Merge branch 'master' into break_compatibility

.clang-tidy

@@ -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',
@@ -36,6 +38,7 @@ 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.performance.Padding',
 
@@ -99,6 +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',

.git-blame-ignore-revs

@@ -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

.github/PULL_REQUEST_TEMPLATE.md

@@ -59,6 +59,9 @@ At a minimum, the following information should be added (but add more as needed)
 - [ ] <!---ci_exclude_tsan|msan|ubsan|coverage--> Exclude: All with TSAN, MSAN, UBSAN, Coverage
 - [ ] <!---ci_exclude_aarch64|release|debug--> Exclude: All with aarch64, release, debug
 ---
+- [ ] <!---ci_include_fuzzer--> Run only fuzzers related jobs (libFuzzer fuzzers, AST fuzzers, etc.)
+- [ ] <!---ci_exclude_ast--> Exclude: AST fuzzers
+---
 - [ ] <!---do_not_test--> Do not test
 - [ ] <!---woolen_wolfdog--> Woolen Wolfdog
 - [ ] <!---upload_all--> Upload binaries for special builds

.github/actionlint.yml

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

.github/actions/check_workflow/action.yml

@@ -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

.github/actions/clean/action.yml

@@ -1,11 +1,23 @@
 name: Clean runner
 description: Clean the runner's temp path on ending
+inputs:
+  images:
+    description: clean docker images
+    default: false
+    type: boolean
 runs:
   using: "composite"
   steps:
-    - name: Clean
+    - name: Clean Temp
       shell: bash
       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 "${{runner.temp}}"
+    - name: Clean Docker Containers
+      shell: bash
+      run: |
+          docker rm -vf $(docker ps -aq) ||:
+    - name: Clean Docker Images
+      if: ${{ inputs.images }}
+      shell: bash
+      run: |
+        docker rmi -f $(docker images -aq) ||:

.github/actions/debug/action.yml

@@ -0,0 +1,18 @@
+name: DebugInfo
+description: Prints workflow debug info
+
+runs:
+  using: "composite"
+  steps:
+    - name: Print envs
+      shell: bash
+      run: |
+          echo "::group::Envs"
+          env
+          echo "::endgroup::"
+    - name: Print Event.json
+      shell: bash
+      run: |
+          echo "::group::Event.json"
+          python3 -m json.tool "$GITHUB_EVENT_PATH"
+          echo "::endgroup::"

.github/workflows/auto_release.yml

@@ -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"

.github/workflows/auto_releases.yml

@@ -0,0 +1,99 @@
+name: AutoReleases
+
+env:
+  PYTHONUNBUFFERED: 1
+
+concurrency:
+  group: autoreleases
+
+on:
+  #  schedule:
+  #    - cron: '0 9 * * *'
+  workflow_dispatch:
+    inputs:
+      dry-run:
+        description: 'Dry run'
+        required: false
+        default: false
+        type: boolean
+
+jobs:
+  AutoReleaseInfo:
+    runs-on: [self-hosted, release-maker]
+    outputs:
+      data: ${{ steps.info.outputs.AUTO_RELEASE_PARAMS }}
+      dry_run: ${{ steps.info.outputs.DRY_RUN }}
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
+          ${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
+          RCSK
+          EOF
+          echo "DRY_RUN=true" >> "$GITHUB_ENV"
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          fetch-depth: 0  # full history needed
+      - name: Debug Info
+        uses: ./.github/actions/debug
+      - name: Prepare Info
+        id: info
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 auto_release.py --prepare
+          echo "::group::Auto Release Info"
+          python3 -m json.tool /tmp/autorelease_info.json
+          echo "::endgroup::"
+          {
+              echo 'AUTO_RELEASE_PARAMS<<EOF'
+              cat  /tmp/autorelease_params.json
+              echo 'EOF'
+          } >> "$GITHUB_OUTPUT"
+          if [[ "${{ github.event_name }}" == "schedule" ]]; then
+            echo "DRY_RUN=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "DRY_RUN=${{ github.event.inputs.dry-run }}" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Post Release Branch statuses
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 auto_release.py --post-status
+      - name: Clean up
+        uses: ./.github/actions/clean
+
+  Releases:
+    needs: AutoReleaseInfo
+    strategy:
+      matrix:
+        release_params: ${{ fromJson(needs.AutoReleaseInfo.outputs.data).releases }}
+      max-parallel: 1
+    name: Release ${{ matrix.release_params.release_branch }}
+    uses: ./.github/workflows/create_release.yml
+    with:
+      ref: ${{ matrix.release_params.commit_sha }}
+      type: patch
+      dry-run: ${{ fromJson(needs.AutoReleaseInfo.outputs.dry_run) }}
+    secrets:
+      ROBOT_CLICKHOUSE_COMMIT_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
+
+  CleanUp:
+    needs: [Releases]
+    runs-on: [self-hosted, release-maker]
+    steps:
+      - uses: ./.github/actions/clean
+        with:
+          images: true
+
+#  PostSlackMessage:
+#    needs: [Releases]
+#    runs-on: [self-hosted, release-maker]
+#    if: ${{ !cancelled() }}
+#    steps:
+#      - name: Check out repository code
+#        uses: ClickHouse/checkout@v1
+#      - name: Post
+#        run: |
+#          cd "$GITHUB_WORKSPACE/tests/ci"
+#          python3 auto_release.py --post-auto-release-complete --wf-status ${{ job.status }}

.github/workflows/backport_branches.yml

@@ -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:
@@ -245,8 +241,9 @@ jobs:
       runner_type: stress-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - Builds_Report
       - FunctionalStatelessTestAsan
       - FunctionalStatefulTestDebug
@@ -261,10 +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"
           # update mergeable check
-          python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+          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

.github/workflows/create_release.yml

@@ -6,8 +6,8 @@ concurrency:
 'on':
   workflow_dispatch:
     inputs:
-      sha:
+      ref:
-        description: 'The SHA hash of the commit from which to create the release'
+        description: 'Git reference (branch or commit sha) from which to create the release'
         required: true
         type: string
       type:
@@ -15,15 +15,212 @@ concurrency:
         required: true
         type: choice
         options:
-          - new
           - 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
+  workflow_call:
+    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: string
+      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
+    secrets:
+      ROBOT_CLICKHOUSE_COMMIT_TOKEN:
 
 jobs:
-  Release:
+  CreateRelease:
-    runs-on: [self-hosted, style-checker-aarch64]
+    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
-      - name: Print greeting
+        with:
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+          fetch-depth: 0
+      - name: Prepare Release Info
+        shell: bash
         run: |
-          python3 ./tests/ci/release.py --commit ${{ inputs.sha }} --type ${{ inputs.type }} --dry-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 \
+            --gh-user-or-token ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }} \
+            --jobs=5 \
+            --output="./docs/changelogs/${{ 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: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
+        shell: bash
+        run: |
+          git reset --hard HEAD
+          git checkout "$GITHUB_REF_NAME"
+          python3 ./tests/ci/create_release.py --set-progress-completed
+      - 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' || '' }}

.github/workflows/jepsen.yml

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

.github/workflows/master.yml

@@ -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:
@@ -97,21 +93,21 @@ 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 }}
-  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]
-    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 run even if Builds_1/2 fail - run them separately, not in Tests_1/2/3
@@ -125,37 +121,9 @@ jobs:
       runner_type: style-checker-aarch64
       data: ${{ needs.RunConfig.outputs.data }}
 
-  MarkReleaseReady:
-    if: ${{ !failure() && !cancelled() }}
-    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
-
   FinishCheck:
     if: ${{ !cancelled() }}
-    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code
@@ -164,3 +132,11 @@ jobs:
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
           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

.github/workflows/merge_queue.yml

@@ -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:
@@ -97,7 +93,7 @@ jobs:
       data: ${{ needs.RunConfig.outputs.data }}
 
   CheckReadyForMerge:
-    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
+    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]
@@ -105,6 +101,19 @@ jobs:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
       - 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 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+          python3 merge_pr.py --set-ci-status
+      - 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

.github/workflows/nightly.yml

@@ -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

.github/workflows/pull_request.yml

@@ -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:
@@ -127,27 +123,32 @@ jobs:
       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:
+  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_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 }}
-  Tests_3:
-    needs: [RunConfig, Builds_1, Tests_1]
-    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 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, 'Builds') }}
+    if: ${{ !cancelled()
-    needs: [RunConfig, StyleCheck, Builds_1, Builds_2]
+      && 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: Builds
@@ -155,9 +156,10 @@ jobs:
       data: ${{ needs.RunConfig.outputs.data }}
 
   CheckReadyForMerge:
-    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
+    if: ${{ !cancelled() }}
-    # Test_2 or Test_3 must not have jobs required for Mergeable check
+    # Test_2 or Test_3 do not have the jobs required for Mergeable check,
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1]
+    #  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
@@ -165,15 +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: ${{ !failure() }}
+    if: ${{ !failure() && !cancelled() }}
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    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

.github/workflows/release.yml

@@ -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"

.github/workflows/release_branches.yml

@@ -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:
@@ -134,6 +130,7 @@ jobs:
     with:
       build_name: package_debug
       data: ${{ needs.RunConfig.outputs.data }}
+      force: true
   BuilderBinDarwin:
     needs: [RunConfig, BuildDockers]
     if: ${{ !failure() && !cancelled() }}
@@ -445,8 +442,9 @@ jobs:
       runner_type: stress-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - DockerServerImage
       - DockerKeeperImage
       - Builds_Report
@@ -482,9 +480,15 @@ jobs:
         with:
           clear-repository: true
       - name: Finish label
+        if: ${{ !failure() }}
         run: |
-          cd "$GITHUB_WORKSPACE/tests/ci"
-          # update mergeable check
-          python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
           # update overall ci report
-          python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+          python3 ./tests/ci/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

.github/workflows/reusable_test.yml

@@ -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: |

.github/workflows/tags_stable.yml

@@ -1,74 +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 "${UID}")
-        # --network=host and CI=1 are required for the S3 access from a container
-        docker run -u "${UID}:${GID}" -e PYTHONUNBUFFERED=1 -e CI=1 --network=host \
-            --volume="${GITHUB_WORKSPACE}:/ClickHouse" clickhouse/style-test \
-                /ClickHouse/tests/ci/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)

.gitmodules

@@ -108,7 +108,7 @@
 	url = https://github.com/ClickHouse/icudata
 [submodule "contrib/icu"]
 	path = contrib/icu
-	url = https://github.com/unicode-org/icu
+	url = https://github.com/ClickHouse/icu
 [submodule "contrib/flatbuffers"]
 	path = contrib/flatbuffers
 	url = https://github.com/ClickHouse/flatbuffers
@@ -230,9 +230,6 @@
 [submodule "contrib/minizip-ng"]
 	path = contrib/minizip-ng
 	url = https://github.com/zlib-ng/minizip-ng
-[submodule "contrib/annoy"]
-	path = contrib/annoy
-	url = https://github.com/ClickHouse/annoy
 [submodule "contrib/qpl"]
 	path = contrib/qpl
 	url = https://github.com/intel/qpl
@@ -341,16 +338,13 @@
 	url = https://github.com/graphitemaster/incbin.git
 [submodule "contrib/usearch"]
 	path = contrib/usearch
-	url = https://github.com/unum-cloud/usearch.git
+	url = https://github.com/ClickHouse/usearch.git
 [submodule "contrib/SimSIMD"]
 	path = contrib/SimSIMD
 	url = https://github.com/ashvardanian/SimSIMD.git
 [submodule "contrib/FP16"]
 	path = contrib/FP16
 	url = https://github.com/Maratyszcza/FP16.git
-[submodule "contrib/robin-map"]
-	path = contrib/robin-map
-	url = https://github.com/Tessil/robin-map.git
 [submodule "contrib/aklomp-base64"]
 	path = contrib/aklomp-base64
 	url = https://github.com/aklomp/base64.git
@@ -372,3 +366,6 @@
 [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

.yamllint

@@ -5,12 +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: disable
+    colons: disable
+    indentation: disable
+    line-length: disable
+    trailing-spaces: disable
+    truthy: disable
+    new-line-at-end-of-file: disable

CHANGELOG.md

@@ -1,4 +1,6 @@
 ### Table of Contents
+**[ClickHouse release v24.8 LTS, 2024-08-20](#243)**<br/>
+**[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/>
@@ -9,6 +11,319 @@
 
 # 2024 Changelog
 
+### <a id="248"></a> ClickHouse release 24.8 LTS, 2024-08-20
+
+#### Backward Incompatible Change
+* `clickhouse-client` and `clickhouse-local` now default to multi-query mode (instead single-query mode). As an example, `clickhouse-client -q "SELECT 1; SELECT 2"` now works, whereas users previously had to add `--multiquery` (or `-n`). The `--multiquery/-n` switch became obsolete. INSERT queries in multi-query statements are treated specially based on their FORMAT clause: If the FORMAT is `VALUES` (the most common case), the end of the INSERT statement is represented by a trailing semicolon `;` at the end of the query. For all other FORMATs (e.g. `CSV` or `JSONEachRow`), the end of the INSERT statement is represented by two newlines `\n\n` at the end of the query. [#63898](https://github.com/ClickHouse/ClickHouse/pull/63898) ([FFish](https://github.com/wxybear)).
+* In previous versions, it was possible to use an alternative syntax for `LowCardinality` data types by appending `WithDictionary` to the name of the data type. It was an initial working implementation, and it was never documented or exposed to the public. Now, it is deprecated. If you have used this syntax, you have to ALTER your tables and rename the data types to `LowCardinality`. [#66842](https://github.com/ClickHouse/ClickHouse/pull/66842) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix logical errors with storage `Buffer` used with distributed destination table. It's a backward incompatible change: queries using `Buffer` with a distributed destination table may stop working if the table appears more than once in the query (e.g., in a self-join). [#67015](https://github.com/ClickHouse/ClickHouse/pull/67015) ([vdimir](https://github.com/vdimir)).
+* In previous versions, calling functions for random distributions based on the Gamma function (such as Chi-Squared, Student, Fisher) with negative arguments close to zero led to a long computation or an infinite loop. In the new version, calling these functions with zero or negative arguments will produce an exception. This closes [#67297](https://github.com/ClickHouse/ClickHouse/issues/67297). [#67326](https://github.com/ClickHouse/ClickHouse/pull/67326) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* The system table `text_log` is enabled by default. This is fully compatible with previous versions, but you may notice subtly increased disk usage on the local disk (this system table takes a tiny amount of disk space). [#67428](https://github.com/ClickHouse/ClickHouse/pull/67428) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* In previous versions, `arrayWithConstant` can be slow if asked to generate very large arrays. In the new version, it is limited to 1 GB per array. This closes [#32754](https://github.com/ClickHouse/ClickHouse/issues/32754). [#67741](https://github.com/ClickHouse/ClickHouse/pull/67741) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix REPLACE modifier formatting (forbid omitting brackets). [#67774](https://github.com/ClickHouse/ClickHouse/pull/67774) ([Azat Khuzhin](https://github.com/azat)).
+* Backported in [#68349](https://github.com/ClickHouse/ClickHouse/issues/68349): Reimplement `Dynamic` type. Now when the limit of dynamic data types is reached new types are not casted to String but stored in a special data structure in binary format with binary encoded data type. Now any type ever inserted into `Dynamic` column can be read from it as subcolumn. [#68132](https://github.com/ClickHouse/ClickHouse/pull/68132) ([Kruglov Pavel](https://github.com/Avogar)).
+
+#### New Feature
+* Added a new `MergeTree` setting `deduplicate_merge_projection_mode` to control the projections during merges (for specific engines) and `OPTIMIZE DEDUPLICATE` query. Supported options: `throw` (throw an exception in case the projection is not fully supported for *MergeTree engine), `drop` (remove projection during merge if it can't be merged itself consistently) and `rebuild` (rebuild projection from scratch, which is a heavy operation). [#66672](https://github.com/ClickHouse/ClickHouse/pull/66672) ([jsc0218](https://github.com/jsc0218)).
+* Add `_etag` virtual column for S3 table engine. Fixes [#65312](https://github.com/ClickHouse/ClickHouse/issues/65312). [#65386](https://github.com/ClickHouse/ClickHouse/pull/65386) ([skyoct](https://github.com/skyoct)).
+* Added a tagging (namespace) mechanism for the query cache. The same queries with different tags are considered different by the query cache. Example: `SELECT 1 SETTINGS use_query_cache = 1, query_cache_tag = 'abc'` and `SELECT 1 SETTINGS use_query_cache = 1, query_cache_tag = 'def'` now create different query cache entries. [#68235](https://github.com/ClickHouse/ClickHouse/pull/68235) ([sakulali](https://github.com/sakulali)).
+* Support more variants of JOIN strictness (`LEFT/RIGHT SEMI/ANTI/ANY JOIN`) with inequality conditions which involve columns from both left and right table. e.g. `t1.y < t2.y` (see the setting `allow_experimental_join_condition`). [#64281](https://github.com/ClickHouse/ClickHouse/pull/64281) ([lgbo](https://github.com/lgbo-ustc)).
+* Intrpret Hive-style partitioning for different engines (`File`, `URL`, `S3`, `AzureBlobStorage`, `HDFS`). Hive-style partitioning organizes data into partitioned sub-directories, making it efficient to query and manage large datasets. Currently, it only creates virtual columns with the appropriate name and data. The follow-up PR will introduce the appropriate data filtering (performance speedup). [#65997](https://github.com/ClickHouse/ClickHouse/pull/65997) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Add function `printf` for Spark compatiability (but you can use the existing `format` function). [#66257](https://github.com/ClickHouse/ClickHouse/pull/66257) ([李扬](https://github.com/taiyang-li)).
+* Add options `restore_replace_external_engines_to_null` and `restore_replace_external_table_functions_to_null` to replace external engines and table_engines to `Null` engine that can be useful for testing. It should work for RESTORE and explicit table creation. [#66536](https://github.com/ClickHouse/ClickHouse/pull/66536) ([Ilya Yatsishin](https://github.com/qoega)).
+* Added support for reading `MULTILINESTRING` geometry in `WKT` format using function `readWKTLineString`. [#67647](https://github.com/ClickHouse/ClickHouse/pull/67647) ([Jacob Reckhard](https://github.com/jacobrec)).
+* Add a new table function `fuzzQuery`. This function allows the modification of a given query string with random variations. Example: `SELECT query FROM fuzzQuery('SELECT 1') LIMIT 5;`. [#67655](https://github.com/ClickHouse/ClickHouse/pull/67655) ([pufit](https://github.com/pufit)).
+* Add a query `ALTER TABLE ... DROP DETACHED PARTITION ALL` to drop all detached partitions. [#67885](https://github.com/ClickHouse/ClickHouse/pull/67885) ([Duc Canh Le](https://github.com/canhld94)).
+* Add the `rows_before_aggregation_at_least` statistic to the query response when a new setting, `rows_before_aggregation` is enabled. This statistic represents the number of rows read before aggregation. In the context of a distributed query, when using the `group by` or `max` aggregation function without a `limit`, `rows_before_aggregation_at_least` can reflect the number of rows hit by the query. [#66084](https://github.com/ClickHouse/ClickHouse/pull/66084) ([morning-color](https://github.com/morning-color)).
+* Support `OPTIMIZE` query on `Join` tables to reduce their memory footprint. [#67883](https://github.com/ClickHouse/ClickHouse/pull/67883) ([Duc Canh Le](https://github.com/canhld94)).
+* Allow run query instantly in play if you add `&run=1` in the URL [#66457](https://github.com/ClickHouse/ClickHouse/pull/66457) ([Aleksandr Musorin](https://github.com/AVMusorin)).
+
+#### Experimental Feature
+* Implement a new `JSON` data type. [#66444](https://github.com/ClickHouse/ClickHouse/pull/66444) ([Kruglov Pavel](https://github.com/Avogar)).
+* Add the new `TimeSeries` table engine. [#64183](https://github.com/ClickHouse/ClickHouse/pull/64183) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Add new experimental `Kafka` storage engine to store offsets in Keeper instead of relying on committing them to Kafka. It makes the commit to ClickHouse tables atomic with regard to consumption from the queue. [#57625](https://github.com/ClickHouse/ClickHouse/pull/57625) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Use adaptive read task size calculation method (adaptive meaning it depends on read column sizes) for parallel replicas. [#60377](https://github.com/ClickHouse/ClickHouse/pull/60377) ([Nikita Taranov](https://github.com/nickitat)).
+* Added statistics type `count_min` (count-min sketches) which provide selectivity estimations for equality predicates like `col = 'val'`. Supported data types are string, date, datatime and numeric types. [#65521](https://github.com/ClickHouse/ClickHouse/pull/65521) ([JackyWoo](https://github.com/JackyWoo)).
+
+#### Performance Improvement
+* Setting `optimize_functions_to_subcolumns` is enabled by default. [#68053](https://github.com/ClickHouse/ClickHouse/pull/68053) ([Anton Popov](https://github.com/CurtizJ)).
+* Store the `plain_rewritable` disk directory metadata in `__meta` layout, separately from the merge tree data in the object storage. Move the `plain_rewritable` disk to a flat directory structure. [#65751](https://github.com/ClickHouse/ClickHouse/pull/65751) ([Julia Kartseva](https://github.com/jkartseva)).
+* Improve columns squashing (an operation happening in INSERT queries) for `String`/`Array`/`Map`/`Variant`/`Dynamic` types by reserving required memory in advance for all subcolumns. [#67043](https://github.com/ClickHouse/ClickHouse/pull/67043) ([Kruglov Pavel](https://github.com/Avogar)).
+* Speed up `SYSTEM FLUSH LOGS` and flush logs on shutdown. [#67472](https://github.com/ClickHouse/ClickHouse/pull/67472) ([Sema Checherinda](https://github.com/CheSema)).
+* Improved overall performance of merges by reducing the overhead of the scheduling steps of merges. [#68016](https://github.com/ClickHouse/ClickHouse/pull/68016) ([Anton Popov](https://github.com/CurtizJ)).
+* Speed up tables removal for `DROP DATABASE` query, increased the default value for `database_catalog_drop_table_concurrency` to 16. [#67228](https://github.com/ClickHouse/ClickHouse/pull/67228) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Avoid allocating too much capacity for array column while writing ORC. Performance speeds up 15% for an Array column. [#67879](https://github.com/ClickHouse/ClickHouse/pull/67879) ([李扬](https://github.com/taiyang-li)).
+* Speed up mutations for non-replicated MergeTree significantly [#66911](https://github.com/ClickHouse/ClickHouse/pull/66911) [#66909](https://github.com/ClickHouse/ClickHouse/pull/66909) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### Improvement
+* Setting `allow_experimental_analyzer` is renamed to `enable_analyzer`. The old name is preserved in a form of an alias. This signifies that Analyzer is no longer in beta and is fully promoted to production. [#66438](https://github.com/ClickHouse/ClickHouse/pull/66438) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Improve schema inference of date times. Now DateTime64 used only when date time has fractional part, otherwise regular DateTime is used. Inference of Date/DateTime is more strict now, especially when `date_time_input_format='best_effort'` to avoid inferring date times from strings in corner cases. [#68382](https://github.com/ClickHouse/ClickHouse/pull/68382) ([Kruglov Pavel](https://github.com/Avogar)).
+* ClickHouse server now supports new setting `max_keep_alive_requests`. For keep-alive HTTP connections to the server it works in tandem with `keep_alive_timeout` - if idle timeout not expired but there already more than `max_keep_alive_requests` requests done through the given connection - it will be closed by the server. [#61793](https://github.com/ClickHouse/ClickHouse/pull/61793) ([Nikita Taranov](https://github.com/nickitat)).
+* Various improvements in the advanced dashboard. This closes [#67697](https://github.com/ClickHouse/ClickHouse/issues/67697). This closes [#63407](https://github.com/ClickHouse/ClickHouse/issues/63407). This closes [#51129](https://github.com/ClickHouse/ClickHouse/issues/51129). This closes [#61204](https://github.com/ClickHouse/ClickHouse/issues/61204). [#67701](https://github.com/ClickHouse/ClickHouse/pull/67701) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Do not require a grant for REMOTE when creating a Distributed table: a grant for the Distributed engine is enough. [#65419](https://github.com/ClickHouse/ClickHouse/pull/65419) ([jsc0218](https://github.com/jsc0218)).
+* Do not pass logs for keeper explicitly in the Docker image to allow overriding. [#65564](https://github.com/ClickHouse/ClickHouse/pull/65564) ([Azat Khuzhin](https://github.com/azat)).
+* Introduced `use_same_password_for_base_backup` settings for `BACKUP` and `RESTORE` queries, allowing to create and restore incremental backups to/from password protected archives. [#66214](https://github.com/ClickHouse/ClickHouse/pull/66214) ([Samuele](https://github.com/sguerrini97)).
+* Ignore `async_load_databases` for `ATTACH` query (previously it was possible for ATTACH to return before the tables had been attached). [#66240](https://github.com/ClickHouse/ClickHouse/pull/66240) ([Azat Khuzhin](https://github.com/azat)).
+* Added logs and metrics for rejected connections (where there are not enough resources). [#66410](https://github.com/ClickHouse/ClickHouse/pull/66410) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Support proper `UUID` type for MongoDB engine. [#66671](https://github.com/ClickHouse/ClickHouse/pull/66671) ([Azat Khuzhin](https://github.com/azat)).
+* Add replication lag and recovery time metrics. [#66703](https://github.com/ClickHouse/ClickHouse/pull/66703) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Add `DiskS3NoSuchKeyErrors` metric. [#66704](https://github.com/ClickHouse/ClickHouse/pull/66704) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Ensure the `COMMENT` clause works for all table engines. [#66832](https://github.com/ClickHouse/ClickHouse/pull/66832) ([Joe Lynch](https://github.com/joelynch)).
+* Function `mapFromArrays` now accepts `Map(K, V)` as first argument, for example: `SELECT mapFromArrays(map('a', 4, 'b', 4), ['aa', 'bb'])` now works and returns `{('a',4):'aa',('b',4):'bb'}`. Also, if the 1st argument is an Array, it can now also be of type `Array(Nullable(T))` or `Array(LowCardinality(Nullable(T)))` as long as the actual array values are not `NULL`. [#67103](https://github.com/ClickHouse/ClickHouse/pull/67103) ([李扬](https://github.com/taiyang-li)).
+* Read configuration for `clickhouse-local` from `~/.clickhouse-local`. [#67135](https://github.com/ClickHouse/ClickHouse/pull/67135) ([Azat Khuzhin](https://github.com/azat)).
+* Rename setting `input_format_orc_read_use_writer_time_zone` to `input_format_orc_reader_timezone` and allow the user to set the reader timezone. [#67175](https://github.com/ClickHouse/ClickHouse/pull/67175) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Decrease level of the `Socket is not connected` error when HTTP connection immediately reset by peer after connecting, close [#34218](https://github.com/ClickHouse/ClickHouse/issues/34218). [#67177](https://github.com/ClickHouse/ClickHouse/pull/67177) ([vdimir](https://github.com/vdimir)).
+* Add ability to load dashboards for `system.dashboards` from config (once set, they overrides the default dashboards preset). [#67232](https://github.com/ClickHouse/ClickHouse/pull/67232) ([Azat Khuzhin](https://github.com/azat)).
+* The window functions in SQL are traditionally in snake case. ClickHouse uses `camelCase`, so new aliases `denseRank()` and `percentRank()` have been created. These new functions can be called the exact same as the original `dense_rank()` and `percent_rank()` functions. Both snake case and camelCase syntaxes remain usable. A new test for each of the functions has been added as well. This closes [#67042](https://github.com/ClickHouse/ClickHouse/issues/67042) . [#67334](https://github.com/ClickHouse/ClickHouse/pull/67334) ([Peter Nguyen](https://github.com/petern48)).
+* Autodetect configuration file format if is not `.xml`, `.yml` or `.yaml`. If the file begins with &lt; it might be XML, otherwise it might be YAML. It is useful when providing a configuration file from a pipe: `clickhouse-server --config-file <(echo "hello: world")`. [#67391](https://github.com/ClickHouse/ClickHouse/pull/67391) ([sakulali](https://github.com/sakulali)).
+* Functions `formatDateTime` and `formatDateTimeInJodaSyntax` now treat their format parameter as optional. If it is not specified, format strings `%Y-%m-%d %H:%i:%s` and `yyyy-MM-dd HH:mm:ss` are assumed. Example: `SELECT parseDateTime('2021-01-04 23:12:34')` now returns DateTime value `2021-01-04 23:12:34` (previously, this threw an exception). [#67399](https://github.com/ClickHouse/ClickHouse/pull/67399) ([Robert Schulze](https://github.com/rschu1ze)).
+* Automatically retry Keeper requests in KeeperMap if they happen because of timeout or connection loss. [#67448](https://github.com/ClickHouse/ClickHouse/pull/67448) ([Antonio Andelic](https://github.com/antonio2368)).
+* Add `-no-pie` to Aarch64 Linux builds to allow proper introspection and symbolizing of stacktraces after a ClickHouse restart. [#67916](https://github.com/ClickHouse/ClickHouse/pull/67916) ([filimonov](https://github.com/filimonov)).
+* Added profile events for merges and mutations for better introspection. [#68015](https://github.com/ClickHouse/ClickHouse/pull/68015) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix settings and `current_database` in `system.processes` for async BACKUP/RESTORE. [#68163](https://github.com/ClickHouse/ClickHouse/pull/68163) ([Azat Khuzhin](https://github.com/azat)).
+* Remove unnecessary logs for non-replicated `MergeTree`. [#68238](https://github.com/ClickHouse/ClickHouse/pull/68238) ([Daniil Ivanik](https://github.com/divanik)).
+
+#### Build/Testing/Packaging Improvement
+* Integration tests flaky check will not run each test case multiple times to find more issues in tests and make them more reliable. It is using `pytest-repeat` library to run test case multiple times for the same environment. It is important to cleanup tables and other entities in the end of a test case to pass. Repeating works much faster than several pytest runs as it starts necessary containers only once. [#66986](https://github.com/ClickHouse/ClickHouse/pull/66986) ([Ilya Yatsishin](https://github.com/qoega)).
+* Unblock the usage of CLion with ClickHouse. In previous versions, CLion freezed for a minute on every keypress. This closes [#66994](https://github.com/ClickHouse/ClickHouse/issues/66994). [#66995](https://github.com/ClickHouse/ClickHouse/pull/66995) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* getauxval: avoid a crash under a sanitizer re-exec due to high ASLR entropy in newer Linux kernels. [#67081](https://github.com/ClickHouse/ClickHouse/pull/67081) ([Raúl Marín](https://github.com/Algunenano)).
+* Some parts of client code are extracted to a single file and highest possible level optimization is applied to them even for debug builds. This closes: [#65745](https://github.com/ClickHouse/ClickHouse/issues/65745). [#67215](https://github.com/ClickHouse/ClickHouse/pull/67215) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+
+#### Bug Fix
+* Only relevant to the experimental Variant data type. Fix crash with Variant + AggregateFunction type. [#67122](https://github.com/ClickHouse/ClickHouse/pull/67122) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix crash in DistributedAsyncInsert when connection is empty. [#67219](https://github.com/ClickHouse/ClickHouse/pull/67219) ([Pablo Marcos](https://github.com/pamarcos)).
+* Fix crash of `uniq` and `uniqTheta ` with `tuple()` argument. Closes [#67303](https://github.com/ClickHouse/ClickHouse/issues/67303). [#67306](https://github.com/ClickHouse/ClickHouse/pull/67306) ([flynn](https://github.com/ucasfl)).
+* Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
+* Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
+* Fixed `Not-ready Set` in some system tables when filtering using subqueries. [#66018](https://github.com/ClickHouse/ClickHouse/pull/66018) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fixed reading of subcolumns after `ALTER ADD COLUMN` query. [#66243](https://github.com/ClickHouse/ClickHouse/pull/66243) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
+* Fix formatting of query with aliased JOIN ON expression, e.g. `... JOIN t2 ON (x = y) AS e ORDER BY x` should be formatted as `... JOIN t2 ON ((x = y) AS e) ORDER BY x`. [#66312](https://github.com/ClickHouse/ClickHouse/pull/66312) ([vdimir](https://github.com/vdimir)).
+* Fix cluster() for inter-server secret (preserve initial user as before). [#66364](https://github.com/ClickHouse/ClickHouse/pull/66364) ([Azat Khuzhin](https://github.com/azat)).
+* Fix possible runtime error while converting Array field with nulls to Array(Variant). [#66727](https://github.com/ClickHouse/ClickHouse/pull/66727) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix for occasional deadlock in Context::getDDLWorker. [#66843](https://github.com/ClickHouse/ClickHouse/pull/66843) ([Alexander Gololobov](https://github.com/davenger)).
+* Fix creating KeeperMap table after an incomplete drop. [#66865](https://github.com/ClickHouse/ClickHouse/pull/66865) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix broken part error while restoring to a `s3_plain_rewritable` disk. [#66881](https://github.com/ClickHouse/ClickHouse/pull/66881) ([Vitaly Baranov](https://github.com/vitlibar)).
+* In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
+* Fix invalid format detection in schema inference that could lead to logical error Format {} doesn't support schema inference. [#66899](https://github.com/ClickHouse/ClickHouse/pull/66899) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix possible deadlock on query cancel with parallel replicas. [#66905](https://github.com/ClickHouse/ClickHouse/pull/66905) ([Nikita Taranov](https://github.com/nickitat)).
+* Forbid create as select even when database_replicated_allow_heavy_create is set. It was unconditionally forbidden in 23.12 and accidentally allowed under the setting in unreleased 24.7. [#66980](https://github.com/ClickHouse/ClickHouse/pull/66980) ([vdimir](https://github.com/vdimir)).
+* Reading from the `numbers` could wrongly throw an exception when the `max_rows_to_read` limit was set. This closes [#66992](https://github.com/ClickHouse/ClickHouse/issues/66992). [#66996](https://github.com/ClickHouse/ClickHouse/pull/66996) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add proper type conversion to lagInFrame and leadInFrame window functions - fixes msan test. [#67091](https://github.com/ClickHouse/ClickHouse/pull/67091) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* TRUNCATE DATABASE used to stop replication as if it was a DROP DATABASE query, it's fixed. [#67129](https://github.com/ClickHouse/ClickHouse/pull/67129) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Use a separate client context in `clickhouse-local`. [#67133](https://github.com/ClickHouse/ClickHouse/pull/67133) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix error `Cannot convert column because it is non constant in source stream but must be constant in result.` for a query that reads from the `Merge` table over the `Distriburted` table with one shard. [#67146](https://github.com/ClickHouse/ClickHouse/pull/67146) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Correct behavior of `ORDER BY all` with disabled `enable_order_by_all` and parallel replicas (distributed queries as well). [#67153](https://github.com/ClickHouse/ClickHouse/pull/67153) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix wrong usage of input_format_max_bytes_to_read_for_schema_inference in schema cache. [#67157](https://github.com/ClickHouse/ClickHouse/pull/67157) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix the memory leak for count distinct, when exception issued during group by single nullable key. [#67171](https://github.com/ClickHouse/ClickHouse/pull/67171) ([Jet He](https://github.com/compasses)).
+* Fix an error in optimization which converts OUTER JOIN to INNER JOIN. This closes [#67156](https://github.com/ClickHouse/ClickHouse/issues/67156). This closes [#66447](https://github.com/ClickHouse/ClickHouse/issues/66447). The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/62907. [#67178](https://github.com/ClickHouse/ClickHouse/pull/67178) ([Maksim Kita](https://github.com/kitaisreal)).
+* Fix error `Conversion from AggregateFunction(name, Type) to AggregateFunction(name, Nullable(Type)) is not supported`. The bug was caused by the `optimize_rewrite_aggregate_function_with_if` optimization. Fixes [#67112](https://github.com/ClickHouse/ClickHouse/issues/67112). [#67229](https://github.com/ClickHouse/ClickHouse/pull/67229) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix hung query when using empty tuple as lhs of function IN. [#67295](https://github.com/ClickHouse/ClickHouse/pull/67295) ([Duc Canh Le](https://github.com/canhld94)).
+* It was possible to create a very deep nested JSON data that triggered stack overflow while skipping unknown fields. This closes [#67292](https://github.com/ClickHouse/ClickHouse/issues/67292). [#67324](https://github.com/ClickHouse/ClickHouse/pull/67324) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix attaching ReplicatedMergeTree table after exception during startup. [#67360](https://github.com/ClickHouse/ClickHouse/pull/67360) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix segfault caused by incorrectly detaching from thread group in `Aggregator`. [#67385](https://github.com/ClickHouse/ClickHouse/pull/67385) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix one more case when a non-deterministic function is specified in PK. [#67395](https://github.com/ClickHouse/ClickHouse/pull/67395) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fixed `bloom_filter` index breaking queries with mildly weird conditions like `(k=2)=(k=2)` or `has([1,2,3], k)`. [#67423](https://github.com/ClickHouse/ClickHouse/pull/67423) ([Michael Kolupaev](https://github.com/al13n321)).
+* Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix wait for tasks in ~WriteBufferFromS3 in case WriteBuffer was cancelled. [#67459](https://github.com/ClickHouse/ClickHouse/pull/67459) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Protect temporary part directories from removing during RESTORE. [#67491](https://github.com/ClickHouse/ClickHouse/pull/67491) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix execution of nested short-circuit functions. [#67520](https://github.com/ClickHouse/ClickHouse/pull/67520) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix `Logical error: Expected the argument №N of type T to have X rows, but it has 0`. The error could happen in a remote query with constant expression in `GROUP BY` (with a new analyzer). [#67536](https://github.com/ClickHouse/ClickHouse/pull/67536) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix join on tuple with NULLs: Some queries with the new analyzer and `NULL` inside the tuple in the `JOIN ON` section returned incorrect results. [#67538](https://github.com/ClickHouse/ClickHouse/pull/67538) ([vdimir](https://github.com/vdimir)).
+* Fix redundant reschedule of FileCache::freeSpaceRatioKeepingThreadFunc() in case of full non-evictable cache. [#67540](https://github.com/ClickHouse/ClickHouse/pull/67540) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix for function `toStartOfWeek` which returned the wrong result with a small `DateTime64` value. [#67558](https://github.com/ClickHouse/ClickHouse/pull/67558) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix creation of view with recursive CTE. [#67587](https://github.com/ClickHouse/ClickHouse/pull/67587) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Fix `Logical error: 'file_offset_of_buffer_end <= read_until_position'` in filesystem cache. Closes [#57508](https://github.com/ClickHouse/ClickHouse/issues/57508). [#67623](https://github.com/ClickHouse/ClickHouse/pull/67623) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fixes [#62282](https://github.com/ClickHouse/ClickHouse/issues/62282). Removed the call to `convertFieldToString()` and added datatype specific serialization code. Parameterized view substitution was broken for multiple datatypes when parameter value was a function or expression returning datatype instance. [#67654](https://github.com/ClickHouse/ClickHouse/pull/67654) ([Shankar](https://github.com/shiyer7474)).
+* Fix crash on `percent_rank`. `percent_rank`'s default frame type is changed to `range unbounded preceding and unbounded following`. `IWindowFunction`'s default window frame is considered and now window functions without window frame definition in sql can be put into different `WindowTransfomer`s properly. [#67661](https://github.com/ClickHouse/ClickHouse/pull/67661) ([lgbo](https://github.com/lgbo-ustc)).
+* Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix possible logical error "Unexpected return type from if" with experimental Variant type and enabled setting `use_variant_as_common_type ` in function if with Tuples and Maps. [#67687](https://github.com/ClickHouse/ClickHouse/pull/67687) ([Kruglov Pavel](https://github.com/Avogar)).
+* Due to a bug in Linux Kernel, a query can hung in `TimerDescriptor::drain`. This closes [#37686](https://github.com/ClickHouse/ClickHouse/issues/37686). [#67702](https://github.com/ClickHouse/ClickHouse/pull/67702) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix completion of `RESTORE ON CLUSTER` command. [#67720](https://github.com/ClickHouse/ClickHouse/pull/67720) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix dictionary hang in case of CANNOT_SCHEDULE_TASK while loading. [#67751](https://github.com/ClickHouse/ClickHouse/pull/67751) ([Azat Khuzhin](https://github.com/azat)).
+* Queries like `SELECT count() FROM t WHERE cast(c = 1 or c = 9999 AS Bool) SETTINGS use_skip_indexes=1` with bloom filter indexes on `c` now work correctly. [#67781](https://github.com/ClickHouse/ClickHouse/pull/67781) ([jsc0218](https://github.com/jsc0218)).
+* Fix wrong aggregation result in some queries with aggregation without keys and filter, close [#67419](https://github.com/ClickHouse/ClickHouse/issues/67419). [#67804](https://github.com/ClickHouse/ClickHouse/pull/67804) ([vdimir](https://github.com/vdimir)).
+* Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix DateTime64 parsing after constant folding in distributed queries, close [#66773](https://github.com/ClickHouse/ClickHouse/issues/66773). [#67920](https://github.com/ClickHouse/ClickHouse/pull/67920) ([vdimir](https://github.com/vdimir)).
+* Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
+* Now ClickHouse doesn't consider part as broken if projection doesn't exist on disk but exists in `checksums.txt`. [#68003](https://github.com/ClickHouse/ClickHouse/pull/68003) ([alesapin](https://github.com/alesapin)).
+* Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
+* Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
+* Attempt to fix `Block structure mismatch in AggregatingStep stream: different types` for aggregate projection optimization. [#68107](https://github.com/ClickHouse/ClickHouse/pull/68107) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix missing sync replica mode in query `SYSTEM SYNC REPLICA`. [#68326](https://github.com/ClickHouse/ClickHouse/pull/68326) ([Duc Canh Le](https://github.com/canhld94)).
+
+
+### <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

CMakeLists.txt

@@ -187,14 +187,6 @@ else ()
     set(NO_WHOLE_ARCHIVE --no-whole-archive)
 endif ()
 
-if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
-    # Can be lld or ld-lld or lld-13 or /path/to/lld.
-    if (LINKER_NAME MATCHES "lld")
-        set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
-        message (STATUS "Adding .gdb-index via --gdb-index linker option.")
-    endif ()
-endif()
-
 if (NOT (SANITIZE_COVERAGE OR WITH_COVERAGE)
     AND (CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE"
         OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO"
@@ -330,17 +322,21 @@ if (DISABLE_OMIT_FRAME_POINTER)
     set (CMAKE_ASM_FLAGS_ADD "${CMAKE_ASM_FLAGS_ADD} -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer")
 endif()
 
+# Before you start hating your debugger because it refuses to show variables ('<optimized out>'), try building with -DDEBUG_O_LEVEL="0"
+# https://stackoverflow.com/questions/63386189/whats-the-difference-between-a-compilers-o0-option-and-og-option/63386263#63386263
+set(DEBUG_O_LEVEL "g" CACHE STRING "The -Ox level used for debug builds")
+
 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} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
+set (CMAKE_CXX_FLAGS_DEBUG               "${CMAKE_CXX_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${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} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
+set (CMAKE_C_FLAGS_DEBUG                 "${CMAKE_C_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${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} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
+set (CMAKE_ASM_FLAGS_DEBUG               "${CMAKE_ASM_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
 
 if (OS_DARWIN)
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
@@ -402,7 +398,7 @@ if ((NOT OS_LINUX AND NOT OS_ANDROID) OR (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
     set(ENABLE_GWP_ASAN OFF)
 endif ()
 
-option (ENABLE_FIU "Enable Fiu" ON)
+option (ENABLE_LIBFIU "Enable libfiu" ON)
 
 option(WERROR "Enable -Werror compiler option" ON)
 
@@ -428,12 +424,17 @@ if (NOT SANITIZE)
     set (CMAKE_POSITION_INDEPENDENT_CODE OFF)
 endif()
 
-if (OS_LINUX AND NOT (ARCH_AARCH64 OR ARCH_S390X) AND NOT SANITIZE)
+if (NOT OS_ANDROID AND OS_LINUX AND NOT ARCH_S390X AND NOT SANITIZE)
-    # Slightly more efficient code can be generated
+    # Using '-no-pie' builds executables with fixed addresses, resulting in slightly more efficient code
-    # It's disabled for ARM because otherwise ClickHouse cannot run on Android.
+    # and keeping binary addresses constant even with ASLR enabled.
+    # Disabled on Android as it requires PIE: https://source.android.com/docs/security/enhancements#android-5
+    # Disabled on IBM S390X due to build issues with 'no-pie'
+    # Disabled with sanitizers to avoid issues with maximum relocation size: https://github.com/ClickHouse/ClickHouse/pull/49145
     set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-pie")
     set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -fno-pie")
     set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -no-pie -Wl,-no-pie")
+else ()
+    message (WARNING "ClickHouse is built as PIE, system.trace_log will contain invalid addresses after server restart.")
 endif ()
 
 if (ENABLE_TESTS)
@@ -604,7 +605,9 @@ if (NATIVE_BUILD_TARGETS
 
     execute_process(
         COMMAND ${CMAKE_COMMAND} -E make_directory "${NATIVE_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     execute_process(
         COMMAND ${CMAKE_COMMAND}
@@ -616,9 +619,13 @@ if (NATIVE_BUILD_TARGETS
             "-DENABLE_CLICKHOUSE_SELF_EXTRACTING=${ENABLE_CLICKHOUSE_SELF_EXTRACTING}"
         ${PROJECT_SOURCE_DIR}
         WORKING_DIRECTORY "${NATIVE_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     execute_process(
         COMMAND ${CMAKE_COMMAND} --build "${NATIVE_BUILD_DIR}" --target ${NATIVE_BUILD_TARGETS}
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 endif ()

PreLoad.cmake

@@ -51,8 +51,14 @@ if (NOT "$ENV{CFLAGS}" STREQUAL ""
 endif()
 
 # Default toolchain - this is needed to avoid dependency on OS files.
-execute_process(COMMAND uname -s OUTPUT_VARIABLE OS)
+execute_process(COMMAND uname -s
-execute_process(COMMAND uname -m OUTPUT_VARIABLE ARCH)
+    OUTPUT_VARIABLE OS
+    COMMAND_ERROR_IS_FATAL ANY
+)
+execute_process(COMMAND uname -m
+    OUTPUT_VARIABLE ARCH
+    COMMAND_ERROR_IS_FATAL ANY
+)
 
 # By default, prefer clang on Linux
 # But note, that you still may change the compiler with -DCMAKE_C_COMPILER/-DCMAKE_CXX_COMPILER.

README.md

@@ -34,21 +34,41 @@ 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.
 
-* [v24.7 Community Call](https://clickhouse.com/company/events/v24-7-community-release-call) - Jul 30
+* [v24.9 Community Call](https://clickhouse.com/company/events/v24-9-community-release-call) - September 26
 
 ## 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 Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/300783448/) - Jul 9
+The following upcoming meetups are featuring creator of ClickHouse & CTO, Alexey Milovidov:
-* [ClickHouse Cloud - Live Update Call](https://clickhouse.com/company/events/202407-cloud-update-live) - Jul 9
+
-* [ClickHouse Meetup @ Ramp - New York City](https://www.meetup.com/clickhouse-new-york-user-group/events/300595845/) - Jul 9
+* [ClickHouse Guangzhou User Group Meetup](https://mp.weixin.qq.com/s/GSvo-7xUoVzCsuUvlLTpCw) - August 25
-* [AWS Summit in New York](https://clickhouse.com/company/events/2024-07-awssummit-nyc) - Jul 10
+* [San Francisco Meetup (Cloudflare)](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/302540575) - September 5
-* [ClickHouse Meetup @ Klaviyo - Boston](https://www.meetup.com/clickhouse-boston-user-group/events/300907870) - Jul 11
+* [Raleigh Meetup (Deutsche Bank)](https://www.meetup.com/triangletechtalks/events/302723486/) - September 9
+* [New York Meetup (Rokt)](https://www.meetup.com/clickhouse-new-york-user-group/events/302575342) - September 10
+* [Chicago Meetup (Jump Capital)](https://lu.ma/43tvmrfw) - September 12
+
+Other upcoming meetups
+* [Seattle Meetup (Statsig)](https://www.meetup.com/clickhouse-seattle-user-group/events/302518075/) - August 27
+* [Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302732666/) - August 27
+* [Sydney Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302862966/) - September 5
+* [Zurich Meetup](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/302267429/) - September 5
+* [Toronto Meetup (Shopify)](https://www.meetup.com/clickhouse-toronto-user-group/events/301490855/) - September 10
+* [Austin Meetup](https://www.meetup.com/clickhouse-austin-user-group/events/302558689/) - September 17
+* [London Meetup](https://www.meetup.com/clickhouse-london-user-group/events/302977267) - September 17
+* [Tel Aviv Meetup](https://www.meetup.com/clickhouse-meetup-israel/events/303095121) - September 22
+* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22
+* [Barcelona Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096876/) - October 29
+* [Oslo Meetup](https://www.meetup.com/open-source-real-time-data-warehouse-real-time-analytics/events/302938622) - October 31
+* [Ghent Meetup](https://www.meetup.com/clickhouse-belgium-user-group/events/303049405/) - November 19
+* [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - November 21
+* [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/303096434) - November 26
+
+
 
 ## 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"
-* **Recording available**: [**v24.4 Release Call**](https://www.youtube.com/watch?v=dtUqgcfOGmE) All the features of 24.4, one convenient video! Watch it now!
+* **Recording available**: [**v24.8 LTS Release Call**](https://www.youtube.com/watch?v=AeLmp2jc51k) All the features of 24.8 LTS, one convenient video! Watch it now!
   
  ## Interested in joining ClickHouse and making it your full-time job? 
   

SECURITY.md

@@ -14,24 +14,15 @@ The following versions of ClickHouse server are currently supported with securit
 
 | Version | Supported |
 |:-|:-|
+| 24.8 | ✔️ |
+| 24.7 | ✔️ |
 | 24.6 | ✔️ |
-| 24.5 | ✔️ |
+| 24.5 | ❌ |
-| 24.4 | ✔️ |
+| 24.4 | ❌ |
 | 24.3 | ✔️ |
 | 24.2 | ❌ |
 | 24.1 | ❌ |
-| 23.12 | ❌ |
+| 23.* | ❌ |
-| 23.11 | ❌ |
-| 23.10 | ❌ |
-| 23.9 | ❌ |
-| 23.8 | ✔️ |
-| 23.7 | ❌ |
-| 23.6 | ❌ |
-| 23.5 | ❌ |
-| 23.4 | ❌ |
-| 23.3 | ❌ |
-| 23.2 | ❌ |
-| 23.1 | ❌ |
 | 22.* | ❌ |
 | 21.* | ❌ |
 | 20.* | ❌ |

base/base/CMakeLists.txt

@@ -1,4 +1,4 @@
-add_compile_options($<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>)
+add_compile_options("$<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>")
 
 if (USE_CLANG_TIDY)
     set (CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_PATH}")
@@ -8,6 +8,8 @@ endif ()
 # when instantiated from JSON.cpp. Try again when libcxx(abi) and Clang are upgraded to 16.
 set (CMAKE_CXX_STANDARD 20)
 
+configure_file(GitHash.cpp.in GitHash.generated.cpp)
+
 set (SRCS
     argsToConfig.cpp
     cgroupsv2.cpp
@@ -32,6 +34,8 @@ set (SRCS
     StringRef.cpp
     safeExit.cpp
     throwError.cpp
+    Numa.cpp
+    GitHash.generated.cpp
 )
 
 add_library (common ${SRCS})
@@ -46,6 +50,10 @@ 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

base/base/Numa.cpp

@@ -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;
+}
+
+}

base/base/Numa.h

@@ -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();
+
+}

base/base/cgroupsv2.cpp

@@ -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
     }
@@ -26,27 +27,7 @@ bool cgroupsV2Enabled()
 #endif
 }
 
-bool cgroupsV2MemoryControllerEnabled()
+fs::path cgroupV2PathOfProcess()
-{
-#if defined(OS_LINUX)
-    chassert(cgroupsV2Enabled());
-    /// 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);
-    std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
-    if (!controllers_file.is_open())
-        return false;
-    std::string controllers;
-    std::getline(controllers_file, controllers);
-    return controllers.find("memory") != std::string::npos;
-#else
-    return false;
-#endif
-}
-
-std::string cgroupV2OfProcess()
 {
 #if defined(OS_LINUX)
     chassert(cgroupsV2Enabled());
@@ -54,17 +35,43 @@ 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
+}
+
+std::optional<std::string> getCgroupsV2PathContainingFile([[maybe_unused]] std::string_view file_name)
+{
+#if defined(OS_LINUX)
+    if (!cgroupsV2Enabled())
+        return {};
+
+    fs::path current_cgroup = cgroupV2PathOfProcess();
+    if (current_cgroup.empty())
+        return {};
+
+    /// Return the bottom-most nested file. If there is no such file at the current
+    /// level, try again at the parent level as settings are inherited.
+    while (current_cgroup != default_cgroups_mount.parent_path())
+    {
+        const auto path = current_cgroup / file_name;
+        if (fs::exists(path))
+            return {current_cgroup};
+        current_cgroup = current_cgroup.parent_path();
+    }
+    return {};
+#else
+    return {};
 #endif
 }

base/base/cgroupsv2.h

@@ -1,7 +1,7 @@
 #pragma once
 
 #include <filesystem>
-#include <string>
+#include <string_view>
 
 #if defined(OS_LINUX)
 /// I think it is possible to mount the cgroups hierarchy somewhere else (e.g. when in containers).
@@ -12,11 +12,11 @@ static inline const std::filesystem::path default_cgroups_mount = "/sys/fs/cgrou
 /// Is cgroups v2 enabled on the system?
 bool cgroupsV2Enabled();
 
-/// Is the memory controller of cgroups v2 enabled on the system?
+/// 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.
-bool cgroupsV2MemoryControllerEnabled();
+std::filesystem::path cgroupV2PathOfProcess();
 
-/// Which cgroup does the process belong to?
+/// Returns the most nested cgroup dir containing the specified file.
-/// Returns an empty string if the cgroup cannot be determined.
+/// If cgroups v2 is not enabled - returns an empty optional.
-/// Assumes that cgroupsV2Enabled() is enabled.
+std::optional<std::string> getCgroupsV2PathContainingFile([[maybe_unused]] std::string_view file_name);
-std::string cgroupV2OfProcess();

base/base/defines.h

@@ -87,9 +87,12 @@
 #   define ASAN_POISON_MEMORY_REGION(a, b)
 #endif
 
-#if !defined(ABORT_ON_LOGICAL_ERROR)
+/// 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
-    #if !defined(NDEBUG) || defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) || defined(UNDEFINED_BEHAVIOR_SANITIZER)
+/// but wanted to check exactly if the current build type is debug or with sanitizer. This new macro is introduced to fix those places.
-        #define ABORT_ON_LOGICAL_ERROR
+#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
 
@@ -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

base/base/getMemoryAmount.cpp

@@ -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
 {
 
@@ -20,12 +19,10 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
     if (!cgroupsV2Enabled())
         return {};
 
-    if (!cgroupsV2MemoryControllerEnabled())
+    std::filesystem::path current_cgroup = cgroupV2PathOfProcess();
+    if (current_cgroup.empty())
         return {};
 
-    std::string cgroup = cgroupV2OfProcess();
-    auto current_cgroup = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
-
     /// 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.
     while (current_cgroup != default_cgroups_mount.parent_path())
@@ -62,6 +59,9 @@ 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)

base/glibc-compatibility/CMakeLists.txt

@@ -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")
 

base/glibc-compatibility/musl/getauxval.c

@@ -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);
 }

base/poco/Foundation/include/Poco/ErrorHandler.h

@@ -21,6 +21,7 @@
 #include "Poco/Exception.h"
 #include "Poco/Foundation.h"
 #include "Poco/Mutex.h"
+#include "Poco/Message.h"
 
 
 namespace Poco
@@ -78,6 +79,10 @@ public:
     ///
     /// The default implementation just breaks into the debugger.
 
+    virtual void logMessageImpl(Message::Priority priority, const std::string & msg) {}
+    /// Write a messages to the log
+    /// Useful for logging from Poco
+
     static void handle(const Exception & exc);
     /// Invokes the currently registered ErrorHandler.
 
@@ -87,6 +92,9 @@ public:
     static void handle();
     /// Invokes the currently registered ErrorHandler.
 
+    static void logMessage(Message::Priority priority, const std::string & msg);
+    /// Invokes the currently registered ErrorHandler to log a message.
+
     static ErrorHandler * set(ErrorHandler * pHandler);
     /// Registers the given handler as the current error handler.
     ///

base/poco/Foundation/include/Poco/UUID.h

@@ -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);

base/poco/Foundation/src/ErrorHandler.cpp

@@ -89,6 +89,18 @@ void ErrorHandler::handle()
     }
 }
 
+void ErrorHandler::logMessage(Message::Priority priority, const std::string & msg)
+{
+    FastMutex::ScopedLock lock(_mutex);
+    try
+    {
+        _pHandler->logMessageImpl(priority, msg);
+    }
+    catch (...)
+    {
+    }
+}
+
 
 ErrorHandler* ErrorHandler::set(ErrorHandler* pHandler)
 {

base/poco/MongoDB/src/Binary.cpp

@@ -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()));
 }
 
 

base/poco/Net/include/Poco/Net/HTTPResponse.h

@@ -18,7 +18,9 @@
 #define Net_HTTPResponse_INCLUDED
 
 
+#include <map>
 #include <vector>
+
 #include "Poco/Net/HTTPCookie.h"
 #include "Poco/Net/HTTPMessage.h"
 #include "Poco/Net/Net.h"
@@ -180,6 +182,8 @@ namespace Net
         /// May throw an exception in case of a malformed
         /// Set-Cookie header.
 
+        void getHeaders(std::map<std::string, std::string> & headers) const;
+
         void write(std::ostream & ostr) const;
         /// Writes the HTTP response to the given
         /// output stream.

base/poco/Net/include/Poco/Net/HTTPServerSession.h

@@ -58,6 +58,10 @@ namespace Net
 
         void setKeepAliveTimeout(Poco::Timespan keepAliveTimeout);
 
+        size_t getKeepAliveTimeout() const { return _keepAliveTimeout.totalSeconds(); }
+
+        size_t getMaxKeepAliveRequests() const { return _maxKeepAliveRequests; }
+
     private:
         bool _firstRequest;
         Poco::Timespan _keepAliveTimeout;

base/poco/Net/include/Poco/Net/HTTPSession.h

@@ -19,6 +19,8 @@
 
 
 #include <ios>
+#include <memory>
+#include <functional>
 #include "Poco/Any.h"
 #include "Poco/Buffer.h"
 #include "Poco/Exception.h"
@@ -33,6 +35,27 @@ namespace Net
 {
 
 
+    class IHTTPSessionDataHooks
+    /// Interface to control stream of data bytes being sent or received though socket by HTTPSession
+    /// It allows to monitor, throttle and schedule data streams with syscall granulatrity
+    {
+    public:
+        virtual ~IHTTPSessionDataHooks() = default;
+
+        virtual void atStart(int bytes) = 0;
+        /// Called before sending/receiving data `bytes` to/from socket.
+
+        virtual void atFinish(int bytes) = 0;
+        /// Called when sending/receiving of data `bytes` is successfully finished.
+
+        virtual void atFail() = 0;
+        /// If an error occurred during send/receive `fail()` is called instead of `finish()`.
+    };
+
+
+    using HTTPSessionDataHooksPtr = std::shared_ptr<IHTTPSessionDataHooks>;
+
+
     class Net_API HTTPSession
     /// HTTPSession implements basic HTTP session management
     /// for both HTTP clients and HTTP servers.
@@ -73,6 +96,12 @@ namespace Net
         Poco::Timespan getReceiveTimeout() const;
         /// Returns receive timeout for the HTTP session.
 
+        void setSendDataHooks(const HTTPSessionDataHooksPtr & sendDataHooks = {});
+        /// Sets data hooks that will be called on every sent to the socket.
+
+        void setReceiveDataHooks(const HTTPSessionDataHooksPtr & receiveDataHooks = {});
+        /// Sets data hooks that will be called on every receive from the socket.
+
         bool connected() const;
         /// Returns true if the underlying socket is connected.
 
@@ -211,6 +240,10 @@ namespace Net
         Poco::Exception * _pException;
         Poco::Any _data;
 
+        // Data hooks
+        HTTPSessionDataHooksPtr _sendDataHooks;
+        HTTPSessionDataHooksPtr _receiveDataHooks;
+
         friend class HTTPStreamBuf;
         friend class HTTPHeaderStreamBuf;
         friend class HTTPFixedLengthStreamBuf;
@@ -246,6 +279,16 @@ namespace Net
         return _receiveTimeout;
     }
 
+    inline void HTTPSession::setSendDataHooks(const HTTPSessionDataHooksPtr & sendDataHooks)
+    {
+        _sendDataHooks = sendDataHooks;
+    }
+
+    inline void HTTPSession::setReceiveDataHooks(const HTTPSessionDataHooksPtr & receiveDataHooks)
+    {
+        _receiveDataHooks = receiveDataHooks;
+    }
+
     inline StreamSocket & HTTPSession::socket()
     {
         return _socket;

base/poco/Net/src/HTTPResponse.cpp

@@ -209,6 +209,15 @@ void HTTPResponse::getCookies(std::vector<HTTPCookie>& cookies) const
 	}
 }
 
+void HTTPResponse::getHeaders(std::map<std::string, std::string> & headers) const
+{
+    headers.clear();
+    for (const auto & it : *this)
+    {
+        headers.emplace(it.first, it.second);
+    }
+}
+
 
 void HTTPResponse::write(std::ostream& ostr) const
 {

base/poco/Net/src/HTTPServerSession.cpp

@@ -19,11 +19,11 @@ namespace Poco {
 namespace Net {
 
 
-HTTPServerSession::HTTPServerSession(const StreamSocket& socket, HTTPServerParams::Ptr pParams):
+HTTPServerSession::HTTPServerSession(const StreamSocket & socket, HTTPServerParams::Ptr pParams)
-	HTTPSession(socket, pParams->getKeepAlive()),
+    : HTTPSession(socket, pParams->getKeepAlive())
-	_firstRequest(true),
+    , _firstRequest(true)
-	_keepAliveTimeout(pParams->getKeepAliveTimeout()),
+    , _keepAliveTimeout(pParams->getKeepAliveTimeout())
-	_maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
+    , _maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
 {
 	setTimeout(pParams->getTimeout());
 }
@@ -56,7 +56,8 @@ bool HTTPServerSession::hasMoreRequests()
             --_maxKeepAliveRequests;
         return buffered() > 0 || socket().poll(_keepAliveTimeout, Socket::SELECT_READ);
     }
-	else return false;
+    else
+        return false;
 }
 
 

base/poco/Net/src/HTTPSession.cpp

@@ -166,10 +166,17 @@ int HTTPSession::write(const char* buffer, std::streamsize length)
 {
 	try
 	{
-		return _socket.sendBytes(buffer, (int) length);
+		if (_sendDataHooks)
+			_sendDataHooks->atStart((int) length);
+		int result = _socket.sendBytes(buffer, (int) length);
+		if (_sendDataHooks)
+			_sendDataHooks->atFinish(result);
+		return result;
 	}
 	catch (Poco::Exception& exc)
 	{
+		if (_sendDataHooks)
+			_sendDataHooks->atFail();
 		setException(exc);
 		throw;
 	}
@@ -180,10 +187,17 @@ int HTTPSession::receive(char* buffer, int length)
 {
 	try
 	{
-		return _socket.receiveBytes(buffer, length);
+		if (_receiveDataHooks)
+			_receiveDataHooks->atStart(length);
+		int result = _socket.receiveBytes(buffer, length);
+		if (_receiveDataHooks)
+			_receiveDataHooks->atFinish(result);
+		return result;
 	}
 	catch (Poco::Exception& exc)
 	{
+		if (_receiveDataHooks)
+			_receiveDataHooks->atFail();
 		setException(exc);
 		throw;
 	}

base/poco/Net/src/SocketImpl.cpp

@@ -17,6 +17,7 @@
 #include "Poco/Net/StreamSocketImpl.h"
 #include "Poco/NumberFormatter.h"
 #include "Poco/Timestamp.h"
+#include "Poco/ErrorHandler.h"
 #include <string.h> // FD_SET needs memset on some platforms, so we can't use <cstring>
 
 

base/poco/Net/src/TCPServer.cpp

@@ -147,6 +147,10 @@ void TCPServer::run()
                         }
                         _pDispatcher->enqueue(ss);
                     }
+                    else
+                    {
+                        ErrorHandler::logMessage(Message::PRIO_WARNING, "Filtered out connection from " + ss.peerAddress().toString());
+                    }
                 }
                 catch (Poco::Exception& exc)
                 {

base/poco/Net/src/TCPServerDispatcher.cpp

@@ -143,8 +143,23 @@ void TCPServerDispatcher::enqueue(const StreamSocket& socket)
 {
     FastMutex::ScopedLock lock(_mutex);
 
+    ErrorHandler::logMessage(Message::PRIO_TEST, "Queue size: " + std::to_string(_queue.size()) +
+                                 ", current threads: " + std::to_string(_currentThreads) +
+                                 ", threads in pool: " + std::to_string(_threadPool.allocated()) +
+                                 ", current connections: " + std::to_string(_currentConnections));
+
+
     if (_queue.size() < _pParams->getMaxQueued())
     {
+        /// NOTE: the condition below is wrong.
+        /// Since the thread pool is shared between multiple servers/TCPServerDispatchers,
+        /// _currentThreads < _pParams->getMaxThreads() will be true when the pool is actually saturated.
+        /// As a result, queue is useless and connections never wait in queue.
+        /// Instead, we (mistakenly) think that we can create a thread for this connection, but we fail to create it
+        /// and the connection get rejected.
+        /// We could check _currentThreads < _threadPool.allocated() to make it work,
+        /// but it's not clear if we want to make it work
+        /// because it may be better to reject connection immediately if we don't have resources to handle it.
         if (!_queue.hasIdleThreads() && _currentThreads < _pParams->getMaxThreads())
         {
             try
@@ -155,17 +170,25 @@ void TCPServerDispatcher::enqueue(const StreamSocket& socket)
             }
             catch (Poco::Exception& exc)
             {
+                ErrorHandler::logMessage(Message::PRIO_WARNING, "Got an exception while starting thread for connection from " +
+                                             socket.peerAddress().toString());
+                ErrorHandler::handle(exc);
                 this->release();
                 ++_refusedConnections;
-				std::cerr << "Got exception while starting thread for connection. Error code: "
-						  << exc.code() << ", message: '" << exc.displayText() << "'" << std::endl;
                 return;
             }
         }
+        else if (!_queue.hasIdleThreads())
+        {
+            ErrorHandler::logMessage(Message::PRIO_TRACE, "Don't have idle threads, adding connection from " +
+                                         socket.peerAddress().toString() + " to the queue, size: " + std::to_string(_queue.size()));
+        }
         _queue.enqueueNotification(new TCPConnectionNotification(socket));
     }
     else
     {
+        ErrorHandler::logMessage(Message::PRIO_WARNING, "Refusing connection from " + socket.peerAddress().toString() +
+                                     ", reached max queue size " + std::to_string(_pParams->getMaxQueued()));
         ++_refusedConnections;
     }
 }

base/poco/NetSSL_OpenSSL/src/SecureSocketImpl.cpp

@@ -311,6 +311,14 @@ int SecureSocketImpl::sendBytes(const void* buffer, int length, int flags)
 	while (mustRetry(rc, remaining_time));
 	if (rc <= 0)
 	{
+		// At this stage we still can have last not yet received SSL message containing SSL error
+		// so make a read to force SSL to process possible SSL error
+		if (SSL_get_error(_pSSL, rc) == SSL_ERROR_SYSCALL && SocketImpl::lastError() == POCO_ECONNRESET)
+		{
+			char c = 0;
+			SSL_read(_pSSL, &c, 1);
+		}
+
 		rc = handleError(rc);
 		if (rc == 0) throw SSLConnectionUnexpectedlyClosedException();
 	}

base/poco/Util/CMakeLists.txt

@@ -18,4 +18,4 @@ target_compile_options (_poco_util
         -Wno-zero-as-null-pointer-constant
 )
 target_include_directories (_poco_util SYSTEM PUBLIC "include")
-target_link_libraries (_poco_util PUBLIC Poco::JSON Poco::XML)
+target_link_libraries (_poco_util PUBLIC Poco::JSON Poco::XML Poco::Net)

base/poco/Util/include/Poco/Util/AbstractConfiguration.h

@@ -241,6 +241,20 @@ namespace Util
         /// If the value contains references to other properties (${<property>}), these
         /// are expanded.
 
+        std::string getHost(const std::string & key) const;
+        /// Returns the string value of the host property with the given name.
+        /// Throws a NotFoundException if the key does not exist.
+        /// Throws a SyntaxException if the property is not a valid host (IP address or domain).
+        /// If the value contains references to other properties (${<property>}), these
+        /// are expanded.
+
+        std::string getHost(const std::string & key, const std::string & defaultValue) const;
+        /// If a property with the given key exists, returns the host property's string value,
+        /// otherwise returns the given default value.
+        /// Throws a SyntaxException if the property is not a valid host (IP address or domain).
+        /// If the value contains references to other properties (${<property>}), these
+        /// are expanded.
+
         virtual void setString(const std::string & key, const std::string & value);
         /// Sets the property with the given key to the given value.
         /// An already existing value for the key is overwritten.
@@ -339,12 +353,35 @@ namespace Util
         static bool parseBool(const std::string & value);
         void setRawWithEvent(const std::string & key, std::string value);
 
+        static void checkHostValidity(const std::string & value);
+        /// Throws a SyntaxException if the value is not a valid host (IP address or domain).
+
         virtual ~AbstractConfiguration();
 
     private:
         std::string internalExpand(const std::string & value) const;
         std::string uncheckedExpand(const std::string & value) const;
 
+        static bool isValidIPv4Address(const std::string & value);
+        /// IPv4 address considered valid if it is "0.0.0.0" or one of those,
+        /// defined by inet_aton() or inet_addr()
+
+        static bool isValidIPv6Address(const std::string & value);
+        /// IPv6 address considered valid if it is "::" or one of those,
+        /// defined by inet_pton() with AF_INET6 flag
+        /// (in this case it may have scope id and may be surrounded by '[', ']')
+
+        static bool isValidDomainName(const std::string & value);
+        /// <domain> ::= <subdomain> [ "." ]
+        /// <subdomain> ::= <label> | <subdomain> "." <label>
+        /// <label> ::= <letter> [ [ <ldh-str> ] <let-dig> ]
+        /// <ldh-str> ::= <let-dig-hyp> | <let-dig-hyp> <ldh-str>
+        /// <let-dig-hyp> ::= <let-dig> | "-"
+        /// <let-dig> ::= <letter> | <digit>
+        /// <letter> ::= any one of the 52 alphabetic characters A through Z in
+        /// upper case and a through z in lower case
+        /// <digit> ::= any one of the ten digits 0 through 9
+
         AbstractConfiguration(const AbstractConfiguration &);
         AbstractConfiguration & operator=(const AbstractConfiguration &);
 

base/poco/Util/include/Poco/Util/Application.h

@@ -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;

base/poco/Util/src/AbstractConfiguration.cpp

@@ -18,6 +18,7 @@
 #include "Poco/NumberParser.h"
 #include "Poco/NumberFormatter.h"
 #include "Poco/String.h"
+#include "Poco/Net/IPAddressImpl.h"
 
 
 using Poco::Mutex;
@@ -263,6 +264,41 @@ bool AbstractConfiguration::getBool(const std::string& key, bool defaultValue) c
 }
 
 
+std::string AbstractConfiguration::getHost(const std::string& key) const
+{
+	Mutex::ScopedLock lock(_mutex);
+
+	std::string value;
+	if (getRaw(key, value))
+	{
+		std::string expandedValue = internalExpand(value);
+		checkHostValidity(expandedValue);
+		return expandedValue;
+	}
+	else
+		throw NotFoundException(key);
+}
+
+
+std::string AbstractConfiguration::getHost(const std::string& key, const std::string& defaultValue) const
+{
+	Mutex::ScopedLock lock(_mutex);
+
+	std::string value;
+	if (getRaw(key, value))
+	{
+		std::string expandedValue = internalExpand(value);
+		checkHostValidity(expandedValue);
+		return expandedValue;
+	}
+	else
+	{
+		checkHostValidity(defaultValue);
+		return defaultValue;
+	}
+}
+
+
 void AbstractConfiguration::setString(const std::string& key, const std::string& value)
 {
 	setRawWithEvent(key, value);
@@ -529,4 +565,68 @@ void AbstractConfiguration::setRawWithEvent(const std::string& key, std::string
 }
 
 
+void AbstractConfiguration::checkHostValidity(const std::string& value)
+{
+	if (!isValidIPv4Address(value) && !isValidIPv6Address(value) && !isValidDomainName(value))
+	{
+		throw SyntaxException("Property is not a valid host name", value);
+	}
+}
+
+
+bool AbstractConfiguration::isValidIPv4Address(const std::string& value)
+{
+	using Poco::Net::Impl::IPv4AddressImpl;
+	IPv4AddressImpl empty4 = IPv4AddressImpl();
+
+	IPv4AddressImpl ipAddress = IPv4AddressImpl::parse(value);
+	return ipAddress != empty4 || value == "0.0.0.0";
+}
+
+
+bool AbstractConfiguration::isValidIPv6Address(const std::string& value)
+{
+#if defined(POCO_HAVE_IPv6)
+	using Poco::Net::Impl::IPv6AddressImpl;
+	IPv6AddressImpl empty6 = IPv6AddressImpl();
+
+	IPv6AddressImpl ipAddress = IPv6AddressImpl::parse(value);
+	return ipAddress != empty6 || value == "::";
+#else
+	return false;
+#endif
+}
+
+
+bool AbstractConfiguration::isValidDomainName(const std::string& value)
+{
+	if (value.empty() || value == "." || value.length() > 253)
+		return false;
+	int labelLength = 0;
+	char oldChar = 0;
+
+	for (char ch : value)
+	{
+		if (ch == '.')
+		{
+			if (labelLength == 0 || labelLength > 63 || oldChar == '-')
+				return false;
+			labelLength = 0;
+		}
+		else if (isalnum(ch) || ch == '-')
+		{
+			if (labelLength == 0 && (ch == '-' || isdigit(ch)))
+				return false;
+			++labelLength;
+		}
+		else
+		{
+			return false;
+		}
+		oldChar = ch;
+	}
+	return oldChar == '.' || (labelLength > 0 && labelLength <= 63 && oldChar != '-');
+}
+
+
 } } // namespace Poco::Util

cmake/autogenerated_versions.txt

@@ -2,11 +2,11 @@
 
 # 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 54488)
+SET(VERSION_REVISION 54490)
 SET(VERSION_MAJOR 24)
-SET(VERSION_MINOR 7)
+SET(VERSION_MINOR 9)
 SET(VERSION_PATCH 1)
-SET(VERSION_GITHASH aa023477a9265e403982fca5ee29a714db5133d9)
+SET(VERSION_GITHASH e02b434d2fc0c4fbee29ca675deab7474d274608)
-SET(VERSION_DESCRIBE v24.7.1.1-testing)
+SET(VERSION_DESCRIBE v24.9.1.1-testing)
-SET(VERSION_STRING 24.7.1.1)
+SET(VERSION_STRING 24.9.1.1)
 # end of autochange

cmake/freebsd/default_libs.cmake

@@ -9,10 +9,18 @@ endif ()
 file(GLOB bprefix "/usr/local/llvm${COMPILER_VERSION_MAJOR}/lib/clang/${COMPILER_VERSION_MAJOR}/lib/${system_processor}-portbld-freebsd*/")
 message(STATUS "-Bprefix: ${bprefix}")
 
-execute_process(COMMAND ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins-${system_processor}.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
+execute_process(COMMAND
+    ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins-${system_processor}.a
+    OUTPUT_VARIABLE BUILTINS_LIBRARY
+    COMMAND_ERROR_IS_FATAL ANY
+    OUTPUT_STRIP_TRAILING_WHITESPACE)
 # --print-file-name simply prints what you passed in case of nothing was resolved, so let's try one other possible option
 if (BUILTINS_LIBRARY STREQUAL "libclang_rt.builtins-${system_processor}.a")
-    execute_process(COMMAND ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
+    execute_process(COMMAND
+        ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins.a
+        OUTPUT_VARIABLE BUILTINS_LIBRARY
+        COMMAND_ERROR_IS_FATAL ANY
+        OUTPUT_STRIP_TRAILING_WHITESPACE)
 endif()
 if (BUILTINS_LIBRARY STREQUAL "libclang_rt.builtins.a")
     message(FATAL_ERROR "libclang_rt.builtins had not been found")

cmake/freebsd/toolchain-x86_64.cmake

@@ -8,4 +8,7 @@ set (CMAKE_CXX_COMPILER_TARGET "x86_64-pc-freebsd11")
 set (CMAKE_ASM_COMPILER_TARGET "x86_64-pc-freebsd11")
 set (CMAKE_SYSROOT "${CMAKE_CURRENT_LIST_DIR}/../../contrib/sysroot/freebsd-x86_64")
 
+# dprintf is used in a patched version of replxx
+add_compile_definitions(_WITH_DPRINTF)
+
 set (CMAKE_TRY_COMPILE_TARGET_TYPE STATIC_LIBRARY)  # disable linkage check - it doesn't work in CMake

cmake/linux/default_libs.cmake

@@ -5,7 +5,11 @@ set (DEFAULT_LIBS "-nodefaultlibs")
 
 # We need builtins from Clang's RT even without libcxx - for ubsan+int128.
 # See https://bugs.llvm.org/show_bug.cgi?id=16404
-execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
+execute_process (COMMAND
+    ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt
+    OUTPUT_VARIABLE BUILTINS_LIBRARY
+    COMMAND_ERROR_IS_FATAL ANY
+    OUTPUT_STRIP_TRAILING_WHITESPACE)
 
 # Apparently, in clang-19, the UBSan support library for C++ was moved out into ubsan_standalone_cxx.a, so we have to include both.
 if (SANITIZE STREQUAL undefined)

cmake/sanitize.cmake

@@ -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 -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)

cmake/tools.cmake

@@ -5,7 +5,11 @@ if (NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang")
 endif ()
 
 # Print details to output
-execute_process(COMMAND ${CMAKE_CXX_COMPILER} --version OUTPUT_VARIABLE COMPILER_SELF_IDENTIFICATION OUTPUT_STRIP_TRAILING_WHITESPACE)
+execute_process(COMMAND ${CMAKE_CXX_COMPILER} --version
+    OUTPUT_VARIABLE COMPILER_SELF_IDENTIFICATION
+    COMMAND_ERROR_IS_FATAL ANY
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
 message (STATUS "Using compiler:\n${COMPILER_SELF_IDENTIFICATION}")
 
 # Require minimum compiler versions

cmake/utils.cmake

@@ -90,7 +90,10 @@ endfunction()
 
 # Function get_cmake_properties returns list of all propreties that cmake supports
 function(get_cmake_properties outvar)
-    execute_process(COMMAND cmake --help-property-list OUTPUT_VARIABLE cmake_properties)
+    execute_process(COMMAND cmake --help-property-list
+        OUTPUT_VARIABLE cmake_properties
+        COMMAND_ERROR_IS_FATAL ANY
+    )
     # Convert command output into a CMake list
     string(REGEX REPLACE ";" "\\\\;" cmake_properties "${cmake_properties}")
     string(REGEX REPLACE "\n" ";" cmake_properties "${cmake_properties}")

contrib/CMakeLists.txt

@@ -71,7 +71,6 @@ add_contrib (zlib-ng-cmake zlib-ng)
 add_contrib (bzip2-cmake bzip2)
 add_contrib (minizip-ng-cmake minizip-ng)
 add_contrib (snappy-cmake snappy)
-add_contrib (rocksdb-cmake rocksdb)
 add_contrib (thrift-cmake thrift)
 # parquet/arrow/orc
 add_contrib (arrow-cmake arrow) # requires: snappy, thrift, double-conversion
@@ -148,6 +147,7 @@ add_contrib (hive-metastore-cmake hive-metastore) # requires: thrift, avro, arro
 add_contrib (cppkafka-cmake cppkafka)
 add_contrib (libpqxx-cmake libpqxx)
 add_contrib (libpq-cmake libpq)
+add_contrib (rocksdb-cmake rocksdb) # requires: jemalloc, snappy, zlib, lz4, zstd, liburing
 add_contrib (nuraft-cmake NuRaft)
 add_contrib (fast_float-cmake fast_float)
 add_contrib (idna-cmake idna)
@@ -179,7 +179,7 @@ else()
     message(STATUS "Not using QPL")
 endif ()
 
-if (OS_LINUX AND ARCH_AMD64)
+if (OS_LINUX AND ARCH_AMD64 AND NOT NO_SSE3_OR_HIGHER)
     option (ENABLE_QATLIB "Enable Intel® QuickAssist Technology Library (QATlib)" ${ENABLE_LIBRARIES})
 elseif(ENABLE_QATLIB)
     message (${RECONFIGURE_MESSAGE_LEVEL} "QATLib is only supported on x86_64")
@@ -205,14 +205,12 @@ add_contrib (morton-nd-cmake morton-nd)
 if (ARCH_S390X)
     add_contrib(crc32-s390x-cmake crc32-s390x)
 endif()
-add_contrib (annoy-cmake annoy)
 
-option(ENABLE_USEARCH "Enable USearch (Approximate Neighborhood Search, HNSW) support" ${ENABLE_LIBRARIES})
+option(ENABLE_USEARCH "Enable USearch" ${ENABLE_LIBRARIES})
 if (ENABLE_USEARCH)
     add_contrib (FP16-cmake FP16)
-    add_contrib (robin-map-cmake robin-map)
     add_contrib (SimSIMD-cmake SimSIMD)
-    add_contrib (usearch-cmake usearch) # requires: FP16, robin-map, SimdSIMD
+    add_contrib (usearch-cmake usearch) # requires: FP16, SimdSIMD
 else ()
     message(STATUS "Not using USearch")
 endif ()
@@ -230,6 +228,8 @@ 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,

contrib/NuRaft

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

contrib/QAT-ZSTD-Plugin-cmake/CMakeLists.txt

@@ -27,7 +27,7 @@ if (ENABLE_QAT_OUT_OF_TREE_BUILD)
                 ${QAT_AL_INCLUDE_DIR}
                 ${QAT_USDM_INCLUDE_DIR}
                 ${ZSTD_LIBRARY_DIR})
-    target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DENABLE_ZSTD_QAT_CODEC)
+    target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0)
     add_library (ch_contrib::qatzstd_plugin ALIAS _qatzstd_plugin)
 else () # In-tree build
     message(STATUS "Intel QATZSTD in-tree build")
@@ -78,7 +78,7 @@ else () # In-tree build
         ${QAT_USDM_INCLUDE_DIR}
         ${ZSTD_LIBRARY_DIR}
         ${LIBQAT_HEADER_DIR})
-    target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DENABLE_ZSTD_QAT_CODEC -DINTREE)
+    target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DINTREE)
     target_include_directories(_qatzstd_plugin SYSTEM PUBLIC $<BUILD_INTERFACE:${QATZSTD_SRC_DIR}> $<INSTALL_INTERFACE:include>)
     add_library (ch_contrib::qatzstd_plugin ALIAS _qatzstd_plugin)
 endif ()

contrib/SimSIMD

@@ -1 +1 @@
-Subproject commit de2cb75b9e9e3389d5e1e51fd9f8ed151f3c17cf
+Subproject commit 91a76d1ac519b3b9dc8957734a3dabd985f00c26

contrib/annoy

@@ -1 +0,0 @@
-Subproject commit f2ac8e7b48f9a9cf676d3b58286e5455aba8e956

contrib/annoy-cmake/CMakeLists.txt

@@ -1,24 +0,0 @@
-option(ENABLE_ANNOY "Enable Annoy index support" ${ENABLE_LIBRARIES})
-
-# Annoy index should be disabled with undefined sanitizer. Because of memory storage optimizations
-# (https://github.com/ClickHouse/annoy/blob/9d8a603a4cd252448589e84c9846f94368d5a289/src/annoylib.h#L442-L463)
-# UBSan fails and leads to crash. Simmilar issue is already opened in Annoy repo
-# https://github.com/spotify/annoy/issues/456
-# Problem with aligment can lead to errors like
-# (https://stackoverflow.com/questions/46790550/c-undefined-behavior-strict-aliasing-rule-or-incorrect-alignment)
-# or will lead to crash on arm https://developer.arm.com/documentation/ka003038/latest
-# This issues should be resolved before annoy became non-experimental (--> setting "allow_experimental_annoy_index")
-if ((NOT ENABLE_ANNOY) OR (SANITIZE STREQUAL "undefined") OR (ARCH_AARCH64))
-    message (STATUS "Not using annoy")
-    return()
-endif()
-
-set(ANNOY_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/annoy")
-set(ANNOY_SOURCE_DIR "${ANNOY_PROJECT_DIR}/src")
-
-add_library(_annoy INTERFACE)
-target_include_directories(_annoy SYSTEM INTERFACE ${ANNOY_SOURCE_DIR})
-
-add_library(ch_contrib::annoy ALIAS _annoy)
-target_compile_definitions(_annoy INTERFACE ENABLE_ANNOY)
-target_compile_definitions(_annoy INTERFACE ANNOYLIB_MULTITHREADED_BUILD)

contrib/aws

@@ -1 +1 @@
-Subproject commit 1c2946bfcb7f1e3ae0a858de0b59d4f1a7b4ccaf
+Subproject commit d5450d76abda556ce145ddabe7e0cc6a7644ec59

contrib/aws-crt-cpp

@@ -1 +1 @@
-Subproject commit f532d6abc0d2b0d8b5d6fe9e7c51eaedbe4afbd0
+Subproject commit e5aa45cacfdcda7719ead38760e7c61076f5745f

contrib/azure

@@ -1 +1 @@
-Subproject commit ea3e19a7be08519134c643177d56c7484dfec884
+Subproject commit 67272b7ee0adff6b69921b26eb071ba1a353062c

contrib/cctz-cmake/CMakeLists.txt

@@ -37,7 +37,9 @@ message(STATUS "Packaging with tzdata version: ${TZDATA_VERSION}")
 execute_process(COMMAND
     bash -c "cd ${TZDIR} && find * -type f -and ! -name '*.tab' -and ! -name 'localtime' | LC_ALL=C sort | paste -sd ';' -"
     OUTPUT_STRIP_TRAILING_WHITESPACE
-    OUTPUT_VARIABLE TIMEZONES)
+    OUTPUT_VARIABLE TIMEZONES
+    COMMAND_ERROR_IS_FATAL ANY
+)
 
 file(APPEND ${TIMEZONES_FILE} "// autogenerated by ClickHouse/contrib/cctz-cmake/CMakeLists.txt\n")
 file(APPEND ${TIMEZONES_FILE} "#include <incbin.h>\n")

contrib/datasketches-cpp-cmake/CMakeLists.txt

@@ -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)

contrib/google-protobuf-cmake/CMakeLists.txt

@@ -359,7 +359,9 @@ else ()
 
         execute_process(
             COMMAND mkdir -p ${PROTOC_BUILD_DIR}
-            COMMAND_ECHO STDOUT)
+            COMMAND_ECHO STDOUT
+            COMMAND_ERROR_IS_FATAL ANY
+        )
 
         execute_process(
             COMMAND ${CMAKE_COMMAND}
@@ -375,11 +377,15 @@ else ()
                 "-DABSL_ENABLE_INSTALL=0"
                 "${protobuf_source_dir}"
             WORKING_DIRECTORY "${PROTOC_BUILD_DIR}"
-            COMMAND_ECHO STDOUT)
+            COMMAND_ECHO STDOUT
+            COMMAND_ERROR_IS_FATAL ANY
+        )
 
         execute_process(
             COMMAND ${CMAKE_COMMAND} --build "${PROTOC_BUILD_DIR}"
-            COMMAND_ECHO STDOUT)
+            COMMAND_ECHO STDOUT
+            COMMAND_ERROR_IS_FATAL ANY
+        )
     endif ()
 
     add_executable(protoc IMPORTED GLOBAL)

contrib/grpc

@@ -1 +1 @@
-Subproject commit f5b7fdc2dff09ada06dbf6c75df298fb40f898df
+Subproject commit 1716359d2e28d304a250f9df0e6c0ccad03de8db

contrib/grpc-cmake/CMakeLists.txt

@@ -53,6 +53,7 @@ if (NOT CMAKE_HOST_SYSTEM_NAME STREQUAL CMAKE_SYSTEM_NAME
     execute_process(
         COMMAND mkdir -p ${OPENSSL_BUILD_DIR}
         COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
     )
 
     if (CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "amd64|x86_64")
@@ -89,15 +90,21 @@ if (NOT CMAKE_HOST_SYSTEM_NAME STREQUAL CMAKE_SYSTEM_NAME
             "-DClickHouse_SOURCE_DIR=${ClickHouse_SOURCE_DIR}"
             "${OPENSSL_SOURCE_DIR}"
         WORKING_DIRECTORY "${OPENSSL_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     execute_process(
         COMMAND ${CMAKE_COMMAND} --build "${OPENSSL_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     execute_process(
         COMMAND ${CMAKE_COMMAND} --install "${OPENSSL_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     # It's not important on which file we depend, we just want to specify right order
     add_library(openssl_for_grpc STATIC IMPORTED GLOBAL)
@@ -110,6 +117,7 @@ if (NOT CMAKE_HOST_SYSTEM_NAME STREQUAL CMAKE_SYSTEM_NAME
     execute_process(
         COMMAND mkdir -p ${GRPC_CPP_PLUGIN_BUILD_DIR}
         COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
     )
 
     set(abseil_source_dir "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
@@ -140,11 +148,15 @@ if (NOT CMAKE_HOST_SYSTEM_NAME STREQUAL CMAKE_SYSTEM_NAME
             "-DgRPC_SSL_PROVIDER=package"
             "${_gRPC_SOURCE_DIR}"
         WORKING_DIRECTORY "${GRPC_CPP_PLUGIN_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     execute_process(
         COMMAND ${CMAKE_COMMAND} --build "${GRPC_CPP_PLUGIN_BUILD_DIR}"
-        COMMAND_ECHO STDOUT)
+        COMMAND_ECHO STDOUT
+        COMMAND_ERROR_IS_FATAL ANY
+    )
 
     add_executable(grpc_cpp_plugin IMPORTED GLOBAL)
     set_target_properties (grpc_cpp_plugin PROPERTIES IMPORTED_LOCATION "${GRPC_CPP_PLUGIN_BUILD_DIR}/grpc_cpp_plugin")

contrib/icu

@@ -1 +1 @@
-Subproject commit a56dde820dc35665a66f2e9ee8ba58e75049b668
+Subproject commit 4216173eeeb39c1d4caaa54a68860e800412d273

contrib/icu-cmake/CMakeLists.txt

@@ -12,8 +12,6 @@ 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

contrib/icudata

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

contrib/jemalloc-cmake/CMakeLists.txt

@@ -34,11 +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.
-    if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
-        set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
-    else()
     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")
-    endif()
 else()
     set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
 endif()

contrib/jemalloc-cmake/README

@@ -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 */@'

contrib/jemalloc-cmake/include_freebsd_ppc64le/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_ppc64le/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_riscv64/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_s390x/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_x86_64/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/jemalloc-cmake/include_linux_x86_64_musl/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -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.

contrib/libfiu

@@ -1 +1 @@
-Subproject commit b85edbde4cf974b1b40d27828a56f0505f4e2ee5
+Subproject commit a1290d8cd3d7b4541d6c976e0a54f572ac03f2a3

contrib/libfiu-cmake/CMakeLists.txt

@@ -1,20 +1,21 @@
-if (NOT ENABLE_FIU)
+if (NOT ENABLE_LIBFIU)
-  message (STATUS "Not using fiu")
+  message (STATUS "Not using libfiu")
   return ()
 endif ()
 
-set(FIU_DIR "${ClickHouse_SOURCE_DIR}/contrib/libfiu/")
+set(LIBFIU_DIR "${ClickHouse_SOURCE_DIR}/contrib/libfiu/")
 
-set(FIU_SOURCES
+set(LIBFIU_SOURCES
-  ${FIU_DIR}/libfiu/fiu.c
+    ${LIBFIU_DIR}/libfiu/fiu.c
-  ${FIU_DIR}/libfiu/fiu-rc.c
+    ${LIBFIU_DIR}/libfiu/fiu-rc.c
-  ${FIU_DIR}/libfiu/backtrace.c
+    ${LIBFIU_DIR}/libfiu/backtrace.c
-  ${FIU_DIR}/libfiu/wtable.c
+    ${LIBFIU_DIR}/libfiu/wtable.c
 )
 
-set(FIU_HEADERS "${FIU_DIR}/libfiu")
+set(LIBFIU_HEADERS "${LIBFIU_DIR}/libfiu")
 
-add_library(_fiu ${FIU_SOURCES})
+add_library(_libfiu ${LIBFIU_SOURCES})
-target_compile_definitions(_fiu PUBLIC DUMMY_BACKTRACE)
+target_compile_definitions(_libfiu PUBLIC DUMMY_BACKTRACE)
-target_include_directories(_fiu PUBLIC ${FIU_HEADERS})
+target_compile_definitions(_libfiu PUBLIC FIU_ENABLE)
-add_library(ch_contrib::fiu ALIAS _fiu)
+target_include_directories(_libfiu PUBLIC ${LIBFIU_HEADERS})
+add_library(ch_contrib::libfiu ALIAS _libfiu)

contrib/libprotobuf-mutator

@@ -1 +1 @@
-Subproject commit a304ec48dcf15d942607032151f7e9ee504b5dcf
+Subproject commit b922c8ab9004ef9944982e4f165e2747b13223fa

contrib/librdkafka

@@ -1 +1 @@
-Subproject commit 2d2aab6f5b79db1cfca15d7bf0dee75d00d82082
+Subproject commit 39d4ed49ccf3406e2bf825d5d7b0903b5a290782

contrib/libunwind

@@ -1 +1 @@
-Subproject commit d6a01c46327e56fd86beb8aaa31591fcd9a6b7df
+Subproject commit 601db0b0e03018c01710470a37703b618f9cf08b

contrib/libunwind-cmake/CMakeLists.txt

@@ -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)
 

contrib/numactl

@@ -0,0 +1 @@
+Subproject commit 8d13d63a05f0c3cd88bf777cbb61541202b7da08

contrib/numactl-cmake/CMakeLists.txt

@@ -0,0 +1,30 @@
+if (NOT (
+    OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64 OR ARCH_LOONGARCH64))
+)
+    if (ENABLE_NUMACTL)
+        message (${RECONFIGURE_MESSAGE_LEVEL}
+            "numactl is disabled implicitly because the OS or architecture is not supported. Use -DENABLE_NUMACTL=0")
+    endif ()
+    set (ENABLE_NUMACTL OFF)
+else()
+    option (ENABLE_NUMACTL "Enable numactl" ${ENABLE_LIBRARIES})
+endif()
+
+if (NOT ENABLE_NUMACTL)
+    message (STATUS "Not using numactl")
+    return()
+endif ()
+
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/numactl")
+
+set (SRCS
+    "${LIBRARY_DIR}/libnuma.c"
+    "${LIBRARY_DIR}/syscall.c"
+)
+
+add_library(_numactl ${SRCS})
+
+target_include_directories(_numactl SYSTEM PRIVATE include)
+target_include_directories(_numactl SYSTEM PUBLIC "${LIBRARY_DIR}")
+
+add_library(ch_contrib::numactl ALIAS _numactl)

contrib/numactl-cmake/include/config.h

@@ -0,0 +1,82 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Checking for symver attribute */
+#define HAVE_ATTRIBUTE_SYMVER 0
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#define HAVE_DLFCN_H 1
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#define HAVE_INTTYPES_H 1
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#define HAVE_STDINT_H 1
+
+/* Define to 1 if you have the <stdio.h> header file. */
+#define HAVE_STDIO_H 1
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#define HAVE_STDLIB_H 1
+
+/* Define to 1 if you have the <strings.h> header file. */
+#define HAVE_STRINGS_H 1
+
+/* Define to 1 if you have the <string.h> header file. */
+#define HAVE_STRING_H 1
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#define HAVE_SYS_STAT_H 1
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#define HAVE_SYS_TYPES_H 1
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#define HAVE_UNISTD_H 1
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#define LT_OBJDIR ".libs/"
+
+/* Name of package */
+#define PACKAGE "numactl"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "numactl"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "numactl 2.1"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "numactl"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "2.1"
+
+/* Define to 1 if all of the C89 standard headers exist (not just the ones
+   required in a freestanding environment). This macro is provided for
+   backward compatibility; new code need not use it. */
+#define STDC_HEADERS 1
+
+/* If the compiler supports a TLS storage class define it to that here */
+#define TLS __thread
+
+/* Version number of package */
+#define VERSION "2.1"
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+/* #undef _FILE_OFFSET_BITS */
+
+/* Define to 1 on platforms where this makes off_t a 64-bit type. */
+/* #undef _LARGE_FILES */
+
+/* Number of bits in time_t, on hosts where this is settable. */
+/* #undef _TIME_BITS */
+
+/* Define to 1 on platforms where this makes time_t a 64-bit type. */
+/* #undef __MINGW_USE_VC2005_COMPAT */

contrib/openssl

@@ -1 +1 @@
-Subproject commit ee2bb8513b28bf86b35404dd17a0e29305ca9e08
+Subproject commit 66deddc1e53cda8706604a019777259372d1bd62

contrib/openssl-cmake/CMakeLists.txt

@@ -1298,7 +1298,6 @@ elseif(ARCH_PPC64LE)
         ${OPENSSL_SOURCE_DIR}/crypto/camellia/camellia.c
         ${OPENSSL_SOURCE_DIR}/crypto/camellia/cmll_cbc.c
         ${OPENSSL_SOURCE_DIR}/crypto/chacha/chacha_enc.c
-        ${OPENSSL_SOURCE_DIR}/crypto/mem_clr.c
         ${OPENSSL_SOURCE_DIR}/crypto/rc4/rc4_enc.c
         ${OPENSSL_SOURCE_DIR}/crypto/rc4/rc4_skey.c
         ${OPENSSL_SOURCE_DIR}/crypto/sha/keccak1600.c