhouse.com/company/events/v24-8-community-release-call) - August 29
## Upcoming Events
Keep an eye out for upcoming meetups and events around the world. Somewhere else you want us to be? Please feel free to reach out to tyler `<at>` clickhouse `<dot>` com. You can also peruse [ClickHouse Events](https://clickhouse.com/company/news-events) for a list of all upcoming trainings, meetups, speaking engagements, etc.
* [ClickHouse Happy Hour @ Tom's Watch Bar - Los Angeles](https://www.meetup.com/clickhouse-los-angeles-user-group/events/300740584/) - May 22
* [ClickHouse & Confluent Meetup in Dubai](https://www.meetup.com/clickhouse-dubai-meetup-group/events/299629189/) - May 28
* [ClickHouse Meetup in Stockholm](https://www.meetup.com/clickhouse-stockholm-user-group/events/299752651/) - Jun 3
* [ClickHouse Meetup @ Cloudflare - San Francisco](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/300523061/) - Jun 4
* [ClickHouse (クリックハウス) Meetup Tokyo](https://www.meetup.com/clickhouse-tokyo-user-group/events/300798053/) - Jun 5
* [ClickHouse Meetup in Amsterdam](https://www.meetup.com/clickhouse-netherlands-user-group/events/300781068/) - Jun 27
* [ClickHouse Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/300783448/) - Jul 9
* [ClickHouse Meetup @ Ramp - New York City](https://www.meetup.com/clickhouse-new-york-user-group/events/300595845/) - Jul 9
* [ClickHouse Meetup @ Klaviyo - Boston](https://www.meetup.com/clickhouse-boston-user-group/events/300907870) - Jul 11
* MORE COMING SOON!
## Recent Recordings
* **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments"

4
SECURITY.md
View File

@ -14,8 +14,10 @@ The following versions of ClickHouse server are currently supported with securit
| Version | Supported |
|:-|:-|
| 24.7 | ✔️ |
| 24.6 | ✔️ |
| 24.5 | ✔️ |
| 24.4 | ✔️ |
| 24.4 | ❌ |
| 24.3 | ✔️ |
| 24.2 | ❌ |
| 24.1 | ❌ |

5
base/base/CMakeLists.txt
View File

@ -32,6 +32,7 @@ set (SRCS
StringRef.cpp
safeExit.cpp
throwError.cpp
Numa.cpp
)
add_library (common ${SRCS})
@ -46,6 +47,10 @@ if (TARGET ch_contrib::crc32_s390x)
target_link_libraries(common PUBLIC ch_contrib::crc32_s390x)
endif()
if (TARGET ch_contrib::numactl)
target_link_libraries(common PUBLIC ch_contrib::numactl)
endif()
target_include_directories(common PUBLIC .. "${CMAKE_CURRENT_BINARY_DIR}/..")
target_link_libraries (common

2
base/base/EnumReflection.h
View File

@ -32,7 +32,7 @@ constexpr void static_for(F && f)
template <is_enum T>
struct fmt::formatter<T> : fmt::formatter<std::string_view>
{
constexpr auto format(T value, auto& format_context)
constexpr auto format(T value, auto& format_context) const
{
return formatter<string_view>::format(magic_enum::enum_name(value), format_context);
}

37
base/base/Numa.cpp Normal file
View File

@ -0,0 +1,37 @@
#include <base/Numa.h>
#include "config.h"
#if USE_NUMACTL
# include <numa.h>
#endif
namespace DB
{
std::optional<size_t> getNumaNodesTotalMemory()
{
std::optional<size_t> total_memory;
#if USE_NUMACTL
if (numa_available() != -1)
{
auto * membind = numa_get_membind();
if (!numa_bitmask_equal(membind, numa_all_nodes_ptr))
{
total_memory.emplace(0);
auto max_node = numa_max_node();
for (int i = 0; i <= max_node; ++i)
{
if (numa_bitmask_isbitset(membind, i))
*total_memory += numa_node_size(i, nullptr);
}
}
numa_bitmask_free(membind);
}
#endif
return total_memory;
}
}

12
base/base/Numa.h Normal file
View File

@ -0,0 +1,12 @@
#pragma once
#include <optional>
namespace DB
{
/// return total memory of NUMA nodes the process is bound to
/// if NUMA is not supported or process can use all nodes, std::nullopt is returned
std::optional<size_t> getNumaNodesTotalMemory();
}

4
base/base/StringRef.h
View File

@ -12,6 +12,8 @@
#include <base/types.h>
#include <base/unaligned.h>
#include <base/simd.h>
#include <fmt/core.h>
#include <fmt/ostream.h>
#include <city.h>
@ -376,3 +378,5 @@ namespace PackedZeroTraits
std::ostream & operator<<(std::ostream & os, const StringRef & str);
template<> struct fmt::formatter<StringRef> : fmt::ostream_formatter {};

23
base/base/cgroupsv2.cpp
View File

@ -3,8 +3,9 @@
#include <base/defines.h>
#include <fstream>
#include <sstream>
#include <string>
namespace fs = std::filesystem;
bool cgroupsV2Enabled()
{
@ -13,11 +14,11 @@ bool cgroupsV2Enabled()
{
/// This file exists iff the host has cgroups v2 enabled.
auto controllers_file = default_cgroups_mount / "cgroup.controllers";
if (!std::filesystem::exists(controllers_file))
if (!fs::exists(controllers_file))
return false;
return true;
}
catch (const std::filesystem::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
catch (const fs::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
{
return false; /// not logging the exception as most callers fall back to cgroups v1
}
@ -33,8 +34,9 @@ bool cgroupsV2MemoryControllerEnabled()
/// According to https://docs.kernel.org/admin-guide/cgroup-v2.html, file "cgroup.controllers" defines which controllers are available
/// for the current + child cgroups. The set of available controllers can be restricted from level to level using file
/// "cgroups.subtree_control". It is therefore sufficient to check the bottom-most nested "cgroup.controllers" file.
std::string cgroup = cgroupV2OfProcess();
auto cgroup_dir = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
fs::path cgroup_dir = cgroupV2PathOfProcess();
if (cgroup_dir.empty())
return false;
std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
if (!controllers_file.is_open())
return false;
@ -46,7 +48,7 @@ bool cgroupsV2MemoryControllerEnabled()
#endif
}
std::string cgroupV2OfProcess()
fs::path cgroupV2PathOfProcess()
{
#if defined(OS_LINUX)
chassert(cgroupsV2Enabled());
@ -54,17 +56,18 @@ std::string cgroupV2OfProcess()
/// A simpler way to get the membership is:
std::ifstream cgroup_name_file("/proc/self/cgroup");
if (!cgroup_name_file.is_open())
return "";
return {};
/// With cgroups v2, there will be a *single* line with prefix "0::/"
/// (see https://docs.kernel.org/admin-guide/cgroup-v2.html)
std::string cgroup;
std::getline(cgroup_name_file, cgroup);
static const std::string v2_prefix = "0::/";
if (!cgroup.starts_with(v2_prefix))
return "";
return {};
cgroup = cgroup.substr(v2_prefix.length());
return cgroup;
/// Note: The 'root' cgroup can have an empty cgroup name, this is valid
return default_cgroups_mount / cgroup;
#else
return "";
return {};
#endif
}

7
base/base/cgroupsv2.h
View File

@ -1,7 +1,6 @@
#pragma once
#include <filesystem>
#include <string>
#if defined(OS_LINUX)
/// I think it is possible to mount the cgroups hierarchy somewhere else (e.g. when in containers).
@ -16,7 +15,7 @@ bool cgroupsV2Enabled();
/// Assumes that cgroupsV2Enabled() is enabled.
bool cgroupsV2MemoryControllerEnabled();
/// Which cgroup does the process belong to?
/// Returns an empty string if the cgroup cannot be determined.
/// Detects which cgroup v2 the process belongs to and returns the filesystem path to the cgroup.
/// Returns an empty path the cgroup cannot be determined.
/// Assumes that cgroupsV2Enabled() is enabled.
std::string cgroupV2OfProcess();
std::filesystem::path cgroupV2PathOfProcess();

13
base/base/defines.h
View File

@ -87,10 +87,13 @@
# define ASAN_POISON_MEMORY_REGION(a, b)
#endif
#if !defined(ABORT_ON_LOGICAL_ERROR)
#if !defined(NDEBUG) || defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) || defined(UNDEFINED_BEHAVIOR_SANITIZER)
#define ABORT_ON_LOGICAL_ERROR
#endif
/// We used to have only ABORT_ON_LOGICAL_ERROR macro, but most of its uses were actually in places where we didn't care about logical errors
/// but wanted to check exactly if the current build type is debug or with sanitizer. This new macro is introduced to fix those places.
#if !defined(DEBUG_OR_SANITIZER_BUILD)
# if !defined(NDEBUG) || defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) \
|| defined(UNDEFINED_BEHAVIOR_SANITIZER)
# define DEBUG_OR_SANITIZER_BUILD
# endif
#endif
/// chassert(x) is similar to assert(x), but:
@ -101,7 +104,7 @@
/// Also it makes sense to call abort() instead of __builtin_unreachable() in debug builds,
/// because SIGABRT is easier to debug than SIGTRAP (the second one makes gdb crazy)
#if !defined(chassert)
#if defined(ABORT_ON_LOGICAL_ERROR)
# if defined(DEBUG_OR_SANITIZER_BUILD)
// clang-format off
#include <base/types.h>
namespace DB

1
base/base/demangle.h
View File

@ -1,5 +1,6 @@
#pragma once
#include <cstdlib>
#include <memory>
#include <string>

16
base/base/extended_types.h
View File

@ -108,6 +108,14 @@ struct make_unsigned // NOLINT(readability-identifier-naming)
using type = std::make_unsigned_t<T>;
};
template <> struct make_unsigned<Int8> { using type = UInt8; };
template <> struct make_unsigned<UInt8> { using type = UInt8; };
template <> struct make_unsigned<Int16> { using type = UInt16; };
template <> struct make_unsigned<UInt16> { using type = UInt16; };
template <> struct make_unsigned<Int32> { using type = UInt32; };
template <> struct make_unsigned<UInt32> { using type = UInt32; };
template <> struct make_unsigned<Int64> { using type = UInt64; };
template <> struct make_unsigned<UInt64> { using type = UInt64; };
template <> struct make_unsigned<Int128> { using type = UInt128; };
template <> struct make_unsigned<UInt128> { using type = UInt128; };
template <> struct make_unsigned<Int256> { using type = UInt256; };
@ -121,6 +129,14 @@ struct make_signed // NOLINT(readability-identifier-naming)
using type = std::make_signed_t<T>;
};
template <> struct make_signed<Int8> { using type = Int8; };
template <> struct make_signed<UInt8> { using type = Int8; };
template <> struct make_signed<Int16> { using type = Int16; };
template <> struct make_signed<UInt16> { using type = Int16; };
template <> struct make_signed<Int32> { using type = Int32; };
template <> struct make_signed<UInt32> { using type = Int32; };
template <> struct make_signed<Int64> { using type = Int64; };
template <> struct make_signed<UInt64> { using type = Int64; };
template <> struct make_signed<Int128> { using type = Int128; };
template <> struct make_signed<UInt128> { using type = Int128; };
template <> struct make_signed<Int256> { using type = Int256; };

4
base/base/getFQDNOrHostName.cpp
View File

@ -6,6 +6,9 @@ namespace
{
std::string getFQDNOrHostNameImpl()
{
#if defined(OS_DARWIN)
return Poco::Net::DNS::hostName();
#else
try
{
return Poco::Net::DNS::thisHost().name();
@ -14,6 +17,7 @@ namespace
{
return Poco::Net::DNS::hostName();
}
#endif
}
}

11
base/base/getMemoryAmount.cpp
View File

@ -2,15 +2,14 @@
#include <base/cgroupsv2.h>
#include <base/getPageSize.h>
#include <base/Numa.h>
#include <fstream>
#include <stdexcept>
#include <unistd.h>
#include <sys/types.h>
#include <sys/param.h>
namespace
{
@ -23,8 +22,9 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
if (!cgroupsV2MemoryControllerEnabled())
return {};
std::string cgroup = cgroupV2OfProcess();
auto current_cgroup = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
std::filesystem::path current_cgroup = cgroupV2PathOfProcess();
if (current_cgroup.empty())
return {};
/// Open the bottom-most nested memory limit setting file. If there is no such file at the current
/// level, try again at the parent level as memory settings are inherited.
@ -62,6 +62,9 @@ uint64_t getMemoryAmountOrZero()
uint64_t memory_amount = num_pages * page_size;
if (auto total_numa_memory = DB::getNumaNodesTotalMemory(); total_numa_memory.has_value())
memory_amount = *total_numa_memory;
/// Respect the memory limit set by cgroups v2.
auto limit_v2 = getCgroupsV2MemoryLimit();
if (limit_v2.has_value() && *limit_v2 < memory_amount)

9
base/base/isSharedPtrUnique.h Normal file
View File

@ -0,0 +1,9 @@
#pragma once
#include <memory>
template <typename T>
bool isSharedPtrUnique(const std::shared_ptr<T> & ptr)
{
return ptr.use_count() == 1;
}

493
base/base/itoa.cpp
View File

@ -1,32 +1,3 @@
// Based on https://github.com/amdn/itoa and combined with our optimizations
//
//=== itoa.cpp - Fast integer to ascii conversion --*- C++ -*-//
//
// The MIT License (MIT)
// Copyright (c) 2016 Arturo Martin-de-Nicolas
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
// SOFTWARE.
//===----------------------------------------------------------------------===//
#include <cstddef>
#include <cstdint>
#include <cstring>
#include <type_traits>
#include <base/defines.h>
#include <base/extended_types.h>
@ -34,99 +5,15 @@
namespace
{
template <typename T>
ALWAYS_INLINE inline constexpr T pow10(size_t x)
{
return x ? 10 * pow10<T>(x - 1) : 1;
}
// Division by a power of 10 is implemented using a multiplicative inverse.
// This strength reduction is also done by optimizing compilers, but
// presently the fastest results are produced by using the values
// for the multiplication and the shift as given by the algorithm
// described by Agner Fog in "Optimizing Subroutines in Assembly Language"
//
// http://www.agner.org/optimize/optimizing_assembly.pdf
//
// "Integer division by a constant (all processors)
// A floating point number can be divided by a constant by multiplying
// with the reciprocal. If we want to do the same with integers, we have
// to scale the reciprocal by 2n and then shift the product to the right
// by n. There are various algorithms for finding a suitable value of n
// and compensating for rounding errors. The algorithm described below
// was invented by Terje Mathisen, Norway, and not published elsewhere."
/// Division by constant is performed by:
/// 1. Adding 1 if needed;
/// 2. Multiplying by another constant;
/// 3. Shifting right by another constant.
template <typename UInt, bool add_, UInt multiplier_, unsigned shift_>
struct Division
{
static constexpr bool add{add_};
static constexpr UInt multiplier{multiplier_};
static constexpr unsigned shift{shift_};
};
/// Select a type with appropriate number of bytes from the list of types.
/// First parameter is the number of bytes requested. Then goes a list of types with 1, 2, 4, ... number of bytes.
/// Example: SelectType<4, uint8_t, uint16_t, uint32_t, uint64_t> will select uint32_t.
template <size_t N, typename T, typename... Ts>
struct SelectType
{
using Result = typename SelectType<N / 2, Ts...>::Result;
};
template <typename T, typename... Ts>
struct SelectType<1, T, Ts...>
{
using Result = T;
};
/// Division by 10^N where N is the size of the type.
template <size_t N>
using DivisionBy10PowN = typename SelectType<
N,
Division<uint8_t, false, 205U, 11>, /// divide by 10
Division<uint16_t, true, 41943U, 22>, /// divide by 100
Division<uint32_t, false, 3518437209U, 45>, /// divide by 10000
Division<uint64_t, false, 12379400392853802749ULL, 90> /// divide by 100000000
>::Result;
template <size_t N>
using UnsignedOfSize = typename SelectType<N, uint8_t, uint16_t, uint32_t, uint64_t, __uint128_t>::Result;
/// Holds the result of dividing an unsigned N-byte variable by 10^N resulting in
template <size_t N>
struct QuotientAndRemainder
{
UnsignedOfSize<N> quotient; // quotient with fewer than 2*N decimal digits
UnsignedOfSize<N / 2> remainder; // remainder with at most N decimal digits
};
template <size_t N>
QuotientAndRemainder<N> inline split(UnsignedOfSize<N> value)
{
constexpr DivisionBy10PowN<N> division;
UnsignedOfSize<N> quotient = (division.multiplier * (UnsignedOfSize<2 * N>(value) + division.add)) >> division.shift;
UnsignedOfSize<N / 2> remainder = static_cast<UnsignedOfSize<N / 2>>(value - quotient * pow10<UnsignedOfSize<N / 2>>(N));
return {quotient, remainder};
}
ALWAYS_INLINE inline char * outDigit(char * p, uint8_t value)
ALWAYS_INLINE inline char * outOneDigit(char * p, uint8_t value)
{
*p = '0' + value;
++p;
return p;
return p + 1;
}
// Using a lookup table to convert binary numbers from 0 to 99
// into ascii characters as described by Andrei Alexandrescu in
// https://www.facebook.com/notes/facebook-engineering/three-optimization-tips-for-c/10151361643253920/
const char digits[201] = "00010203040506070809"
"10111213141516171819"
"20212223242526272829"
@ -137,7 +24,6 @@ const char digits[201] = "00010203040506070809"
"70717273747576777879"
"80818283848586878889"
"90919293949596979899";
ALWAYS_INLINE inline char * outTwoDigits(char * p, uint8_t value)
{
memcpy(p, &digits[value * 2], 2);
@ -145,153 +31,260 @@ ALWAYS_INLINE inline char * outTwoDigits(char * p, uint8_t value)
return p;
}
namespace convert
namespace jeaiii
{
template <typename UInt, size_t N = sizeof(UInt)>
char * head(char * p, UInt u);
template <typename UInt, size_t N = sizeof(UInt)>
char * tail(char * p, UInt u);
/*
MIT License
//===----------------------------------------------------------===//
// head: find most significant digit, skip leading zeros
//===----------------------------------------------------------===//
Copyright (c) 2022 James Edward Anhalt III - https://github.com/jeaiii/itoa
// "x" contains quotient and remainder after division by 10^N
// quotient is less than 10^N
template <size_t N>
ALWAYS_INLINE inline char * head(char * p, QuotientAndRemainder<N> x)
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/
struct pair
{
p = head(p, UnsignedOfSize<N / 2>(x.quotient));
p = tail(p, x.remainder);
return p;
}
char dd[2];
constexpr pair(char c) : dd{c, '\0'} { } /// NOLINT(google-explicit-constructor)
constexpr pair(int n) : dd{"0123456789"[n / 10], "0123456789"[n % 10]} { } /// NOLINT(google-explicit-constructor)
};
// "u" is less than 10^2*N
template <typename UInt, size_t N>
ALWAYS_INLINE inline char * head(char * p, UInt u)
constexpr struct
{
return u < pow10<UnsignedOfSize<N>>(N) ? head(p, UnsignedOfSize<N / 2>(u)) : head<N>(p, split<N>(u));
}
pair dd[100]{
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, //
10, 11, 12, 13, 14, 15, 16, 17, 18, 19, //
20, 21, 22, 23, 24, 25, 26, 27, 28, 29, //
30, 31, 32, 33, 34, 35, 36, 37, 38, 39, //
40, 41, 42, 43, 44, 45, 46, 47, 48, 49, //
50, 51, 52, 53, 54, 55, 56, 57, 58, 59, //
60, 61, 62, 63, 64, 65, 66, 67, 68, 69, //
70, 71, 72, 73, 74, 75, 76, 77, 78, 79, //
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, //
90, 91, 92, 93, 94, 95, 96, 97, 98, 99, //
};
pair fd[100]{
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', //
10, 11, 12, 13, 14, 15, 16, 17, 18, 19, //
20, 21, 22, 23, 24, 25, 26, 27, 28, 29, //
30, 31, 32, 33, 34, 35, 36, 37, 38, 39, //
40, 41, 42, 43, 44, 45, 46, 47, 48, 49, //
50, 51, 52, 53, 54, 55, 56, 57, 58, 59, //
60, 61, 62, 63, 64, 65, 66, 67, 68, 69, //
70, 71, 72, 73, 74, 75, 76, 77, 78, 79, //
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, //
90, 91, 92, 93, 94, 95, 96, 97, 98, 99, //
};
} digits;
// recursion base case, selected when "u" is one byte
template <>
ALWAYS_INLINE inline char * head<UnsignedOfSize<1>, 1>(char * p, UnsignedOfSize<1> u)
constexpr UInt64 mask24 = (UInt64(1) << 24) - 1;
constexpr UInt64 mask32 = (UInt64(1) << 32) - 1;
constexpr UInt64 mask57 = (UInt64(1) << 57) - 1;
template <bool, class, class F>
struct _cond
{
return u < 10 ? outDigit(p, u) : outTwoDigits(p, u);
}
//===----------------------------------------------------------===//
// tail: produce all digits including leading zeros
//===----------------------------------------------------------===//
// recursive step, "u" is less than 10^2*N
template <typename UInt, size_t N>
ALWAYS_INLINE inline char * tail(char * p, UInt u)
using type = F;
};
template <class T, class F>
struct _cond<true, T, F>
{
QuotientAndRemainder<N> x = split<N>(u);
p = tail(p, UnsignedOfSize<N / 2>(x.quotient));
p = tail(p, x.remainder);
return p;
}
using type = T;
};
template <bool B, class T, class F>
using cond = typename _cond<B, T, F>::type;
// recursion base case, selected when "u" is one byte
template <>
ALWAYS_INLINE inline char * tail<UnsignedOfSize<1>, 1>(char * p, UnsignedOfSize<1> u)
template <class T>
inline ALWAYS_INLINE char * to_text_from_integer(char * b, T i)
{
return outTwoDigits(p, u);
}
constexpr auto q = sizeof(T);
using U = cond<q == 1, char8_t, cond<q <= sizeof(UInt16), UInt16, cond<q <= sizeof(UInt32), UInt32, UInt64>>>;
//===----------------------------------------------------------===//
// large values are >= 10^2*N
// where x contains quotient and remainder after division by 10^N
//===----------------------------------------------------------===//
template <size_t N>
ALWAYS_INLINE inline char * large(char * p, QuotientAndRemainder<N> x)
{
QuotientAndRemainder<N> y = split<N>(x.quotient);
p = head(p, UnsignedOfSize<N / 2>(y.quotient));
p = tail(p, y.remainder);
p = tail(p, x.remainder);
return p;
}
// convert bool to int before test with unary + to silence warning if T happens to be bool
U const n = +i < 0 ? *b++ = '-', U(0) - U(i) : U(i);
//===----------------------------------------------------------===//
// handle values of "u" that might be >= 10^2*N
// where N is the size of "u" in bytes
//===----------------------------------------------------------===//
template <typename UInt, size_t N = sizeof(UInt)>
ALWAYS_INLINE inline char * uitoa(char * p, UInt u)
{
if (u < pow10<UnsignedOfSize<N>>(N))
return head(p, UnsignedOfSize<N / 2>(u));
QuotientAndRemainder<N> x = split<N>(u);
if (n < U(1e2))
{
/// This is changed from the original jeaiii implementation
/// For small numbers the extra branch to call outOneDigit() is worth it as it saves some instructions
/// and a memory access (no need to read digits.fd[n])
/// This is not true for pure random numbers, but that's not the common use case of a database
/// Original jeaii code
// *reinterpret_cast<pair *>(b) = digits.fd[n];
// return n < 10 ? b + 1 : b + 2;
return n < 10 ? outOneDigit(b, n) : outTwoDigits(b, n);
}
if (n < UInt32(1e6))
{
if (sizeof(U) == 1 || n < U(1e4))
{
auto f0 = UInt32(10 * (1 << 24) / 1e3 + 1) * n;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 24];
if constexpr (sizeof(U) == 1)
b -= 1;
else
b -= n < U(1e3);
auto f2 = (f0 & mask24) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 24];
return b + 4;
}
auto f0 = UInt64(10 * (1ull << 32ull) / 1e5 + 1) * n;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 32];
if constexpr (sizeof(U) == 2)
b -= 1;
else
b -= n < U(1e5);
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
return b + 6;
}
if (sizeof(U) == 4 || n < UInt64(1ull << 32ull))
{
if (n < U(1e8))
{
auto f0 = UInt64(10 * (1ull << 48ull) / 1e7 + 1) * n >> 16;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 32];
b -= n < U(1e7);
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
auto f6 = (f4 & mask32) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 32];
return b + 8;
}
auto f0 = UInt64(10 * (1ull << 57ull) / 1e9 + 1) * n;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 57];
b -= n < UInt32(1e9);
auto f2 = (f0 & mask57) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 57];
auto f4 = (f2 & mask57) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 57];
auto f6 = (f4 & mask57) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 57];
auto f8 = (f6 & mask57) * 100;
*reinterpret_cast<pair *>(b + 8) = digits.dd[f8 >> 57];
return b + 10;
}
return u < pow10<UnsignedOfSize<N>>(2 * N) ? head<N>(p, x) : large<N>(p, x);
}
// if we get here U must be UInt64 but some compilers don't know that, so reassign n to a UInt64 to avoid warnings
UInt32 z = n % UInt32(1e8);
UInt64 u = n / UInt32(1e8);
// selected when "u" is one byte
template <>
ALWAYS_INLINE inline char * uitoa<UnsignedOfSize<1>, 1>(char * p, UnsignedOfSize<1> u)
{
if (u < 10)
return outDigit(p, u);
else if (u < 100)
return outTwoDigits(p, u);
if (u < UInt32(1e2))
{
// u can't be 1 digit (if u < 10 it would have been handled above as a 9 digit 32bit number)
*reinterpret_cast<pair *>(b) = digits.dd[u];
b += 2;
}
else if (u < UInt32(1e6))
{
if (u < UInt32(1e4))
{
auto f0 = UInt32(10 * (1 << 24) / 1e3 + 1) * u;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 24];
b -= u < UInt32(1e3);
auto f2 = (f0 & mask24) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 24];
b += 4;
}
else
{
auto f0 = UInt64(10 * (1ull << 32ull) / 1e5 + 1) * u;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 32];
b -= u < UInt32(1e5);
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
b += 6;
}
}
else if (u < UInt32(1e8))
{
auto f0 = UInt64(10 * (1ull << 48ull) / 1e7 + 1) * u >> 16;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 32];
b -= u < UInt32(1e7);
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
auto f6 = (f4 & mask32) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 32];
b += 8;
}
else if (u < UInt64(1ull << 32ull))
{
auto f0 = UInt64(10 * (1ull << 57ull) / 1e9 + 1) * u;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 57];
b -= u < UInt32(1e9);
auto f2 = (f0 & mask57) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 57];
auto f4 = (f2 & mask57) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 57];
auto f6 = (f4 & mask57) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 57];
auto f8 = (f6 & mask57) * 100;
*reinterpret_cast<pair *>(b + 8) = digits.dd[f8 >> 57];
b += 10;
}
else
{
p = outDigit(p, u / 100);
p = outTwoDigits(p, u % 100);
return p;
UInt32 y = u % UInt32(1e8);
u /= UInt32(1e8);
// u is 2, 3, or 4 digits (if u < 10 it would have been handled above)
if (u < UInt32(1e2))
{
*reinterpret_cast<pair *>(b) = digits.dd[u];
b += 2;
}
else
{
auto f0 = UInt32(10 * (1 << 24) / 1e3 + 1) * u;
*reinterpret_cast<pair *>(b) = digits.fd[f0 >> 24];
b -= u < UInt32(1e3);
auto f2 = (f0 & mask24) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 24];
b += 4;
}
// do 8 digits
auto f0 = (UInt64((1ull << 48ull) / 1e6 + 1) * y >> 16) + 1;
*reinterpret_cast<pair *>(b) = digits.dd[f0 >> 32];
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
auto f6 = (f4 & mask32) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 32];
b += 8;
}
}
//===----------------------------------------------------------===//
// handle unsigned and signed integral operands
//===----------------------------------------------------------===//
// itoa: handle unsigned integral operands (selected by SFINAE)
template <typename U>
requires(!std::is_signed_v<U> && std::is_integral_v<U>)
ALWAYS_INLINE inline char * itoa(U u, char * p)
{
return convert::uitoa(p, u);
}
// itoa: handle signed integral operands (selected by SFINAE)
template <typename I, size_t N = sizeof(I)>
requires(std::is_signed_v<I> && std::is_integral_v<I>)
ALWAYS_INLINE inline char * itoa(I i, char * p)
{
// Need "mask" to be filled with a copy of the sign bit.
// If "i" is a negative value, then the result of "operator >>"
// is implementation-defined, though usually it is an arithmetic
// right shift that replicates the sign bit.
// Use a conditional expression to be portable,
// a good optimizing compiler generates an arithmetic right shift
// and avoids the conditional branch.
UnsignedOfSize<N> mask = i < 0 ? ~UnsignedOfSize<N>(0) : 0;
// Now get the absolute value of "i" and cast to unsigned type UnsignedOfSize<N>.
// Cannot use std::abs() because the result is undefined
// in 2's complement systems for the most-negative value.
// Want to avoid conditional branch for performance reasons since
// CPU branch prediction will be ineffective when negative values
// occur randomly.
// Let "u" be "i" cast to unsigned type UnsignedOfSize<N>.
// Subtract "u" from 2*u if "i" is positive or 0 if "i" is negative.
// This yields the absolute value with the desired type without
// using a conditional branch and without invoking undefined or
// implementation defined behavior:
UnsignedOfSize<N> u = ((2 * UnsignedOfSize<N>(i)) & ~mask) - UnsignedOfSize<N>(i);
// Unconditionally store a minus sign when producing digits
// in a forward direction and increment the pointer only if
// the value is in fact negative.
// This avoids a conditional branch and is safe because we will
// always produce at least one digit and it will overwrite the
// minus sign when the value is not negative.
*p = '-';
p += (mask & 1);
p = convert::uitoa(p, u);
return p;
// do 8 digits
auto f0 = (UInt64((1ull << 48ull) / 1e6 + 1) * z >> 16) + 1;
*reinterpret_cast<pair *>(b) = digits.dd[f0 >> 32];
auto f2 = (f0 & mask32) * 100;
*reinterpret_cast<pair *>(b + 2) = digits.dd[f2 >> 32];
auto f4 = (f2 & mask32) * 100;
*reinterpret_cast<pair *>(b + 4) = digits.dd[f4 >> 32];
auto f6 = (f4 & mask32) * 100;
*reinterpret_cast<pair *>(b + 6) = digits.dd[f6 >> 32];
return b + 8;
}
}
@ -303,7 +296,7 @@ ALWAYS_INLINE inline char * writeUIntText(UInt128 _x, char * p)
{
/// If we the highest 64bit item is empty, we can print just the lowest item as u64
if (_x.items[UInt128::_impl::little(1)] == 0)
return convert::itoa(_x.items[UInt128::_impl::little(0)], p);
return jeaiii::to_text_from_integer(p, _x.items[UInt128::_impl::little(0)]);
/// Doing operations using __int128 is faster and we already rely on this feature
using T = unsigned __int128;
@ -334,7 +327,7 @@ ALWAYS_INLINE inline char * writeUIntText(UInt128 _x, char * p)
current_block += max_multiple_of_hundred_blocks;
}
char * highest_part_print = convert::itoa(uint64_t(x), p);
char * highest_part_print = jeaiii::to_text_from_integer(p, uint64_t(x));
for (int i = 0; i < current_block; i++)
{
outTwoDigits(highest_part_print, two_values[current_block - 1 - i]);
@ -450,12 +443,12 @@ ALWAYS_INLINE inline char * writeSIntText(T x, char * pos)
char * itoa(UInt8 i, char * p)
{
return convert::itoa(uint8_t(i), p);
return jeaiii::to_text_from_integer(p, uint8_t(i));
}
char * itoa(Int8 i, char * p)
{
return convert::itoa(int8_t(i), p);
return jeaiii::to_text_from_integer(p, int8_t(i));
}
char * itoa(UInt128 i, char * p)
@ -481,7 +474,7 @@ char * itoa(Int256 i, char * p)
#define DEFAULT_ITOA(T) \
char * itoa(T i, char * p) \
{ \
return convert::itoa(i, p); \
return jeaiii::to_text_from_integer(p, i); \
}
#define FOR_MISSING_INTEGER_TYPES(M) \

2
base/base/wide_integer_to_string.h
View File

@ -62,7 +62,7 @@ struct fmt::formatter<wide::integer<Bits, Signed>>
}
template <typename FormatContext>
auto format(const wide::integer<Bits, Signed> & value, FormatContext & ctx)
auto format(const wide::integer<Bits, Signed> & value, FormatContext & ctx) const
{
return fmt::format_to(ctx.out(), "{}", to_string(value));
}

10
base/glibc-compatibility/CMakeLists.txt
View File

@ -18,6 +18,16 @@ if (GLIBC_COMPATIBILITY)
message (FATAL_ERROR "glibc_compatibility can only be used on x86_64 or aarch64.")
endif ()
if (SANITIZE STREQUAL thread)
# Disable TSAN instrumentation that conflicts with re-exec due to high ASLR entropy using getauxval
# See longer comment in __auxv_init_procfs
# In the case of tsan we need to make sure getauxval is not instrumented as that would introduce tsan
# internal calls to functions that depend on a state that isn't initialized yet
set_source_files_properties(
musl/getauxval.c
PROPERTIES COMPILE_FLAGS "-mllvm -tsan-instrument-func-entry-exit=false")
endif()
# Need to omit frame pointers to match the performance of glibc
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fomit-frame-pointer")

40
base/glibc-compatibility/musl/getauxval.c
View File

@ -75,6 +75,44 @@ unsigned long NO_SANITIZE_THREAD __getauxval_procfs(unsigned long type)
}
static unsigned long NO_SANITIZE_THREAD __auxv_init_procfs(unsigned long type)
{
#if defined(__x86_64__) && defined(__has_feature)
# if __has_feature(memory_sanitizer) || __has_feature(thread_sanitizer)
/// Sanitizers are not compatible with high ASLR entropy, which is the default on modern Linux distributions, and
/// to workaround this limitation, TSAN and MSAN (couldn't see other sanitizers doing the same), re-exec the binary
/// without ASLR (see https://github.com/llvm/llvm-project/commit/0784b1eefa36d4acbb0dacd2d18796e26313b6c5)
/// The problem we face is that, in order to re-exec, the sanitizer wants to use the original pathname in the call
/// and to get its value it uses getauxval (https://github.com/llvm/llvm-project/blob/20eff684203287828d6722fc860b9d3621429542/compiler-rt/lib/sanitizer_common/sanitizer_linux_libcdep.cpp#L985-L988).
/// Since we provide getauxval ourselves (to minimize the version dependency on runtime glibc), we are the ones
// being called and we fail horribly:
///
/// ==301455==ERROR: MemorySanitizer: SEGV on unknown address 0x2ffc6d721550 (pc 0x5622c1cc0073 bp 0x000000000003 sp 0x7ffc6d721530 T301455)
/// ==301455==The signal is caused by a WRITE memory access.
/// #0 0x5622c1cc0073 in __auxv_init_procfs ./ClickHouse/base/glibc-compatibility/musl/getauxval.c:129:5
/// #1 0x5622c1cbffe9 in getauxval ./ClickHouse/base/glibc-compatibility/musl/getauxval.c:240:12
/// #2 0x5622c0d7bfb4 in __sanitizer::ReExec() crtstuff.c
/// #3 0x5622c0df7bfc in __msan::InitShadowWithReExec(bool) crtstuff.c
/// #4 0x5622c0d95356 in __msan_init (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x256356) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
/// #5 0x5622c0dfe878 in msan.module_ctor main.cc
/// #6 0x5622c1cc156c in __libc_csu_init (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x118256c) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
/// #7 0x73dc05dd7ea3 in __libc_start_main /usr/src/debug/glibc/glibc/csu/../csu/libc-start.c:343:6
/// #8 0x5622c0d6b7cd in _start (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x22c7cd) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
/// The source of the issue above is that, at this point in time during __msan_init, we can't really do much as
/// most global variables aren't initialized or available yet, so we can't initiate the auxiliary vector.
/// Normal glibc / musl getauxval doesn't have this problem since they initiate their auxval vector at the very
/// start of __libc_start_main (just keeping track of argv+argc+1), but we don't have such option (otherwise
/// this complexity of reading "/proc/self/auxv" or using __environ would not be necessary).
/// To avoid this crashes on the re-exec call (see above how it would fail when creating `aux`, and if we used
/// __auxv_init_environ then it would SIGSEV on READing `__environ`) we capture this call for `AT_EXECFN` and
/// unconditionally return "/proc/self/exe" without any preparation. Theoretically this should be fine in
/// our case, as we don't load any libraries. That's the theory at least.
if (type == AT_EXECFN)
return (unsigned long)"/proc/self/exe";
# endif
#endif
// For debugging:
// - od -t dL /proc/self/auxv
// - LD_SHOW_AUX= ls
@ -199,7 +237,7 @@ static unsigned long NO_SANITIZE_THREAD __auxv_init_environ(unsigned long type)
// - __auxv_init_procfs -> __auxv_init_environ -> __getauxval_environ
static void * volatile getauxval_func = (void *)__auxv_init_procfs;
unsigned long getauxval(unsigned long type)
unsigned long NO_SANITIZE_THREAD getauxval(unsigned long type)
{
return ((unsigned long (*)(unsigned long))getauxval_func)(type);
}

21
base/poco/Crypto/src/OpenSSLInitializer.cpp
View File

@ -23,9 +23,6 @@
#include <openssl/conf.h>
#endif
#if __has_feature(address_sanitizer)
#include <sanitizer/lsan_interface.h>
#endif
using Poco::RandomInputStream;
using Poco::Thread;
@ -70,18 +67,12 @@ void OpenSSLInitializer::initialize()
SSL_library_init();
SSL_load_error_strings();
OpenSSL_add_all_algorithms();
char seed[SEEDSIZE];
RandomInputStream rnd;
rnd.read(seed, sizeof(seed));
{
# if __has_feature(address_sanitizer)
/// Leak sanitizer (part of address sanitizer) thinks that a few bytes of memory in OpenSSL are allocated during but never released.
__lsan::ScopedDisabler lsan_disabler;
#endif
RAND_seed(seed, SEEDSIZE);
}
RAND_seed(seed, SEEDSIZE);
int nMutexes = CRYPTO_num_locks();
_mutexes = new Poco::FastMutex[nMutexes];
CRYPTO_set_locking_callback(&OpenSSLInitializer::lock);
@ -89,8 +80,8 @@ void OpenSSLInitializer::initialize()
// https://sourceforge.net/p/poco/bugs/110/
//
// From http://www.openssl.org/docs/crypto/threads.html :
// "If the application does not register such a callback using CRYPTO_THREADID_set_callback(),
// then a default implementation is used - on Windows and BeOS this uses the system's
// "If the application does not register such a callback using CRYPTO_THREADID_set_callback(),
// then a default implementation is used - on Windows and BeOS this uses the system's
// default thread identifying APIs"
CRYPTO_set_id_callback(&OpenSSLInitializer::id);
CRYPTO_set_dynlock_create_callback(&OpenSSLInitializer::dynlockCreate);
@ -109,7 +100,7 @@ void OpenSSLInitializer::uninitialize()
CRYPTO_set_locking_callback(0);
CRYPTO_set_id_callback(0);
delete [] _mutexes;
CONF_modules_free();
}
}

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

@ -213,6 +213,7 @@ target_compile_definitions (_poco_foundation
)
target_include_directories (_poco_foundation SYSTEM PUBLIC "include")
target_link_libraries (_poco_foundation PRIVATE clickhouse_common_io)
target_link_libraries (_poco_foundation
PRIVATE

2
base/poco/Foundation/include/Poco/Format.h
View File

@ -232,7 +232,7 @@ void Foundation_API format(
const Any & value10);
void Foundation_API format(std::string & result, const std::string & fmt, const std::vector<Any> & values);
void Foundation_API formatVector(std::string & result, const std::string & fmt, const std::vector<Any> & values);
/// Supports a variable number of arguments and is used by
/// all other variants of format().

2
base/poco/Foundation/include/Poco/Logger.h
View File

@ -21,6 +21,8 @@
#include <atomic>
#include <cstddef>
#include <map>
#include <memory>
#include <unordered_map>
#include <vector>
#include "Poco/Channel.h"

1
base/poco/Foundation/include/Poco/Message.h
View File

@ -19,6 +19,7 @@
#include <map>
#include <vector>
#include "Poco/Foundation.h"
#include "Poco/Timestamp.h"

2
base/poco/Foundation/include/Poco/RefCountedObject.h
View File

@ -21,6 +21,8 @@
#include "Poco/AtomicCounter.h"
#include "Poco/Foundation.h"
#include <atomic>
namespace Poco
{

20
base/poco/Foundation/include/Poco/ThreadPool.h
View File

@ -48,7 +48,13 @@ class Foundation_API ThreadPool
/// from the pool.
{
public:
ThreadPool(int minCapacity = 2, int maxCapacity = 16, int idleTime = 60, int stackSize = POCO_THREAD_STACK_SIZE);
explicit ThreadPool(
int minCapacity = 2,
int maxCapacity = 16,
int idleTime = 60,
int stackSize = POCO_THREAD_STACK_SIZE,
size_t global_profiler_real_time_period_ns_ = 0,
size_t global_profiler_cpu_time_period_ns_ = 0);
/// Creates a thread pool with minCapacity threads.
/// If required, up to maxCapacity threads are created
/// a NoThreadAvailableException exception is thrown.
@ -56,8 +62,14 @@ public:
/// and more than minCapacity threads are running, the thread
/// is killed. Threads are created with given stack size.
ThreadPool(
const std::string & name, int minCapacity = 2, int maxCapacity = 16, int idleTime = 60, int stackSize = POCO_THREAD_STACK_SIZE);
explicit ThreadPool(
const std::string & name,
int minCapacity = 2,
int maxCapacity = 16,
int idleTime = 60,
int stackSize = POCO_THREAD_STACK_SIZE,
size_t global_profiler_real_time_period_ns_ = 0,
size_t global_profiler_cpu_time_period_ns_ = 0);
/// Creates a thread pool with the given name and minCapacity threads.
/// If required, up to maxCapacity threads are created
/// a NoThreadAvailableException exception is thrown.
@ -171,6 +183,8 @@ private:
int _serial;
int _age;
int _stackSize;
size_t _globalProfilerRealTimePeriodNs;
size_t _globalProfilerCPUTimePeriodNs;
ThreadVec _threads;
mutable FastMutex _mutex;
};

7
base/poco/Foundation/include/Poco/UUID.h
View File

@ -19,6 +19,7 @@
#include "Poco/Foundation.h"
#include <Poco/Types.h>
namespace Poco
@ -135,6 +136,12 @@ public:
static const UUID & x500();
/// Returns the namespace identifier for the X500 namespace.
UInt32 getTimeLow() const { return _timeLow; }
UInt16 getTimeMid() const { return _timeMid; }
UInt16 getTimeHiAndVersion() const { return _timeHiAndVersion; }
UInt16 getClockSeq() const { return _clockSeq; }
std::array<UInt8, 6> getNode() const { return std::array<UInt8, 6>{_node[0], _node[1], _node[2], _node[3], _node[4], _node[5]}; }
protected:
UUID(UInt32 timeLow, UInt32 timeMid, UInt32 timeHiAndVersion, UInt16 clockSeq, UInt8 node[]);
UUID(const char * bytes, Version version);

40
base/poco/Foundation/src/Format.cpp
View File

@ -51,8 +51,8 @@ namespace
}
if (width != 0) str.width(width);
}
void parsePrec(std::ostream& str, std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
if (itFmt != endFmt && *itFmt == '.')
@ -67,7 +67,7 @@ namespace
if (prec >= 0) str.precision(prec);
}
}
char parseMod(std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
char mod = 0;
@ -77,13 +77,13 @@ namespace
{
case 'l':
case 'h':
case 'L':
case 'L':
case '?': mod = *itFmt++; break;
}
}
return mod;
}
std::size_t parseIndex(std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
int index = 0;
@ -110,8 +110,8 @@ namespace
case 'f': str << std::fixed; break;
}
}
void writeAnyInt(std::ostream& str, const Any& any)
{
if (any.type() == typeid(char))
@ -201,7 +201,7 @@ namespace
str << RefAnyCast<std::string>(*itVal++);
break;
case 'z':
str << AnyCast<std::size_t>(*itVal++);
str << AnyCast<std::size_t>(*itVal++);
break;
case 'I':
case 'D':
@ -303,7 +303,7 @@ void format(std::string& result, const std::string& fmt, const Any& value)
{
std::vector<Any> args;
args.push_back(value);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -312,7 +312,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
std::vector<Any> args;
args.push_back(value1);
args.push_back(value2);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -322,7 +322,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value1);
args.push_back(value2);
args.push_back(value3);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -333,7 +333,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value2);
args.push_back(value3);
args.push_back(value4);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -345,7 +345,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value3);
args.push_back(value4);
args.push_back(value5);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -358,7 +358,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value4);
args.push_back(value5);
args.push_back(value6);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -372,7 +372,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value5);
args.push_back(value6);
args.push_back(value7);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -387,7 +387,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value6);
args.push_back(value7);
args.push_back(value8);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -403,7 +403,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value7);
args.push_back(value8);
args.push_back(value9);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -420,16 +420,16 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value8);
args.push_back(value9);
args.push_back(value10);
format(result, fmt, args);
formatVector(result, fmt, args);
}
void format(std::string& result, const std::string& fmt, const std::vector<Any>& values)
void formatVector(std::string& result, const std::string& fmt, const std::vector<Any>& values)
{
std::string::const_iterator itFmt = fmt.begin();
std::string::const_iterator endFmt = fmt.end();
std::vector<Any>::const_iterator itVal = values.begin();
std::vector<Any>::const_iterator endVal = values.end();
std::vector<Any>::const_iterator endVal = values.end();
while (itFmt != endFmt)
{
switch (*itFmt)

75
base/poco/Foundation/src/ThreadPool.cpp
View File

@ -20,6 +20,7 @@
#include "Poco/ErrorHandler.h"
#include <sstream>
#include <ctime>
#include <Common/ThreadPool.h>
namespace Poco {
@ -28,7 +29,11 @@ namespace Poco {
class PooledThread: public Runnable
{
public:
PooledThread(const std::string& name, int stackSize = POCO_THREAD_STACK_SIZE);
explicit PooledThread(
const std::string& name,
int stackSize = POCO_THREAD_STACK_SIZE,
size_t globalProfilerRealTimePeriodNs_ = 0,
size_t globalProfilerCPUTimePeriodNs_ = 0);
~PooledThread();
void start();
@ -51,16 +56,24 @@ private:
Event _targetCompleted;
Event _started;
FastMutex _mutex;
size_t _globalProfilerRealTimePeriodNs;
size_t _globalProfilerCPUTimePeriodNs;
};
PooledThread::PooledThread(const std::string& name, int stackSize):
_idle(true),
_idleTime(0),
_pTarget(0),
_name(name),
PooledThread::PooledThread(
const std::string& name,
int stackSize,
size_t globalProfilerRealTimePeriodNs_,
size_t globalProfilerCPUTimePeriodNs_) :
_idle(true),
_idleTime(0),
_pTarget(0),
_name(name),
_thread(name),
_targetCompleted(false)
_targetCompleted(false),
_globalProfilerRealTimePeriodNs(globalProfilerRealTimePeriodNs_),
_globalProfilerCPUTimePeriodNs(globalProfilerCPUTimePeriodNs_)
{
poco_assert_dbg (stackSize >= 0);
_thread.setStackSize(stackSize);
@ -83,7 +96,7 @@ void PooledThread::start()
void PooledThread::start(Thread::Priority priority, Runnable& target)
{
FastMutex::ScopedLock lock(_mutex);
poco_assert (_pTarget == 0);
_pTarget = &target;
@ -109,7 +122,7 @@ void PooledThread::start(Thread::Priority priority, Runnable& target, const std:
}
_thread.setName(fullName);
_thread.setPriority(priority);
poco_assert (_pTarget == 0);
_pTarget = &target;
@ -145,7 +158,7 @@ void PooledThread::join()
void PooledThread::activate()
{
FastMutex::ScopedLock lock(_mutex);
poco_assert (_idle);
_idle = false;
_targetCompleted.reset();
@ -155,7 +168,7 @@ void PooledThread::activate()
void PooledThread::release()
{
const long JOIN_TIMEOUT = 10000;
_mutex.lock();
_pTarget = 0;
_mutex.unlock();
@ -174,6 +187,10 @@ void PooledThread::release()
void PooledThread::run()
{
DB::ThreadStatus thread_status;
if (unlikely(_globalProfilerRealTimePeriodNs != 0 || _globalProfilerCPUTimePeriodNs != 0))
thread_status.initGlobalProfiler(_globalProfilerRealTimePeriodNs, _globalProfilerCPUTimePeriodNs);
_started.set();
for (;;)
{
@ -220,13 +237,17 @@ void PooledThread::run()
ThreadPool::ThreadPool(int minCapacity,
int maxCapacity,
int idleTime,
int stackSize):
_minCapacity(minCapacity),
_maxCapacity(maxCapacity),
int stackSize,
size_t globalProfilerRealTimePeriodNs_,
size_t globalProfilerCPUTimePeriodNs_) :
_minCapacity(minCapacity),
_maxCapacity(maxCapacity),
_idleTime(idleTime),
_serial(0),
_age(0),
_stackSize(stackSize)
_stackSize(stackSize),
_globalProfilerRealTimePeriodNs(globalProfilerRealTimePeriodNs_),
_globalProfilerCPUTimePeriodNs(globalProfilerCPUTimePeriodNs_)
{
poco_assert (minCapacity >= 1 && maxCapacity >= minCapacity && idleTime > 0);
@ -243,14 +264,18 @@ ThreadPool::ThreadPool(const std::string& name,
int minCapacity,
int maxCapacity,
int idleTime,
int stackSize):
int stackSize,
size_t globalProfilerRealTimePeriodNs_,
size_t globalProfilerCPUTimePeriodNs_) :
_name(name),
_minCapacity(minCapacity),
_maxCapacity(maxCapacity),
_minCapacity(minCapacity),
_maxCapacity(maxCapacity),
_idleTime(idleTime),
_serial(0),
_age(0),
_stackSize(stackSize)
_stackSize(stackSize),
_globalProfilerRealTimePeriodNs(globalProfilerRealTimePeriodNs_),
_globalProfilerCPUTimePeriodNs(globalProfilerCPUTimePeriodNs_)
{
poco_assert (minCapacity >= 1 && maxCapacity >= minCapacity && idleTime > 0);
@ -393,15 +418,15 @@ void ThreadPool::housekeep()
ThreadVec activeThreads;
idleThreads.reserve(_threads.size());
activeThreads.reserve(_threads.size());
for (ThreadVec::iterator it = _threads.begin(); it != _threads.end(); ++it)
{
if ((*it)->idle())
{
if ((*it)->idleTime() < _idleTime)
idleThreads.push_back(*it);
else
expiredThreads.push_back(*it);
else
expiredThreads.push_back(*it);
}
else activeThreads.push_back(*it);
}
@ -463,7 +488,7 @@ PooledThread* ThreadPool::createThread()
{
std::ostringstream name;
name << _name << "[#" << ++_serial << "]";
return new PooledThread(name.str(), _stackSize);
return new PooledThread(name.str(), _stackSize, _globalProfilerRealTimePeriodNs, _globalProfilerCPUTimePeriodNs);
}
@ -481,7 +506,7 @@ public:
ThreadPool* pool()
{
FastMutex::ScopedLock lock(_mutex);
if (!_pPool)
{
_pPool = new ThreadPool("default");
@ -490,7 +515,7 @@ public:
}
return _pPool;
}
private:
ThreadPool* _pPool;
FastMutex _mutex;

4
base/poco/MongoDB/src/Binary.cpp
View File

@ -76,13 +76,13 @@ std::string Binary::toString(int indent) const
UUID Binary::uuid() const
{
if (_subtype == 0x04 && _buffer.size() == 16)
if ((_subtype == 0x04 || _subtype == 0x03) && _buffer.size() == 16)
{
UUID uuid;
uuid.copyFrom((const char*) _buffer.begin());
return uuid;
}
throw BadCastException("Invalid subtype");
throw BadCastException("Invalid subtype: " + std::to_string(_subtype) + ", size: " + std::to_string(_buffer.size()));
}

2
base/poco/MongoDB/src/ObjectId.cpp
View File

@ -57,7 +57,7 @@ std::string ObjectId::toString(const std::string& fmt) const
for (int i = 0; i < 12; ++i)
{
s += format(fmt, (unsigned int) _id[i]);
s += Poco::format(fmt, (unsigned int) _id[i]);
}
return s;
}

8
base/poco/MongoDB/src/OpMsgCursor.cpp
View File

@ -43,9 +43,9 @@ namespace Poco {
namespace MongoDB {
static const std::string keyCursor {"cursor"};
static const std::string keyFirstBatch {"firstBatch"};
static const std::string keyNextBatch {"nextBatch"};
[[ maybe_unused ]] static const std::string keyCursor {"cursor"};
[[ maybe_unused ]] static const std::string keyFirstBatch {"firstBatch"};
[[ maybe_unused ]] static const std::string keyNextBatch {"nextBatch"};
static Poco::Int64 cursorIdFromResponse(const MongoDB::Document& doc);
@ -131,7 +131,7 @@ OpMsgMessage& OpMsgCursor::next(Connection& connection)
connection.readResponse(_response);
}
else
#endif
#endif
{
_response.clear();
_query.setCursor(_cursorID, _batchSize);

2
base/poco/Net/include/Poco/Net/NameValueCollection.h
View File

@ -79,7 +79,7 @@ namespace Net
/// Returns the value of the first name-value pair with the given name.
/// If no value with the given name has been found, the defaultValue is returned.
const std::vector<std::reference_wrapper<const std::string>> getAll(const std::string & name) const;
std::vector<std::string> getAll(const std::string & name) const;
/// Returns all values of all name-value pairs with the given name.
///
/// Returns an empty vector if there are no name-value pairs with the given name.

12
base/poco/Net/src/HTTPMessage.cpp
View File

@ -17,9 +17,9 @@
#include "Poco/NumberFormatter.h"
#include "Poco/NumberParser.h"
#include "Poco/String.h"
#include <charconv>
#include <format>
using Poco::NumberFormatter;
using Poco::NumberParser;
using Poco::icompare;
@ -75,7 +75,7 @@ void HTTPMessage::setContentLength(std::streamsize length)
erase(CONTENT_LENGTH);
}
std::streamsize HTTPMessage::getContentLength() const
{
const std::string& contentLength = get(CONTENT_LENGTH, EMPTY);
@ -98,7 +98,7 @@ void HTTPMessage::setContentLength64(Poco::Int64 length)
erase(CONTENT_LENGTH);
}
Poco::Int64 HTTPMessage::getContentLength64() const
{
const std::string& contentLength = get(CONTENT_LENGTH, EMPTY);
@ -133,13 +133,13 @@ void HTTPMessage::setChunkedTransferEncoding(bool flag)
setTransferEncoding(IDENTITY_TRANSFER_ENCODING);
}
bool HTTPMessage::getChunkedTransferEncoding() const
{
return icompare(getTransferEncoding(), CHUNKED_TRANSFER_ENCODING) == 0;
}
void HTTPMessage::setContentType(const std::string& mediaType)
{
if (mediaType.empty())
@ -154,7 +154,7 @@ void HTTPMessage::setContentType(const MediaType& mediaType)
setContentType(mediaType.toString());
}
const std::string& HTTPMessage::getContentType() const
{
return get(CONTENT_TYPE, UNKNOWN_CONTENT_TYPE);

4
base/poco/Net/src/NameValueCollection.cpp
View File

@ -102,9 +102,9 @@ const std::string& NameValueCollection::get(const std::string& name, const std::
return defaultValue;
}
const std::vector<std::reference_wrapper<const std::string>> NameValueCollection::getAll(const std::string& name) const
std::vector<std::string> NameValueCollection::getAll(const std::string& name) const
{
std::vector<std::reference_wrapper<const std::string>> values;
std::vector<std::string> values;
for (ConstIterator it = _map.find(name); it != _map.end(); it++)
if (it->first == name)
values.push_back(it->second);

76
base/poco/NetSSL_OpenSSL/include/Poco/Net/SSLManager.h
View File

@ -17,6 +17,7 @@
#ifndef NetSSL_SSLManager_INCLUDED
#define NetSSL_SSLManager_INCLUDED
#include <unordered_map>
#include <openssl/ssl.h>
#include "Poco/BasicEvent.h"
@ -219,6 +220,13 @@ namespace Net
/// Unless initializeClient() has been called, the first call to this method initializes the default Context
/// from the application configuration.
Context::Ptr getCustomServerContext(const std::string & name);
/// Return custom Context used by the server.
Context::Ptr setCustomServerContext(const std::string & name, Context::Ptr ctx);
/// Set custom Context used by the server.
/// Return pointer on inserted Context or on old Context if exists.
PrivateKeyPassphraseHandlerPtr serverPassphraseHandler();
/// Returns the configured passphrase handler of the server. If none is set, the method will create a default one
/// from an application configuration.
@ -258,6 +266,40 @@ namespace Net
static const std::string CFG_SERVER_PREFIX;
static const std::string CFG_CLIENT_PREFIX;
static const std::string CFG_PRIV_KEY_FILE;
static const std::string CFG_CERTIFICATE_FILE;
static const std::string CFG_CA_LOCATION;
static const std::string CFG_VER_MODE;
static const Context::VerificationMode VAL_VER_MODE;
static const std::string CFG_VER_DEPTH;
static const int VAL_VER_DEPTH;
static const std::string CFG_ENABLE_DEFAULT_CA;
static const bool VAL_ENABLE_DEFAULT_CA;
static const std::string CFG_CIPHER_LIST;
static const std::string CFG_CYPHER_LIST; // for backwards compatibility
static const std::string VAL_CIPHER_LIST;
static const std::string CFG_PREFER_SERVER_CIPHERS;
static const std::string CFG_DELEGATE_HANDLER;
static const std::string VAL_DELEGATE_HANDLER;
static const std::string CFG_CERTIFICATE_HANDLER;
static const std::string VAL_CERTIFICATE_HANDLER;
static const std::string CFG_CACHE_SESSIONS;
static const std::string CFG_SESSION_ID_CONTEXT;
static const std::string CFG_SESSION_CACHE_SIZE;
static const std::string CFG_SESSION_TIMEOUT;
static const std::string CFG_EXTENDED_VERIFICATION;
static const std::string CFG_REQUIRE_TLSV1;
static const std::string CFG_REQUIRE_TLSV1_1;
static const std::string CFG_REQUIRE_TLSV1_2;
static const std::string CFG_DISABLE_PROTOCOLS;
static const std::string CFG_DH_PARAMS_FILE;
static const std::string CFG_ECDH_CURVE;
#ifdef OPENSSL_FIPS
static const std::string CFG_FIPS_MODE;
static const bool VAL_FIPS_MODE;
#endif
protected:
static int verifyClientCallback(int ok, X509_STORE_CTX * pStore);
/// The return value of this method defines how errors in
@ -314,39 +356,7 @@ namespace Net
InvalidCertificateHandlerPtr _ptrClientCertificateHandler;
Poco::FastMutex _mutex;
static const std::string CFG_PRIV_KEY_FILE;
static const std::string CFG_CERTIFICATE_FILE;
static const std::string CFG_CA_LOCATION;
static const std::string CFG_VER_MODE;
static const Context::VerificationMode VAL_VER_MODE;
static const std::string CFG_VER_DEPTH;
static const int VAL_VER_DEPTH;
static const std::string CFG_ENABLE_DEFAULT_CA;
static const bool VAL_ENABLE_DEFAULT_CA;
static const std::string CFG_CIPHER_LIST;
static const std::string CFG_CYPHER_LIST; // for backwards compatibility
static const std::string VAL_CIPHER_LIST;
static const std::string CFG_PREFER_SERVER_CIPHERS;
static const std::string CFG_DELEGATE_HANDLER;
static const std::string VAL_DELEGATE_HANDLER;
static const std::string CFG_CERTIFICATE_HANDLER;
static const std::string VAL_CERTIFICATE_HANDLER;
static const std::string CFG_CACHE_SESSIONS;
static const std::string CFG_SESSION_ID_CONTEXT;
static const std::string CFG_SESSION_CACHE_SIZE;
static const std::string CFG_SESSION_TIMEOUT;
static const std::string CFG_EXTENDED_VERIFICATION;
static const std::string CFG_REQUIRE_TLSV1;
static const std::string CFG_REQUIRE_TLSV1_1;
static const std::string CFG_REQUIRE_TLSV1_2;
static const std::string CFG_DISABLE_PROTOCOLS;
static const std::string CFG_DH_PARAMS_FILE;
static const std::string CFG_ECDH_CURVE;
#ifdef OPENSSL_FIPS
static const std::string CFG_FIPS_MODE;
static const bool VAL_FIPS_MODE;
#endif
std::unordered_map<std::string, Context::Ptr> _mapPtrServerContexts;
friend class Poco::SingletonHolder<SSLManager>;
friend class Context;

5
base/poco/NetSSL_OpenSSL/include/Poco/Net/SecureSocketImpl.h
View File

@ -235,8 +235,6 @@ namespace Net
/// Note that simply closing a socket is not sufficient
/// to be able to re-use it again.
Poco::Timespan getMaxTimeout();
private:
SecureSocketImpl(const SecureSocketImpl &);
SecureSocketImpl & operator=(const SecureSocketImpl &);
@ -250,6 +248,9 @@ namespace Net
Session::Ptr _pSession;
friend class SecureStreamSocketImpl;
Poco::Timespan getMaxTimeoutOrLimit();
//// Return max(send, receive) if non zero, otherwise maximum timeout
};

58
base/poco/NetSSL_OpenSSL/src/SSLManager.cpp
View File

@ -330,27 +330,26 @@ void SSLManager::initDefaultContext(bool server)
else
_ptrDefaultClientContext->disableProtocols(disabledProtocols);
/// Temporarily disabled during the transition from boringssl to OpenSSL due to tsan issues.
/// bool cacheSessions = config.getBool(prefix + CFG_CACHE_SESSIONS, false);
/// if (server)
/// {
/// std::string sessionIdContext = config.getString(prefix + CFG_SESSION_ID_CONTEXT, config.getString("application.name", ""));
/// _ptrDefaultServerContext->enableSessionCache(cacheSessions, sessionIdContext);
/// if (config.hasProperty(prefix + CFG_SESSION_CACHE_SIZE))
/// {
/// int cacheSize = config.getInt(prefix + CFG_SESSION_CACHE_SIZE);
/// _ptrDefaultServerContext->setSessionCacheSize(cacheSize);
/// }
/// if (config.hasProperty(prefix + CFG_SESSION_TIMEOUT))
/// {
/// int timeout = config.getInt(prefix + CFG_SESSION_TIMEOUT);
/// _ptrDefaultServerContext->setSessionTimeout(timeout);
/// }
/// }
/// else
/// {
/// _ptrDefaultClientContext->enableSessionCache(cacheSessions);
/// }
bool cacheSessions = config.getBool(prefix + CFG_CACHE_SESSIONS, false);
if (server)
{
std::string sessionIdContext = config.getString(prefix + CFG_SESSION_ID_CONTEXT, config.getString("application.name", ""));
_ptrDefaultServerContext->enableSessionCache(cacheSessions, sessionIdContext);
if (config.hasProperty(prefix + CFG_SESSION_CACHE_SIZE))
{
int cacheSize = config.getInt(prefix + CFG_SESSION_CACHE_SIZE);
_ptrDefaultServerContext->setSessionCacheSize(cacheSize);
}
if (config.hasProperty(prefix + CFG_SESSION_TIMEOUT))
{
int timeout = config.getInt(prefix + CFG_SESSION_TIMEOUT);
_ptrDefaultServerContext->setSessionTimeout(timeout);
}
}
else
{
_ptrDefaultClientContext->enableSessionCache(cacheSessions);
}
bool extendedVerification = config.getBool(prefix + CFG_EXTENDED_VERIFICATION, false);
if (server)
_ptrDefaultServerContext->enableExtendedCertificateVerification(extendedVerification);
@ -429,6 +428,23 @@ void SSLManager::initCertificateHandler(bool server)
}
Context::Ptr SSLManager::getCustomServerContext(const std::string & name)
{
Poco::FastMutex::ScopedLock lock(_mutex);
auto it = _mapPtrServerContexts.find(name);
if (it != _mapPtrServerContexts.end())
return it->second;
return nullptr;
}
Context::Ptr SSLManager::setCustomServerContext(const std::string & name, Context::Ptr ctx)
{
Poco::FastMutex::ScopedLock lock(_mutex);
ctx = _mapPtrServerContexts.insert({name, ctx}).first->second;
return ctx;
}
Poco::Util::AbstractConfiguration& SSLManager::appConfig()
{
try

31
base/poco/NetSSL_OpenSSL/src/SecureSocketImpl.cpp
View File

@ -199,7 +199,7 @@ void SecureSocketImpl::connectSSL(bool performHandshake)
if (performHandshake && _pSocket->getBlocking())
{
int ret;
Poco::Timespan remaining_time = getMaxTimeout();
Poco::Timespan remaining_time = getMaxTimeoutOrLimit();
do
{
RemainingTimeCounter counter(remaining_time);
@ -302,7 +302,7 @@ int SecureSocketImpl::sendBytes(const void* buffer, int length, int flags)
return rc;
}
Poco::Timespan remaining_time = getMaxTimeout();
Poco::Timespan remaining_time = getMaxTimeoutOrLimit();
do
{
RemainingTimeCounter counter(remaining_time);
@ -338,7 +338,7 @@ int SecureSocketImpl::receiveBytes(void* buffer, int length, int flags)
return rc;
}
Poco::Timespan remaining_time = getMaxTimeout();
Poco::Timespan remaining_time = getMaxTimeoutOrLimit();
do
{
/// SSL record may consist of several TCP packets,
@ -372,7 +372,7 @@ int SecureSocketImpl::completeHandshake()
poco_check_ptr (_pSSL);
int rc;
Poco::Timespan remaining_time = getMaxTimeout();
Poco::Timespan remaining_time = getMaxTimeoutOrLimit();
do
{
RemainingTimeCounter counter(remaining_time);
@ -453,18 +453,29 @@ X509* SecureSocketImpl::peerCertificate() const
return 0;
}
Poco::Timespan SecureSocketImpl::getMaxTimeout()
Poco::Timespan SecureSocketImpl::getMaxTimeoutOrLimit()
{
std::lock_guard<std::recursive_mutex> lock(_mutex);
Poco::Timespan remaining_time = _pSocket->getReceiveTimeout();
Poco::Timespan send_timeout = _pSocket->getSendTimeout();
if (remaining_time < send_timeout)
remaining_time = send_timeout;
/// zero SO_SNDTIMEO/SO_RCVTIMEO works as no timeout, let's replicate this
///
/// NOTE: we cannot use INT64_MAX (std::numeric_limits<Poco::Timespan::TimeDiff>::max()),
/// since it will be later passed to poll() which accept int timeout, and
/// even though poll() accepts milliseconds and Timespan() accepts
/// microseconds, let's use smaller maximum value just to avoid some possible
/// issues, this should be enough anyway (it is ~24 days).
if (remaining_time == 0)
remaining_time = Poco::Timespan(std::numeric_limits<int>::max());
return remaining_time;
}
bool SecureSocketImpl::mustRetry(int rc, Poco::Timespan& remaining_time)
{
if (remaining_time == 0)
return false;
std::lock_guard<std::recursive_mutex> lock(_mutex);
if (rc <= 0)
{
@ -475,9 +486,7 @@ bool SecureSocketImpl::mustRetry(int rc, Poco::Timespan& remaining_time)
case SSL_ERROR_WANT_READ:
if (_pSocket->getBlocking())
{
/// Level-triggered mode of epoll_wait is used, so if SSL_read don't read all available data from socket,
/// epoll_wait returns true without waiting for new data even if remaining_time == 0
if (_pSocket->pollImpl(remaining_time, Poco::Net::Socket::SELECT_READ) && remaining_time != 0)
if (_pSocket->pollImpl(remaining_time, Poco::Net::Socket::SELECT_READ))
return true;
else
throw Poco::TimeoutException();
@ -486,13 +495,15 @@ bool SecureSocketImpl::mustRetry(int rc, Poco::Timespan& remaining_time)
case SSL_ERROR_WANT_WRITE:
if (_pSocket->getBlocking())
{
/// The same as for SSL_ERROR_WANT_READ
if (_pSocket->pollImpl(remaining_time, Poco::Net::Socket::SELECT_WRITE) && remaining_time != 0)
if (_pSocket->pollImpl(remaining_time, Poco::Net::Socket::SELECT_WRITE))
return true;
else
throw Poco::TimeoutException();
}
break;
/// NOTE: POCO_EINTR is the same as SSL_ERROR_WANT_READ (at least in
/// OpenSSL), so this likely dead code, but let's leave it for
/// compatibility with other implementations
case SSL_ERROR_SYSCALL:
return socketError == POCO_EAGAIN || socketError == POCO_EINTR;
default:

11
base/poco/Util/include/Poco/Util/Application.h
View File

@ -261,6 +261,11 @@ namespace Util
///
/// Throws a NullPointerException if no Application instance exists.
static Application * instanceRawPtr();
/// Returns a raw pointer to the Application singleton.
///
/// The caller should check whether the result is nullptr.
const Poco::Timestamp & startTime() const;
/// Returns the application start time (UTC).
@ -448,6 +453,12 @@ namespace Util
}
inline Application * Application::instanceRawPtr()
{
return _pInstance;
}
inline const Poco::Timestamp & Application::startTime() const
{
return _startTime;

12
cmake/autogenerated_versions.txt
View File

@ -1,12 +1,12 @@
# This variables autochanged by tests/ci/version_helper.py:
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# NOTE: VERSION_REVISION has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54487)
SET(VERSION_REVISION 54489)
SET(VERSION_MAJOR 24)
SET(VERSION_MINOR 6)
SET(VERSION_MINOR 8)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 70a1d3a63d47f0be077d67b8deb907230fc7cfb0)
SET(VERSION_DESCRIBE v24.6.1.1-testing)
SET(VERSION_STRING 24.6.1.1)
SET(VERSION_GITHASH 3f8b27d7accd2b5ec4afe7d0dd459115323304af)
SET(VERSION_DESCRIBE v24.8.1.1-testing)
SET(VERSION_STRING 24.8.1.1)
# end of autochange

16
cmake/limit_jobs.cmake
View File

@ -42,9 +42,19 @@ endif ()
# But use 2 parallel jobs, since:
# - this is what llvm does
# - and I've verfied that lld-11 does not use all available CPU time (in peak) while linking one binary
if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO" AND ENABLE_THINLTO AND PARALLEL_LINK_JOBS GREATER 2)
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 2.")
set (PARALLEL_LINK_JOBS 2)
if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO" AND ENABLE_THINLTO)
if (ARCH_AARCH64)
# aarch64 builds start to often fail with OOMs (reason not yet clear), for now let's limit the concurrency
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 1.")
set (PARALLEL_LINK_JOBS 1)
if (LINKER_NAME MATCHES "lld")
math(EXPR LTO_JOBS ${NUMBER_OF_LOGICAL_CORES}/4)
set (CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO "${CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO} -Wl,--thinlto-jobs=${LTO_JOBS}")
endif()
elseif (PARALLEL_LINK_JOBS GREATER 2)
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 2.")
set (PARALLEL_LINK_JOBS 2)
endif ()
endif()
message(STATUS "Building sub-tree with ${PARALLEL_COMPILE_JOBS} compile jobs and ${PARALLEL_LINK_JOBS} linker jobs (system: ${NUMBER_OF_LOGICAL_CORES} cores, ${TOTAL_PHYSICAL_MEMORY} MB RAM, 'OFF' means the native core count).")

3
cmake/sanitize.cmake
View File

@ -57,7 +57,8 @@ option(WITH_COVERAGE "Instrumentation for code coverage with default implementat
if (WITH_COVERAGE)
message (STATUS "Enabled instrumentation for code coverage")
set(COVERAGE_FLAGS "-fprofile-instr-generate -fcoverage-mapping")
set(COVERAGE_FLAGS "SHELL:-fprofile-instr-generate -fcoverage-mapping")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
endif()
option (SANITIZE_COVERAGE "Instrumentation for code coverage with custom callbacks" OFF)

2
cmake/target.cmake
View File

@ -84,5 +84,5 @@ if (CMAKE_CROSSCOMPILING)
message (FATAL_ERROR "Trying to cross-compile to unsupported system: ${CMAKE_SYSTEM_NAME}!")
endif ()
message (STATUS "Cross-compiling for target: ${CMAKE_CXX_COMPILE_TARGET}")
message (STATUS "Cross-compiling for target: ${CMAKE_CXX_COMPILER_TARGET}")
endif ()

4
contrib/CMakeLists.txt vendored
View File

@ -228,6 +228,10 @@ add_contrib (ulid-c-cmake ulid-c)
add_contrib (libssh-cmake libssh)
add_contrib (prometheus-protobufs-cmake prometheus-protobufs prometheus-protobufs-gogo)
add_contrib(numactl-cmake numactl)
# Put all targets defined here and in subdirectories under "contrib/<immediate-subdir>" folders in GUI-based IDEs.
# Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they would not appear
# in "contrib/..." as originally planned, so we workaround this by fixing FOLDER properties of all targets manually,

2
contrib/NuRaft vendored

@ -1 +1 @@
Subproject commit cb5dc3c906e80f253e9ce9535807caef827cc2e0
Subproject commit c2b0811f164a7948208489562dab4f186eb305ce

2
contrib/abseil-cpp vendored

@ -1 +1 @@
Subproject commit 3bd86026c93da5a40006fd53403dff9d5f5e30e3
Subproject commit a3c4dd3e77f28b526efbb0eb394b72e29c633936

259
contrib/abseil-cpp-cmake/CMakeLists.txt
View File

@ -1,6 +1,8 @@
set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
set(ABSL_COMMON_INCLUDE_DIRS "${ABSL_ROOT_DIR}")
# This is a minimized version of the function definition in CMake/AbseilHelpers.cmake
#
# Copyright 2017 The Abseil Authors.
#
@ -16,7 +18,6 @@ set(ABSL_COMMON_INCLUDE_DIRS "${ABSL_ROOT_DIR}")
# See the License for the specific language governing permissions and
# limitations under the License.
#
function(absl_cc_library)
cmake_parse_arguments(ABSL_CC_LIB
"DISABLE_INSTALL;PUBLIC;TESTONLY"
@ -76,6 +77,12 @@ function(absl_cc_library)
add_library(absl::${ABSL_CC_LIB_NAME} ALIAS ${_NAME})
endfunction()
# The following definitions are an amalgamation of the CMakeLists.txt files in absl/*/
# To refresh them when upgrading to a new version:
# - copy them over from upstream
# - remove calls of 'absl_cc_test'
# - remove calls of `absl_cc_library` that contain `TESTONLY`
# - append '${DIR}' to the file definitions
set(DIR ${ABSL_ROOT_DIR}/absl/algorithm)
@ -102,12 +109,12 @@ absl_cc_library(
absl::algorithm
absl::core_headers
absl::meta
absl::nullability
PUBLIC
)
set(DIR ${ABSL_ROOT_DIR}/absl/base)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
atomic_hook
@ -146,6 +153,18 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
)
absl_cc_library(
NAME
no_destructor
HDRS
"${DIR}/no_destructor.h"
DEPS
absl::config
absl::nullability
COPTS
${ABSL_DEFAULT_COPTS}
)
absl_cc_library(
NAME
nullability
@ -305,6 +324,8 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
$<$<BOOL:${LIBRT}>:-lrt>
$<$<BOOL:${MINGW}>:-ladvapi32>
DEPS
absl::atomic_hook
absl::base_internal
@ -312,6 +333,7 @@ absl_cc_library(
absl::core_headers
absl::dynamic_annotations
absl::log_severity
absl::nullability
absl::raw_logging_internal
absl::spinlock_wait
absl::type_traits
@ -357,6 +379,7 @@ absl_cc_library(
absl::base
absl::config
absl::core_headers
absl::nullability
PUBLIC
)
@ -467,10 +490,11 @@ absl_cc_library(
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::container_common
absl::common_policy_traits
absl::compare
absl::compressed_tuple
absl::config
absl::container_common
absl::container_memory
absl::cord
absl::core_headers
@ -480,7 +504,6 @@ absl_cc_library(
absl::strings
absl::throw_delegate
absl::type_traits
absl::utility
)
# Internal-only target, do not depend on directly.
@ -523,7 +546,9 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::base_internal
absl::compressed_tuple
absl::config
absl::core_headers
absl::memory
absl::span
@ -548,18 +573,6 @@ absl_cc_library(
PUBLIC
)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
counting_allocator
HDRS
"${DIR}/internal/counting_allocator.h"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
)
absl_cc_library(
NAME
flat_hash_map
@ -570,7 +583,7 @@ absl_cc_library(
DEPS
absl::container_memory
absl::core_headers
absl::hash_function_defaults
absl::hash_container_defaults
absl::raw_hash_map
absl::algorithm_container
absl::memory
@ -586,7 +599,7 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
DEPS
absl::container_memory
absl::hash_function_defaults
absl::hash_container_defaults
absl::raw_hash_set
absl::algorithm_container
absl::core_headers
@ -604,7 +617,7 @@ absl_cc_library(
DEPS
absl::container_memory
absl::core_headers
absl::hash_function_defaults
absl::hash_container_defaults
absl::node_slot_policy
absl::raw_hash_map
absl::algorithm_container
@ -620,8 +633,9 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::container_memory
absl::core_headers
absl::hash_function_defaults
absl::hash_container_defaults
absl::node_slot_policy
absl::raw_hash_set
absl::algorithm_container
@ -629,6 +643,19 @@ absl_cc_library(
PUBLIC
)
absl_cc_library(
NAME
hash_container_defaults
HDRS
"${DIR}/hash_container_defaults.h"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
absl::hash_function_defaults
PUBLIC
)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
@ -655,9 +682,11 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
absl::container_common
absl::cord
absl::hash
absl::strings
absl::type_traits
PUBLIC
)
@ -703,6 +732,7 @@ absl_cc_library(
absl::base
absl::config
absl::exponential_biased
absl::no_destructor
absl::raw_logging_internal
absl::sample_recorder
absl::synchronization
@ -756,7 +786,9 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
absl::container_memory
absl::core_headers
absl::raw_hash_set
absl::throw_delegate
PUBLIC
@ -817,6 +849,7 @@ absl_cc_library(
DEPS
absl::config
absl::core_headers
absl::debugging_internal
absl::meta
absl::strings
absl::span
@ -931,6 +964,7 @@ absl_cc_library(
absl::crc32c
absl::config
absl::strings
absl::no_destructor
)
set(DIR ${ABSL_ROOT_DIR}/absl/debugging)
@ -954,6 +988,8 @@ absl_cc_library(
"${DIR}/stacktrace.cc"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
$<$<BOOL:${EXECINFO_LIBRARY}>:${EXECINFO_LIBRARY}>
DEPS
absl::debugging_internal
absl::config
@ -980,6 +1016,7 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
$<$<BOOL:${MINGW}>:-ldbghelp>
DEPS
absl::debugging_internal
absl::demangle_internal
@ -1058,8 +1095,10 @@ absl_cc_library(
demangle_internal
HDRS
"${DIR}/internal/demangle.h"
"${DIR}/internal/demangle_rust.h"
SRCS
"${DIR}/internal/demangle.cc"
"${DIR}/internal/demangle_rust.cc"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
@ -1252,6 +1291,7 @@ absl_cc_library(
absl::strings
absl::synchronization
absl::flat_hash_map
absl::no_destructor
)
# Internal-only target, do not depend on directly.
@ -1283,12 +1323,9 @@ absl_cc_library(
absl_cc_library(
NAME
flags
SRCS
"${DIR}/flag.cc"
HDRS
"${DIR}/declare.h"
"${DIR}/flag.h"
"${DIR}/internal/flag_msvc.inc"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
@ -1299,7 +1336,6 @@ absl_cc_library(
absl::flags_config
absl::flags_internal
absl::flags_reflection
absl::base
absl::core_headers
absl::strings
)
@ -1379,6 +1415,9 @@ absl_cc_library(
absl::synchronization
)
############################################################################
# Unit tests in alphabetical order.
set(DIR ${ABSL_ROOT_DIR}/absl/functional)
absl_cc_library(
@ -1431,6 +1470,18 @@ absl_cc_library(
PUBLIC
)
absl_cc_library(
NAME
overload
HDRS
"${DIR}/overload.h"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::meta
PUBLIC
)
set(DIR ${ABSL_ROOT_DIR}/absl/hash)
absl_cc_library(
@ -1640,6 +1691,7 @@ absl_cc_library(
absl::log_internal_conditions
absl::log_internal_message
absl::log_internal_strip
absl::absl_vlog_is_on
)
absl_cc_library(
@ -1721,6 +1773,7 @@ absl_cc_library(
absl::log_entry
absl::log_severity
absl::log_sink
absl::no_destructor
absl::raw_logging_internal
absl::synchronization
absl::span
@ -1771,6 +1824,7 @@ absl_cc_library(
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::core_headers
absl::log_internal_message
absl::log_internal_nullstream
absl::log_severity
@ -1876,6 +1930,11 @@ absl_cc_library(
PUBLIC
)
# Warning: Many linkers will strip the contents of this library because its
# symbols are only used in a global constructor. A workaround is for clients
# to link this using $<LINK_LIBRARY:WHOLE_ARCHIVE,absl::log_flags> instead of
# the plain absl::log_flags.
# TODO(b/320467376): Implement the equivalent of Bazel's alwayslink=True.
absl_cc_library(
NAME
log_flags
@ -1897,6 +1956,7 @@ absl_cc_library(
absl::flags
absl::flags_marshalling
absl::strings
absl::vlog_config_internal
PUBLIC
)
@ -1919,6 +1979,7 @@ absl_cc_library(
absl::log_severity
absl::raw_logging_internal
absl::strings
absl::vlog_config_internal
)
absl_cc_library(
@ -1952,6 +2013,7 @@ absl_cc_library(
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::log_internal_log_impl
absl::vlog_is_on
PUBLIC
)
@ -2064,21 +2126,75 @@ absl_cc_library(
)
absl_cc_library(
NAME
log_internal_fnmatch
SRCS
"${DIR}/internal/fnmatch.cc"
HDRS
"${DIR}/internal/fnmatch.h"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::config
absl::strings
NAME
vlog_config_internal
SRCS
"${DIR}/internal/vlog_config.cc"
HDRS
"${DIR}/internal/vlog_config.h"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::base
absl::config
absl::core_headers
absl::log_internal_fnmatch
absl::memory
absl::no_destructor
absl::strings
absl::synchronization
absl::optional
)
absl_cc_library(
NAME
absl_vlog_is_on
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
HDRS
"${DIR}/absl_vlog_is_on.h"
DEPS
absl::vlog_config_internal
absl::config
absl::core_headers
absl::strings
)
absl_cc_library(
NAME
vlog_is_on
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
HDRS
"${DIR}/vlog_is_on.h"
DEPS
absl::absl_vlog_is_on
)
absl_cc_library(
NAME
log_internal_fnmatch
SRCS
"${DIR}/internal/fnmatch.cc"
HDRS
"${DIR}/internal/fnmatch.h"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::config
absl::strings
)
# Test targets
set(DIR ${ABSL_ROOT_DIR}/absl/memory)
absl_cc_library(
@ -2147,6 +2263,7 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::compare
absl::config
absl::core_headers
absl::bits
@ -2176,6 +2293,8 @@ absl_cc_library(
PUBLIC
)
set(DIR ${ABSL_ROOT_DIR}/absl/profiling)
absl_cc_library(
NAME
sample_recorder
@ -2188,8 +2307,6 @@ absl_cc_library(
absl::synchronization
)
set(DIR ${ABSL_ROOT_DIR}/absl/profiling)
absl_cc_library(
NAME
exponential_biased
@ -2265,6 +2382,7 @@ absl_cc_library(
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::config
absl::fast_type_id
absl::optional
)
@ -2336,11 +2454,13 @@ absl_cc_library(
DEPS
absl::config
absl::inlined_vector
absl::nullability
absl::random_internal_pool_urbg
absl::random_internal_salted_seed_seq
absl::random_internal_seed_material
absl::random_seed_gen_exception
absl::span
absl::string_view
)
# Internal-only target, do not depend on directly.
@ -2399,6 +2519,7 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
$<$<BOOL:${MINGW}>:-lbcrypt>
DEPS
absl::core_headers
absl::optional
@ -2658,6 +2779,29 @@ absl_cc_library(
absl::config
)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
random_internal_distribution_test_util
SRCS
"${DIR}/internal/chi_square.cc"
"${DIR}/internal/distribution_test_util.cc"
HDRS
"${DIR}/internal/chi_square.h"
"${DIR}/internal/distribution_test_util.h"
COPTS
${ABSL_DEFAULT_COPTS}
LINKOPTS
${ABSL_DEFAULT_LINKOPTS}
DEPS
absl::config
absl::core_headers
absl::raw_logging_internal
absl::strings
absl::str_format
absl::span
)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
@ -2699,6 +2843,8 @@ absl_cc_library(
absl::function_ref
absl::inlined_vector
absl::memory
absl::no_destructor
absl::nullability
absl::optional
absl::raw_logging_internal
absl::span
@ -2724,8 +2870,11 @@ absl_cc_library(
absl::base
absl::config
absl::core_headers
absl::has_ostream_operator
absl::nullability
absl::raw_logging_internal
absl::status
absl::str_format
absl::strings
absl::type_traits
absl::utility
@ -2748,6 +2897,7 @@ absl_cc_library(
absl::base
absl::config
absl::core_headers
absl::nullability
absl::throw_delegate
PUBLIC
)
@ -2762,6 +2912,7 @@ absl_cc_library(
"${DIR}/has_absl_stringify.h"
"${DIR}/internal/damerau_levenshtein_distance.h"
"${DIR}/internal/string_constant.h"
"${DIR}/internal/has_absl_stringify.h"
"${DIR}/match.h"
"${DIR}/numbers.h"
"${DIR}/str_cat.h"
@ -2805,6 +2956,7 @@ absl_cc_library(
absl::endian
absl::int128
absl::memory
absl::nullability
absl::raw_logging_internal
absl::throw_delegate
absl::type_traits
@ -2824,6 +2976,18 @@ absl_cc_library(
PUBLIC
)
absl_cc_library(
NAME
has_ostream_operator
HDRS
"${DIR}/has_ostream_operator.h"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
PUBLIC
)
# Internal-only target, do not depend on directly.
absl_cc_library(
NAME
@ -2855,7 +3019,12 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
absl::core_headers
absl::nullability
absl::span
absl::str_format_internal
absl::string_view
PUBLIC
)
@ -2886,6 +3055,7 @@ absl_cc_library(
absl::strings
absl::config
absl::core_headers
absl::fixed_array
absl::inlined_vector
absl::numeric_representation
absl::type_traits
@ -2989,6 +3159,7 @@ absl_cc_library(
DEPS
absl::base
absl::config
absl::no_destructor
absl::raw_logging_internal
absl::synchronization
)
@ -3079,6 +3250,7 @@ absl_cc_library(
absl::endian
absl::function_ref
absl::inlined_vector
absl::nullability
absl::optional
absl::raw_logging_internal
absl::span
@ -3246,6 +3418,8 @@ absl_cc_library(
${ABSL_DEFAULT_COPTS}
DEPS
Threads::Threads
# TODO(#1495): Use $<LINK_LIBRARY:FRAMEWORK,CoreFoundation> once our
# minimum CMake version >= 3.24
$<$<PLATFORM_ID:Darwin>:-Wl,-framework,CoreFoundation>
)
@ -3286,8 +3460,8 @@ absl_cc_library(
NAME
bad_any_cast_impl
SRCS
"${DIR}/bad_any_cast.h"
"${DIR}/bad_any_cast.cc"
"${DIR}/bad_any_cast.h"
"${DIR}/bad_any_cast.cc"
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
@ -3307,6 +3481,7 @@ absl_cc_library(
DEPS
absl::algorithm
absl::core_headers
absl::nullability
absl::throw_delegate
absl::type_traits
PUBLIC
@ -3327,6 +3502,7 @@ absl_cc_library(
absl::config
absl::core_headers
absl::memory
absl::nullability
absl::type_traits
absl::utility
PUBLIC
@ -3389,6 +3565,7 @@ absl_cc_library(
COPTS
${ABSL_DEFAULT_COPTS}
DEPS
absl::config
absl::core_headers
absl::type_traits
PUBLIC

2
contrib/avro vendored

@ -1 +1 @@
Subproject commit d43acc84d3d455b016f847d6666fbc3cd27f16a9
Subproject commit 545e7002683cbc2198164d93088ac8e4955b4628

2
contrib/aws vendored

@ -1 +1 @@
Subproject commit deeaa9e7c5fe690e3dacc4005d7ecfa7a66a32bb
Subproject commit 1c2946bfcb7f1e3ae0a858de0b59d4f1a7b4ccaf

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

@ -125,7 +125,7 @@ configure_file("${AWS_SDK_CORE_DIR}/include/aws/core/SDKConfig.h.in"
"${CMAKE_CURRENT_BINARY_DIR}/include/aws/core/SDKConfig.h" @ONLY)
aws_get_version(AWS_CRT_CPP_VERSION_MAJOR AWS_CRT_CPP_VERSION_MINOR AWS_CRT_CPP_VERSION_PATCH FULL_VERSION GIT_HASH)
configure_file("${AWS_CRT_DIR}/include/aws/crt/Config.h.in" "${AWS_CRT_DIR}/include/aws/crt/Config.h" @ONLY)
configure_file("${AWS_CRT_DIR}/include/aws/crt/Config.h.in" "${CMAKE_CURRENT_BINARY_DIR}/include/aws/crt/Config.h" @ONLY)
list(APPEND AWS_SOURCES ${AWS_SDK_CORE_SRC} ${AWS_SDK_CORE_NET_SRC} ${AWS_SDK_CORE_PLATFORM_SRC})

2
contrib/azure vendored

@ -1 +1 @@
Subproject commit 6262a76ef4c4c330c84e58dd4f6f13f4e6230fcd
Subproject commit 67272b7ee0adff6b69921b26eb071ba1a353062c

2
contrib/cld2 vendored

@ -1 +1 @@
Subproject commit bc6d493a2f64ed1fc1c4c4b4294a542a04e04217
Subproject commit 217ba8b8805b41557faadaa47bb6e99f2242eea3

1
contrib/datasketches-cpp-cmake/CMakeLists.txt
View File

@ -9,6 +9,7 @@ set(DATASKETCHES_LIBRARY theta)
add_library(_datasketches INTERFACE)
target_include_directories(_datasketches SYSTEM BEFORE INTERFACE
"${ClickHouse_SOURCE_DIR}/contrib/datasketches-cpp/common/include"
"${ClickHouse_SOURCE_DIR}/contrib/datasketches-cpp/count/include"
"${ClickHouse_SOURCE_DIR}/contrib/datasketches-cpp/theta/include")
add_library(ch_contrib::datasketches ALIAS _datasketches)

2
contrib/fmtlib vendored

@ -1 +1 @@
Subproject commit b6f4ceaed0a0a24ccf575fab6c56dd50ccf6f1a9
Subproject commit a33701196adfad74917046096bf5a2aa0ab0bb50

1
contrib/fmtlib-cmake/CMakeLists.txt
View File

@ -13,7 +13,6 @@ set (SRCS
${FMT_SOURCE_DIR}/include/fmt/core.h
${FMT_SOURCE_DIR}/include/fmt/format.h
${FMT_SOURCE_DIR}/include/fmt/format-inl.h
${FMT_SOURCE_DIR}/include/fmt/locale.h
${FMT_SOURCE_DIR}/include/fmt/os.h
${FMT_SOURCE_DIR}/include/fmt/ostream.h
${FMT_SOURCE_DIR}/include/fmt/printf.h

51
contrib/google-protobuf-cmake/protobuf_generate.cmake
View File

@ -157,15 +157,13 @@ function(protobuf_generate)
set(_generated_srcs_all)
foreach(_proto ${protobuf_generate_PROTOS})
get_filename_component(_abs_file ${_proto} ABSOLUTE)
get_filename_component(_abs_dir ${_abs_file} DIRECTORY)
get_filename_component(_basename ${_proto} NAME_WE)
file(RELATIVE_PATH _rel_dir ${CMAKE_CURRENT_SOURCE_DIR} ${_abs_dir})
set(_possible_rel_dir)
if (NOT protobuf_generate_APPEND_PATH)
set(_possible_rel_dir ${_rel_dir}/)
endif()
# The protobuf compiler doesn't return paths to the files it generates so we have to calculate those paths here:
# _abs_file - absolute path to a .proto file,
# _possible_rel_dir - relative path to the .proto file from some import directory specified in Protobuf_IMPORT_DIRS,
# _basename - filename of the .proto file (without path and without extenstion).
get_proto_absolute_path(_abs_file "${_proto}" ${_protobuf_include_path})
get_proto_relative_path(_possible_rel_dir "${_abs_file}" ${_protobuf_include_path})
get_filename_component(_basename "${_abs_file}" NAME_WE)
set(_generated_srcs)
foreach(_ext ${protobuf_generate_GENERATE_EXTENSIONS})
@ -173,7 +171,7 @@ function(protobuf_generate)
endforeach()
if(protobuf_generate_DESCRIPTORS AND protobuf_generate_LANGUAGE STREQUAL cpp)
set(_descriptor_file "${CMAKE_CURRENT_BINARY_DIR}/${_basename}.desc")
set(_descriptor_file "${protobuf_generate_PROTOC_OUT_DIR}/${_possible_rel_dir}${_basename}.desc")
set(_dll_desc_out "--descriptor_set_out=${_descriptor_file}")
list(APPEND _generated_srcs ${_descriptor_file})
endif()
@ -196,3 +194,36 @@ function(protobuf_generate)
target_sources(${protobuf_generate_TARGET} PRIVATE ${_generated_srcs_all})
endif()
endfunction()
# Calculates the absolute path to a .proto file.
function(get_proto_absolute_path result proto)
cmake_path(IS_ABSOLUTE proto _is_abs_path)
if(_is_abs_path)
set(${result} "${proto}" PARENT_SCOPE)
return()
endif()
foreach(_include_dir ${ARGN})
if(EXISTS "${_include_dir}/${proto}")
set(${result} "${_include_dir}/${proto}" PARENT_SCOPE)
return()
endif()
endforeach()
message(SEND_ERROR "Not found protobuf ${proto} in Protobuf_IMPORT_DIRS: ${ARGN}")
endfunction()
# Calculates a relative path to a .proto file. The returned path is relative to one of include directories.
function(get_proto_relative_path result abs_path)
set(${result} "" PARENT_SCOPE)
get_filename_component(_abs_dir "${abs_path}" DIRECTORY)
foreach(_include_dir ${ARGN})
cmake_path(IS_PREFIX _include_dir "${_abs_dir}" _is_prefix)
if(_is_prefix)
file(RELATIVE_PATH _rel_dir "${_include_dir}" "${_abs_dir}")
if(NOT _rel_dir STREQUAL "")
set(${result} "${_rel_dir}/" PARENT_SCOPE)
endif()
return()
endif()
endforeach()
message(WARNING "Not found protobuf ${abs_path} in Protobuf_IMPORT_DIRS: ${ARGN}")
endfunction()

2
contrib/googletest vendored

@ -1 +1 @@
Subproject commit e47544ad31cb3ceecd04cc13e8fe556f8df9fe0b
Subproject commit a7f443b80b105f940225332ed3c31f2790092f47

2
contrib/grpc vendored

@ -1 +1 @@
Subproject commit 77b2737a709d43d8c6895e3f03ca62b00bd9201c
Subproject commit 1716359d2e28d304a250f9df0e6c0ccad03de8db

2
contrib/icu vendored

@ -1 +1 @@
Subproject commit a56dde820dc35665a66f2e9ee8ba58e75049b668
Subproject commit 7750081bda4b3bc1768ae03849ec70f67ea10625

8
contrib/icu-cmake/CMakeLists.txt
View File

@ -5,15 +5,13 @@ else ()
endif ()
if (NOT ENABLE_ICU)
message(STATUS "Not using icu")
message(STATUS "Not using ICU")
return()
endif()
set(ICU_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/icu/icu4c/source")
set(ICUDATA_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/icudata/")
set (CMAKE_CXX_STANDARD 17)
# These lists of sources were generated from build log of the original ICU build system (configure + make).
set(ICUUC_SOURCES
@ -462,9 +460,9 @@ file(GENERATE OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/empty.cpp" CONTENT " ")
enable_language(ASM)
if (ARCH_S390X)
set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt70b_dat.S" )
set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt75b_dat.S" )
else()
set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt70l_dat.S" )
set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt75l_dat.S" )
endif()
set(ICUDATA_SOURCES

2
contrib/icudata vendored

@ -1 +1 @@
Subproject commit c8e717892a557b4d2852317c7d628aacc0a0e5ab
Subproject commit 4904951339a70b4814d2d3723436b20d079cb01b

19
contrib/jemalloc-cmake/CMakeLists.txt
View File

@ -34,7 +34,7 @@ if (OS_LINUX)
# avoid spurious latencies and additional work associated with
# MADV_DONTNEED. See
# https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
else()
set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
endif()
@ -175,12 +175,19 @@ endif ()
target_compile_definitions(_jemalloc PRIVATE -DJEMALLOC_PROF=1)
# jemalloc provides support for two different libunwind flavors: the original HP libunwind and the one coming with gcc / g++ / libstdc++.
# The latter is identified by `JEMALLOC_PROF_LIBGCC` and uses `_Unwind_Backtrace` method instead of `unw_backtrace`.
# At the time ClickHouse uses LLVM libunwind which follows libgcc's way of backtracking.
# jemalloc provides support two unwind flavors:
# - JEMALLOC_PROF_LIBUNWIND - unw_backtrace() - gnu libunwind (compatible with llvm libunwind)
# - JEMALLOC_PROF_LIBGCC - _Unwind_Backtrace() - the original HP libunwind and the one coming with gcc / g++ / libstdc++.
#
# ClickHouse has to provide `unw_backtrace` method by the means of [commit 8e2b31e](https://github.com/ClickHouse/libunwind/commit/8e2b31e766dd502f6df74909e04a7dbdf5182eb1).
target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBGCC=1)
# But for JEMALLOC_PROF_LIBGCC it also calls _Unwind_Backtrace() during
# bootstraping of jemalloc, which may lead to deadlock, if the dlsym will do
# allocations somewhere (like glibc does prio 2.34, see [1]).
#
# [1]: https://sourceware.org/git/?p=glibc.git;a=commit;h=fada9018199c21c469ff0e731ef75c6020074ac9
#
# And since ClickHouse unwind already supports unw_backtrace() we can safely
# switch to it to avoid this deadlock.
target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBUNWIND=1)
target_link_libraries (_jemalloc PRIVATE unwind)
# for RTLD_NEXT

11
contrib/jemalloc-cmake/README
View File

@ -4,3 +4,14 @@ It allows to integrate JEMalloc into CMake project.
- Added JEMALLOC_CONFIG_MALLOC_CONF substitution
- Add musl support (USE_MUSL)
- Also note, that darwin build requires JEMALLOC_PREFIX, while others do not
- JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE should be disabled
CLOCK_MONOTONIC_COARSE can go backwards after clock_adjtime(ADJ_FREQUENCY)
Let's disable it for now, and this menas that CLOCK_MONOTONIC will be used,
and this, should not be a problem, since:
- jemalloc do not call clock_gettime() that frequently
- the difference is CLOCK_MONOTONIC 20ns and CLOCK_MONOTONIC_COARSE 4ns
This can be done with the following command:
gg JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE | cut -d: -f1 | xargs sed -i 's@#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE@/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */@'

2
contrib/jemalloc-cmake/include_freebsd_ppc64le/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -96,7 +96,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_ppc64le/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_riscv64/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_s390x/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -96,7 +96,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

2
contrib/jemalloc-cmake/include_linux_x86_64_musl/jemalloc/internal/jemalloc_internal_defs.h.in
View File

@ -99,7 +99,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

1
contrib/libpq-cmake/CMakeLists.txt
View File

@ -54,7 +54,6 @@ set(SRCS
"${LIBPQ_SOURCE_DIR}/port/pgstrcasecmp.c"
"${LIBPQ_SOURCE_DIR}/port/thread.c"
"${LIBPQ_SOURCE_DIR}/port/path.c"
"${LIBPQ_SOURCE_DIR}/port/explicit_bzero.c"
)
add_library(_libpq ${SRCS})

2
contrib/libprotobuf-mutator vendored

@ -1 +1 @@
Subproject commit a304ec48dcf15d942607032151f7e9ee504b5dcf
Subproject commit 1f95f8083066f5b38fd2db172e7e7f9aa7c49d2d

2
contrib/libunwind vendored

@ -1 +1 @@
Subproject commit d6a01c46327e56fd86beb8aaa31591fcd9a6b7df
Subproject commit a89d904befea07814628c6ce0b44083c4e149c62

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

@ -4,9 +4,6 @@ set(LIBUNWIND_CXX_SOURCES
"${LIBUNWIND_SOURCE_DIR}/src/libunwind.cpp"
"${LIBUNWIND_SOURCE_DIR}/src/Unwind-EHABI.cpp"
"${LIBUNWIND_SOURCE_DIR}/src/Unwind-seh.cpp")
if (APPLE)
set(LIBUNWIND_CXX_SOURCES ${LIBUNWIND_CXX_SOURCES} "${LIBUNWIND_SOURCE_DIR}/src/Unwind_AppleExtras.cpp")
endif ()
set(LIBUNWIND_C_SOURCES
"${LIBUNWIND_SOURCE_DIR}/src/UnwindLevel1.c"
@ -32,6 +29,7 @@ set_target_properties(unwind PROPERTIES FOLDER "contrib/libunwind-cmake")
target_include_directories(unwind SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBUNWIND_SOURCE_DIR}/include>)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_NO_HEAP=1)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_REMEMBER_STACK_ALLOC=1)
# NOTE: from this macros sizeof(unw_context_t)/sizeof(unw_cursor_t) is depends, so it should be set always
target_compile_definitions(unwind PUBLIC -D_LIBUNWIND_IS_NATIVE_ONLY)

2
contrib/llvm-project vendored

@ -1 +1 @@
Subproject commit d2142eed98046a47ff7112e3cc1e197c8a5cd80f
Subproject commit 2a8967b60cbe5bc2df253712bac343cc5263c5fc

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