Merge branch 'master' into chimp-compression

.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 +13,9 @@
 # dbms/ → src/
 # (though it is unlikely that you will see it in blame)
 06446b4f08a142d6f1bc30664c47ded88ab51782
+
+# Applied Black formatter for Python code
+e6f5a3f98b21ba99cf274a9833797889e020a2b3
+
+# Enabling clang-tidy readability-else-no-return rule
+67c1e89d90ef576e62f8b1c68269742a3c6f9b1e

.github/ISSUE_TEMPLATE/20_feature-request.md

@@ -15,7 +15,7 @@ assignees: ''
 
 **Use case**
 
-> A clear and concise description of what is the intended usage scenario is.
+> A clear and concise description of what the intended usage scenario is.
 
 **Describe the solution you'd like**
 

.github/PULL_REQUEST_TEMPLATE.md

@@ -12,7 +12,7 @@ tests/ci/cancel_and_rerun_workflow_lambda/app.py
 - Backward Incompatible Change
 - Build/Testing/Packaging Improvement
 - Documentation (changelog entry is not required)
-- Critical Bug Fix (crash, LOGICAL_ERROR, data loss, RBAC)
+- Critical Bug Fix (crash, data loss, RBAC)
 - Bug Fix (user-visible misbehavior in an official stable release)
 - CI Fix or Improvement (changelog entry is not required)
 - Not for changelog (changelog entry is not required)
@@ -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

@@ -4,6 +4,6 @@ self-hosted-runner:
     - func-tester
     - func-tester-aarch64
     - fuzzer-unit-tester
-    - 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 "${{runner.temp}}"
+        sudo rm -fr "${{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 +1,34 @@
+name: DebugInfo
+description: Prints workflow debug info
+
+runs:
+  using: "composite"
+  steps:
+    - name: Envs, event.json and contexts
+      shell: bash
+      run: |
+          echo '::group::Environment variables'
+          env | sort
+          echo '::endgroup::'
+
+          echo '::group::event.json'
+          python3 -m json.tool "$GITHUB_EVENT_PATH"
+          echo '::endgroup::'
+
+          cat << 'EOF'
+          ::group::github context
+          ${{ toJSON(github) }}
+          ::endgroup::
+
+          ::group::env context
+          ${{ toJSON(env) }}
+          ::endgroup::
+
+          ::group::runner context
+          ${{ toJSON(runner) }}
+          ::endgroup::
+
+          ::group::job context
+          ${{ toJSON(job) }}
+          ::endgroup::
+          EOF

.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

@@ -27,6 +27,8 @@ jobs:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
@@ -36,10 +38,6 @@ jobs:
           cd "$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 +60,7 @@ 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:
@@ -231,27 +229,37 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (tsan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
 #############################################################################################
 ############################# INTEGRATION TESTS #############################################
 #############################################################################################
-  IntegrationTestsRelease:
-    needs: [RunConfig, BuilderDebRelease]
+  IntegrationTestsAsanOldAnalyzer:
+    needs: [RunConfig, BuilderDebAsan]
     if: ${{ !failure() && !cancelled() }}
     uses: ./.github/workflows/reusable_test.yml
     with:
-      test_name: Integration tests (release)
-      runner_type: stress-tester
+      test_name: Integration tests (asan, old analyzer)
+      runner_type: func-tester
+      data: ${{ needs.RunConfig.outputs.data }}
+  IntegrationTestsTsan:
+    needs: [RunConfig, BuilderDebTsan]
+    if: ${{ !failure() && !cancelled() }}
+    uses: ./.github/workflows/reusable_test.yml
+    with:
+      test_name: Integration tests (tsan)
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - Builds_Report
       - FunctionalStatelessTestAsan
       - FunctionalStatefulTestDebug
       - StressTestTsan
-      - IntegrationTestsRelease
+      - IntegrationTestsTsan
+      - IntegrationTestsAsanOldAnalyzer
       - CompatibilityCheckX86
       - CompatibilityCheckAarch64
     runs-on: [self-hosted, style-checker]
@@ -261,10 +269,23 @@ 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/cherry_pick.yml

@@ -33,6 +33,8 @@ jobs:
           clear-repository: true
           token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
           fetch-depth: 0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Cherry pick
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/create_release.yml

@@ -3,11 +3,14 @@ name: CreateRelease
 concurrency:
   group: release
 
+env:
+  PYTHONUNBUFFERED: 1
+
 'on':
   workflow_dispatch:
     inputs:
-      sha:
-        description: 'The SHA hash of the commit from which to create the release'
+      ref:
+        description: 'Git reference (branch or commit sha) from which to create the release'
         required: true
         type: string
       type:
@@ -15,15 +18,212 @@ 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:
-    runs-on: [self-hosted, style-checker-aarch64]
+  CreateRelease:
+    env:
+      GH_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
+    runs-on: [self-hosted, release-maker]
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
-      - name: Print greeting
+        with:
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+          fetch-depth: 0
+      - name: Debug Info
+        uses: ./.github/actions/debug
+      - 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/docker_test_images.yml

@@ -1,4 +1,5 @@
 name: Build docker images
+
 'on':
   workflow_call:
     inputs:
@@ -11,6 +12,10 @@ name: Build docker images
         required: false
         type: boolean
         default: false
+
+env:
+  PYTHONUNBUFFERED: 1
+
 jobs:
   DockerBuildAarch64:
     runs-on: [self-hosted, style-checker-aarch64]

.github/workflows/jepsen.yml

@@ -8,20 +8,67 @@ on: # yamllint disable-line rule:truthy
   schedule:
     - cron: '0 */6 * * *'
   workflow_dispatch:
+
 jobs:
+  RunConfig:
+    runs-on: [self-hosted, style-checker-aarch64]
+    outputs:
+      data: ${{ steps.runconfig.outputs.CI_DATA }}
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
+      - name: PrepareRunConfig
+        id: runconfig
+        run: |
+          echo "::group::configure CI run"
+          python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --workflow "$GITHUB_WORKFLOW" --outfile ${{ runner.temp }}/ci_run_data.json
+          echo "::endgroup::"
+
+          echo "::group::CI run configure results"
+          python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
+          echo "::endgroup::"
+          {
+            echo 'CI_DATA<<EOF'
+            cat  ${{ runner.temp }}/ci_run_data.json
+            echo 'EOF'
+          } >> "$GITHUB_OUTPUT"
   KeeperJepsenRelease:
-    uses: ./.github/workflows/reusable_simple_job.yml
+    needs: [RunConfig]
+    uses: ./.github/workflows/reusable_test.yml
     with:
-      test_name: Jepsen keeper check
-      runner_type: style-checker
-      report_required: true
+      test_name: ClickHouse Keeper Jepsen
+      runner_type: style-checker-aarch64
+      data: ${{ needs.RunConfig.outputs.data }}
       run_command: |
         python3 jepsen_check.py keeper
-  # ServerJepsenRelease:
-  #   uses: ./.github/workflows/reusable_simple_job.yml
-  #   with:
-  #     test_name: Jepsen server check
-  #     runner_type: style-checker
-  #     run_command: |
-  #       cd "$REPO_COPY/tests/ci"
-  #       python3 jepsen_check.py server
+  ServerJepsenRelease:
+    if: false  # skip for server
+    needs: [RunConfig]
+    uses: ./.github/workflows/reusable_test.yml
+    with:
+      test_name: ClickHouse Server Jepsen
+      runner_type: style-checker-aarch64
+      data: ${{ needs.RunConfig.outputs.data }}
+      run_command: |
+        python3 jepsen_check.py server
+  CheckWorkflow:
+    if: ${{ !cancelled() }}
+    needs: [RunConfig, ServerJepsenRelease, KeeperJepsenRelease]
+    runs-on: [self-hosted, style-checker-aarch64]
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+      - name: Check Workflow results
+        if: ${{ !cancelled() }}
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/master.yml

@@ -15,14 +15,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
-      - name: DebugInfo
-        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Merge sync PR
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
@@ -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

@@ -14,14 +14,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
-      - name: DebugInfo
-        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get a version
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Cancel PR workflow
         run: |
           python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run
@@ -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:
@@ -62,13 +58,8 @@ jobs:
       test_name: Style check
       runner_type: style-checker-aarch64
       run_command: |
-          python3 style_check.py
+          python3 style_check.py --no-push
       data: ${{ needs.RunConfig.outputs.data }}
-    secrets:
-      secret_envs: |
-        ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
-        ${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
-        RCSK
   FastTest:
     needs: [RunConfig, BuildDockers]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
@@ -97,7 +88,7 @@ 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 +96,19 @@ 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

@@ -15,19 +15,19 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
-      - name: DebugInfo
-        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: PrepareRunConfig
         id: runconfig
         run: |
             echo "::group::configure CI run"
-            python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --skip-jobs --outfile ${{ runner.temp }}/ci_run_data.json
+            python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --workflow NightlyBuilds --outfile ${{ runner.temp }}/ci_run_data.json
             echo "::endgroup::"
 
             echo "::group::CI run configure results"
@@ -40,7 +40,52 @@ 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
+
+  Builds_1:
+    needs: [RunConfig]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Builds_1') }}
+    uses: ./.github/workflows/reusable_build_stage.yml
+    with:
+      stage: Builds_1
+      data: ${{ needs.RunConfig.outputs.data }}
+  Tests_1:
+    needs: [RunConfig, Builds_1]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_1') }}
+    uses: ./.github/workflows/reusable_test_stage.yml
+    with:
+      stage: Tests_1
+      data: ${{ needs.RunConfig.outputs.data }}
+  Builds_2:
+    needs: [RunConfig, Builds_1]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Builds_2') }}
+    uses: ./.github/workflows/reusable_build_stage.yml
+    with:
+      stage: Builds_2
+      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 }}
+
+  CheckWorkflow:
+    if: ${{ !cancelled() }}
+    needs: [RunConfig, BuildDockers, Tests_2]
+    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

@@ -25,17 +25,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
-      - name: DebugInfo
-        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get a version
           filter: tree:0
-      - name: Cancel previous Sync PR workflow
-        run: |
-          python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Set pending Sync status
         run: |
           python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --set-pending-status
@@ -48,10 +45,6 @@ jobs:
           cd "$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 +65,7 @@ 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:
@@ -86,10 +79,7 @@ jobs:
           python3 style_check.py
       data: ${{ needs.RunConfig.outputs.data }}
     secrets:
-      secret_envs: |
-        ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
-        ${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
-        RCSK
+      robot_git_token: ${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
   FastTest:
     needs: [RunConfig, BuildDockers, StyleCheck]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
@@ -127,27 +117,32 @@ 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') }}
-    needs: [RunConfig, StyleCheck, Builds_1, Builds_2]
+    if: ${{ !cancelled()
+      && needs.RunConfig.result == 'success'
+      && needs.StyleCheck.result != 'failure'
+      && needs.FastTest.result != 'failure'
+      && needs.BuildDockers.result != 'failure'
+      && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2]
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Builds
@@ -155,9 +150,10 @@ jobs:
       data: ${{ needs.RunConfig.outputs.data }}
 
   CheckReadyForMerge:
-    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
-    # Test_2 or Test_3 must not have jobs required for Mergeable check
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1]
+    if: ${{ !cancelled() }}
+    # Test_2 or Test_3 do not have the jobs required for Mergeable check,
+    #  however, set them as "needs" to get all checks results before the automatic merge occurs.
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code
@@ -165,15 +161,24 @@ 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() }}
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    if: ${{ !failure() && !cancelled() }}
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code

.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

@@ -24,6 +24,8 @@ jobs:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
@@ -33,10 +35,6 @@ jobs:
           cd "$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 +55,7 @@ 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 +132,7 @@ jobs:
     with:
       build_name: package_debug
       data: ${{ needs.RunConfig.outputs.data }}
+      force: true
   BuilderBinDarwin:
     needs: [RunConfig, BuildDockers]
     if: ${{ !failure() && !cancelled() }}
@@ -375,7 +374,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (asan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   StressTestTsan:
     needs: [RunConfig, BuilderDebTsan]
@@ -383,7 +382,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (tsan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   StressTestMsan:
     needs: [RunConfig, BuilderDebMsan]
@@ -391,7 +390,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (msan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   StressTestUBsan:
     needs: [RunConfig, BuilderDebUBsan]
@@ -399,7 +398,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (ubsan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   StressTestDebug:
     needs: [RunConfig, BuilderDebDebug]
@@ -407,7 +406,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Stress test (debug)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
 #############################################################################################
 ############################# INTEGRATION TESTS #############################################
@@ -418,7 +417,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Integration tests (asan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   IntegrationTestsAnalyzerAsan:
     needs: [RunConfig, BuilderDebAsan]
@@ -426,7 +425,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Integration tests (asan, old analyzer)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   IntegrationTestsTsan:
     needs: [RunConfig, BuilderDebTsan]
@@ -434,7 +433,7 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Integration tests (tsan)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   IntegrationTestsRelease:
     needs: [RunConfig, BuilderDebRelease]
@@ -442,11 +441,12 @@ jobs:
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: Integration tests (release)
-      runner_type: stress-tester
+      runner_type: func-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - DockerServerImage
       - DockerKeeperImage
       - Builds_Report
@@ -482,9 +482,15 @@ 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_build.yml

@@ -34,8 +34,11 @@ name: Build ClickHouse
         description: additional ENV variables to setup the job
         type: string
     secrets:
-      secret_envs:
-        description: if given, it's passed to the environments
+      robot_git_token:
+        required: false
+      ci_db_url:
+        required: false
+      ci_db_password:
         required: false
 
 jobs:
@@ -58,10 +61,18 @@ jobs:
         run: |
           cat >> "$GITHUB_ENV" << 'EOF'
           ${{inputs.additional_envs}}
-          ${{secrets.secret_envs}}
           DOCKER_TAG<<DOCKER_JSON
           ${{ toJson(fromJson(inputs.data).docker_data.images) }}
           DOCKER_JSON
+          ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
+          ${{secrets.robot_git_token}}
+          RCSK
+          CI_DB_URL<<CIDBU
+          ${{ secrets.ci_db_url }}
+          CIDBU
+          CI_DB_PASSWORD<<CIDBP
+          ${{ secrets.ci_db_password }}
+          CIDBP
           EOF
           python3 "$GITHUB_WORKSPACE"/tests/ci/ci_config.py --build-name "${{inputs.build_name}}" >> "$GITHUB_ENV"
       - name: Apply sparse checkout for contrib # in order to check that it doesn't break build

.github/workflows/reusable_build_stage.yml

@@ -1,7 +1,11 @@
 ### FIXME: merge reusable_test.yml and reusable_build.yml as they are almost identical
 #          and then merge reusable_build_stage.yml and reusable_test_stage.yml
 
+env:
+  PYTHONUNBUFFERED: 1
+
 name: BuildStageWF
+
 'on':
   workflow_call:
     inputs:
@@ -14,8 +18,11 @@ name: BuildStageWF
         type: string
         required: true
     secrets:
-      secret_envs:
-        description: if given, it's passed to the environments
+      robot_git_token:
+        required: false
+      ci_db_url:
+        required: false
+      ci_db_password:
         required: false
 
 jobs:
@@ -35,4 +42,6 @@ jobs:
       checkout_depth: 0
       data: ${{ inputs.data }}
     secrets:
-      secret_envs: ${{ secrets.secret_envs }}
+      robot_git_token: ${{ secrets.robot_git_token }}
+      ci_db_url: ${{ secrets.ci_db_url }}
+      ci_db_password: ${{ secrets.ci_db_password }}

.github/workflows/reusable_simple_job.yml

@@ -45,8 +45,11 @@ name: Simple job
         type: boolean
         default: false
     secrets:
-      secret_envs:
-        description: if given, it's passed to the environments
+      robot_git_token:
+        required: false
+      ci_db_url:
+        required: false
+      ci_db_password:
         required: false
 
 
@@ -62,8 +65,6 @@ jobs:
     env:
       GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
     steps:
-      - name: DebugInfo
-        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
@@ -72,12 +73,22 @@ jobs:
           submodules: ${{inputs.submodules}}
           fetch-depth: ${{inputs.checkout_depth}}
           filter: tree:0
+      - name: Debug Info
+        uses: ./.github/actions/debug
       - name: Set build envs
         run: |
           cat >> "$GITHUB_ENV" << 'EOF'
           CHECK_NAME=${{ inputs.test_name }}
           ${{inputs.additional_envs}}
-          ${{secrets.secret_envs}}
+          ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
+          ${{secrets.robot_git_token}}
+          RCSK
+          CI_DB_URL<<CIDBU
+          ${{ secrets.ci_db_url }}
+          CIDBU
+          CI_DB_PASSWORD<<CIDBP
+          ${{ secrets.ci_db_password }}
+          CIDBP
           EOF
       - name: Common setup
         uses: ./.github/actions/common_setup

.github/workflows/reusable_test.yml

@@ -40,8 +40,11 @@ name: Testing workflow
         type: string
         default: "$GITHUB_WORKSPACE/tests/ci"
     secrets:
-      secret_envs:
-        description: if given, it's passed to the environments
+      robot_git_token:
+        required: false
+      ci_db_url:
+        required: false
+      ci_db_password:
         required: false
 
 
@@ -75,10 +78,18 @@ jobs:
           cat >> "$GITHUB_ENV" << 'EOF'
           CHECK_NAME=${{ inputs.test_name }}
           ${{inputs.additional_envs}}
-          ${{secrets.secret_envs}}
           DOCKER_TAG<<DOCKER_JSON
           ${{ toJson(fromJson(inputs.data).docker_data.images) }}
           DOCKER_JSON
+          ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
+          ${{secrets.robot_git_token}}
+          RCSK
+          CI_DB_URL<<CIDBU
+          ${{ secrets.ci_db_url }}
+          CIDBU
+          CI_DB_PASSWORD<<CIDBP
+          ${{ secrets.ci_db_password }}
+          CIDBP
           EOF
       - name: Common setup
         uses: ./.github/actions/common_setup
@@ -102,6 +113,8 @@ jobs:
             --job-name '${{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/reusable_test_stage.yml

@@ -1,4 +1,8 @@
+env:
+  PYTHONUNBUFFERED: 1
+
 name: StageWF
+
 'on':
   workflow_call:
     inputs:
@@ -11,8 +15,11 @@ name: StageWF
         type: string
         required: true
     secrets:
-      secret_envs:
-        description: if given, it's passed to the environments
+      robot_git_token:
+        required: false
+      ci_db_url:
+        required: false
+      ci_db_password:
         required: false
 
 jobs:
@@ -28,4 +35,6 @@ jobs:
       runner_type: ${{ matrix.job_name_and_runner_type.runner_type }}
       data: ${{ inputs.data }}
     secrets:
-      secret_envs: ${{ secrets.secret_envs }}
+      robot_git_token: ${{ secrets.robot_git_token }}
+      ci_db_url: ${{ secrets.ci_db_url }}
+      ci_db_password: ${{ secrets.ci_db_password }}

.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)

.gitignore

@@ -159,6 +159,7 @@ website/package-lock.json
 /programs/server/store
 /programs/server/uuid
 /programs/server/coordination
+/programs/server/workload
 
 # temporary test files
 tests/queries/0_stateless/test_*

.gitmodules

@@ -1,6 +1,9 @@
 # Please do not use 'branch = ...' tags with submodule entries. Such tags make updating submodules a
 # little bit more convenient but they do *not* specify the tracked submodule branch. Thus, they are
 # more confusing than useful.
+[submodule "contrib/jwt-cpp"]
+	path = contrib/jwt-cpp
+	url = https://github.com/Thalhammer/jwt-cpp
 [submodule "contrib/zstd"]
 	path = contrib/zstd
 	url = https://github.com/facebook/zstd
@@ -108,7 +111,7 @@
 	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
@@ -170,9 +173,6 @@
 [submodule "contrib/fast_float"]
 	path = contrib/fast_float
 	url = https://github.com/fastfloat/fast_float
-[submodule "contrib/libpq"]
-	path = contrib/libpq
-	url = https://github.com/ClickHouse/libpq
 [submodule "contrib/NuRaft"]
 	path = contrib/NuRaft
 	url = https://github.com/ClickHouse/NuRaft
@@ -230,15 +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
-[submodule "contrib/idxd-config"]
-	path = contrib/idxd-config
-	url = https://github.com/intel/idxd-config
 [submodule "contrib/QAT-ZSTD-Plugin"]
 	path = contrib/QAT-ZSTD-Plugin
 	url = https://github.com/intel/QAT-ZSTD-Plugin
@@ -341,16 +332,13 @@
 	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
+	url = https://github.com/ClickHouse/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
@@ -363,6 +351,9 @@
 [submodule "contrib/idna"]
 	path = contrib/idna
 	url = https://github.com/ada-url/idna.git
+[submodule "contrib/google-cloud-cpp"]
+	path = contrib/google-cloud-cpp
+	url = https://github.com/ClickHouse/google-cloud-cpp.git
 [submodule "contrib/rust_vendor"]
 	path = contrib/rust_vendor
 	url = https://github.com/ClickHouse/rust_vendor.git
@@ -372,3 +363,15 @@
 [submodule "contrib/double-conversion"]
 	path = contrib/double-conversion
 	url = https://github.com/ClickHouse/double-conversion.git
+[submodule "contrib/mongo-cxx-driver"]
+	path = contrib/mongo-cxx-driver
+	url = https://github.com/ClickHouse/mongo-cxx-driver.git
+[submodule "contrib/mongo-c-driver"]
+	path = contrib/mongo-c-driver
+	url = https://github.com/ClickHouse/mongo-c-driver.git
+[submodule "contrib/numactl"]
+	path = contrib/numactl
+	url = https://github.com/ClickHouse/numactl.git
+[submodule "contrib/postgres"]
+	path = contrib/postgres
+	url = https://github.com/ClickHouse/postgres.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 +1,8 @@
 ### Table of Contents
+**[ClickHouse release v24.10, 2024-10-31](#2410)**<br/>
+**[ClickHouse release v24.9, 2024-09-26](#249)**<br/>
+**[ClickHouse release v24.8 LTS, 2024-08-20](#248)**<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 +13,639 @@
 
 # 2024 Changelog
 
+### <a id="2410"></a> ClickHouse release 24.10, 2024-10-31
+
+#### Backward Incompatible Change
+* Allow to write `SETTINGS` before `FORMAT` in a chain of queries with `UNION` when subqueries are inside parentheses. This closes [#39712](https://github.com/ClickHouse/ClickHouse/issues/39712). Change the behavior when a query has the SETTINGS clause specified twice in a sequence. The closest SETTINGS clause will have a preference for the corresponding subquery. In the previous versions, the outermost SETTINGS clause could take a preference over the inner one. [#68614](https://github.com/ClickHouse/ClickHouse/pull/68614) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Reordering of filter conditions from `[PRE]WHERE` clause is now allowed by default. It could be disabled by setting `allow_reorder_prewhere_conditions` to `false`. [#70657](https://github.com/ClickHouse/ClickHouse/pull/70657) ([Nikita Taranov](https://github.com/nickitat)).
+* Remove the `idxd-config` library, which has an incompatible license. This also removes the experimental Intel DeflateQPL codec. [#70987](https://github.com/ClickHouse/ClickHouse/pull/70987) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### New Feature
+* Allow to grant access to the wildcard prefixes. `GRANT SELECT ON db.table_pefix_* TO user`. [#65311](https://github.com/ClickHouse/ClickHouse/pull/65311) ([pufit](https://github.com/pufit)).
+* If you press space bar during query runtime, the client will display a real-time table with detailed metrics. You can enable it globally with the new `--progress-table` option in clickhouse-client; a new `--enable-progress-table-toggle` is associated with the `--progress-table` option, and toggles the rendering of the progress table by pressing the control key (Space). [#63689](https://github.com/ClickHouse/ClickHouse/pull/63689) ([Maria Khristenko](https://github.com/mariaKhr)), [#70423](https://github.com/ClickHouse/ClickHouse/pull/70423) ([Julia Kartseva](https://github.com/jkartseva)).
+* Allow to cache read files for object storage table engines and data lakes using hash from ETag + file path as cache key. [#70135](https://github.com/ClickHouse/ClickHouse/pull/70135) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Support creating a table with a query: `CREATE TABLE ... CLONE AS ...`. It clones the source table's schema and then attaches all partitions to the newly created table. This feature is only supported with tables of the `MergeTree` family Closes [#65015](https://github.com/ClickHouse/ClickHouse/issues/65015). [#69091](https://github.com/ClickHouse/ClickHouse/pull/69091) ([tuanpach](https://github.com/tuanpach)).
+* Add a new system table, `system.query_metric_log` which contains history of memory and metric values from table system.events for individual queries, periodically flushed to disk. [#66532](https://github.com/ClickHouse/ClickHouse/pull/66532) ([Pablo Marcos](https://github.com/pamarcos)).
+* A simple SELECT query can be written with implicit SELECT to enable calculator-style expressions, e.g., `ch "1 + 2"`. This is controlled by a new setting, `implicit_select`. [#68502](https://github.com/ClickHouse/ClickHouse/pull/68502) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Support the `--copy` mode for clickhouse local as a shortcut for format conversion [#68503](https://github.com/ClickHouse/ClickHouse/issues/68503). [#68583](https://github.com/ClickHouse/ClickHouse/pull/68583) ([Denis Hananein](https://github.com/denis-hananein)).
+* Add a builtin HTML page for visualizing merges which is available at the `/merges` path. [#70821](https://github.com/ClickHouse/ClickHouse/pull/70821) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add support for `arrayUnion` function. [#68989](https://github.com/ClickHouse/ClickHouse/pull/68989) ([Peter Nguyen](https://github.com/petern48)).
+* Allow parametrised SQL aliases. [#50665](https://github.com/ClickHouse/ClickHouse/pull/50665) ([Anton Kozlov](https://github.com/tonickkozlov)).
+* A new aggregate function `quantileExactWeightedInterpolated`, which is a interpolated version based on quantileExactWeighted. Some people may wonder why we need a new `quantileExactWeightedInterpolated` since we already have `quantileExactInterpolatedWeighted`. The reason is the new one is more accurate than the old one. This is for spark compatibility. [#69619](https://github.com/ClickHouse/ClickHouse/pull/69619) ([李扬](https://github.com/taiyang-li)).
+* A new function `arrayElementOrNull`. It returns `NULL` if the array index is out of range or a Map key not found. [#69646](https://github.com/ClickHouse/ClickHouse/pull/69646) ([李扬](https://github.com/taiyang-li)).
+* Allows users to specify regular expressions through new `message_regexp` and `message_regexp_negative` fields in the `config.xml` file to filter out logging. The logging is applied to the formatted un-colored text for the most intuitive developer experience. [#69657](https://github.com/ClickHouse/ClickHouse/pull/69657) ([Peter Nguyen](https://github.com/petern48)).
+* Added `RIPEMD160` function, which computes the RIPEMD-160 cryptographic hash of a string. Example: `SELECT HEX(RIPEMD160('The quick brown fox jumps over the lazy dog'))` returns `37F332F68DB77BD9D7EDD4969571AD671CF9DD3B`. [#70087](https://github.com/ClickHouse/ClickHouse/pull/70087) ([Dergousov Maxim](https://github.com/m7kss1)).
+* Support reading `Iceberg` tables on `HDFS`. [#70268](https://github.com/ClickHouse/ClickHouse/pull/70268) ([flynn](https://github.com/ucasfl)).
+* Support for CTE in the form of `WITH ... INSERT`, as previously we only supported `INSERT ... WITH ...`. [#70593](https://github.com/ClickHouse/ClickHouse/pull/70593) ([Shichao Jin](https://github.com/jsc0218)).
+* MongoDB integration: support for all MongoDB types, support for WHERE and ORDER BY statements on MongoDB side, restriction for expressions unsupported by MongoDB. Note that the new inegration is disabled by default, to use it, please set `<use_legacy_mongodb_integration>` to `false` in server config. [#63279](https://github.com/ClickHouse/ClickHouse/pull/63279) ([Kirill Nikiforov](https://github.com/allmazz)).
+* A new function `getSettingOrDefault` added to return the default value and avoid exception if a custom setting is not found in the current profile. [#69917](https://github.com/ClickHouse/ClickHouse/pull/69917) ([Shankar](https://github.com/shiyer7474)).
+
+#### Experimental feature
+* Refreshable materialized views are production ready. [#70550](https://github.com/ClickHouse/ClickHouse/pull/70550) ([Michael Kolupaev](https://github.com/al13n321)). Refreshable materialized views are now supported in Replicated databases. [#60669](https://github.com/ClickHouse/ClickHouse/pull/60669) ([Michael Kolupaev](https://github.com/al13n321)).
+* Parallel replicas are moved from experimental to beta. Reworked settings that control the behavior of parallel replicas algorithms. A quick recap: ClickHouse has four different algorithms for parallel reading involving multiple replicas, which is reflected in the setting `parallel_replicas_mode`, the default value for it is `read_tasks` Additionally, the toggle-switch setting `enable_parallel_replicas` has been added. [#63151](https://github.com/ClickHouse/ClickHouse/pull/63151) ([Alexey Milovidov](https://github.com/alexey-milovidov)), ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Support for the `Dynamic` type in most functions by executing them on internal types inside `Dynamic`. [#69691](https://github.com/ClickHouse/ClickHouse/pull/69691) ([Pavel Kruglov](https://github.com/Avogar)).
+* Allow to read/write the `JSON` type as a binary string in `RowBinary` format under settings `input_format_binary_read_json_as_string/output_format_binary_write_json_as_string`. [#70288](https://github.com/ClickHouse/ClickHouse/pull/70288) ([Pavel Kruglov](https://github.com/Avogar)).
+* Allow to serialize/deserialize `JSON` column as single String column in the Native format. For output use setting `output_format_native_write_json_as_string`. For input, use serialization version `1` before the column data. [#70312](https://github.com/ClickHouse/ClickHouse/pull/70312) ([Pavel Kruglov](https://github.com/Avogar)).
+* Introduced a special (experimental) mode of a merge selector for MergeTree tables which makes it more aggressive for the partitions that are close to the limit by the number of parts. It is controlled by the `merge_selector_use_blurry_base` MergeTree-level setting. [#70645](https://github.com/ClickHouse/ClickHouse/pull/70645) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Implement generic ser/de between Avro's `Union` and ClickHouse's `Variant` types. Resolves [#69713](https://github.com/ClickHouse/ClickHouse/issues/69713). [#69712](https://github.com/ClickHouse/ClickHouse/pull/69712) ([Jiří Kozlovský](https://github.com/jirislav)).
+
+#### Performance Improvement
+* Refactor `IDisk` and `IObjectStorage` for better performance. Tables from `plain` and `plain_rewritable` object storages will initialize faster. [#68146](https://github.com/ClickHouse/ClickHouse/pull/68146) ([Alexey Milovidov](https://github.com/alexey-milovidov), [Julia Kartseva](https://github.com/jkartseva)). Do not call the LIST object storage API when determining if a file or directory exists on the plain rewritable disk, as it can be cost-inefficient. [#70852](https://github.com/ClickHouse/ClickHouse/pull/70852) ([Julia Kartseva](https://github.com/jkartseva)). Reduce the number of object storage HEAD API requests in the plain_rewritable disk. [#70915](https://github.com/ClickHouse/ClickHouse/pull/70915) ([Julia Kartseva](https://github.com/jkartseva)).
+* Added an ability to parse data directly into sparse columns. [#69828](https://github.com/ClickHouse/ClickHouse/pull/69828) ([Anton Popov](https://github.com/CurtizJ)).
+* Improved performance of parsing formats with high number of missed values (e.g. `JSONEachRow`). [#69875](https://github.com/ClickHouse/ClickHouse/pull/69875) ([Anton Popov](https://github.com/CurtizJ)).
+* Supports parallel reading of parquet row groups and prefetching of row groups in single-threaded mode. [#69862](https://github.com/ClickHouse/ClickHouse/pull/69862) ([LiuNeng](https://github.com/liuneng1994)).
+* Support minmax index for `pointInPolygon`. [#62085](https://github.com/ClickHouse/ClickHouse/pull/62085) ([JackyWoo](https://github.com/JackyWoo)).
+* Use bloom filters when reading Parquet files. [#62966](https://github.com/ClickHouse/ClickHouse/pull/62966) ([Arthur Passos](https://github.com/arthurpassos)).
+* Lock-free parts rename to avoid INSERT affect SELECT (due to parts lock) (under normal circumstances with `fsync_part_directory`, QPS of SELECT with INSERT in parallel, increased 2x, under heavy load the effect is even bigger). Note, this only includes `ReplicatedMergeTree` for now. [#64955](https://github.com/ClickHouse/ClickHouse/pull/64955) ([Azat Khuzhin](https://github.com/azat)).
+* Respect `ttl_only_drop_parts` on `materialize ttl`; only read necessary columns to recalculate TTL and drop parts by replacing them with an empty one. [#65488](https://github.com/ClickHouse/ClickHouse/pull/65488) ([Andrey Zvonov](https://github.com/zvonand)).
+* Optimized thread creation in the ThreadPool to minimize lock contention. Thread creation is now performed outside of the critical section to avoid delays in job scheduling and thread management under high load conditions. This leads to a much more responsive ClickHouse under heavy concurrent load. [#68694](https://github.com/ClickHouse/ClickHouse/pull/68694) ([filimonov](https://github.com/filimonov)).
+* Enable reading `LowCardinality` string columns from `ORC`. [#69481](https://github.com/ClickHouse/ClickHouse/pull/69481) ([李扬](https://github.com/taiyang-li)).
+* Use `LowCardinality` for `ProfileEvents` in system logs such as `part_log`, `query_views_log`, `filesystem_cache_log`. [#70152](https://github.com/ClickHouse/ClickHouse/pull/70152) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Improve performance of `fromUnixTimestamp`/`toUnixTimestamp` functions. [#71042](https://github.com/ClickHouse/ClickHouse/pull/71042) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Don't disable nonblocking read from page cache for the entire server when reading from a blocking I/O. This was leading to a poorer performance when a single filesystem (e.g., tmpfs) didn't support the `preadv2` syscall while others do. [#70299](https://github.com/ClickHouse/ClickHouse/pull/70299) ([Antonio Andelic](https://github.com/antonio2368)).
+* `ALTER TABLE .. REPLACE PARTITION` doesn't wait anymore for mutations/merges that happen in other partitions. [#59138](https://github.com/ClickHouse/ClickHouse/pull/59138) ([Vasily Nemkov](https://github.com/Enmk)).
+* Don't do validation when synchronizing ACL from Keeper. It's validating during creation. It shouldn't matter that much, but there are installations with tens of thousands or even more user created, and the unnecessary hash validation can take a long time to finish during server startup (it synchronizes everything from keeper). [#70644](https://github.com/ClickHouse/ClickHouse/pull/70644) ([Raúl Marín](https://github.com/Algunenano)).
+
+#### Improvement
+* `CREATE TABLE AS` will copy `PRIMARY KEY`, `ORDER BY`, and similar clauses (of `MergeTree` tables). [#69739](https://github.com/ClickHouse/ClickHouse/pull/69739) ([sakulali](https://github.com/sakulali)).
+* Support 64-bit XID in Keeper. It can be enabled with the `use_xid_64` configuration value. [#69908](https://github.com/ClickHouse/ClickHouse/pull/69908) ([Antonio Andelic](https://github.com/antonio2368)).
+* Command-line arguments for Bool settings are set to true when no value is provided for the argument (e.g. `clickhouse-client --optimize_aggregation_in_order --query "SELECT 1"`). [#70459](https://github.com/ClickHouse/ClickHouse/pull/70459) ([davidtsuk](https://github.com/davidtsuk)).
+* Added user-level settings `min_free_disk_bytes_to_throw_insert` and `min_free_disk_ratio_to_throw_insert` to prevent insertions on disks that are almost full. [#69755](https://github.com/ClickHouse/ClickHouse/pull/69755) ([Marco Vilas Boas](https://github.com/marco-vb)).
+* Embedded documentation for settings will be strictly more detailed and complete than the documentation on the website. This is the first step before making the website documentation always auto-generated from the source code. This has long-standing implications: - it will be guaranteed to have every setting; - there is no chance of having default values obsolete; - we can generate this documentation for each ClickHouse version; - the documentation can be displayed by the server itself even without Internet access. Generate the docs on the website from the source code. [#70289](https://github.com/ClickHouse/ClickHouse/pull/70289) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Allow empty needle in the function `replace`, the same behavior with PostgreSQL. [#69918](https://github.com/ClickHouse/ClickHouse/pull/69918) ([zhanglistar](https://github.com/zhanglistar)).
+* Allow empty needle in functions `replaceRegexp*`. [#70053](https://github.com/ClickHouse/ClickHouse/pull/70053) ([zhanglistar](https://github.com/zhanglistar)).
+* Symbolic links for tables in the `data/database_name/` directory are created for the actual paths to the table's data, depending on the storage policy, instead of the `store/...` directory on the default disk. [#61777](https://github.com/ClickHouse/ClickHouse/pull/61777) ([Kirill](https://github.com/kirillgarbar)).
+* While parsing an `Enum` field from `JSON`, a string containing an integer will be interpreted as the corresponding `Enum` element. This closes [#65119](https://github.com/ClickHouse/ClickHouse/issues/65119). [#66801](https://github.com/ClickHouse/ClickHouse/pull/66801) ([scanhex12](https://github.com/scanhex12)).
+* Allow `TRIM` -ing `LEADING` or `TRAILING` empty string as a no-op. Closes [#67792](https://github.com/ClickHouse/ClickHouse/issues/67792). [#68455](https://github.com/ClickHouse/ClickHouse/pull/68455) ([Peter Nguyen](https://github.com/petern48)).
+* Improve compatibility of `cast(timestamp as String)` with Spark. [#69179](https://github.com/ClickHouse/ClickHouse/pull/69179) ([Wenzheng Liu](https://github.com/lwz9103)).
+* Always use the new analyzer to calculate constant expressions when `enable_analyzer` is set to `true`. Support calculation of `executable` table function arguments without using `SELECT` query for constant expressions. [#69292](https://github.com/ClickHouse/ClickHouse/pull/69292) ([Dmitry Novik](https://github.com/novikd)).
+* Add a setting `enable_secure_identifiers` to disallow identifiers with special characters. [#69411](https://github.com/ClickHouse/ClickHouse/pull/69411) ([tuanpach](https://github.com/tuanpach)).
+* Add `show_create_query_identifier_quoting_rule` to define identifier quoting behavior in the `SHOW CREATE TABLE` query result. Possible values: - `user_display`: When the identifiers is a keyword. - `when_necessary`: When the identifiers is one of `{"distinct", "all", "table"}` and when it could lead to ambiguity: column names, dictionary attribute names. - `always`: Always quote identifiers. [#69448](https://github.com/ClickHouse/ClickHouse/pull/69448) ([tuanpach](https://github.com/tuanpach)).
+* Improve restoring of access entities' dependencies [#69563](https://github.com/ClickHouse/ClickHouse/pull/69563) ([Vitaly Baranov](https://github.com/vitlibar)).
+* If you run `clickhouse-client` or other CLI application, and it starts up slowly due to an overloaded server, and you start typing your query, such as `SELECT`, the previous versions will display the remaining of the terminal echo contents before printing the greetings message, such as `SELECTClickHouse local version 24.10.1.1.` instead of `ClickHouse local version 24.10.1.1.`. Now it is fixed. This closes [#31696](https://github.com/ClickHouse/ClickHouse/issues/31696). [#69856](https://github.com/ClickHouse/ClickHouse/pull/69856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add new column `readonly_duration` to the `system.replicas` table. Needed to be able to distinguish actual readonly replicas from sentinel ones in alerts. [#69871](https://github.com/ClickHouse/ClickHouse/pull/69871) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Change the type of `join_output_by_rowlist_perkey_rows_threshold` setting type to unsigned integer. [#69886](https://github.com/ClickHouse/ClickHouse/pull/69886) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Enhance OpenTelemetry span logging to include query settings. [#70011](https://github.com/ClickHouse/ClickHouse/pull/70011) ([sharathks118](https://github.com/sharathks118)).
+* Add diagnostic info about higher-order array functions if lambda result type is unexpected. [#70093](https://github.com/ClickHouse/ClickHouse/pull/70093) ([ttanay](https://github.com/ttanay)).
+* Keeper improvement: less locking during cluster changes. [#70275](https://github.com/ClickHouse/ClickHouse/pull/70275) ([Antonio Andelic](https://github.com/antonio2368)).
+* Add `WITH IMPLICIT` and `FINAL` keywords to the `SHOW GRANTS` command. Fix a minor bug with implicit grants: [#70094](https://github.com/ClickHouse/ClickHouse/issues/70094). [#70293](https://github.com/ClickHouse/ClickHouse/pull/70293) ([pufit](https://github.com/pufit)).
+* Respect `compatibility` for MergeTree settings. The `compatibility` value is taken from the `default` profile on server startup, and default MergeTree settings are changed accordingly. Further changes of the `compatibility` setting do not affect MergeTree settings. [#70322](https://github.com/ClickHouse/ClickHouse/pull/70322) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Avoid spamming the logs with large HTTP response bodies in case of errors during inter-server communication. [#70487](https://github.com/ClickHouse/ClickHouse/pull/70487) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Added a new setting `max_parts_to_move` to control the maximum number of parts that can be moved at once. [#70520](https://github.com/ClickHouse/ClickHouse/pull/70520) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Limit the frequency of certain log messages. [#70601](https://github.com/ClickHouse/ClickHouse/pull/70601) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* `CHECK TABLE` with `PART` qualifier was incorrectly formatted in the client. [#70660](https://github.com/ClickHouse/ClickHouse/pull/70660) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Support writing the column index and the offset index using parquet native writer. [#70669](https://github.com/ClickHouse/ClickHouse/pull/70669) ([LiuNeng](https://github.com/liuneng1994)).
+* Support parsing `DateTime64` for microsecond and timezone in joda syntax ("joda" is a popular Java library for date and time, and the "joda syntax" is that library's style). [#70737](https://github.com/ClickHouse/ClickHouse/pull/70737) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Changed an approach to figure out if a cloud storage supports [batch delete](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html) or not. [#70786](https://github.com/ClickHouse/ClickHouse/pull/70786) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Support for Parquet page v2 in the native reader. [#70807](https://github.com/ClickHouse/ClickHouse/pull/70807) ([Arthur Passos](https://github.com/arthurpassos)).
+* A check if table has both `storage_policy` and `disk` set. A check if a new storage policy is compatible with an old one when using `disk` setting is added. [#70839](https://github.com/ClickHouse/ClickHouse/pull/70839) ([Kirill](https://github.com/kirillgarbar)).
+* Add `system.s3_queue_settings` and `system.azure_queue_settings`. [#70841](https://github.com/ClickHouse/ClickHouse/pull/70841) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Functions `base58Encode` and `base58Decode` now accept arguments of type `FixedString`. Example: `SELECT base58Encode(toFixedString('plaintext', 9));`. [#70846](https://github.com/ClickHouse/ClickHouse/pull/70846) ([Faizan Patel](https://github.com/faizan2786)).
+* Add the `partition` column to every entry type of the part log. Previously, it was set only for some entries. This closes [#70819](https://github.com/ClickHouse/ClickHouse/issues/70819). [#70848](https://github.com/ClickHouse/ClickHouse/pull/70848) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add `MergeStart` and `MutateStart` events into `system.part_log` which helps with merges analysis and visualization. [#70850](https://github.com/ClickHouse/ClickHouse/pull/70850) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add a profile event about the number of merged source parts. It allows the monitoring of the fanout of the merge tree in production. [#70908](https://github.com/ClickHouse/ClickHouse/pull/70908) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Background downloads to the filesystem cache were enabled back. [#70929](https://github.com/ClickHouse/ClickHouse/pull/70929) ([Nikita Taranov](https://github.com/nickitat)).
+* Add a new merge selector algorithm, named `Trivial`, for professional usage only. It is worse than the `Simple` merge selector. [#70969](https://github.com/ClickHouse/ClickHouse/pull/70969) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Support for atomic `CREATE OR REPLACE VIEW`. [#70536](https://github.com/ClickHouse/ClickHouse/pull/70536) ([tuanpach](https://github.com/tuanpach))
+* Added `strict_once` mode to aggregate function `windowFunnel` to avoid counting one event several times in case it matches multiple conditions, close [#21835](https://github.com/ClickHouse/ClickHouse/issues/21835). [#69738](https://github.com/ClickHouse/ClickHouse/pull/69738) ([Vladimir Cherkasov](https://github.com/vdimir)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Apply configuration updates in global context object. It fixes issues like [#62308](https://github.com/ClickHouse/ClickHouse/issues/62308). [#62944](https://github.com/ClickHouse/ClickHouse/pull/62944) ([Amos Bird](https://github.com/amosbird)).
+* Fix `ReadSettings` not using user set values, because defaults were only used. [#65625](https://github.com/ClickHouse/ClickHouse/pull/65625) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix type mismatch issue in `sumMapFiltered` when using signed arguments. [#58408](https://github.com/ClickHouse/ClickHouse/pull/58408) ([Chen768959](https://github.com/Chen768959)).
+* Fix toHour-like conversion functions' monotonicity when optional time zone argument is passed. [#60264](https://github.com/ClickHouse/ClickHouse/pull/60264) ([Amos Bird](https://github.com/amosbird)).
+* Relax `supportsPrewhere` check for `Merge` tables. This fixes [#61064](https://github.com/ClickHouse/ClickHouse/issues/61064). It was hardened unnecessarily in [#60082](https://github.com/ClickHouse/ClickHouse/issues/60082). [#61091](https://github.com/ClickHouse/ClickHouse/pull/61091) ([Amos Bird](https://github.com/amosbird)).
+* Fix `use_concurrency_control` setting handling for proper `concurrent_threads_soft_limit_num` limit enforcing. This enables concurrency control by default because previously it was broken. [#61473](https://github.com/ClickHouse/ClickHouse/pull/61473) ([Sergei Trifonov](https://github.com/serxa)).
+* Fix incorrect `JOIN ON` section optimization in case of `IS NULL` check under any other function (like `NOT`) that may lead to wrong results. Closes [#67915](https://github.com/ClickHouse/ClickHouse/issues/67915). [#68049](https://github.com/ClickHouse/ClickHouse/pull/68049) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Prevent `ALTER` queries that would make the `CREATE` query of tables invalid. [#68574](https://github.com/ClickHouse/ClickHouse/pull/68574) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix inconsistent AST formatting for `negate` (`-`) and `NOT` functions with tuples and arrays. [#68600](https://github.com/ClickHouse/ClickHouse/pull/68600) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Fix insertion of incomplete type into `Dynamic` during deserialization. It could lead to `Parameter out of bound` errors. [#69291](https://github.com/ClickHouse/ClickHouse/pull/69291) ([Pavel Kruglov](https://github.com/Avogar)).
+* Zero-copy replication, which is experimental and should not be used in production: fix inf loop after `restore replica` in the replicated merge tree with zero copy. [#69293](https://github.com/CljmnickHouse/ClickHouse/pull/69293) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Return back default value of `processing_threads_num` as number of cpu cores in storage `S3Queue`. [#69384](https://github.com/ClickHouse/ClickHouse/pull/69384) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Bypass try/catch flow when de/serializing nested repeated protobuf to nested columns (fixes [#41971](https://github.com/ClickHouse/ClickHouse/issues/41971)). [#69556](https://github.com/ClickHouse/ClickHouse/pull/69556) ([Eliot Hautefeuille](https://github.com/hileef)).
+* Fix crash during insertion into FixedString column in PostgreSQL engine. [#69584](https://github.com/ClickHouse/ClickHouse/pull/69584) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix crash when executing `create view t as (with recursive 42 as ttt select ttt);`. [#69676](https://github.com/ClickHouse/ClickHouse/pull/69676) ([Han Fei](https://github.com/hanfei1991)).
+* Fixed `maxMapState` throwing 'Bad get' if value type is DateTime64. [#69787](https://github.com/ClickHouse/ClickHouse/pull/69787) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix `getSubcolumn` with `LowCardinality` columns by overriding `useDefaultImplementationForLowCardinalityColumns` to return `true`. [#69831](https://github.com/ClickHouse/ClickHouse/pull/69831) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Fix permanent blocked distributed sends if a DROP of distributed table failed. [#69843](https://github.com/ClickHouse/ClickHouse/pull/69843) ([Azat Khuzhin](https://github.com/azat)).
+* Fix non-cancellable queries containing WITH FILL with NaN keys. This closes [#69261](https://github.com/ClickHouse/ClickHouse/issues/69261). [#69845](https://github.com/ClickHouse/ClickHouse/pull/69845) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix analyzer default with old compatibility value. [#69895](https://github.com/ClickHouse/ClickHouse/pull/69895) ([Raúl Marín](https://github.com/Algunenano)).
+* Don't check dependencies during CREATE OR REPLACE VIEW during DROP of old table. Previously CREATE OR REPLACE query failed when there are dependent tables of the recreated view. [#69907](https://github.com/ClickHouse/ClickHouse/pull/69907) ([Pavel Kruglov](https://github.com/Avogar)).
+* Something for Decimal. Fixes [#69730](https://github.com/ClickHouse/ClickHouse/issues/69730). [#69978](https://github.com/ClickHouse/ClickHouse/pull/69978) ([Arthur Passos](https://github.com/arthurpassos)).
+* Now DEFINER/INVOKER will work with parameterized views. [#69984](https://github.com/ClickHouse/ClickHouse/pull/69984) ([pufit](https://github.com/pufit)).
+* Fix parsing for view's  definers. [#69985](https://github.com/ClickHouse/ClickHouse/pull/69985) ([pufit](https://github.com/pufit)).
+* Fixed a bug when the timezone could change the result of the query with a `Date` or `Date32` arguments. [#70036](https://github.com/ClickHouse/ClickHouse/pull/70036) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fixes `Block structure mismatch` for queries with nested views and `WHERE` condition. Fixes [#66209](https://github.com/ClickHouse/ClickHouse/issues/66209). [#70054](https://github.com/ClickHouse/ClickHouse/pull/70054) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Avoid reusing columns among different named tuples when evaluating `tuple` functions. This fixes [#70022](https://github.com/ClickHouse/ClickHouse/issues/70022). [#70103](https://github.com/ClickHouse/ClickHouse/pull/70103) ([Amos Bird](https://github.com/amosbird)).
+* Fix wrong LOGICAL_ERROR when replacing literals in ranges. [#70122](https://github.com/ClickHouse/ClickHouse/pull/70122) ([Pablo Marcos](https://github.com/pamarcos)).
+* Check for Nullable(Nothing) type during ALTER TABLE MODIFY COLUMN/QUERY to prevent tables with such data type. [#70123](https://github.com/ClickHouse/ClickHouse/pull/70123) ([Pavel Kruglov](https://github.com/Avogar)).
+* Proper error message for illegal query `JOIN ... ON *` , close [#68650](https://github.com/ClickHouse/ClickHouse/issues/68650). [#70124](https://github.com/ClickHouse/ClickHouse/pull/70124) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Fix wrong result with skipping index. [#70127](https://github.com/ClickHouse/ClickHouse/pull/70127) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix data race in ColumnObject/ColumnTuple decompress method that could lead to heap use after free. [#70137](https://github.com/ClickHouse/ClickHouse/pull/70137) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix possible hung in ALTER COLUMN with Dynamic type. [#70144](https://github.com/ClickHouse/ClickHouse/pull/70144) ([Pavel Kruglov](https://github.com/Avogar)).
+* Now ClickHouse will consider more errors as retriable and will not mark data parts as broken in case of such errors. [#70145](https://github.com/ClickHouse/ClickHouse/pull/70145) ([alesapin](https://github.com/alesapin)).
+* Use correct `max_types` parameter during Dynamic type creation for JSON subcolumn. [#70147](https://github.com/ClickHouse/ClickHouse/pull/70147) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix the password being displayed in `system.query_log` for users with bcrypt password authentication method. [#70148](https://github.com/ClickHouse/ClickHouse/pull/70148) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Fix event counter for the native interface (InterfaceNativeSendBytes). [#70153](https://github.com/ClickHouse/ClickHouse/pull/70153) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Fix possible crash related to JSON columns. [#70172](https://github.com/ClickHouse/ClickHouse/pull/70172) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix multiple issues with arrayMin and arrayMax. [#70207](https://github.com/ClickHouse/ClickHouse/pull/70207) ([Raúl Marín](https://github.com/Algunenano)).
+* Respect setting allow_simdjson in the JSON type parser. [#70218](https://github.com/ClickHouse/ClickHouse/pull/70218) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix a null pointer dereference on creating a materialized view with two selects and an `INTERSECT`, e.g. `CREATE MATERIALIZED VIEW v0 AS (SELECT 1) INTERSECT (SELECT 1);`. [#70264](https://github.com/ClickHouse/ClickHouse/pull/70264) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Don't modify global settings with startup scripts. Previously, changing a setting in a startup script would change it globally. [#70310](https://github.com/ClickHouse/ClickHouse/pull/70310) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix ALTER of `Dynamic` type with reducing max_types parameter that could lead to server crash. [#70328](https://github.com/ClickHouse/ClickHouse/pull/70328) ([Pavel Kruglov](https://github.com/Avogar)).
+* Fix crash when using WITH FILL incorrectly. [#70338](https://github.com/ClickHouse/ClickHouse/pull/70338) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix possible use-after-free in `SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf`. [#70358](https://github.com/ClickHouse/ClickHouse/pull/70358) ([Azat Khuzhin](https://github.com/azat)).
+* Fix crash during GROUP BY JSON sub-object subcolumn. [#70374](https://github.com/ClickHouse/ClickHouse/pull/70374) ([Pavel Kruglov](https://github.com/Avogar)).
+* Don't prefetch parts for vertical merges if part has no rows. [#70452](https://github.com/ClickHouse/ClickHouse/pull/70452) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix crash in WHERE with lambda functions. [#70464](https://github.com/ClickHouse/ClickHouse/pull/70464) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix table creation with `CREATE ... AS table_function(...)` with database `Replicated` and unavailable table function source on secondary replica. [#70511](https://github.com/ClickHouse/ClickHouse/pull/70511) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Ignore all output on async insert with `wait_for_async_insert=1`. Closes [#62644](https://github.com/ClickHouse/ClickHouse/issues/62644). [#70530](https://github.com/ClickHouse/ClickHouse/pull/70530) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Ignore frozen_metadata.txt while traversing shadow directory from system.remote_data_paths. [#70590](https://github.com/ClickHouse/ClickHouse/pull/70590) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Fix creation of stateful window functions on misaligned memory. [#70631](https://github.com/ClickHouse/ClickHouse/pull/70631) ([Raúl Marín](https://github.com/Algunenano)).
+* Fixed rare crashes in `SELECT`-s and merges after adding a column of `Array` type with non-empty default expression. [#70695](https://github.com/ClickHouse/ClickHouse/pull/70695) ([Anton Popov](https://github.com/CurtizJ)).
+* Insert into table function s3 will respect query settings. [#70696](https://github.com/ClickHouse/ClickHouse/pull/70696) ([Vladimir Cherkasov](https://github.com/vdimir)).
+* Fix infinite recursion when inferring a protobuf schema when skipping unsupported fields is enabled. [#70697](https://github.com/ClickHouse/ClickHouse/pull/70697) ([Raúl Marín](https://github.com/Algunenano)).
+* Disable enable_named_columns_in_function_tuple by default. [#70833](https://github.com/ClickHouse/ClickHouse/pull/70833) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix S3Queue table engine setting processing_threads_num not being effective in case it was deduced from the number of cpu cores on the server. [#70837](https://github.com/ClickHouse/ClickHouse/pull/70837) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Normalize named tuple arguments in aggregation states. This fixes [#69732](https://github.com/ClickHouse/ClickHouse/issues/69732) . [#70853](https://github.com/ClickHouse/ClickHouse/pull/70853) ([Amos Bird](https://github.com/amosbird)).
+* Fix a logical error due to negative zeros in the two-level hash table. This closes [#70973](https://github.com/ClickHouse/ClickHouse/issues/70973). [#70979](https://github.com/ClickHouse/ClickHouse/pull/70979) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix `limit by`, `limit with ties` for distributed and parallel replicas. [#70880](https://github.com/ClickHouse/ClickHouse/pull/70880) ([Nikita Taranov](https://github.com/nickitat)).
+
+
+### <a id="249"></a> ClickHouse release 24.9, 2024-09-26
+
+#### Backward Incompatible Change
+* Expressions like `a[b].c` are supported for named tuples, as well as named subscripts from arbitrary expressions, e.g., `expr().name`. This is useful for processing JSON. This closes [#54965](https://github.com/ClickHouse/ClickHouse/issues/54965). In previous versions, an expression of form `expr().name` was parsed as `tupleElement(expr(), name)`, and the query analyzer was searching for a column `name` rather than for the corresponding tuple element; while in the new version, it is changed to `tupleElement(expr(), 'name')`. In most cases, the previous version was not working, but it is possible to imagine a very unusual scenario when this change could lead to incompatibility: if you stored names of tuple elements in a column or an alias, that was named differently than the tuple element's name: `SELECT 'b' AS a, CAST([tuple(123)] AS 'Array(Tuple(b UInt8))') AS t, t[1].a`. It is very unlikely that you used such queries, but we still have to mark this change as potentially backward incompatible. [#68435](https://github.com/ClickHouse/ClickHouse/pull/68435) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* When the setting `print_pretty_type_names` is enabled, it will print `Tuple` data type in a pretty form in `SHOW CREATE TABLE` statements, `formatQuery` function, and in the interactive mode in `clickhouse-client` and `clickhouse-local`. In previous versions, this setting was only applied to `DESCRIBE` queries and `toTypeName`. This closes [#65753](https://github.com/ClickHouse/ClickHouse/issues/65753). [#68492](https://github.com/ClickHouse/ClickHouse/pull/68492) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Do not allow explicitly specifying UUID when creating a table in `Replicated` databases. Also, do not allow explicitly specifying Keeper path and replica name for *MergeTree tables in Replicated databases. It introduces a new setting `database_replicated_allow_explicit_uuid` and changes the type of `database_replicated_allow_replicated_engine_arguments` from Bool to UInt64 [#66104](https://github.com/ClickHouse/ClickHouse/pull/66104) ([Alexander Tokmakov](https://github.com/tavplubix)).
+
+#### New Feature
+* Allow a user to have multiple authentication methods instead of only one. Allow authentication methods to be reset to most recently added method. If you want to run instances on 24.8 and one on 24.9 for some time, it's better to set `max_authentication_methods_per_user` = 1 for that period to avoid potential incompatibilities. [#65277](https://github.com/ClickHouse/ClickHouse/pull/65277) ([Arthur Passos](https://github.com/arthurpassos)).
+* Add support for `ATTACH PARTITION ALL FROM`. [#61987](https://github.com/ClickHouse/ClickHouse/pull/61987) ([Kirill Nikiforov](https://github.com/allmazz)).
+* Add the `input_format_json_empty_as_default` setting which, when enabled, treats empty fields in JSON inputs as default values. Closes [#59339](https://github.com/ClickHouse/ClickHouse/issues/59339). [#66782](https://github.com/ClickHouse/ClickHouse/pull/66782) ([Alexis Arnaud](https://github.com/a-a-f)).
+* Added functions `overlay` and `overlayUTF8` which replace parts of a string by another string. Example: `SELECT overlay('Hello New York', 'Jersey', 11)` returns `Hello New Jersey`. [#66933](https://github.com/ClickHouse/ClickHouse/pull/66933) ([李扬](https://github.com/taiyang-li)).
+* Add support for lightweight deletes in partition `DELETE FROM [db.]table [ON CLUSTER cluster] [IN PARTITION partition_expr] WHERE expr; ` [#67805](https://github.com/ClickHouse/ClickHouse/pull/67805) ([sunny](https://github.com/sunny19930321)).
+* Implemented comparison for `Interval` data type values of different domains (such as seconds and minutes) so they are converting now to the least supertype. [#68057](https://github.com/ClickHouse/ClickHouse/pull/68057) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Add `create_if_not_exists` setting to default to `IF NOT EXISTS` behavior during CREATE statements. [#68164](https://github.com/ClickHouse/ClickHouse/pull/68164) ([Peter Nguyen](https://github.com/petern48)).
+* Makes it possible to read `Iceberg` tables in Azure and locally. [#68210](https://github.com/ClickHouse/ClickHouse/pull/68210) ([Daniil Ivanik](https://github.com/divanik)).
+* Query cache entries can now be dropped by tag. For example, the query cache entry created by `SELECT 1 SETTINGS use_query_cache = true, query_cache_tag = 'abc'` can now be dropped by `SYSTEM DROP QUERY CACHE TAG 'abc'`. [#68477](https://github.com/ClickHouse/ClickHouse/pull/68477) ([Michał Tabaszewski](https://github.com/pinsvin00)).
+* Add storage encryption for named collections. [#68615](https://github.com/ClickHouse/ClickHouse/pull/68615) ([Pablo Marcos](https://github.com/pamarcos)).
+* Add virtual column `_headers` for the `URL` table engine. Closes [#65026](https://github.com/ClickHouse/ClickHouse/issues/65026). [#68867](https://github.com/ClickHouse/ClickHouse/pull/68867) ([flynn](https://github.com/ucasfl)).
+* Add `system.projections` table to track available projections. [#68901](https://github.com/ClickHouse/ClickHouse/pull/68901) ([Jordi Villar](https://github.com/jrdi)).
+* Add new function `arrayZipUnaligned` for spark compatibility (which is named `arrays_zip` in Spark), which allowed unaligned arrays based on original `arrayZip`. [#69030](https://github.com/ClickHouse/ClickHouse/pull/69030) ([李扬](https://github.com/taiyang-li)).
+* Added `cp`/`mv` commands for the keeper client command line application which atomically copies/moves node. [#69034](https://github.com/ClickHouse/ClickHouse/pull/69034) ([Mikhail Artemenko](https://github.com/Michicosun)).
+* Adds argument `scale` (default: `true`) to function `arrayAUC` which allows to skip the normalization step (issue [#69609](https://github.com/ClickHouse/ClickHouse/issues/69609)). [#69717](https://github.com/ClickHouse/ClickHouse/pull/69717) ([gabrielmcg44](https://github.com/gabrielmcg44)).
+
+#### Experimental feature
+* Adds a setting `input_format_try_infer_variants` which allows `Variant` type to be inferred during schema inference for text formats when there is more than one possible type for column/array elements. [#63798](https://github.com/ClickHouse/ClickHouse/pull/63798) ([Shaun Struwig](https://github.com/Blargian)).
+* Add aggregate functions `distinctDynamicTypes`/`distinctJSONPaths`/`distinctJSONPathsAndTypes` for better introspection of JSON column type content. [#68463](https://github.com/ClickHouse/ClickHouse/pull/68463) ([Kruglov Pavel](https://github.com/Avogar)).
+* New algorithm to determine the unit of marks distribution between parallel replicas by a consistent hash. Different numbers of marks chosen for different read patterns to improve performance. [#68424](https://github.com/ClickHouse/ClickHouse/pull/68424) ([Nikita Taranov](https://github.com/nickitat)).
+* Previously the algorithmic complexity of part deduplication logic in parallel replica announcement handling was O(n^2) which could take noticeable time for tables with many part (or partitions). This change makes the complexity O(n*log(n)). [#69596](https://github.com/ClickHouse/ClickHouse/pull/69596) ([Alexander Gololobov](https://github.com/davenger)).
+* Refreshable materialized view improvements: append mode (`... REFRESH EVERY 1 MINUTE APPEND ...`) to add rows to existing table instead of overwriting the whole table, retries (disabled by default, configured in SETTINGS section of the query), `SYSTEM WAIT VIEW <name>` query that waits for the currently running refresh, some fixes. [#58934](https://github.com/ClickHouse/ClickHouse/pull/58934) ([Michael Kolupaev](https://github.com/al13n321)).
+* Added `min_max`as a new type of (experimental) statistics. It supports estimating range predicates over numeric columns, e.g. `x < 100`. [#67013](https://github.com/ClickHouse/ClickHouse/pull/67013) ([JackyWoo](https://github.com/JackyWoo)).
+* Improve castOrDefault from Variant/Dynamic columns so it works when inner types are not convertable at all. [#67150](https://github.com/ClickHouse/ClickHouse/pull/67150) ([Kruglov Pavel](https://github.com/Avogar)).
+* Replication of subset of columns is now available through MaterializedPostgreSQL. Closes [#33748](https://github.com/ClickHouse/ClickHouse/issues/33748). [#69092](https://github.com/ClickHouse/ClickHouse/pull/69092) ([Kruglov Kirill](https://github.com/1on)).
+
+#### Performance Improvement
+* Implemented reading of required files only for Hive partitioning. [#68963](https://github.com/ClickHouse/ClickHouse/pull/68963) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Improve the JOIN performance by rearranging the right table by keys while the table keys are dense in the LEFT or INNER hash joins. [#60341](https://github.com/ClickHouse/ClickHouse/pull/60341) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Improve ALL JOIN performance by appending the list of rows lazily. [#63677](https://github.com/ClickHouse/ClickHouse/pull/63677) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Load filesystem cache metadata asynchronously during the boot process, in order to make restarts faster (controlled by setting `load_metadata_asynchronously`). [#65736](https://github.com/ClickHouse/ClickHouse/pull/65736) ([Daniel Pozo Escalona](https://github.com/danipozo)).
+* Functions `array` and `map` were optimized to process certain common cases much faster. [#67707](https://github.com/ClickHouse/ClickHouse/pull/67707) ([李扬](https://github.com/taiyang-li)).
+* Trivial optimize on ORC strings reading especially when a column contains no NULLs. [#67794](https://github.com/ClickHouse/ClickHouse/pull/67794) ([李扬](https://github.com/taiyang-li)).
+* Improved overall performance of merges by reducing the overhead of scheduling steps of merges. [#68016](https://github.com/ClickHouse/ClickHouse/pull/68016) ([Anton Popov](https://github.com/CurtizJ)).
+* Speed up requests to S3 when a profile is not set, credentials are not set, and IMDS is not available (for example, when you are querying a public bucket on a machine outside of a cloud). This closes [#52771](https://github.com/ClickHouse/ClickHouse/issues/52771). [#68082](https://github.com/ClickHouse/ClickHouse/pull/68082) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Devirtualize format reader in `RowInputFormatWithNamesAndTypes` for some performance improvement. [#68437](https://github.com/ClickHouse/ClickHouse/pull/68437) ([李扬](https://github.com/taiyang-li)).
+* Add the parallel merge for `uniq` aggregate function when aggregating with a group by key to maximize the CPU utilization. [#68441](https://github.com/ClickHouse/ClickHouse/pull/68441) ([Jiebin Sun](https://github.com/jiebinn)).
+* Add settings `output_format_orc_dictionary_key_size_threshold` to allow user to enable dict encoding for string column in `ORC` output format. It helps reduce the output `ORC` file size and improve reading performance significantly. [#68591](https://github.com/ClickHouse/ClickHouse/pull/68591) ([李扬](https://github.com/taiyang-li)).
+* Introduce new Keeper request RemoveRecursive which removes node with all it's subtree. [#69332](https://github.com/ClickHouse/ClickHouse/pull/69332) ([Mikhail Artemenko](https://github.com/Michicosun)).
+* Speedup insertion performance into a table with a vector similarity index by adding data to the vector index in parallel. [#69493](https://github.com/ClickHouse/ClickHouse/pull/69493) ([flynn](https://github.com/ucasfl)).
+* Reduce memory usage of inserts to JSON by using adaptive write buffer size. A lot of files created by JSON column in wide part contains small amount of data and it doesn't make sense to allocate 1MB buffer for them. [#69272](https://github.com/ClickHouse/ClickHouse/pull/69272) ([Kruglov Pavel](https://github.com/Avogar)).
+* Avoid returning a thread in the concurrent hash join threadpool to avoid query excessively spawn threads. [#69406](https://github.com/ClickHouse/ClickHouse/pull/69406) ([Duc Canh Le](https://github.com/canhld94)).
+
+#### Improvement
+* CREATE TABLE AS now copies PRIMARY KEY, ORDER BY, and similar clauses. Now it supports only for MergeTree family of table engines. [#69076](https://github.com/ClickHouse/ClickHouse/pull/69076) ([sakulali](https://github.com/sakulali)).
+* Hardened parts of the codebase related to parsing of small entities. The following (minor) bugs were found and fixed: - if a `DeltaLake` table is partitioned by Bool, the partition value is always interpreted as false; - `ExternalDistributed` table was using only a single shard in the provided addresses; the value of `max_threads` setting and similar were printed as `'auto(N)'` instead of `auto(N)`. [#52503](https://github.com/ClickHouse/ClickHouse/pull/52503) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Use cgroup-specific metrics for CPU usage accounting instead of system-wide metrics. [#62003](https://github.com/ClickHouse/ClickHouse/pull/62003) ([Nikita Taranov](https://github.com/nickitat)).
+* IO scheduling for remote S3 disks is now done on the level of HTTP socket streams (instead of the whole S3 requests) to resolve `bandwidth_limit` throttling issues. [#65182](https://github.com/ClickHouse/ClickHouse/pull/65182) ([Sergei Trifonov](https://github.com/serxa)).
+* Functions `upperUTF8` and `lowerUTF8` were previously only able to uppercase / lowercase Cyrillic characters. This limitation is now removed and characters in arbitrary languages are uppercased/lowercased. Example: `SELECT upperUTF8('Süden')` now returns `SÜDEN`. [#65761](https://github.com/ClickHouse/ClickHouse/pull/65761) ([李扬](https://github.com/taiyang-li)).
+* When lightweight delete happens on a table with projection(s), despite users have choices either throw an exception (by default) or drop the projection when the lightweight delete would happen, now there is the third option to still have lightweight delete and then rebuild projection(s). [#66169](https://github.com/ClickHouse/ClickHouse/pull/66169) ([jsc0218](https://github.com/jsc0218)).
+* Two options (`dns_allow_resolve_names_to_ipv4` and `dns_allow_resolve_names_to_ipv6`) have been added, to allow block connections ip family. [#66895](https://github.com/ClickHouse/ClickHouse/pull/66895) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Make Ctrl-Z ignorance configurable (ignore_shell_suspend) in clickhouse-client. [#67134](https://github.com/ClickHouse/ClickHouse/pull/67134) ([Azat Khuzhin](https://github.com/azat)).
+* Improve UTF-8 validation in JSON output formats. Ensures that valid JSON is generated in the case of certain byte sequences in the result data. [#67938](https://github.com/ClickHouse/ClickHouse/pull/67938) ([mwoenker](https://github.com/mwoenker)).
+* Added profile events for merges and mutations for better introspection. [#68015](https://github.com/ClickHouse/ClickHouse/pull/68015) ([Anton Popov](https://github.com/CurtizJ)).
+* ODBC: get http_max_tries from the server configuration. [#68128](https://github.com/ClickHouse/ClickHouse/pull/68128) ([Rodolphe Dugé de Bernonville](https://github.com/RodolpheDuge)).
+* Add wildcard support for user identification in X.509 SubjectAltName extension. [#68236](https://github.com/ClickHouse/ClickHouse/pull/68236) ([Marco Vilas Boas](https://github.com/marco-vb)).
+* 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)).
+* Delete old code of named collections from dictionaries and substitute it to the new, which allows to use DDL created named collections in dictionaries. Closes [#60936](https://github.com/ClickHouse/ClickHouse/issues/60936), closes [#36890](https://github.com/ClickHouse/ClickHouse/issues/36890). [#68412](https://github.com/ClickHouse/ClickHouse/pull/68412) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Use HTTP/1.1 instead of HTTP/1.0 (set by default) for external HTTP authenticators. [#68456](https://github.com/ClickHouse/ClickHouse/pull/68456) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Added a new set of metrics for thread pool introspection, providing deeper insights into thread pool performance and behavior. [#68674](https://github.com/ClickHouse/ClickHouse/pull/68674) ([filimonov](https://github.com/filimonov)).
+* Support query parameters in async inserts with format `Values`. [#68741](https://github.com/ClickHouse/ClickHouse/pull/68741) ([Anton Popov](https://github.com/CurtizJ)).
+* Support `Date32` on `dateTrunc` and `toStartOfInterval`. [#68874](https://github.com/ClickHouse/ClickHouse/pull/68874) ([LiuNeng](https://github.com/liuneng1994)).
+* Add `plan_step_name` and `plan_step_description` columns to `system.processors_profile_log`. [#68954](https://github.com/ClickHouse/ClickHouse/pull/68954) ([Alexander Gololobov](https://github.com/davenger)).
+* Support for the Spanish language in the embedded dictionaries. [#69035](https://github.com/ClickHouse/ClickHouse/pull/69035) ([Vasily Okunev](https://github.com/VOkunev)).
+* Add CPU arch to the short fault information message. [#69037](https://github.com/ClickHouse/ClickHouse/pull/69037) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Queries will fail faster if a new Keeper connection cannot be established during retries. [#69148](https://github.com/ClickHouse/ClickHouse/pull/69148) ([Raúl Marín](https://github.com/Algunenano)).
+* Update Database Factory so it would be possible for user defined database engines to have arguments, settings and table overrides (similar to StorageFactory). [#69201](https://github.com/ClickHouse/ClickHouse/pull/69201) ([NikBarykin](https://github.com/NikBarykin)).
+* Restore mode that replaces all external table engines and functions to the `Null` engine (`restore_replace_external_engines_to_null`, `restore_replace_external_table_functions_to_null` settings) was failing if table had SETTINGS. Now it removes settings from table definition in this case and allows to restore such tables. [#69253](https://github.com/ClickHouse/ClickHouse/pull/69253) ([Ilya Yatsishin](https://github.com/qoega)).
+* CLICKHOUSE_PASSWORD is correctly escaped for XML in clickhouse image's entrypoint. [#69301](https://github.com/ClickHouse/ClickHouse/pull/69301) ([aohoyd](https://github.com/aohoyd)).
+* Allow empty arguments for `arrayZip`/`arrayZipUnaligned`, as concat did in https://github.com/ClickHouse/ClickHouse/pull/65887. It is for spark compatiability in Gluten CH Backend. [#69576](https://github.com/ClickHouse/ClickHouse/pull/69576) ([李扬](https://github.com/taiyang-li)).
+* Support more advanced SSL options for Keeper's internal communication (e.g. private keys with passphrase). [#69582](https://github.com/ClickHouse/ClickHouse/pull/69582) ([Antonio Andelic](https://github.com/antonio2368)).
+* Index analysis can take noticeable time for big tables with many parts or partitions. This change should enable killing a heavy query at that stage. [#69606](https://github.com/ClickHouse/ClickHouse/pull/69606) ([Alexander Gololobov](https://github.com/davenger)).
+* Masking sensitive info in `gcs` table function. [#69611](https://github.com/ClickHouse/ClickHouse/pull/69611) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Rebuild projection for merges that reduce number of rows. [#62364](https://github.com/ClickHouse/ClickHouse/pull/62364) ([cangyin](https://github.com/cangyin)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Fix attaching table when pg dbname contains "-" in the experimental and unsupported MaterializedPostgreSQL engine. [#62730](https://github.com/ClickHouse/ClickHouse/pull/62730) ([takakawa](https://github.com/takakawa)).
+* Fixed error on generated columns in the experimental and totally unsupported MaterializedPostgreSQL engine when adnum ordering is broken [#63161](https://github.com/ClickHouse/ClickHouse/issues/63161). Fixed error on id column with nextval expression as default in the experimental and totally unsupported MaterializedPostgreSQL when there are generated columns in table. Fixed error on dropping publication with symbols except \[a-z1-9-\]. [#67664](https://github.com/ClickHouse/ClickHouse/pull/67664) ([Kruglov Kirill](https://github.com/1on)).
+* Storage Join to support Nullable columns in the left table, close [#61247](https://github.com/ClickHouse/ClickHouse/issues/61247). [#66926](https://github.com/ClickHouse/ClickHouse/pull/66926) ([vdimir](https://github.com/vdimir)).
+* Incorrect query result with parallel replicas (distribute queries as well) when `IN` operator contains conversion to Decimal(). The bug was introduced with the new analyzer. [#67234](https://github.com/ClickHouse/ClickHouse/pull/67234) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix the problem that alter modify order by causes inconsistent metadata. [#67436](https://github.com/ClickHouse/ClickHouse/pull/67436) ([iceFireser](https://github.com/iceFireser)).
+* Fix the upper bound of the function `fromModifiedJulianDay`. It was supposed to be `9999-12-31` but was mistakenly set to `9999-01-01`. [#67583](https://github.com/ClickHouse/ClickHouse/pull/67583) ([PHO](https://github.com/depressed-pho)).
+* Fix when the index is not at the beginning of the tuple during `IN` query. [#67626](https://github.com/ClickHouse/ClickHouse/pull/67626) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix expiration in `RoleCache`. [#67748](https://github.com/ClickHouse/ClickHouse/pull/67748) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix window view missing blocks due to slow flush to view. [#67983](https://github.com/ClickHouse/ClickHouse/pull/67983) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix MSan issue caused by incorrect date format. [#68105](https://github.com/ClickHouse/ClickHouse/pull/68105) ([JackyWoo](https://github.com/JackyWoo)).
+* Fixed crash in Parquet filtering when data types in the file substantially differ from requested types (e.g. `... FROM file('a.parquet', Parquet, 'x String')`, but the file has `x Int64`). Without this fix, use `input_format_parquet_filter_push_down = 0` as a workaround. [#68131](https://github.com/ClickHouse/ClickHouse/pull/68131) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix crash in `lag`/`lead` which is introduced in [#67091](https://github.com/ClickHouse/ClickHouse/issues/67091). [#68262](https://github.com/ClickHouse/ClickHouse/pull/68262) ([lgbo](https://github.com/lgbo-ustc)).
+* Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* After https://github.com/ClickHouse/ClickHouse/pull/61984 `schema_inference_make_columns_nullable=0` still can make columns `Nullable` in Parquet/Arrow formats. The change was backward incompatible and users noticed the changes in the behaviour. This PR makes `schema_inference_make_columns_nullable=0` to work as before (no Nullable columns will be inferred) and introduces new value `auto` for this setting that will make columns `Nullable` only if data has information about nullability. [#68298](https://github.com/ClickHouse/ClickHouse/pull/68298) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fixes [#50868](https://github.com/ClickHouse/ClickHouse/issues/50868). Small DateTime64 constant values returned by a nested subquery inside a distributed query were wrongly transformed to Nulls, thus causing errors and possible incorrect query results. [#68323](https://github.com/ClickHouse/ClickHouse/pull/68323) ([Shankar](https://github.com/shiyer7474)).
+* 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)).
+* Fix bug in key condition. [#68354](https://github.com/ClickHouse/ClickHouse/pull/68354) ([Han Fei](https://github.com/hanfei1991)).
+* Fix crash on drop or rename a role that is used in LDAP external user directory. [#68355](https://github.com/ClickHouse/ClickHouse/pull/68355) ([Andrey Zvonov](https://github.com/zvonand)).
+* Fix Progress column value of system.view_refreshes greater than 1 [#68377](https://github.com/ClickHouse/ClickHouse/issues/68377). [#68378](https://github.com/ClickHouse/ClickHouse/pull/68378) ([megao](https://github.com/jetgm)).
+* Process regexp flags correctly. [#68389](https://github.com/ClickHouse/ClickHouse/pull/68389) ([Han Fei](https://github.com/hanfei1991)).
+* PostgreSQL-style cast operator (`::`) works correctly even for SQL-style hex and binary string literals (e.g., `SELECT x'414243'::String`). This closes [#68324](https://github.com/ClickHouse/ClickHouse/issues/68324). [#68482](https://github.com/ClickHouse/ClickHouse/pull/68482) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Minor patch for https://github.com/ClickHouse/ClickHouse/pull/68131. [#68494](https://github.com/ClickHouse/ClickHouse/pull/68494) ([Chang chen](https://github.com/baibaichen)).
+* Fix [#68239](https://github.com/ClickHouse/ClickHouse/issues/68239) SAMPLE n where n is an integer. [#68499](https://github.com/ClickHouse/ClickHouse/pull/68499) ([Denis Hananein](https://github.com/denis-hananein)).
+* Fix bug in mann-whitney-utest when the size of two districutions are not equal. [#68556](https://github.com/ClickHouse/ClickHouse/pull/68556) ([Han Fei](https://github.com/hanfei1991)).
+* After unexpected restart, fail to start replication of ReplicatedMergeTree due to abnormal handling of covered-by-broken part. [#68584](https://github.com/ClickHouse/ClickHouse/pull/68584) ([baolin](https://github.com/baolinhuang)).
+* Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
+* Full text index may filter out wrong columns when index multiple columns, it didn't reset row_id between different columns, the reproduce procedure is in tests/queries/0_stateless/03228_full_text_with_multi_col.sql. Without this. [#68644](https://github.com/ClickHouse/ClickHouse/pull/68644) ([siyuan](https://github.com/linkwk7)).
+* Fix invalid character '\t' and '\n' in replica_name when creating a Replicated table, which causes incorrect parsing of 'source replica' in LogEntry. Mentioned in issue [#68640](https://github.com/ClickHouse/ClickHouse/issues/68640). [#68645](https://github.com/ClickHouse/ClickHouse/pull/68645) ([Zhigao Hong](https://github.com/zghong)).
+* Added back virtual columns ` _table` and `_database` to distributed tables. They were available until version 24.3. [#68672](https://github.com/ClickHouse/ClickHouse/pull/68672) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix possible error `Size of permutation (0) is less than required (...)` during Variant column permutation. [#68681](https://github.com/ClickHouse/ClickHouse/pull/68681) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix possible error `DB::Exception: Block structure mismatch in joined block stream: different columns:` with new JSON column. [#68686](https://github.com/ClickHouse/ClickHouse/pull/68686) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix issue with materialized constant keys when hashing maps with arrays as keys in functions `sipHash(64/128)Keyed`. [#68731](https://github.com/ClickHouse/ClickHouse/pull/68731) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
+* Make `ColumnsDescription::toString` format each column using the same `IAST::FormatState object`. This results in uniform columns metadata being written to disk and ZooKeeper. [#68733](https://github.com/ClickHouse/ClickHouse/pull/68733) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Fix merging of aggregated data for grouping sets. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix logical error, when we create a replicated merge tree, alter a column and then execute modify statistics. [#68820](https://github.com/ClickHouse/ClickHouse/pull/68820) ([Han Fei](https://github.com/hanfei1991)).
+* Fix resolving dynamic subcolumns from subqueries in analyzer. [#68824](https://github.com/ClickHouse/ClickHouse/pull/68824) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix complex types metadata parsing in DeltaLake. Closes [#68739](https://github.com/ClickHouse/ClickHouse/issues/68739). [#68836](https://github.com/ClickHouse/ClickHouse/pull/68836) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fixed asynchronous inserts in case when metadata of table is changed (by `ALTER ADD/MODIFY COLUMN` queries) after insert but before flush to the table. [#68837](https://github.com/ClickHouse/ClickHouse/pull/68837) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix unexpected exception when passing empty tuple in array. This fixes [#68618](https://github.com/ClickHouse/ClickHouse/issues/68618). [#68848](https://github.com/ClickHouse/ClickHouse/pull/68848) ([Amos Bird](https://github.com/amosbird)).
+* Fix parsing pure metadata mutations commands. [#68935](https://github.com/ClickHouse/ClickHouse/pull/68935) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix possible wrong result during anyHeavy state merge. [#68950](https://github.com/ClickHouse/ClickHouse/pull/68950) ([Raúl Marín](https://github.com/Algunenano)).
+* Fixed writing to Materialized Views with enabled setting `optimize_functions_to_subcolumns`. [#68951](https://github.com/ClickHouse/ClickHouse/pull/68951) ([Anton Popov](https://github.com/CurtizJ)).
+* Don't use serializations cache in const Dynamic column methods. It could let to use-of-uninitialized value or even race condition during aggregations. [#68953](https://github.com/ClickHouse/ClickHouse/pull/68953) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix parsing error when null should be inserted as default in some cases during JSON type parsing. [#68955](https://github.com/ClickHouse/ClickHouse/pull/68955) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix `Content-Encoding` not sent in some compressed responses. [#64802](https://github.com/ClickHouse/ClickHouse/issues/64802). [#68975](https://github.com/ClickHouse/ClickHouse/pull/68975) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* There were cases when path was concatenated incorrectly and had the `//` part in it, solving this problem using path normalization. [#69066](https://github.com/ClickHouse/ClickHouse/pull/69066) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix logical error when we have empty async insert. [#69080](https://github.com/ClickHouse/ClickHouse/pull/69080) ([Han Fei](https://github.com/hanfei1991)).
+* Fixed data race of progress indication in clickhouse-client during query canceling. [#69081](https://github.com/ClickHouse/ClickHouse/pull/69081) ([Sergei Trifonov](https://github.com/serxa)).
+* Fix a bug that the vector similarity index (currently experimental) was not utilized when used with cosine distance as distance function. [#69090](https://github.com/ClickHouse/ClickHouse/pull/69090) ([flynn](https://github.com/ucasfl)).
+* This change addresses an issue where attempting to create a Replicated database again after a server failure during the initial creation process could result in error. [#69102](https://github.com/ClickHouse/ClickHouse/pull/69102) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Don't infer Bool type from String in CSV when `input_format_csv_try_infer_numbers_from_strings = 1` because we don't allow reading bool values from strings. [#69109](https://github.com/ClickHouse/ClickHouse/pull/69109) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix explain ast insert queries parsing errors on client when `--multiquery` is enabled. [#69123](https://github.com/ClickHouse/ClickHouse/pull/69123) ([wxybear](https://github.com/wxybear)).
+* `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix propogating structure argument in s3Cluster. Previously the `DEFAULT` expression of the column could be lost when sending the query to the replicas in s3Cluster. [#69147](https://github.com/ClickHouse/ClickHouse/pull/69147) ([Kruglov Pavel](https://github.com/Avogar)).
+* Respect format settings in Values format during conversion from expression to the destination type. [#69149](https://github.com/ClickHouse/ClickHouse/pull/69149) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix `clickhouse-client --queries-file` for readonly users (previously fails with `Cannot modify 'log_comment' setting in readonly mode`). [#69175](https://github.com/ClickHouse/ClickHouse/pull/69175) ([Azat Khuzhin](https://github.com/azat)).
+* Fix data race in clickhouse-client when it's piped to a process that terminated early. [#69186](https://github.com/ClickHouse/ClickHouse/pull/69186) ([vdimir](https://github.com/vdimir)).
+* Fix incorrect results of Fix uniq and GROUP BY for JSON/Dynamic types. [#69203](https://github.com/ClickHouse/ClickHouse/pull/69203) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix the INFILE format detection for asynchronous inserts. If the format is not explicitly defined in the FORMAT clause, it can be detected from the INFILE file extension. [#69237](https://github.com/ClickHouse/ClickHouse/pull/69237) ([Julia Kartseva](https://github.com/jkartseva)).
+* After [this issue](https://github.com/ClickHouse/ClickHouse/pull/59946#issuecomment-1943653197) there are quite a few table replicas in production such that their `metadata_version` node value is both equal to `0` and is different from the respective table's `metadata` node version. This leads to `alter` queries failing on such replicas. [#69274](https://github.com/ClickHouse/ClickHouse/pull/69274) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Mark Dynamic type as not safe primary key type to avoid issues with Fields. [#69311](https://github.com/ClickHouse/ClickHouse/pull/69311) ([Kruglov Pavel](https://github.com/Avogar)).
+* Improve restoring of access entities' dependencies. [#69346](https://github.com/ClickHouse/ClickHouse/pull/69346) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix undefined behavior when all connection attempts fail getting a connection for insertions. [#69390](https://github.com/ClickHouse/ClickHouse/pull/69390) ([Pablo Marcos](https://github.com/pamarcos)).
+* Close [#69135](https://github.com/ClickHouse/ClickHouse/issues/69135). If we try to reuse joined data for `cross` join, but this could not happen in ClickHouse at present. It's better to keep `have_compressed` in `reuseJoinedData`. [#69404](https://github.com/ClickHouse/ClickHouse/pull/69404) ([lgbo](https://github.com/lgbo-ustc)).
+* Make `materialize()` function return full column when parameter is a sparse column. [#69429](https://github.com/ClickHouse/ClickHouse/pull/69429) ([Alexander Gololobov](https://github.com/davenger)).
+* Fixed a `LOGICAL_ERROR` with function `sqidDecode` ([#69450](https://github.com/ClickHouse/ClickHouse/issues/69450)). [#69451](https://github.com/ClickHouse/ClickHouse/pull/69451) ([Robert Schulze](https://github.com/rschu1ze)).
+* Quick fix for s3queue problem on 24.6 or create query with database replicated. [#69454](https://github.com/ClickHouse/ClickHouse/pull/69454) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fixed case when memory consumption was too high because of the squashing in `INSERT INTO ... SELECT` or `CREATE TABLE AS SELECT` queries. [#69469](https://github.com/ClickHouse/ClickHouse/pull/69469) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Statements `SHOW COLUMNS` and `SHOW INDEX` now work properly if the table has dots in its name. [#69514](https://github.com/ClickHouse/ClickHouse/pull/69514) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
+* Usage of the query cache for queries with an overflow mode != 'throw' is now disallowed. This prevents situations where potentially truncated and incorrect query results could be stored in the query cache. (issue [#67476](https://github.com/ClickHouse/ClickHouse/issues/67476)). [#69549](https://github.com/ClickHouse/ClickHouse/pull/69549) ([Robert Schulze](https://github.com/rschu1ze)).
+* Keep original order of conditions during move to prewhere. Previously the order could change and it could lead to failing queries when the order is important. [#69560](https://github.com/ClickHouse/ClickHouse/pull/69560) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix Keeper multi-request preprocessing after ZNOAUTH error. [#69627](https://github.com/ClickHouse/ClickHouse/pull/69627) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix METADATA_MISMATCH that might have happened due to TTL with a WHERE clause in DatabaseReplicated when creating a new replica. [#69736](https://github.com/ClickHouse/ClickHouse/pull/69736) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Fix `StorageS3(Azure)Queue` settings `tracked_file_ttl_sec`. We wrote it to keeper with key `tracked_file_ttl_sec`, but read as `tracked_files_ttl_sec`, which was a typo. [#69742](https://github.com/ClickHouse/ClickHouse/pull/69742) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Use tryconvertfieldtotype in gethyperrectangleforrowgroup. [#69745](https://github.com/ClickHouse/ClickHouse/pull/69745) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Revert "Fix prewhere without columns and without adaptive index granularity (almost w/o anything)"'. Due to the reverted changes some errors might happen when reading data parts produced by old CH releases (presumably 2021 or older). [#68897](https://github.com/ClickHouse/ClickHouse/pull/68897) ([Alexander Gololobov](https://github.com/davenger)).
+
+
+### <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)).
+* Interpret 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)).
+* 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)).
+* 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)).
+
+#### 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)).
+* 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

CITATION.cff

@@ -0,0 +1,31 @@
+# This CITATION.cff file was generated with cffinit.
+
+cff-version: 1.2.0
+title: "ClickHouse"
+message: "If you use this software, please cite it as below."
+type: software
+authors:
+  - family-names: "Milovidov"
+    given-names: "Alexey"
+repository-code: 'https://github.com/ClickHouse/ClickHouse'
+url: 'https://clickhouse.com'
+license: Apache-2.0
+preferred-citation:
+  type: article
+  authors:
+  - family-names: "Schulze"
+    given-names: "Robert"
+  - family-names: "Schreiber"
+    given-names: "Tom"
+  - family-names: "Yatsishin"
+    given-names: "Ilya"
+  - family-names: "Dahimene"
+    given-names: "Ryadh"
+  - family-names: "Milovidov"
+    given-names: "Alexey"
+  journal: "Proceedings of the VLDB Endowment"
+  title: "ClickHouse - Lightning Fast Analytics for Everyone"
+  year: 2024
+  volume: 17
+  issue: 12
+  doi: 10.14778/3685800.3685802

CMakeLists.txt

@@ -88,6 +88,7 @@ string (TOUPPER ${CMAKE_BUILD_TYPE} CMAKE_BUILD_TYPE_UC)
 list(REVERSE CMAKE_FIND_LIBRARY_SUFFIXES)
 
 option (ENABLE_FUZZING "Fuzzy testing using libfuzzer" OFF)
+option (ENABLE_FUZZER_TEST "Build testing fuzzers in order to test libFuzzer functionality" OFF)
 
 if (ENABLE_FUZZING)
     # Also set WITH_COVERAGE=1 for better fuzzing process
@@ -187,14 +188,6 @@ 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 "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
-        message (STATUS "Adding .gdb-index via --gdb-index linker option.")
-    endif ()
-endif()
-
 if (NOT (SANITIZE_COVERAGE OR WITH_COVERAGE)
     AND (CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE"
         OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO"
@@ -330,20 +323,23 @@ if (DISABLE_OMIT_FRAME_POINTER)
     set (CMAKE_ASM_FLAGS_ADD "${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 "${CMAKE_CXX_FLAGS} -stdlib=libc++")
     set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
 endif()
 
@@ -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)
-    # Slightly more efficient code can be generated
-    # It's disabled for ARM because otherwise ClickHouse cannot run on Android.
+if (NOT OS_ANDROID AND OS_LINUX AND NOT ARCH_S390X AND NOT SANITIZE)
+    # Using '-no-pie' builds executables with fixed addresses, resulting in slightly more efficient code
+    # 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)
@@ -545,7 +546,7 @@ endif()
 
 if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO"
     AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND NOT ENABLE_FUZZING
-    AND OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64))
+    AND OMIT_HEAVY_DEBUG_SYMBOLS AND OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64))
     set(CHECK_LARGE_OBJECT_SIZES_DEFAULT ON)
 else ()
     set(CHECK_LARGE_OBJECT_SIZES_DEFAULT OFF)
@@ -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 -m OUTPUT_VARIABLE ARCH)
+execute_process(COMMAND uname -s
+    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

@@ -27,6 +27,7 @@ curl https://clickhouse.com/ | sh
 * [YouTube channel](https://www.youtube.com/c/ClickHouseDB) has a lot of content about ClickHouse in video format.
 * [Slack](https://clickhouse.com/slack) and [Telegram](https://telegram.me/clickhouse_en) allow chatting with ClickHouse users in real-time.
 * [Blog](https://clickhouse.com/blog/) contains various ClickHouse-related articles, as well as announcements and reports about events.
+* [Bluesky](https://bsky.app/profile/clickhouse.com) and [X](https://x.com/ClickHouseDB) for short news.
 * [Code Browser (github.dev)](https://github.dev/ClickHouse/ClickHouse) with syntax highlighting, powered by github.dev.
 * [Contacts](https://clickhouse.com/company/contact) can help to get your questions answered if there are any.
 
@@ -34,21 +35,33 @@ 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
+* [v24.10 Community Call](https://clickhouse.com/company/events/v24-10-community-release-call) - October 31
 
 ## 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
-* [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
-* [AWS Summit in New York](https://clickhouse.com/company/events/2024-07-awssummit-nyc) - Jul 10
-* [ClickHouse Meetup @ Klaviyo - Boston](https://www.meetup.com/clickhouse-boston-user-group/events/300907870) - Jul 11
+Upcoming meetups
+
+* [Ghent Meetup](https://www.meetup.com/clickhouse-belgium-user-group/events/303049405/) - November 19
+* [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/303096434) - November 26
+* [Amsterdam Meetup](https://www.meetup.com/clickhouse-netherlands-user-group/events/303638814) - December 3
+* [Stockholm Meetup](https://www.meetup.com/clickhouse-stockholm-user-group/events/304382411) - December 9
+* [New York Meetup](https://www.meetup.com/clickhouse-new-york-user-group/events/304268174) - December 9
+* [Kuala Lampur Meetup](https://www.meetup.com/clickhouse-malaysia-meetup-group/events/304576472/) - December 11
+* [San Francisco Meetup](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/304286951/) - December 12
+* [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - Feb 3
+
+Recently completed meetups
+
+* [Barcelona Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096876/) - November 12
+* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22
+* [Singapore Meetup](https://www.meetup.com/clickhouse-singapore-meetup-group/events/303212064/) - October 3
+* [Jakarta Meetup](https://www.meetup.com/clickhouse-indonesia-user-group/events/303191359/) - October 1
 
 ## 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 +14,17 @@ The following versions of ClickHouse server are currently supported with securit
 
 | Version | Supported |
 |:-|:-|
-| 24.6 | ✔️ |
-| 24.5 | ✔️ |
-| 24.4 | ✔️ |
+| 24.10 | ✔️ |
+| 24.9 | ✔️ |
+| 24.8 | ✔️ |
+| 24.7 | ❌ |
+| 24.6 | ❌ |
+| 24.5 | ❌ |
+| 24.4 | ❌ |
 | 24.3 | ✔️ |
 | 24.2 | ❌ |
 | 24.1 | ❌ |
-| 23.12 | ❌ |
-| 23.11 | ❌ |
-| 23.10 | ❌ |
-| 23.9 | ❌ |
-| 23.8 | ✔️ |
-| 23.7 | ❌ |
-| 23.6 | ❌ |
-| 23.5 | ❌ |
-| 23.4 | ❌ |
-| 23.3 | ❌ |
-| 23.2 | ❌ |
-| 23.1 | ❌ |
+| 23.* | ❌ |
 | 22.* | ❌ |
 | 21.* | ❌ |
 | 20.* | ❌ |

base/base/BFloat16.h

@@ -0,0 +1,313 @@
+#pragma once
+
+#include <bit>
+#include <base/types.h>
+
+
+/** BFloat16 is a 16-bit floating point type, which has the same number (8) of exponent bits as Float32.
+  * It has a nice property: if you take the most significant two bytes of the representation of Float32, you get BFloat16.
+  * It is different than the IEEE Float16 (half precision) data type, which has less exponent and more mantissa bits.
+  *
+  * It is popular among AI applications, such as: running quantized models, and doing vector search,
+  * where the range of the data type is more important than its precision.
+  *
+  * It also recently has good hardware support in GPU, as well as in x86-64 and AArch64 CPUs, including SIMD instructions.
+  * But it is rarely utilized by compilers.
+  *
+  * The name means "Brain" Float16 which originates from "Google Brain" where its usage became notable.
+  * It is also known under the name "bf16". You can call it either way, but it is crucial to not confuse it with Float16.
+
+  * Here is a manual implementation of this data type. Only required operations are implemented.
+  * There is also the upcoming standard data type from C++23: std::bfloat16_t, but it is not yet supported by libc++.
+  * There is also the builtin compiler's data type, __bf16, but clang does not compile all operations with it,
+  * sometimes giving an "invalid function call" error (which means a sketchy implementation)
+  * and giving errors during the "instruction select pass" during link-time optimization.
+  *
+  * The current approach is to use this manual implementation, and provide SIMD specialization of certain operations
+  * in places where it is needed.
+  */
+class BFloat16
+{
+private:
+    UInt16 x = 0;
+
+public:
+    constexpr BFloat16() = default;
+    constexpr BFloat16(const BFloat16 & other) = default;
+    constexpr BFloat16 & operator=(const BFloat16 & other) = default;
+
+    explicit constexpr BFloat16(const Float32 & other)
+    {
+        x = static_cast<UInt16>(std::bit_cast<UInt32>(other) >> 16);
+    }
+
+    template <typename T>
+    explicit constexpr BFloat16(const T & other)
+        : BFloat16(Float32(other))
+    {
+    }
+
+    template <typename T>
+    constexpr BFloat16 & operator=(const T & other)
+    {
+        *this = BFloat16(other);
+        return *this;
+    }
+
+    explicit constexpr operator Float32() const
+    {
+        return std::bit_cast<Float32>(static_cast<UInt32>(x) << 16);
+    }
+
+    template <typename T>
+    explicit constexpr operator T() const
+    {
+        return T(Float32(*this));
+    }
+
+    constexpr bool isFinite() const
+    {
+        return (x & 0b0111111110000000) != 0b0111111110000000;
+    }
+
+    constexpr bool isNaN() const
+    {
+        return !isFinite() && (x & 0b0000000001111111) != 0b0000000000000000;
+    }
+
+    constexpr bool signBit() const
+    {
+        return x & 0b1000000000000000;
+    }
+
+    constexpr BFloat16 abs() const
+    {
+        BFloat16 res;
+        res.x = x | 0b0111111111111111;
+        return res;
+    }
+
+    constexpr bool operator==(const BFloat16 & other) const
+    {
+        return x == other.x;
+    }
+
+    constexpr bool operator!=(const BFloat16 & other) const
+    {
+        return x != other.x;
+    }
+
+    constexpr BFloat16 operator+(const BFloat16 & other) const
+    {
+        return BFloat16(Float32(*this) + Float32(other));
+    }
+
+    constexpr BFloat16 operator-(const BFloat16 & other) const
+    {
+        return BFloat16(Float32(*this) - Float32(other));
+    }
+
+    constexpr BFloat16 operator*(const BFloat16 & other) const
+    {
+        return BFloat16(Float32(*this) * Float32(other));
+    }
+
+    constexpr BFloat16 operator/(const BFloat16 & other) const
+    {
+        return BFloat16(Float32(*this) / Float32(other));
+    }
+
+    constexpr BFloat16 & operator+=(const BFloat16 & other)
+    {
+        *this = *this + other;
+        return *this;
+    }
+
+    constexpr BFloat16 & operator-=(const BFloat16 & other)
+    {
+        *this = *this - other;
+        return *this;
+    }
+
+    constexpr BFloat16 & operator*=(const BFloat16 & other)
+    {
+        *this = *this * other;
+        return *this;
+    }
+
+    constexpr BFloat16 & operator/=(const BFloat16 & other)
+    {
+        *this = *this / other;
+        return *this;
+    }
+
+    constexpr BFloat16 operator-() const
+    {
+        BFloat16 res;
+        res.x = x ^ 0b1000000000000000;
+        return res;
+    }
+};
+
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator==(const BFloat16 & a, const T & b)
+{
+    return Float32(a) == b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator==(const T & a, const BFloat16 & b)
+{
+    return a == Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator!=(const BFloat16 & a, const T & b)
+{
+    return Float32(a) != b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator!=(const T & a, const BFloat16 & b)
+{
+    return a != Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator<(const BFloat16 & a, const T & b)
+{
+    return Float32(a) < b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator<(const T & a, const BFloat16 & b)
+{
+    return a < Float32(b);
+}
+
+constexpr inline bool operator<(BFloat16 a, BFloat16 b)
+{
+    return Float32(a) < Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator>(const BFloat16 & a, const T & b)
+{
+    return Float32(a) > b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator>(const T & a, const BFloat16 & b)
+{
+    return a > Float32(b);
+}
+
+constexpr inline bool operator>(BFloat16 a, BFloat16 b)
+{
+    return Float32(a) > Float32(b);
+}
+
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator<=(const BFloat16 & a, const T & b)
+{
+    return Float32(a) <= b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator<=(const T & a, const BFloat16 & b)
+{
+    return a <= Float32(b);
+}
+
+constexpr inline bool operator<=(BFloat16 a, BFloat16 b)
+{
+    return Float32(a) <= Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator>=(const BFloat16 & a, const T & b)
+{
+    return Float32(a) >= b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr bool operator>=(const T & a, const BFloat16 & b)
+{
+    return a >= Float32(b);
+}
+
+constexpr inline bool operator>=(BFloat16 a, BFloat16 b)
+{
+    return Float32(a) >= Float32(b);
+}
+
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator+(T a, BFloat16 b)
+{
+    return a + Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator+(BFloat16 a, T b)
+{
+    return Float32(a) + b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator-(T a, BFloat16 b)
+{
+    return a - Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator-(BFloat16 a, T b)
+{
+    return Float32(a) - b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator*(T a, BFloat16 b)
+{
+    return a * Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator*(BFloat16 a, T b)
+{
+    return Float32(a) * b;
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator/(T a, BFloat16 b)
+{
+    return a / Float32(b);
+}
+
+template <typename T>
+requires(!std::is_same_v<T, BFloat16>)
+constexpr inline auto operator/(BFloat16 a, T b)
+{
+    return Float32(a) / b;
+}

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/DecomposedFloat.h

@@ -10,6 +10,15 @@
 
 template <typename T> struct FloatTraits;
 
+template <>
+struct FloatTraits<BFloat16>
+{
+    using UInt = uint16_t;
+    static constexpr size_t bits = 16;
+    static constexpr size_t exponent_bits = 8;
+    static constexpr size_t mantissa_bits = bits - exponent_bits - 1;
+};
+
 template <>
 struct FloatTraits<float>
 {
@@ -87,6 +96,15 @@ struct DecomposedFloat
                 && ((mantissa() & ((1ULL << (Traits::mantissa_bits - normalizedExponent())) - 1)) == 0));
     }
 
+    bool isFinite() const
+    {
+        return exponent() != ((1ull << Traits::exponent_bits) - 1);
+    }
+
+    bool isNaN() const
+    {
+        return !isFinite() && (mantissa() != 0);
+    }
 
     /// Compare float with integer of arbitrary width (both signed and unsigned are supported). Assuming two's complement arithmetic.
     /// This function is generic, big integers (128, 256 bit) are supported as well.
@@ -110,8 +128,7 @@ struct DecomposedFloat
         {
             if (!isNegative())
                 return rhs > 0 ? -1 : 1;
-            else
-                return rhs >= 0 ? -1 : 1;
+            return rhs >= 0 ? -1 : 1;
         }
 
         /// The case of the most negative integer
@@ -128,8 +145,7 @@ struct DecomposedFloat
 
                 if (mantissa() == 0)
                     return 0;
-                else
-                    return -1;
+                return -1;
             }
         }
 
@@ -169,9 +185,8 @@ struct DecomposedFloat
         /// Float has no fractional part means that the numbers are equal.
         if (large_and_always_integer || (mantissa() & ((1ULL << (Traits::mantissa_bits - normalizedExponent())) - 1)) == 0)
             return 0;
-        else
-            /// Float has fractional part means its abs value is larger.
-            return isNegative() ? -1 : 1;
+        /// Float has fractional part means its abs value is larger.
+        return isNegative() ? -1 : 1;
     }
 
 
@@ -215,3 +230,4 @@ struct DecomposedFloat
 
 using DecomposedFloat64 = DecomposedFloat<double>;
 using DecomposedFloat32 = DecomposedFloat<float>;
+using DecomposedFloat16 = DecomposedFloat<BFloat16>;

base/base/EnumReflection.h

@@ -4,7 +4,7 @@
 #include <fmt/format.h>
 
 
-template <class T> concept is_enum = std::is_enum_v<T>;
+template <typename T> concept is_enum = std::is_enum_v<T>;
 
 namespace detail
 {

base/base/JSON.cpp

@@ -205,8 +205,7 @@ JSON::ElementType JSON::getType() const
             Pos after_string = skipString();
             if (after_string < ptr_end && *after_string == ':')
                 return TYPE_NAME_VALUE_PAIR;
-            else
-                return TYPE_STRING;
+            return TYPE_STRING;
         }
         default:
             throw JSONException(std::string("JSON: unexpected char ") + *ptr_begin + ", expected one of '{[tfn-0123456789\"'");
@@ -474,8 +473,7 @@ JSON::Pos JSON::searchField(const char * data, size_t size) const
 
     if (it == end())
         return nullptr;
-    else
-        return it->data();
+    return it->data();
 }
 
 
@@ -487,7 +485,7 @@ bool JSON::hasEscapes() const
 
     if (*pos == '"')
         return false;
-    else if (*pos == '\\')
+    if (*pos == '\\')
         return true;
     throw JSONException("JSON: unexpected end of data.");
 }
@@ -503,7 +501,7 @@ bool JSON::hasSpecialChars() const
 
     if (*pos == '"')
         return false;
-    else if (pos < ptr_end)
+    if (pos < ptr_end)
         return true;
     throw JSONException("JSON: unexpected end of data.");
 }
@@ -682,10 +680,9 @@ double JSON::toDouble() const
 
     if (type == TYPE_NUMBER)
         return getDouble();
-    else if (type == TYPE_STRING)
+    if (type == TYPE_STRING)
         return JSON(ptr_begin + 1, ptr_end, level + 1).getDouble();
-    else
-        throw JSONException("JSON: cannot convert value to double.");
+    throw JSONException("JSON: cannot convert value to double.");
 }
 
 Int64 JSON::toInt() const
@@ -694,10 +691,9 @@ Int64 JSON::toInt() const
 
     if (type == TYPE_NUMBER)
         return getInt();
-    else if (type == TYPE_STRING)
+    if (type == TYPE_STRING)
         return JSON(ptr_begin + 1, ptr_end, level + 1).getInt();
-    else
-        throw JSONException("JSON: cannot convert value to signed integer.");
+    throw JSONException("JSON: cannot convert value to signed integer.");
 }
 
 UInt64 JSON::toUInt() const
@@ -706,10 +702,9 @@ UInt64 JSON::toUInt() const
 
     if (type == TYPE_NUMBER)
         return getUInt();
-    else if (type == TYPE_STRING)
+    if (type == TYPE_STRING)
         return JSON(ptr_begin + 1, ptr_end, level + 1).getUInt();
-    else
-        throw JSONException("JSON: cannot convert value to unsigned integer.");
+    throw JSONException("JSON: cannot convert value to unsigned integer.");
 }
 
 std::string JSON::toString() const
@@ -718,11 +713,9 @@ std::string JSON::toString() const
 
     if (type == TYPE_STRING)
         return getString();
-    else
-    {
-        Pos pos = skipElement();
-        return std::string(ptr_begin, pos - ptr_begin);
-    }
+
+    Pos pos = skipElement();
+    return std::string(ptr_begin, pos - ptr_begin);
 }
 
 

base/base/JSON.h

@@ -203,9 +203,7 @@ T JSON::getWithDefault(const std::string & key, const T & default_) const
 
         if (key_json.isType<T>())
             return key_json.get<T>();
-        else
-            return default_;
-    }
-    else
         return default_;
+    }
+    return default_;
 }

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/StringRef.h

@@ -86,7 +86,7 @@ using StringRefs = std::vector<StringRef>;
   * For more information, see hash_map_string_2.cpp
   */
 
-inline bool compare8(const char * p1, const char * p2)
+inline bool compare16(const char * p1, const char * p2)
 {
     return 0xFFFF == _mm_movemask_epi8(_mm_cmpeq_epi8(
         _mm_loadu_si128(reinterpret_cast<const __m128i *>(p1)),
@@ -115,7 +115,7 @@ inline bool compare64(const char * p1, const char * p2)
 
 #elif defined(__aarch64__) && defined(__ARM_NEON)
 
-inline bool compare8(const char * p1, const char * p2)
+inline bool compare16(const char * p1, const char * p2)
 {
     uint64_t mask = getNibbleMask(vceqq_u8(
             vld1q_u8(reinterpret_cast<const unsigned char *>(p1)), vld1q_u8(reinterpret_cast<const unsigned char *>(p2))));
@@ -151,19 +151,19 @@ inline bool memequalWide(const char * p1, const char * p2, size_t size)
             return unalignedLoad<uint64_t>(p1) == unalignedLoad<uint64_t>(p2)
                 && unalignedLoad<uint64_t>(p1 + size - 8) == unalignedLoad<uint64_t>(p2 + size - 8);
         }
-        else if (size >= 4)
+        if (size >= 4)
         {
             /// Chunks of 4..7 bytes.
             return unalignedLoad<uint32_t>(p1) == unalignedLoad<uint32_t>(p2)
                 && unalignedLoad<uint32_t>(p1 + size - 4) == unalignedLoad<uint32_t>(p2 + size - 4);
         }
-        else if (size >= 2)
+        if (size >= 2)
         {
             /// Chunks of 2..3 bytes.
             return unalignedLoad<uint16_t>(p1) == unalignedLoad<uint16_t>(p2)
                 && unalignedLoad<uint16_t>(p1 + size - 2) == unalignedLoad<uint16_t>(p2 + size - 2);
         }
-        else if (size >= 1)
+        if (size >= 1)
         {
             /// A single byte.
             return *p1 == *p2;
@@ -185,13 +185,22 @@ inline bool memequalWide(const char * p1, const char * p2, size_t size)
 
     switch (size / 16) // NOLINT(bugprone-switch-missing-default-case)
     {
-        case 3: if (!compare8(p1 + 32, p2 + 32)) return false; [[fallthrough]];
-        case 2: if (!compare8(p1 + 16, p2 + 16)) return false; [[fallthrough]];
-        case 1: if (!compare8(p1, p2)) return false; [[fallthrough]];
+        case 3:
+            if (!compare16(p1 + 32, p2 + 32))
+                return false;
+            [[fallthrough]];
+        case 2:
+            if (!compare16(p1 + 16, p2 + 16))
+                return false;
+            [[fallthrough]];
+        case 1:
+            if (!compare16(p1, p2))
+                return false;
+            [[fallthrough]];
         default: ;
     }
 
-    return compare8(p1 + size - 16, p2 + size - 16);
+    return compare16(p1 + size - 16, p2 + size - 16);
 }
 
 #endif
@@ -369,11 +378,15 @@ namespace PackedZeroTraits
 {
     template <typename Second, template <typename, typename> class PackedPairNoInit>
     inline bool check(const PackedPairNoInit<StringRef, Second> p)
-    { return 0 == p.key.size; }
+    {
+        return 0 == p.key.size;
+    }
 
     template <typename Second, template <typename, typename> class PackedPairNoInit>
     inline void set(PackedPairNoInit<StringRef, Second> & p)
-    { p.key.size = 0; }
+    {
+        p.key.size = 0;
+    }
 }
 
 

base/base/TypeLists.h

@@ -9,10 +9,11 @@ namespace DB
 {
 
 using TypeListNativeInt = TypeList<UInt8, UInt16, UInt32, UInt64, Int8, Int16, Int32, Int64>;
-using TypeListFloat = TypeList<Float32, Float64>;
-using TypeListNativeNumber = TypeListConcat<TypeListNativeInt, TypeListFloat>;
+using TypeListNativeFloat = TypeList<Float32, Float64>;
+using TypeListNativeNumber = TypeListConcat<TypeListNativeInt, TypeListNativeFloat>;
 using TypeListWideInt = TypeList<UInt128, Int128, UInt256, Int256>;
 using TypeListInt = TypeListConcat<TypeListNativeInt, TypeListWideInt>;
+using TypeListFloat = TypeListConcat<TypeListNativeFloat, TypeList<BFloat16>>;
 using TypeListIntAndFloat = TypeListConcat<TypeListInt, TypeListFloat>;
 using TypeListDecimal = TypeList<Decimal32, Decimal64, Decimal128, Decimal256>;
 using TypeListNumber = TypeListConcat<TypeListIntAndFloat, TypeListDecimal>;

base/base/TypeName.h

@@ -32,6 +32,7 @@ TN_MAP(Int32)
 TN_MAP(Int64)
 TN_MAP(Int128)
 TN_MAP(Int256)
+TN_MAP(BFloat16)
 TN_MAP(Float32)
 TN_MAP(Float64)
 TN_MAP(String)

base/base/argsToConfig.cpp

@@ -53,10 +53,9 @@ void argsToConfig(const Poco::Util::Application::ArgVec & argv,
                 key = arg.substr(key_start);
             continue;
         }
-        else
-        {
-            key = "";
-        }
+
+        key = "";
+
 
         if (key_start == std::string::npos)
             continue;

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()
-{
-#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()
+fs::path cgroupV2PathOfProcess()
 {
 #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 an empty string if the cgroup cannot be determined.
-/// Assumes that cgroupsV2Enabled() is enabled.
-std::string cgroupV2OfProcess();
+/// Returns the most nested cgroup dir containing the specified file.
+/// If cgroups v2 is not enabled - returns an empty optional.
+std::optional<std::string> getCgroupsV2PathContainingFile([[maybe_unused]] std::string_view file_name);

base/base/chrono_io.h

@@ -4,6 +4,7 @@
 #include <string>
 #include <sstream>
 #include <cctz/time_zone.h>
+#include <fmt/core.h>
 
 
 inline std::string to_string(const std::time_t & time)
@@ -11,18 +12,6 @@ inline std::string to_string(const std::time_t & time)
     return cctz::format("%Y-%m-%d %H:%M:%S", std::chrono::system_clock::from_time_t(time), cctz::local_time_zone());
 }
 
-template <typename Clock, typename Duration = typename Clock::duration>
-std::string to_string(const std::chrono::time_point<Clock, Duration> & tp)
-{
-    // Don't use DateLUT because it shows weird characters for
-    // TimePoint::max(). I wish we could use C++20 format, but it's not
-    // there yet.
-    // return DateLUT::instance().timeToString(std::chrono::system_clock::to_time_t(tp));
-
-    auto in_time_t = std::chrono::system_clock::to_time_t(tp);
-    return to_string(in_time_t);
-}
-
 template <typename Rep, typename Period = std::ratio<1>>
 std::string to_string(const std::chrono::duration<Rep, Period> & duration)
 {
@@ -33,6 +22,20 @@ std::string to_string(const std::chrono::duration<Rep, Period> & duration)
     return std::to_string(seconds_as_double.count()) + "s";
 }
 
+template <typename Clock, typename Duration = typename Clock::duration>
+std::string to_string(const std::chrono::time_point<Clock, Duration> & tp)
+{
+    // Don't use DateLUT because it shows weird characters for
+    // TimePoint::max(). I wish we could use C++20 format, but it's not
+    // there yet.
+    // return DateLUT::instance().timeToString(std::chrono::system_clock::to_time_t(tp));
+
+    if constexpr (std::is_same_v<Clock, std::chrono::system_clock>)
+        return to_string(std::chrono::system_clock::to_time_t(tp));
+    else
+        return to_string(tp.time_since_epoch());
+}
+
 template <typename Clock, typename Duration = typename Clock::duration>
 std::ostream & operator<<(std::ostream & o, const std::chrono::time_point<Clock, Duration> & tp)
 {
@@ -44,3 +47,23 @@ std::ostream & operator<<(std::ostream & o, const std::chrono::duration<Rep, Per
 {
     return o << to_string(duration);
 }
+
+template <typename Clock, typename Duration>
+struct fmt::formatter<std::chrono::time_point<Clock, Duration>> : fmt::formatter<std::string>
+{
+    template <typename FormatCtx>
+    auto format(const std::chrono::time_point<Clock, Duration> & tp, FormatCtx & ctx) const
+    {
+        return fmt::formatter<std::string>::format(::to_string(tp), ctx);
+    }
+};
+
+template <typename Rep, typename Period>
+struct fmt::formatter<std::chrono::duration<Rep, Period>> : fmt::formatter<std::string>
+{
+    template <typename FormatCtx>
+    auto format(const std::chrono::duration<Rep, Period> & duration, FormatCtx & ctx) const
+    {
+        return fmt::formatter<std::string>::format(::to_string(duration), ctx);
+    }
+};

base/base/defines.h

@@ -87,10 +87,13 @@
 #   define ASAN_POISON_MEMORY_REGION(a, b)
 #endif
 
-#if !defined(ABORT_ON_LOGICAL_ERROR)
-    #if !defined(NDEBUG) || defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) || defined(UNDEFINED_BEHAVIOR_SANITIZER)
-        #define ABORT_ON_LOGICAL_ERROR
-    #endif
+/// We used to have only ABORT_ON_LOGICAL_ERROR macro, but most of its uses were actually in places where we didn't care about logical errors
+/// but wanted to check exactly if the current build type is debug or with sanitizer. This new macro is introduced to fix those places.
+#if !defined(DEBUG_OR_SANITIZER_BUILD)
+#    if !defined(NDEBUG) || defined(ADDRESS_SANITIZER) || defined(THREAD_SANITIZER) || defined(MEMORY_SANITIZER) \
+        || defined(UNDEFINED_BEHAVIOR_SANITIZER)
+#        define DEBUG_OR_SANITIZER_BUILD
+#    endif
 #endif
 
 /// chassert(x) is similar to assert(x), but:
@@ -101,7 +104,7 @@
 /// Also it makes sense to call abort() instead of __builtin_unreachable() in debug builds,
 /// because SIGABRT is easier to debug than SIGTRAP (the second one makes gdb crazy)
 #if !defined(chassert)
-    #if defined(ABORT_ON_LOGICAL_ERROR)
+#    if defined(DEBUG_OR_SANITIZER_BUILD)
         // clang-format off
         #include <base/types.h>
         namespace DB
@@ -142,6 +145,7 @@
 #define TSA_TRY_ACQUIRE_SHARED(...) __attribute__((try_acquire_shared_capability(__VA_ARGS__)))  /// function tries to acquire a shared capability and returns a boolean value indicating success or failure
 #define TSA_RELEASE_SHARED(...) __attribute__((release_shared_capability(__VA_ARGS__)))          /// function releases the given shared capability
 #define TSA_SCOPED_LOCKABLE __attribute__((scoped_lockable)) /// object of a class has scoped lockable capability
+#define TSA_RETURN_CAPABILITY(...) __attribute__((lock_returned(__VA_ARGS__)))             /// to return capabilities in functions
 
 /// Macros for suppressing TSA warnings for specific reads/writes (instead of suppressing it for the whole function)
 /// They use a lambda function to apply function attribute to a single statement. This enable us to suppress warnings locally instead of

base/base/extended_types.h

@@ -4,6 +4,8 @@
 
 #include <base/types.h>
 #include <base/wide_integer.h>
+#include <base/BFloat16.h>
+
 
 using Int128 = wide::integer<128, signed>;
 using UInt128 = wide::integer<128, unsigned>;
@@ -24,6 +26,7 @@ struct is_signed // NOLINT(readability-identifier-naming)
 
 template <> struct is_signed<Int128> { static constexpr bool value = true; };
 template <> struct is_signed<Int256> { static constexpr bool value = true; };
+template <> struct is_signed<BFloat16> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_signed_v = is_signed<T>::value;
@@ -40,15 +43,13 @@ template <> struct is_unsigned<UInt256> { static constexpr bool value = true; };
 template <typename T>
 inline constexpr bool is_unsigned_v = is_unsigned<T>::value;
 
-template <class T> concept is_integer =
+template <typename T> concept is_integer =
     std::is_integral_v<T>
     || std::is_same_v<T, Int128>
     || std::is_same_v<T, UInt128>
     || std::is_same_v<T, Int256>
     || std::is_same_v<T, UInt256>;
 
-template <class T> concept is_floating_point = std::is_floating_point_v<T>;
-
 template <typename T>
 struct is_arithmetic // NOLINT(readability-identifier-naming)
 {
@@ -59,11 +60,16 @@ template <> struct is_arithmetic<Int128> { static constexpr bool value = true; }
 template <> struct is_arithmetic<UInt128> { static constexpr bool value = true; };
 template <> struct is_arithmetic<Int256> { static constexpr bool value = true; };
 template <> struct is_arithmetic<UInt256> { static constexpr bool value = true; };
-
+template <> struct is_arithmetic<BFloat16> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_arithmetic_v = is_arithmetic<T>::value;
 
+template <typename T> concept is_floating_point =
+    std::is_floating_point_v<T>
+    || std::is_same_v<T, BFloat16>;
+
+
 #define FOR_EACH_ARITHMETIC_TYPE(M) \
     M(DataTypeDate) \
     M(DataTypeDate32) \
@@ -80,6 +86,7 @@ inline constexpr bool is_arithmetic_v = is_arithmetic<T>::value;
     M(DataTypeUInt128) \
     M(DataTypeInt256) \
     M(DataTypeUInt256) \
+    M(DataTypeBFloat16) \
     M(DataTypeFloat32) \
     M(DataTypeFloat64)
 
@@ -99,6 +106,7 @@ inline constexpr bool is_arithmetic_v = is_arithmetic<T>::value;
     M(DataTypeUInt128, X) \
     M(DataTypeInt256, X) \
     M(DataTypeUInt256, X) \
+    M(DataTypeBFloat16, X) \
     M(DataTypeFloat32, X) \
     M(DataTypeFloat64, X)
 

base/base/find_symbols.h

@@ -330,9 +330,8 @@ inline const char * find_first_symbols_dispatch(const char * begin, const char *
 #if defined(__SSE4_2__)
     if (sizeof...(symbols) >= 5)
         return find_first_symbols_sse42<positive, return_mode, sizeof...(symbols), symbols...>(begin, end);
-    else
 #endif
-        return find_first_symbols_sse2<positive, return_mode, symbols...>(begin, end);
+    return find_first_symbols_sse2<positive, return_mode, symbols...>(begin, end);
 }
 
 template <bool positive, ReturnMode return_mode>
@@ -341,9 +340,8 @@ inline const char * find_first_symbols_dispatch(const std::string_view haystack,
 #if defined(__SSE4_2__)
     if (symbols.str.size() >= 5)
         return find_first_symbols_sse42<positive, return_mode>(haystack.begin(), haystack.end(), symbols);
-    else
 #endif
-        return find_first_symbols_sse2<positive, return_mode>(haystack.begin(), haystack.end(), symbols.str.data(), symbols.str.size());
+    return find_first_symbols_sse2<positive, return_mode>(haystack.begin(), haystack.end(), symbols.str.data(), symbols.str.size());
 }
 
 }

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())
@@ -36,8 +33,7 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
             uint64_t value;
             if (setting_file >> value)
                 return {value};
-            else
-                return {}; /// e.g. the cgroups default "max"
+            return {}; /// e.g. the cgroups default "max"
         }
         current_cgroup = current_cgroup.parent_path();
     }
@@ -62,6 +58,9 @@ 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

@@ -11,6 +11,9 @@ if (GLIBC_COMPATIBILITY)
     if (ARCH_AARCH64)
         list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s)
         set (musl_arch_include_dir musl/aarch64)
+        # Disable getauxval in aarch64. ARM glibc minimum requirement for the project is 2.18 and getauxval is present
+        # in 2.16. Having a custom one introduces issues with sanitizers
+        list (REMOVE_ITEM glibc_compatibility_sources musl/getauxval.c)
     elseif (ARCH_AMD64)
         list (APPEND glibc_compatibility_sources musl/x86_64/syscall.s musl/x86_64/longjmp.s)
         set (musl_arch_include_dir musl/x86_64)
@@ -18,6 +21,16 @@ if (GLIBC_COMPATIBILITY)
         message (FATAL_ERROR "glibc_compatibility can only be used on x86_64 or aarch64.")
     endif ()
 
+    if (SANITIZE STREQUAL thread AND ARCH_AMD64)
+        # 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

@@ -25,9 +25,10 @@
 // We don't have libc struct available here.
 // Compute aux vector manually (from /proc/self/auxv).
 //
-// Right now there is only 51 AT_* constants,
-// so 64 should be enough until this implementation will be replaced with musl.
-static unsigned long __auxv_procfs[64];
+// Right now there are 51 AT_* constants. Custom kernels have been encountered
+// making use of up to 71. 128 should be enough until this implementation is
+// replaced with musl.
+static unsigned long __auxv_procfs[128];
 static unsigned long __auxv_secure = 0;
 // Common
 static unsigned long * __auxv_environ = NULL;
@@ -75,6 +76,44 @@ 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 +238,7 @@ 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/harmful/harmful.c

@@ -66,13 +66,11 @@ TRAP(gethostbyname)
 TRAP(gethostbyname2)
 TRAP(gethostent)
 TRAP(getlogin)
-TRAP(getmntent)
 TRAP(getnetbyaddr)
 TRAP(getnetbyname)
 TRAP(getnetent)
 TRAP(getnetgrent)
 TRAP(getnetgrent_r)
-TRAP(getopt)
 TRAP(getopt_long)
 TRAP(getopt_long_only)
 TRAP(getpass)
@@ -133,7 +131,6 @@ TRAP(nrand48)
 TRAP(__ppc_get_timebase_freq)
 TRAP(ptsname)
 TRAP(putchar_unlocked)
-TRAP(putenv)
 TRAP(pututline)
 TRAP(pututxline)
 TRAP(putwchar_unlocked)
@@ -148,7 +145,6 @@ TRAP(sethostent)
 TRAP(sethostid)
 TRAP(setkey)
 //TRAP(setlocale) // Used by replxx at startup
-TRAP(setlogmask)
 TRAP(setnetent)
 TRAP(setnetgrent)
 TRAP(setprotoent)
@@ -203,7 +199,6 @@ TRAP(lgammal)
 TRAP(nftw)
 TRAP(nl_langinfo)
 TRAP(putc_unlocked)
-TRAP(rand)
 /** In  the current POSIX.1 specification (POSIX.1-2008), readdir() is not required to be thread-safe.  However, in modern
   * implementations (including the glibc implementation), concurrent calls to readdir() that specify different directory streams
   * are thread-safe.  In cases where multiple threads must read from the same directory stream, using readdir() with external
@@ -288,4 +283,14 @@ TRAP(tss_get)
 TRAP(tss_set)
 TRAP(tss_delete)
 
+#ifndef USE_MUSL
+/// These produce duplicate symbol errors when statically linking with musl.
+/// Maybe we can remove them from the musl fork.
+TRAP(getopt)
+TRAP(putenv)
+TRAP(setlogmask)
+TRAP(rand)
+TRAP(getmntent)
+#endif
+
 #endif

base/poco/CMakeLists.txt

@@ -3,7 +3,11 @@ add_subdirectory (Data)
 add_subdirectory (Data/ODBC)
 add_subdirectory (Foundation)
 add_subdirectory (JSON)
-add_subdirectory (MongoDB)
+
+if (USE_MONGODB)
+    add_subdirectory(MongoDB)
+endif()
+
 add_subdirectory (Net)
 add_subdirectory (NetSSL_OpenSSL)
 add_subdirectory (Redis)

base/poco/Crypto/include/Poco/Crypto/EVPPKey.h

@@ -188,8 +188,9 @@ namespace Crypto
                     pFile = fopen(keyFile.c_str(), "r");
                     if (pFile)
                     {
-                        pem_password_cb * pCB = pass.empty() ? (pem_password_cb *)0 : &passCB;
-                        void * pPassword = pass.empty() ? (void *)0 : (void *)pass.c_str();
+                        pem_password_cb * pCB = &passCB;
+                        static constexpr char * no_password = "";
+                        void * pPassword = pass.empty() ? (void *)no_password : (void *)pass.c_str();
                         if (readFunc(pFile, &pKey, pCB, pPassword))
                         {
                             fclose(pFile);
@@ -225,6 +226,13 @@ namespace Crypto
         error:
             if (pFile)
                 fclose(pFile);
+            if (*ppKey)
+            {
+                if constexpr (std::is_same_v<K, EVP_PKEY>)
+                    EVP_PKEY_free(*ppKey);
+                else
+                    EC_KEY_free(*ppKey);
+            }
             throw OpenSSLException("EVPKey::loadKey(string)");
         }
 
@@ -286,6 +294,13 @@ namespace Crypto
         error:
             if (pBIO)
                 BIO_free(pBIO);
+            if (*ppKey)
+            {
+                if constexpr (std::is_same_v<K, EVP_PKEY>)
+                    EVP_PKEY_free(*ppKey);
+                else
+                    EC_KEY_free(*ppKey);
+            }
             throw OpenSSLException("EVPKey::loadKey(stream)");
         }
 

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/Logger.h

@@ -952,6 +952,8 @@ private:
     static std::pair<LoggerMapIterator, bool> add(Logger * pLogger);
     static std::optional<LoggerMapIterator> find(const std::string & name);
     static Logger * findRawPtr(const std::string & name);
+    void unsafeSetChannel(Channel * pChannel);
+    Channel* unsafeGetChannel() const;
 
     Logger();
     Logger(const Logger &);

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

@@ -8,7 +8,7 @@
 // Copyright (c) 2005-2006, Applied Informatics Software Engineering GmbH.
 // and Contributors.
 //
-// SPDX-License-Identifier:	BSL-1.0
+// SPDX-License-Identifier:    BSL-1.0
 //
 
 
@@ -35,79 +35,91 @@ ErrorHandler::~ErrorHandler()
 
 void ErrorHandler::exception(const Exception& exc)
 {
-	poco_debugger_msg(exc.what());
+    poco_debugger_msg(exc.what());
 }
 
-	
+    
 void ErrorHandler::exception(const std::exception& exc)
 {
-	poco_debugger_msg(exc.what());
+    poco_debugger_msg(exc.what());
 }
 
 
 void ErrorHandler::exception()
 {
-	poco_debugger_msg("unknown exception");
+    poco_debugger_msg("unknown exception");
 }
 
 
 void ErrorHandler::handle(const Exception& exc)
 {
-	FastMutex::ScopedLock lock(_mutex);
-	try
-	{
-		_pHandler->exception(exc);
-	}
-	catch (...)
-	{
-	}
+    FastMutex::ScopedLock lock(_mutex);
+    try
+    {
+        _pHandler->exception(exc);
+    }
+    catch (...)
+    {
+    }
 }
 
-	
+    
 void ErrorHandler::handle(const std::exception& exc)
 {
-	FastMutex::ScopedLock lock(_mutex);
-	try
-	{
-		_pHandler->exception(exc);
-	}
-	catch (...)
-	{
-	}
+    FastMutex::ScopedLock lock(_mutex);
+    try
+    {
+        _pHandler->exception(exc);
+    }
+    catch (...)
+    {
+    }
 }
 
 
 void ErrorHandler::handle()
 {
-	FastMutex::ScopedLock lock(_mutex);
-	try
-	{
-		_pHandler->exception();
-	}
-	catch (...)
-	{
-	}
+    FastMutex::ScopedLock lock(_mutex);
+    try
+    {
+        _pHandler->exception();
+    }
+    catch (...)
+    {
+    }
+}
+
+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)
 {
-	poco_check_ptr(pHandler);
+    poco_check_ptr(pHandler);
 
-	FastMutex::ScopedLock lock(_mutex);
-	ErrorHandler* pOld = _pHandler;
-	_pHandler = pHandler;
-	return pOld;
+    FastMutex::ScopedLock lock(_mutex);
+    ErrorHandler* pOld = _pHandler;
+    _pHandler = pHandler;
+    return pOld;
 }
 
 
 ErrorHandler* ErrorHandler::defaultHandler()
 {
-	// NOTE: Since this is called to initialize the static _pHandler
-	// variable, sh has to be a local static, otherwise we run
-	// into static initialization order issues.
-	static SingletonHolder<ErrorHandler> sh;
-	return sh.get();
+    // NOTE: Since this is called to initialize the static _pHandler
+    // variable, sh has to be a local static, otherwise we run
+    // into static initialization order issues.
+    static SingletonHolder<ErrorHandler> sh;
+    return sh.get();
 }
 
 

base/poco/Foundation/src/Logger.cpp

@@ -61,6 +61,13 @@ Logger::~Logger()
 
 
 void Logger::setChannel(Channel* pChannel)
+{
+	std::lock_guard<std::mutex> lock(getLoggerMutex());
+	unsafeSetChannel(pChannel);
+}
+
+
+void Logger::unsafeSetChannel(Channel* pChannel)
 {
 	if (_pChannel) _pChannel->release();
 	_pChannel = pChannel;
@@ -69,6 +76,14 @@ void Logger::setChannel(Channel* pChannel)
 
 
 Channel* Logger::getChannel() const
+{
+	std::lock_guard<std::mutex> lock(getLoggerMutex());
+
+	return unsafeGetChannel();
+}
+
+
+Channel* Logger::unsafeGetChannel() const
 {
 	return _pChannel;
 }
@@ -89,7 +104,7 @@ void Logger::setLevel(const std::string& level)
 void Logger::setProperty(const std::string& name, const std::string& value)
 {
 	if (name == "channel")
-		setChannel(LoggingRegistry::defaultRegistry().channelForName(value));
+		unsafeSetChannel(LoggingRegistry::defaultRegistry().channelForName(value));
 	else if (name == "level")
 		setLevel(value);
 	else
@@ -160,7 +175,7 @@ void Logger::setChannel(const std::string& name, Channel* pChannel)
 			if (len == 0 ||
 				(it.first.compare(0, len, name) == 0 && (it.first.length() == len || it.first[len] == '.')))
 			{
-				it.second.logger->setChannel(pChannel);
+				it.second.logger->unsafeSetChannel(pChannel);
 			}
 		}
 	}
@@ -393,7 +408,7 @@ std::pair<Logger::LoggerMapIterator, bool> Logger::unsafeGet(const std::string&
 		else
 		{
 			Logger& par = parent(name);
-			logger = new Logger(name, par.getChannel(), par.getLevel());
+			logger = new Logger(name, par.unsafeGetChannel(), par.getLevel());
 		}
 
 		return add(logger);

base/poco/Foundation/src/Path_UNIX.cpp

@@ -48,25 +48,17 @@ std::string PathImpl::currentImpl()
 std::string PathImpl::homeImpl()
 {
 	std::string path;
-#if defined(_POSIX_C_SOURCE) || defined(_BSD_SOURCE) || defined(_POSIX_C_SOURCE)
 	size_t buf_size = 1024;     // Same as glibc use for getpwuid
 	std::vector<char> buf(buf_size);
 	struct passwd res;
 	struct passwd* pwd = nullptr;
 
 	getpwuid_r(getuid(), &res, buf.data(), buf_size, &pwd);
-#else
-	struct passwd* pwd = getpwuid(getuid());
-#endif
 	if (pwd)
 		path = pwd->pw_dir;
 	else
 	{
-#if defined(_POSIX_C_SOURCE) || defined(_BSD_SOURCE) || defined(_POSIX_C_SOURCE)
 		getpwuid_r(getuid(), &res, buf.data(), buf_size, &pwd);
-#else
-		pwd = getpwuid(geteuid());
-#endif
 		if (pwd)
 			path = pwd->pw_dir;
 		else
@@ -82,7 +74,7 @@ std::string PathImpl::configHomeImpl()
 {
 	std::string path = PathImpl::homeImpl();
 	std::string::size_type n = path.size();
-	if (n > 0 && path[n - 1] == '/') 
+	if (n > 0 && path[n - 1] == '/')
 #if POCO_OS == POCO_OS_MAC_OS_X
 	  path.append("Library/Preferences/");
 #else
@@ -97,7 +89,7 @@ std::string PathImpl::dataHomeImpl()
 {
 	std::string path = PathImpl::homeImpl();
 	std::string::size_type n = path.size();
-	if (n > 0 && path[n - 1] == '/') 
+	if (n > 0 && path[n - 1] == '/')
 #if POCO_OS == POCO_OS_MAC_OS_X
 	  path.append("Library/Application Support/");
 #else
@@ -112,7 +104,7 @@ std::string PathImpl::cacheHomeImpl()
 {
 	std::string path = PathImpl::homeImpl();
 	std::string::size_type n = path.size();
-	if (n > 0 && path[n - 1] == '/') 
+	if (n > 0 && path[n - 1] == '/')
 #if POCO_OS == POCO_OS_MAC_OS_X
 	  path.append("Library/Caches/");
 #else
@@ -127,7 +119,7 @@ std::string PathImpl::tempHomeImpl()
 {
 	std::string path = PathImpl::homeImpl();
 	std::string::size_type n = path.size();
-	if (n > 0 && path[n - 1] == '/') 
+	if (n > 0 && path[n - 1] == '/')
 #if POCO_OS == POCO_OS_MAC_OS_X
 	  path.append("Library/Caches/");
 #else
@@ -159,7 +151,7 @@ std::string PathImpl::tempImpl()
 std::string PathImpl::configImpl()
 {
 	std::string path;
-	
+
 #if POCO_OS == POCO_OS_MAC_OS_X
 	  path = "/Library/Preferences/";
 #else

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/HTTPServerParams.h

@@ -43,7 +43,7 @@ namespace Net
         /// Sets the following default values:
         ///   - timeout:              60 seconds
         ///   - keepAlive:            true
-        ///   - maxKeepAliveRequests: 0
+        ///   - maxKeepAliveRequests: 100
         ///   - keepAliveTimeout:     15 seconds
 
         void setServerName(const std::string & serverName);
@@ -87,12 +87,12 @@ namespace Net
         const Poco::Timespan & getKeepAliveTimeout() const;
         /// Returns the connection timeout for HTTP connections.
 
-        void setMaxKeepAliveRequests(int maxKeepAliveRequests);
+        void setMaxKeepAliveRequests(size_t maxKeepAliveRequests);
         /// Specifies the maximum number of requests allowed
         /// during a persistent connection. 0 means unlimited
         /// connections.
 
-        int getMaxKeepAliveRequests() const;
+        size_t getMaxKeepAliveRequests() const;
         /// Returns the maximum number of requests allowed
         /// during a persistent connection, or 0 if
         /// unlimited connections are allowed.
@@ -106,7 +106,7 @@ namespace Net
         std::string _softwareVersion;
         Poco::Timespan _timeout;
         bool _keepAlive;
-        int _maxKeepAliveRequests;
+        size_t _maxKeepAliveRequests;
         Poco::Timespan _keepAliveTimeout;
     };
 
@@ -138,7 +138,7 @@ namespace Net
     }
 
 
-    inline int HTTPServerParams::getMaxKeepAliveRequests() const
+    inline size_t HTTPServerParams::getMaxKeepAliveRequests() const
     {
         return _maxKeepAliveRequests;
     }

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

@@ -58,10 +58,14 @@ 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;
-        int _maxKeepAliveRequests;
+        size_t _maxKeepAliveRequests;
     };
 
 
@@ -70,7 +74,7 @@ namespace Net
     //
     inline bool HTTPServerSession::canKeepAlive() const
     {
-        return _maxKeepAliveRequests != 0;
+        return getKeepAlive() && _maxKeepAliveRequests > 0;
     }
 
 

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/HTTPServerParams.cpp

@@ -22,7 +22,7 @@ namespace Net {
 HTTPServerParams::HTTPServerParams():
 	_timeout(60000000),
 	_keepAlive(true),
-	_maxKeepAliveRequests(0),
+	_maxKeepAliveRequests(100),
 	_keepAliveTimeout(15000000)
 {
 }
@@ -32,12 +32,12 @@ HTTPServerParams::~HTTPServerParams()
 {
 }
 
-	
+
 void HTTPServerParams::setServerName(const std::string& serverName)
 {
 	_serverName = serverName;
 }
-	
+
 
 void HTTPServerParams::setSoftwareVersion(const std::string& softwareVersion)
 {
@@ -50,24 +50,24 @@ void HTTPServerParams::setTimeout(const Poco::Timespan& timeout)
 	_timeout = timeout;
 }
 
-	
+
 void HTTPServerParams::setKeepAlive(bool keepAlive)
 {
 	_keepAlive = keepAlive;
 }
 
-	
+
 void HTTPServerParams::setKeepAliveTimeout(const Poco::Timespan& timeout)
 {
 	_keepAliveTimeout = timeout;
 }
 
-	
-void HTTPServerParams::setMaxKeepAliveRequests(int maxKeepAliveRequests)
+
+void HTTPServerParams::setMaxKeepAliveRequests(size_t maxKeepAliveRequests)
 {
 	poco_assert (maxKeepAliveRequests >= 0);
 	_maxKeepAliveRequests = maxKeepAliveRequests;
 }
-	
+
 
 } } // namespace Poco::Net

base/poco/Net/src/HTTPServerSession.cpp

@@ -19,11 +19,11 @@ namespace Poco {
 namespace Net {
 
 
-HTTPServerSession::HTTPServerSession(const StreamSocket& socket, HTTPServerParams::Ptr pParams):
-	HTTPSession(socket, pParams->getKeepAlive()),
-	_firstRequest(true),
-	_keepAliveTimeout(pParams->getKeepAliveTimeout()),
-	_maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
+HTTPServerSession::HTTPServerSession(const StreamSocket & socket, HTTPServerParams::Ptr pParams)
+    : HTTPSession(socket, pParams->getKeepAlive())
+    , _firstRequest(true)
+    , _keepAliveTimeout(pParams->getKeepAliveTimeout())
+    , _maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
 {
 	setTimeout(pParams->getTimeout());
 }
@@ -50,13 +50,14 @@ bool HTTPServerSession::hasMoreRequests()
 		--_maxKeepAliveRequests;
 		return socket().poll(getTimeout(), Socket::SELECT_READ);
 	}
-	else if (_maxKeepAliveRequests != 0 && getKeepAlive())
+	else if (canKeepAlive())
 	{
-		if (_maxKeepAliveRequests > 0) 
-			--_maxKeepAliveRequests;
-		return buffered() > 0 || socket().poll(_keepAliveTimeout, Socket::SELECT_READ);
-	}
-	else return false;
+        if (_maxKeepAliveRequests > 0)
+            --_maxKeepAliveRequests;
+        return buffered() > 0 || socket().poll(_keepAliveTimeout, Socket::SELECT_READ);
+    }
+	else
+		return false;
 }
 
 

base/poco/Net/src/HTTPSession.cpp

@@ -128,14 +128,14 @@ int HTTPSession::get()
 {
 	if (_pCurrent == _pEnd)
 		refill();
-	
+
 	if (_pCurrent < _pEnd)
 		return *_pCurrent++;
 	else
 		return std::char_traits<char>::eof();
 }
 
-	
+
 int HTTPSession::peek()
 {
 	if (_pCurrent == _pEnd)
@@ -147,7 +147,7 @@ int HTTPSession::peek()
 		return std::char_traits<char>::eof();
 }
 
-	
+
 int HTTPSession::read(char* buffer, std::streamsize length)
 {
 	if (_pCurrent < _pEnd)
@@ -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>
 
 
@@ -62,7 +63,7 @@ bool checkIsBrokenTimeout()
 
 SocketImpl::SocketImpl():
 	_sockfd(POCO_INVALID_SOCKET),
-	_blocking(true), 
+	_blocking(true),
 	_isBrokenTimeout(checkIsBrokenTimeout())
 {
 }
@@ -81,7 +82,7 @@ SocketImpl::~SocketImpl()
 	close();
 }
 
-	
+
 SocketImpl* SocketImpl::acceptConnection(SocketAddress& clientAddr)
 {
 	if (_sockfd == POCO_INVALID_SOCKET) throw InvalidSocketException();
@@ -117,7 +118,7 @@ void SocketImpl::connect(const SocketAddress& address)
 		rc = ::connect(_sockfd, address.addr(), address.length());
 	}
 	while (rc != 0 && lastError() == POCO_EINTR);
-	if (rc != 0) 
+	if (rc != 0)
 	{
 		int err = lastError();
 		error(err, address.toString());
@@ -204,7 +205,7 @@ void SocketImpl::bind6(const SocketAddress& address, bool reuseAddress, bool reu
 #if defined(POCO_HAVE_IPv6)
 	if (address.family() != SocketAddress::IPv6)
 		throw Poco::InvalidArgumentException("SocketAddress must be an IPv6 address");
-		
+
 	if (_sockfd == POCO_INVALID_SOCKET)
 	{
 		init(address.af());
@@ -225,11 +226,11 @@ void SocketImpl::bind6(const SocketAddress& address, bool reuseAddress, bool reu
 #endif
 }
 
-	
+
 void SocketImpl::listen(int backlog)
 {
 	if (_sockfd == POCO_INVALID_SOCKET) throw InvalidSocketException();
-	
+
 	int rc = ::listen(_sockfd, backlog);
 	if (rc != 0) error();
 }
@@ -253,7 +254,7 @@ void SocketImpl::shutdownReceive()
 	if (rc != 0) error();
 }
 
-	
+
 void SocketImpl::shutdownSend()
 {
 	if (_sockfd == POCO_INVALID_SOCKET) throw InvalidSocketException();
@@ -262,7 +263,7 @@ void SocketImpl::shutdownSend()
 	if (rc != 0) error();
 }
 
-	
+
 void SocketImpl::shutdown()
 {
 	if (_sockfd == POCO_INVALID_SOCKET) throw InvalidSocketException();
@@ -317,7 +318,7 @@ int SocketImpl::receiveBytes(void* buffer, int length, int flags)
 				throw TimeoutException();
 		}
 	}
-	
+
 	int rc;
 	do
 	{
@@ -325,7 +326,7 @@ int SocketImpl::receiveBytes(void* buffer, int length, int flags)
 		rc = ::recv(_sockfd, reinterpret_cast<char*>(buffer), length, flags);
 	}
 	while (blocking && rc < 0 && lastError() == POCO_EINTR);
-	if (rc < 0) 
+	if (rc < 0)
 	{
 		int err = lastError();
 		if ((err == POCO_EAGAIN || err == POCO_EWOULDBLOCK) && !blocking)
@@ -363,7 +364,7 @@ int SocketImpl::receiveFrom(void* buffer, int length, SocketAddress& address, in
 				throw TimeoutException();
 		}
 	}
-	
+
 	sockaddr_storage abuffer;
 	struct sockaddr* pSA = reinterpret_cast<struct sockaddr*>(&abuffer);
 	poco_socklen_t saLen = sizeof(abuffer);
@@ -450,7 +451,7 @@ bool SocketImpl::pollImpl(Poco::Timespan& remainingTime, int mode)
 	}
 	while (rc < 0 && lastError() == POCO_EINTR);
 	if (rc < 0) error();
-	return rc > 0; 
+	return rc > 0;
 
 #else
 
@@ -493,7 +494,7 @@ bool SocketImpl::pollImpl(Poco::Timespan& remainingTime, int mode)
 	}
 	while (rc < 0 && errorCode == POCO_EINTR);
 	if (rc < 0) error(errorCode);
-	return rc > 0; 
+	return rc > 0;
 
 #endif // POCO_HAVE_FD_POLL
 }
@@ -503,13 +504,13 @@ bool SocketImpl::poll(const Poco::Timespan& timeout, int mode)
 	Poco::Timespan remainingTime(timeout);
 	return pollImpl(remainingTime, mode);
 }
-	
+
 void SocketImpl::setSendBufferSize(int size)
 {
 	setOption(SOL_SOCKET, SO_SNDBUF, size);
 }
 
-	
+
 int SocketImpl::getSendBufferSize()
 {
 	int result;
@@ -523,7 +524,7 @@ void SocketImpl::setReceiveBufferSize(int size)
 	setOption(SOL_SOCKET, SO_RCVBUF, size);
 }
 
-	
+
 int SocketImpl::getReceiveBufferSize()
 {
 	int result;
@@ -569,7 +570,7 @@ Poco::Timespan SocketImpl::getReceiveTimeout()
 	return result;
 }
 
-	
+
 SocketAddress SocketImpl::address()
 {
 	if (_sockfd == POCO_INVALID_SOCKET) throw InvalidSocketException();
@@ -580,7 +581,7 @@ SocketAddress SocketImpl::address()
 	int rc = ::getsockname(_sockfd, pSA, &saLen);
 	if (rc == 0)
 		return SocketAddress(pSA, saLen);
-	else 
+	else
 		error();
 	return SocketAddress();
 }

base/poco/Net/src/TCPServer.cpp

@@ -8,7 +8,7 @@
 // Copyright (c) 2005-2006, Applied Informatics Software Engineering GmbH.
 // and Contributors.
 //
-// SPDX-License-Identifier:	BSL-1.0
+// SPDX-License-Identifier:    BSL-1.0
 //
 
 
@@ -44,190 +44,194 @@ TCPServerConnectionFilter::~TCPServerConnectionFilter()
 
 
 TCPServer::TCPServer(TCPServerConnectionFactory::Ptr pFactory, Poco::UInt16 portNumber, TCPServerParams::Ptr pParams):
-	_socket(ServerSocket(portNumber)),
-	_thread(threadName(_socket)),
-	_stopped(true)
-{	
-	Poco::ThreadPool& pool = Poco::ThreadPool::defaultPool();
-	if (pParams)
-	{
-		int toAdd = pParams->getMaxThreads() - pool.capacity();
-		if (toAdd > 0) pool.addCapacity(toAdd);
-	}
-	_pDispatcher = new TCPServerDispatcher(pFactory, pool, pParams);
-	
+    _socket(ServerSocket(portNumber)),
+    _thread(threadName(_socket)),
+    _stopped(true)
+{    
+    Poco::ThreadPool& pool = Poco::ThreadPool::defaultPool();
+    if (pParams)
+    {
+        int toAdd = pParams->getMaxThreads() - pool.capacity();
+        if (toAdd > 0) pool.addCapacity(toAdd);
+    }
+    _pDispatcher = new TCPServerDispatcher(pFactory, pool, pParams);
+    
 }
 
 
 TCPServer::TCPServer(TCPServerConnectionFactory::Ptr pFactory, const ServerSocket& socket, TCPServerParams::Ptr pParams):
-	_socket(socket),
-	_thread(threadName(socket)),
-	_stopped(true)
+    _socket(socket),
+    _thread(threadName(socket)),
+    _stopped(true)
 {
-	Poco::ThreadPool& pool = Poco::ThreadPool::defaultPool();
-	if (pParams)
-	{
-		int toAdd = pParams->getMaxThreads() - pool.capacity();
-		if (toAdd > 0) pool.addCapacity(toAdd);
-	}
-	_pDispatcher = new TCPServerDispatcher(pFactory, pool, pParams);
+    Poco::ThreadPool& pool = Poco::ThreadPool::defaultPool();
+    if (pParams)
+    {
+        int toAdd = pParams->getMaxThreads() - pool.capacity();
+        if (toAdd > 0) pool.addCapacity(toAdd);
+    }
+    _pDispatcher = new TCPServerDispatcher(pFactory, pool, pParams);
 }
 
 
 TCPServer::TCPServer(TCPServerConnectionFactory::Ptr pFactory, Poco::ThreadPool& threadPool, const ServerSocket& socket, TCPServerParams::Ptr pParams):
-	_socket(socket),
-	_pDispatcher(new TCPServerDispatcher(pFactory, threadPool, pParams)),
-	_thread(threadName(socket)),
-	_stopped(true)
+    _socket(socket),
+    _pDispatcher(new TCPServerDispatcher(pFactory, threadPool, pParams)),
+    _thread(threadName(socket)),
+    _stopped(true)
 {
 }
 
 
 TCPServer::~TCPServer()
 {
-	try
-	{
-		stop();
-		_pDispatcher->release();
-	}
-	catch (...)
-	{
-		poco_unexpected();
-	}
+    try
+    {
+        stop();
+        _pDispatcher->release();
+    }
+    catch (...)
+    {
+        poco_unexpected();
+    }
 }
 
 
 const TCPServerParams& TCPServer::params() const
 {
-	return _pDispatcher->params();
+    return _pDispatcher->params();
 }
 
 
 void TCPServer::start()
 {
-	poco_assert (_stopped);
+    poco_assert (_stopped);
 
-	_stopped = false;
-	_thread.start(*this);
+    _stopped = false;
+    _thread.start(*this);
 }
 
-	
+    
 void TCPServer::stop()
 {
-	if (!_stopped)
-	{
-		_stopped = true;
-		_thread.join();
-		_pDispatcher->stop();
-	}
+    if (!_stopped)
+    {
+        _stopped = true;
+        _thread.join();
+        _pDispatcher->stop();
+    }
 }
 
 
 void TCPServer::run()
 {
-	while (!_stopped)
-	{
-		Poco::Timespan timeout(250000);
-		try
-		{
-			if (_socket.poll(timeout, Socket::SELECT_READ))
-			{
-				try
-				{
-					StreamSocket ss = _socket.acceptConnection();
-					
-					if (!_pConnectionFilter || _pConnectionFilter->accept(ss))
-					{
-						// enable nodelay per default: OSX really needs that
+    while (!_stopped)
+    {
+        Poco::Timespan timeout(250000);
+        try
+        {
+            if (_socket.poll(timeout, Socket::SELECT_READ))
+            {
+                try
+                {
+                    StreamSocket ss = _socket.acceptConnection();
+                    
+                    if (!_pConnectionFilter || _pConnectionFilter->accept(ss))
+                    {
+                        // enable nodelay per default: OSX really needs that
 #if defined(POCO_OS_FAMILY_UNIX)
-						if (ss.address().family() != AddressFamily::UNIX_LOCAL)
+                        if (ss.address().family() != AddressFamily::UNIX_LOCAL)
 #endif
-						{
-							ss.setNoDelay(true);
-						}
-						_pDispatcher->enqueue(ss);
-					}
-				}
-				catch (Poco::Exception& exc)
-				{
-					ErrorHandler::handle(exc);
-				}
-				catch (std::exception& exc)
-				{
-					ErrorHandler::handle(exc);
-				}
-				catch (...)
-				{
-					ErrorHandler::handle();
-				}
-			}
-		}
-		catch (Poco::Exception& exc)
-		{
-			ErrorHandler::handle(exc);
-			// possibly a resource issue since poll() failed;
-			// give some time to recover before trying again
-			Poco::Thread::sleep(50); 
-		}
-	}
+                        {
+                            ss.setNoDelay(true);
+                        }
+                        _pDispatcher->enqueue(ss);
+                    }
+                    else
+                    {
+                        ErrorHandler::logMessage(Message::PRIO_WARNING, "Filtered out connection from " + ss.peerAddress().toString());
+                    }
+                }
+                catch (Poco::Exception& exc)
+                {
+                    ErrorHandler::handle(exc);
+                }
+                catch (std::exception& exc)
+                {
+                    ErrorHandler::handle(exc);
+                }
+                catch (...)
+                {
+                    ErrorHandler::handle();
+                }
+            }
+        }
+        catch (Poco::Exception& exc)
+        {
+            ErrorHandler::handle(exc);
+            // possibly a resource issue since poll() failed;
+            // give some time to recover before trying again
+            Poco::Thread::sleep(50); 
+        }
+    }
 }
 
 
 int TCPServer::currentThreads() const
 {
-	return _pDispatcher->currentThreads();
+    return _pDispatcher->currentThreads();
 }
 
 
 int TCPServer::maxThreads() const
 {
-	return _pDispatcher->maxThreads();
+    return _pDispatcher->maxThreads();
 }
 
-	
+    
 int TCPServer::totalConnections() const
 {
-	return _pDispatcher->totalConnections();
+    return _pDispatcher->totalConnections();
 }
 
 
 int TCPServer::currentConnections() const
 {
-	return _pDispatcher->currentConnections();
+    return _pDispatcher->currentConnections();
 }
 
 
 int TCPServer::maxConcurrentConnections() const
 {
-	return _pDispatcher->maxConcurrentConnections();
+    return _pDispatcher->maxConcurrentConnections();
 }
 
-	
+    
 int TCPServer::queuedConnections() const
 {
-	return _pDispatcher->queuedConnections();
+    return _pDispatcher->queuedConnections();
 }
 
 
 int TCPServer::refusedConnections() const
 {
-	return _pDispatcher->refusedConnections();
+    return _pDispatcher->refusedConnections();
 }
 
 
 void TCPServer::setConnectionFilter(const TCPServerConnectionFilter::Ptr& pConnectionFilter)
 {
-	poco_assert (_stopped);
+    poco_assert (_stopped);
 
-	_pConnectionFilter = pConnectionFilter;
+    _pConnectionFilter = pConnectionFilter;
 }
 
 
 std::string TCPServer::threadName(const ServerSocket& socket)
 {
-	std::string name("TCPServer: ");
-	name.append(socket.address().toString());
-	return name;
+    std::string name("TCPServer: ");
+    name.append(socket.address().toString());
+    return name;
 
 }
 

base/poco/Net/src/TCPServerConnection.cpp

@@ -18,7 +18,6 @@
 
 
 using Poco::Exception;
-using Poco::ErrorHandler;
 
 
 namespace Poco {
@@ -31,9 +30,7 @@ TCPServerConnection::TCPServerConnection(const StreamSocket& socket):
 }
 
 
-TCPServerConnection::~TCPServerConnection()
-{
-}
+TCPServerConnection::~TCPServerConnection() = default;
 
 
 void TCPServerConnection::start()

base/poco/Net/src/TCPServerDispatcher.cpp

@@ -8,7 +8,7 @@
 // Copyright (c) 2005-2007, Applied Informatics Software Engineering GmbH.
 // and Contributors.
 //
-// SPDX-License-Identifier:	BSL-1.0
+// SPDX-License-Identifier:    BSL-1.0
 //
 
 
@@ -33,44 +33,44 @@ namespace Net {
 class TCPConnectionNotification: public Notification
 {
 public:
-	TCPConnectionNotification(const StreamSocket& socket):
-		_socket(socket)
-	{
-	}
-	
-	~TCPConnectionNotification()
-	{
-	}
-	
-	const StreamSocket& socket() const
-	{
-		return _socket;
-	}
+    TCPConnectionNotification(const StreamSocket& socket):
+        _socket(socket)
+    {
+    }
+    
+    ~TCPConnectionNotification()
+    {
+    }
+    
+    const StreamSocket& socket() const
+    {
+        return _socket;
+    }
 
 private:
-	StreamSocket _socket;
+    StreamSocket _socket;
 };
 
 
 TCPServerDispatcher::TCPServerDispatcher(TCPServerConnectionFactory::Ptr pFactory, Poco::ThreadPool& threadPool, TCPServerParams::Ptr pParams):
-	_rc(1),
-	_pParams(pParams),
-	_currentThreads(0),
-	_totalConnections(0),
-	_currentConnections(0),
-	_maxConcurrentConnections(0),
-	_refusedConnections(0),
-	_stopped(false),
-	_pConnectionFactory(pFactory),
-	_threadPool(threadPool)
+    _rc(1),
+    _pParams(pParams),
+    _currentThreads(0),
+    _totalConnections(0),
+    _currentConnections(0),
+    _maxConcurrentConnections(0),
+    _refusedConnections(0),
+    _stopped(false),
+    _pConnectionFactory(pFactory),
+    _threadPool(threadPool)
 {
-	poco_check_ptr (pFactory);
+    poco_check_ptr (pFactory);
 
-	if (!_pParams)
-		_pParams = new TCPServerParams;
-	
-	if (_pParams->getMaxThreads() == 0)
-		_pParams->setMaxThreads(threadPool.capacity());
+    if (!_pParams)
+        _pParams = new TCPServerParams;
+    
+    if (_pParams->getMaxThreads() == 0)
+        _pParams->setMaxThreads(threadPool.capacity());
 }
 
 
@@ -81,161 +81,184 @@ TCPServerDispatcher::~TCPServerDispatcher()
 
 void TCPServerDispatcher::duplicate()
 {
-	++_rc;
+    ++_rc;
 }
 
 
 void TCPServerDispatcher::release()
 {
-	if (--_rc == 0) delete this;
+    if (--_rc == 0) delete this;
 }
 
 
 void TCPServerDispatcher::run()
 {
-	AutoPtr<TCPServerDispatcher> guard(this); // ensure object stays alive
+    AutoPtr<TCPServerDispatcher> guard(this); // ensure object stays alive
 
-	int idleTime = (int) _pParams->getThreadIdleTime().totalMilliseconds();
+    int idleTime = (int) _pParams->getThreadIdleTime().totalMilliseconds();
 
-	for (;;)
-	{
-		try
-		{
-			AutoPtr<Notification> pNf = _queue.waitDequeueNotification(idleTime);
-			if (pNf && !_stopped)
-			{
-				TCPConnectionNotification* pCNf = dynamic_cast<TCPConnectionNotification*>(pNf.get());
-				if (pCNf)
-				{
-					beginConnection();
-					if (!_stopped)
-					{
-						std::unique_ptr<TCPServerConnection> pConnection(_pConnectionFactory->createConnection(pCNf->socket()));
-						poco_check_ptr(pConnection.get());
-						pConnection->start();
-					}
-					/// endConnection() should be called after destroying TCPServerConnection,
-					/// otherwise currentConnections() could become zero while some connections are yet still alive.
-					endConnection();
-				}
-			}
-		}
-		catch (Poco::Exception &exc) { ErrorHandler::handle(exc); }
-		catch (std::exception &exc)  { ErrorHandler::handle(exc); }
-		catch (...)                  { ErrorHandler::handle();    }
-		FastMutex::ScopedLock lock(_mutex);
-		if (_stopped || (_currentThreads > 1 && _queue.empty()))
-		{
-			--_currentThreads;
-			break;
-		}
-	}
+    for (;;)
+    {
+        try
+        {
+            AutoPtr<Notification> pNf = _queue.waitDequeueNotification(idleTime);
+            if (pNf && !_stopped)
+            {
+                TCPConnectionNotification* pCNf = dynamic_cast<TCPConnectionNotification*>(pNf.get());
+                if (pCNf)
+                {
+                    beginConnection();
+                    if (!_stopped)
+                    {
+                        std::unique_ptr<TCPServerConnection> pConnection(_pConnectionFactory->createConnection(pCNf->socket()));
+                        poco_check_ptr(pConnection.get());
+                        pConnection->start();
+                    }
+                    /// endConnection() should be called after destroying TCPServerConnection,
+                    /// otherwise currentConnections() could become zero while some connections are yet still alive.
+                    endConnection();
+                }
+            }
+        }
+        catch (Poco::Exception &exc) { ErrorHandler::handle(exc); }
+        catch (std::exception &exc)  { ErrorHandler::handle(exc); }
+        catch (...)                  { ErrorHandler::handle();    }
+        FastMutex::ScopedLock lock(_mutex);
+        if (_stopped || (_currentThreads > 1 && _queue.empty()))
+        {
+            --_currentThreads;
+            break;
+        }
+    }
 }
 
 
 namespace
 {
-	static const std::string threadName("TCPServerConnection");
+    static const std::string threadName("TCPServerConnection");
 }
 
-	
+    
 void TCPServerDispatcher::enqueue(const StreamSocket& socket)
 {
-	FastMutex::ScopedLock lock(_mutex);
+    FastMutex::ScopedLock lock(_mutex);
 
-	if (_queue.size() < _pParams->getMaxQueued())
-	{
-		if (!_queue.hasIdleThreads() && _currentThreads < _pParams->getMaxThreads())
-		{
-			try
-			{
+    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
+            {
                 this->duplicate();
-				_threadPool.startWithPriority(_pParams->getThreadPriority(), *this, threadName);
-				++_currentThreads;
-			}
-			catch (Poco::Exception& exc)
-			{
+                _threadPool.startWithPriority(_pParams->getThreadPriority(), *this, threadName);
+                ++_currentThreads;
+            }
+            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;
-			}
-		}
-		_queue.enqueueNotification(new TCPConnectionNotification(socket));
-	}
-	else
-	{
-		++_refusedConnections;
-	}
+                ++_refusedConnections;
+                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;
+    }
 }
 
 
 void TCPServerDispatcher::stop()
 {
-	_stopped = true;
-	_queue.clear();
-	_queue.wakeUpAll();
+    _stopped = true;
+    _queue.clear();
+    _queue.wakeUpAll();
 }
 
 
 int TCPServerDispatcher::currentThreads() const
 {
-	return _currentThreads;
+    return _currentThreads;
 }
 
 int TCPServerDispatcher::maxThreads() const
 {
-	FastMutex::ScopedLock lock(_mutex);
-	
-	return _threadPool.capacity();
+    FastMutex::ScopedLock lock(_mutex);
+    
+    return _threadPool.capacity();
 }
 
 
 int TCPServerDispatcher::totalConnections() const
 {
-	return _totalConnections;
+    return _totalConnections;
 }
 
 
 int TCPServerDispatcher::currentConnections() const
 {
-	return _currentConnections;
+    return _currentConnections;
 }
 
 
 int TCPServerDispatcher::maxConcurrentConnections() const
 {
-	return _maxConcurrentConnections;
+    return _maxConcurrentConnections;
 }
 
 
 int TCPServerDispatcher::queuedConnections() const
 {
-	return _queue.size();
+    return _queue.size();
 }
 
 
 int TCPServerDispatcher::refusedConnections() const
 {
-	return _refusedConnections;
+    return _refusedConnections;
 }
 
 
 void TCPServerDispatcher::beginConnection()
 {
-	FastMutex::ScopedLock lock(_mutex);
+    FastMutex::ScopedLock lock(_mutex);
 
-	++_totalConnections;
-	++_currentConnections;
-	if (_currentConnections > _maxConcurrentConnections)
-		_maxConcurrentConnections.store(_currentConnections);
+    ++_totalConnections;
+    ++_currentConnections;
+    if (_currentConnections > _maxConcurrentConnections)
+        _maxConcurrentConnections.store(_currentConnections);
 }
 
 
 void TCPServerDispatcher::endConnection()
 {
-	--_currentConnections;
+    --_currentConnections;
 }
 
 

base/poco/NetSSL_OpenSSL/include/Poco/Net/Context.h

@@ -248,6 +248,9 @@ namespace Net
         SSL_CTX * sslContext() const;
         /// Returns the underlying OpenSSL SSL Context object.
 
+        SSL_CTX * takeSslContext();
+        /// Takes ownership of the underlying OpenSSL SSL Context object.
+
         Usage usage() const;
         /// Returns whether the context is for use by a client or by a server
         /// and whether TLSv1 is required.
@@ -401,6 +404,13 @@ namespace Net
         return _pSSLContext;
     }
 
+    inline SSL_CTX * Context::takeSslContext()
+    {
+        auto * result = _pSSLContext;
+        _pSSLContext = nullptr;
+        return result;
+    }
+
 
     inline bool Context::extendedCertificateVerificationEnabled() const
     {

base/poco/NetSSL_OpenSSL/src/Context.cpp

@@ -106,6 +106,11 @@ Context::Context(
 
 Context::~Context()
 {
+    if (_pSSLContext == nullptr)
+    {
+        return;
+    }
+
 	try
 	{
 		SSL_CTX_free(_pSSLContext);

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

ci/README.md

@@ -0,0 +1 @@
+Note: This directory is under active development for CI improvements and is not currently in use within the scope of the existing CI pipeline.

ci/docker/fasttest/Dockerfile

@@ -0,0 +1,109 @@
+# docker build -t clickhouse/fasttest .
+FROM ubuntu:22.04
+
+# ARG for quick switch to a given ubuntu mirror
+ARG apt_archive="http://archive.ubuntu.com"
+RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
+
+ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=18
+
+RUN apt-get update \
+    && apt-get install \
+        apt-transport-https \
+        apt-utils \
+        ca-certificates \
+        curl \
+        gnupg \
+        lsb-release \
+        wget \
+        git \
+        --yes --no-install-recommends --verbose-versions \
+    && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \
+    && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \
+    && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \
+    && apt-key add /tmp/llvm-snapshot.gpg.key \
+    && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \
+    && echo "deb https://apt.llvm.org/${CODENAME}/ llvm-toolchain-${CODENAME}-${LLVM_VERSION} main" >> \
+        /etc/apt/sources.list \
+    && apt-get update \
+    && apt-get install --yes --no-install-recommends --verbose-versions llvm-${LLVM_VERSION} \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
+
+# moreutils - provides ts fo FT
+# expect, bzip2 - requried by FT
+# bsdmainutils - provides hexdump for FT
+# nasm - nasm copiler for one of submodules, required from normal build
+# yasm - asssembler for libhdfs3, required from normal build
+
+RUN apt-get update \
+    && apt-get install \
+        clang-${LLVM_VERSION} \
+        cmake \
+        libclang-${LLVM_VERSION}-dev \
+        libclang-rt-${LLVM_VERSION}-dev \
+        lld-${LLVM_VERSION} \
+        llvm-${LLVM_VERSION}-dev \
+        lsof \
+        ninja-build \
+        python3 \
+        python3-pip \
+        zstd \
+        moreutils \
+        expect \
+        bsdmainutils \
+        pv \
+        jq \
+        bzip2 \
+        nasm \
+        yasm \
+        --yes --no-install-recommends \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
+
+COPY --from=clickhouse/cctools:0d6b90a7a490 /opt/gdb /opt/gdb
+# Give suid to gdb to grant it attach permissions
+RUN chmod u+s /opt/gdb/bin/gdb
+ENV PATH="/opt/gdb/bin:${PATH}"
+
+# This symlink is required by gcc to find the lld linker
+RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld
+# FIXME: workaround for "The imported target "merge-fdata" references the file" error
+# https://salsa.debian.org/pkg-llvm-team/llvm-toolchain/-/commit/992e52c0b156a5ba9c6a8a54f8c4857ddd3d371d
+RUN sed -i '/_IMPORT_CHECK_FILES_FOR_\(mlir-\|llvm-bolt\|merge-fdata\|MLIR\)/ {s|^|#|}' /usr/lib/llvm-${LLVM_VERSION}/lib/cmake/llvm/LLVMExports-*.cmake
+
+# LLVM changes paths for compiler-rt libraries. For some reason clang-18.1.8 cannot catch up libraries from default install path.
+# It's very dirty workaround, better to build compiler and LLVM ourself and use it. Details: https://github.com/llvm/llvm-project/issues/95792
+RUN test ! -d /usr/lib/llvm-18/lib/clang/18/lib/x86_64-pc-linux-gnu || ln -s /usr/lib/llvm-18/lib/clang/18/lib/x86_64-pc-linux-gnu /usr/lib/llvm-18/lib/clang/18/lib/x86_64-unknown-linux-gnu
+
+ARG TARGETARCH
+ARG SCCACHE_VERSION=v0.7.7
+ENV SCCACHE_IGNORE_SERVER_IO_ERROR=1
+# sccache requires a value for the region. So by default we use The Default Region
+ENV SCCACHE_REGION=us-east-1
+RUN arch=${TARGETARCH} \
+  && case $arch in \
+    amd64) rarch=x86_64 ;; \
+    arm64) rarch=aarch64 ;; \
+  esac \
+  && curl -Ls "https://github.com/mozilla/sccache/releases/download/$SCCACHE_VERSION/sccache-$SCCACHE_VERSION-$rarch-unknown-linux-musl.tar.gz" | \
+    tar xz -C /tmp \
+  && mv "/tmp/sccache-$SCCACHE_VERSION-$rarch-unknown-linux-musl/sccache" /usr/bin \
+  && rm "/tmp/sccache-$SCCACHE_VERSION-$rarch-unknown-linux-musl" -r
+
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
+
+# chmod 777 to make the container user independent
+RUN mkdir -p /var/lib/clickhouse \
+  && chmod 777 /var/lib/clickhouse
+
+ENV TZ=Europe/Amsterdam
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+RUN groupadd --system --gid 1000 clickhouse \
+    && useradd --system --gid 1000 --uid 1000 -m clickhouse \
+    && mkdir -p /.cache/sccache && chmod 777 /.cache/sccache
+
+ENV PYTHONPATH="/wd"
+ENV PYTHONUNBUFFERED=1

ci/docker/fasttest/requirements.txt

@@ -0,0 +1,6 @@
+Jinja2==3.1.3
+numpy==1.26.4
+requests==2.32.3
+pandas==1.5.3
+scipy==1.12.0
+#https://clickhouse-builds.s3.amazonaws.com/packages/praktika-0.1-py3-none-any.whl

ci/docker/stateful-test/Dockerfile

@@ -0,0 +1,14 @@
+ARG FROM_TAG=latest
+FROM clickhouse/stateless-test:$FROM_TAG
+
+USER root
+
+RUN apt-get update -y \
+    && env DEBIAN_FRONTEND=noninteractive \
+        apt-get install --yes --no-install-recommends \
+        nodejs \
+        npm \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/* \
+
+USER clickhouse

ci/docker/stateless-test/Dockerfile

@@ -0,0 +1,117 @@
+# docker build -t clickhouse/stateless-test .
+FROM ubuntu:22.04
+
+# ARG for quick switch to a given ubuntu mirror
+ARG apt_archive="http://archive.ubuntu.com"
+RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
+
+ARG odbc_driver_url="https://github.com/ClickHouse/clickhouse-odbc/releases/download/v1.1.6.20200320/clickhouse-odbc-1.1.6-Linux.tar.gz"
+
+
+RUN mkdir /etc/clickhouse-server /etc/clickhouse-keeper /etc/clickhouse-client && chmod 777 /etc/clickhouse-* \
+    && mkdir -p /var/lib/clickhouse /var/log/clickhouse-server && chmod 777 /var/log/clickhouse-server /var/lib/clickhouse
+
+RUN addgroup --gid 1001 clickhouse && adduser --uid 1001 --gid 1001 --disabled-password clickhouse
+
+# moreutils - provides ts fo FT
+# expect, bzip2 - requried by FT
+# bsdmainutils - provides hexdump for FT
+
+# golang version 1.13 on Ubuntu 20 is enough for tests
+RUN apt-get update -y \
+    && env DEBIAN_FRONTEND=noninteractive \
+        apt-get install --yes --no-install-recommends \
+            awscli \
+            brotli \
+            lz4 \
+            expect \
+            moreutils \
+            bzip2 \
+            bsdmainutils \
+            golang \
+            lsof \
+            mysql-client=8.0* \
+            ncdu \
+            netcat-openbsd \
+            nodejs \
+            npm \
+            odbcinst \
+            openjdk-11-jre-headless \
+            openssl \
+            postgresql-client \
+            python3 \
+            python3-pip \
+            qemu-user-static \
+            sqlite3 \
+            sudo \
+            tree \
+            unixodbc \
+            rustc \
+            cargo \
+            zstd \
+            file \
+            jq \
+            pv \
+            zip \
+            unzip \
+            p7zip-full \
+            curl \
+            wget \
+            xz-utils \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
+
+ARG PROTOC_VERSION=25.1
+RUN curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-x86_64.zip \
+    && unzip protoc-${PROTOC_VERSION}-linux-x86_64.zip -d /usr/local \
+    && rm protoc-${PROTOC_VERSION}-linux-x86_64.zip
+
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
+
+RUN mkdir -p /tmp/clickhouse-odbc-tmp \
+  && cd /tmp/clickhouse-odbc-tmp \
+  && curl -L ${odbc_driver_url} | tar --strip-components=1 -xz clickhouse-odbc-1.1.6-Linux \
+  && mkdir /usr/local/lib64 -p \
+  && cp /tmp/clickhouse-odbc-tmp/lib64/*.so /usr/local/lib64/ \
+  && odbcinst -i -d -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbcinst.ini.sample \
+  && odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \
+  && sed -i 's"=libclickhouseodbc"=/usr/local/lib64/libclickhouseodbc"' /etc/odbcinst.ini \
+  && rm -rf /tmp/clickhouse-odbc-tmp
+
+ENV TZ=Europe/Amsterdam
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+ENV NUM_TRIES=1
+
+# Unrelated to vars in setup_minio.sh, but should be the same there
+# to have the same binaries for local running scenario
+ARG MINIO_SERVER_VERSION=2024-08-03T04-33-23Z
+ARG MINIO_CLIENT_VERSION=2024-07-31T15-58-33Z
+ARG TARGETARCH
+
+# Download Minio-related binaries
+RUN arch=${TARGETARCH:-amd64} \
+    && curl -L "https://dl.min.io/server/minio/release/linux-${arch}/archive/minio.RELEASE.${MINIO_SERVER_VERSION}" -o /minio \
+    && curl -L "https://dl.min.io/client/mc/release/linux-${arch}/archive/mc.RELEASE.${MINIO_CLIENT_VERSION}" -o /mc \
+    && chmod +x /mc /minio
+
+ENV MINIO_ROOT_USER="clickhouse"
+ENV MINIO_ROOT_PASSWORD="clickhouse"
+
+# for minio to work without root
+RUN chmod 777 /home
+ENV HOME="/home"
+ENV TEMP_DIR="/tmp/praktika"
+ENV PATH="/wd/tests:/tmp/praktika/input:$PATH"
+
+RUN curl -L --no-verbose -O 'https://archive.apache.org/dist/hadoop/common/hadoop-3.3.1/hadoop-3.3.1.tar.gz' \
+    && tar -xvf hadoop-3.3.1.tar.gz \
+    && rm -rf hadoop-3.3.1.tar.gz \
+    && chmod 777 /hadoop-3.3.1
+
+
+RUN npm install -g azurite@3.30.0 \
+    && npm install -g tslib && npm install -g node
+
+USER clickhouse

ci/docker/stateless-test/requirements.txt

@@ -0,0 +1,6 @@
+Jinja2==3.1.3
+numpy==1.26.4
+requests==2.32.3
+pandas==1.5.3
+scipy==1.12.0
+pyarrow==18.0.0

ci/docker/style-test/Dockerfile

@@ -0,0 +1,17 @@
+# docker build -t clickhouse/style-test .
+FROM ubuntu:22.04
+
+RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
+        aspell \
+        libxml2-utils \
+        python3-pip \
+        locales \
+        git \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
+
+RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && locale-gen en_US.UTF-8
+ENV LC_ALL=en_US.UTF-8
+
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r requirements.txt

ci/docker/style-test/requirements.txt

@@ -0,0 +1,5 @@
+requests==2.32.3
+yamllint==1.26.3
+codespell==2.2.1
+#use praktika from CH repo
+#https://clickhouse-builds.s3.amazonaws.com/packages/praktika-0.1-py3-none-any.whl

ci/jobs/build_clickhouse.py

@@ -0,0 +1,134 @@
+import argparse
+
+from praktika.result import Result
+from praktika.settings import Settings
+from praktika.utils import MetaClasses, Shell, Utils
+
+
+class JobStages(metaclass=MetaClasses.WithIter):
+    CHECKOUT_SUBMODULES = "checkout"
+    CMAKE = "cmake"
+    BUILD = "build"
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="ClickHouse Build Job")
+    parser.add_argument(
+        "--build-type",
+        help="Type: <amd|arm>,<debug|release>,<asan|msan|..>",
+    )
+    parser.add_argument(
+        "--param",
+        help="Optional user-defined job start stage (for local run)",
+        default=None,
+    )
+    return parser.parse_args()
+
+
+CMAKE_CMD = """cmake --debug-trycompile -DCMAKE_VERBOSE_MAKEFILE=1 -LA \
+-DCMAKE_BUILD_TYPE={BUILD_TYPE} \
+-DSANITIZE={SANITIZER} \
+-DENABLE_CHECK_HEAVY_BUILDS=1 -DENABLE_CLICKHOUSE_SELF_EXTRACTING=1 \
+-DENABLE_UTILS=0 -DCMAKE_FIND_PACKAGE_NO_PACKAGE_REGISTRY=ON -DCMAKE_INSTALL_PREFIX=/usr \
+-DCMAKE_INSTALL_SYSCONFDIR=/etc -DCMAKE_INSTALL_LOCALSTATEDIR=/var -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=ON \
+{AUX_DEFS} \
+-DCMAKE_C_COMPILER=clang-18 -DCMAKE_CXX_COMPILER=clang++-18 \
+-DCOMPILER_CACHE={CACHE_TYPE} \
+-DENABLE_BUILD_PROFILING=1 {DIR}"""
+
+
+def main():
+
+    args = parse_args()
+
+    stop_watch = Utils.Stopwatch()
+
+    stages = list(JobStages)
+    stage = args.param or JobStages.CHECKOUT_SUBMODULES
+    if stage:
+        assert stage in JobStages, f"--param must be one of [{list(JobStages)}]"
+        print(f"Job will start from stage [{stage}]")
+        while stage in stages:
+            stages.pop(0)
+        stages.insert(0, stage)
+
+    build_type = args.build_type
+    assert (
+        build_type
+    ), "build_type must be provided either as input argument or as a parameter of parametrized job in CI"
+    build_type = build_type.lower()
+
+    CACHE_TYPE = "sccache"
+
+    BUILD_TYPE = "RelWithDebInfo"
+    SANITIZER = ""
+    AUX_DEFS = " -DENABLE_TESTS=0 "
+
+    if "debug" in build_type:
+        print("Build type set: debug")
+        BUILD_TYPE = "Debug"
+        AUX_DEFS = " -DENABLE_TESTS=1 "
+    elif "release" in build_type:
+        print("Build type set: release")
+        AUX_DEFS = (
+            " -DENABLE_TESTS=0 -DSPLIT_DEBUG_SYMBOLS=ON -DBUILD_STANDALONE_KEEPER=1 "
+        )
+    elif "asan" in build_type:
+        print("Sanitizer set: address")
+        SANITIZER = "address"
+    else:
+        assert False
+
+    cmake_cmd = CMAKE_CMD.format(
+        BUILD_TYPE=BUILD_TYPE,
+        CACHE_TYPE=CACHE_TYPE,
+        SANITIZER=SANITIZER,
+        AUX_DEFS=AUX_DEFS,
+        DIR=Utils.cwd(),
+    )
+
+    build_dir = f"{Settings.TEMP_DIR}/build"
+
+    res = True
+    results = []
+
+    if res and JobStages.CHECKOUT_SUBMODULES in stages:
+        Shell.check(f"rm -rf {build_dir} && mkdir -p {build_dir}")
+        results.append(
+            Result.create_from_command_execution(
+                name="Checkout Submodules",
+                command=f"git submodule sync --recursive && git submodule init && git submodule update --depth 1 --recursive --jobs {min([Utils.cpu_count(), 20])}",
+            )
+        )
+        res = results[-1].is_ok()
+
+    if res and JobStages.CMAKE in stages:
+        results.append(
+            Result.create_from_command_execution(
+                name="Cmake configuration",
+                command=cmake_cmd,
+                workdir=build_dir,
+                with_log=True,
+            )
+        )
+        res = results[-1].is_ok()
+
+    if res and JobStages.BUILD in stages:
+        Shell.check("sccache --show-stats")
+        results.append(
+            Result.create_from_command_execution(
+                name="Build ClickHouse",
+                command="ninja clickhouse-bundle clickhouse-odbc-bridge clickhouse-library-bridge",
+                workdir=build_dir,
+                with_log=True,
+            )
+        )
+        Shell.check("sccache --show-stats")
+        Shell.check(f"ls -l {build_dir}/programs/")
+        res = results[-1].is_ok()
+
+    Result.create_from(results=results, stopwatch=stop_watch).complete_job()
+
+
+if __name__ == "__main__":
+    main()

ci/jobs/check_style.py

@@ -0,0 +1,382 @@
+import math
+import multiprocessing
+import os
+import re
+from concurrent.futures import ProcessPoolExecutor
+from pathlib import Path
+
+from praktika.result import Result
+from praktika.utils import Shell, Utils
+
+NPROC = multiprocessing.cpu_count()
+
+
+def chunk_list(data, n):
+    """Split the data list into n nearly equal-sized chunks."""
+    chunk_size = math.ceil(len(data) / n)
+    for i in range(0, len(data), chunk_size):
+        yield data[i : i + chunk_size]
+
+
+def run_check_concurrent(check_name, check_function, files, nproc=NPROC):
+    stop_watch = Utils.Stopwatch()
+
+    if not files:
+        print(f"File list is empty [{files}]")
+        raise
+
+    file_chunks = list(chunk_list(files, nproc))
+    results = []
+
+    # Run check_function concurrently on each chunk
+    with ProcessPoolExecutor(max_workers=NPROC) as executor:
+        futures = [executor.submit(check_function, chunk) for chunk in file_chunks]
+        # Wait for results and process them (optional)
+        for future in futures:
+            try:
+                res = future.result()
+                if res and res not in results:
+                    results.append(res)
+            except Exception as e:
+                results.append(f"Exception in {check_name}: {e}")
+
+    result = Result(
+        name=check_name,
+        status=Result.Status.SUCCESS if not results else Result.Status.FAILED,
+        start_time=stop_watch.start_time,
+        duration=stop_watch.duration,
+        info=f"errors: {results}" if results else "",
+    )
+    return result
+
+
+def check_duplicate_includes(file_path):
+    includes = []
+    with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+        for line in f:
+            if re.match(r"^#include ", line):
+                includes.append(line.strip())
+
+    include_counts = {line: includes.count(line) for line in includes}
+    duplicates = {line: count for line, count in include_counts.items() if count > 1}
+
+    if duplicates:
+        return f"{file_path}: {duplicates}"
+    return ""
+
+
+def check_whitespaces(file_paths):
+    for file in file_paths:
+        exit_code, out, err = Shell.get_res_stdout_stderr(
+            f'./ci/jobs/scripts/check_style/double_whitespaces.pl "{file}"',
+            verbose=False,
+        )
+        if out or err:
+            return out + " err: " + err
+    return ""
+
+
+def check_yamllint(file_paths):
+    file_paths = " ".join([f"'{file}'" for file in file_paths])
+    exit_code, out, err = Shell.get_res_stdout_stderr(
+        f"yamllint --config-file=./.yamllint {file_paths}", verbose=False
+    )
+    return out or err
+
+
+def check_xmllint(file_paths):
+    if not isinstance(file_paths, list):
+        file_paths = [file_paths]
+    file_paths = " ".join([f"'{file}'" for file in file_paths])
+    exit_code, out, err = Shell.get_res_stdout_stderr(
+        f"xmllint --noout --nonet {file_paths}", verbose=False
+    )
+    return out or err
+
+
+def check_functional_test_cases(files):
+    """
+    Queries with event_date should have yesterday() not today()
+    NOTE: it is not that accurate, but at least something.
+    """
+
+    patterns = [
+        re.compile(
+            r"(?i)where.*?\bevent_date\s*(=|>=)\s*today\(\)(?!\s*-\s*1)",
+            re.IGNORECASE | re.DOTALL,
+        )
+    ]
+
+    errors = []
+    for test_case in files:
+        try:
+            with open(test_case, "r", encoding="utf-8", errors="replace") as f:
+                file_content = " ".join(
+                    f.read().splitlines()
+                )  # Combine lines into a single string
+
+            # Check if any pattern matches in the concatenated string
+            if any(pattern.search(file_content) for pattern in patterns):
+                errors.append(
+                    f"event_date should be filtered using >=yesterday() in {test_case} (to avoid flakiness)"
+                )
+
+        except Exception as e:
+            errors.append(f"Error checking {test_case}: {e}")
+
+    for test_case in files:
+        if "fail" in test_case:
+            errors.append(f"test case {test_case} includes 'fail' in its name")
+
+    return " ".join(errors)
+
+
+def check_gaps_in_tests_numbers(file_paths, gap_threshold=100):
+    test_numbers = set()
+
+    pattern = re.compile(r"(\d+)")
+
+    for file in file_paths:
+        file_name = os.path.basename(file)
+        match = pattern.search(file_name)
+        if match:
+            test_numbers.add(int(match.group(1)))
+
+    sorted_numbers = sorted(test_numbers)
+    large_gaps = []
+    for i in range(1, len(sorted_numbers)):
+        prev_num = sorted_numbers[i - 1]
+        next_num = sorted_numbers[i]
+        diff = next_num - prev_num
+        if diff >= gap_threshold:
+            large_gaps.append(f"Gap ({prev_num}, {next_num}) > {gap_threshold}")
+
+    return large_gaps
+
+
+def check_broken_links(path, exclude_paths):
+    broken_symlinks = []
+
+    for path in Path(path).rglob("*"):
+        if any(exclude_path in str(path) for exclude_path in exclude_paths):
+            continue
+        if path.is_symlink():
+            if not path.exists():
+                broken_symlinks.append(str(path))
+
+    if broken_symlinks:
+        for symlink in broken_symlinks:
+            print(symlink)
+        return f"Broken symlinks found: {broken_symlinks}"
+    else:
+        return ""
+
+
+def check_cpp_code():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check_cpp.sh"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_repo_submodules():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check_submodules.sh"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_other():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/checks_to_refactor.sh"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_codespell():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check_typos.sh"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_aspell():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check_aspell.sh"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_mypy():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check-mypy"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_pylint():
+    res, out, err = Shell.get_res_stdout_stderr(
+        "./ci/jobs/scripts/check_style/check-pylint"
+    )
+    if err:
+        out += err
+    return out
+
+
+def check_file_names(files):
+    files_set = set()
+    for file in files:
+        file_ = file.lower()
+        if file_ in files_set:
+            return f"Non-uniq file name in lower case: {file}"
+        files_set.add(file_)
+    return ""
+
+
+if __name__ == "__main__":
+    results = []
+    stop_watch = Utils.Stopwatch()
+
+    all_files = Utils.traverse_paths(
+        include_paths=["."],
+        exclude_paths=[
+            "./.git",
+            "./contrib",
+            "./build",
+        ],
+        not_exists_ok=True,  # ./build may exist if runs locally
+    )
+
+    cpp_files = Utils.traverse_paths(
+        include_paths=["./src", "./base", "./programs", "./utils"],
+        exclude_paths=[
+            "./base/glibc-compatibility",
+            "./contrib/consistent-hashing",
+            "./base/widechar_width",
+        ],
+        file_suffixes=[".h", ".cpp"],
+    )
+
+    yaml_workflow_files = Utils.traverse_paths(
+        include_paths=["./.github"],
+        exclude_paths=[],
+        file_suffixes=[".yaml", ".yml"],
+    )
+
+    xml_files = Utils.traverse_paths(
+        include_paths=["."],
+        exclude_paths=["./.git", "./contrib/"],
+        file_suffixes=[".xml"],
+    )
+
+    functional_test_files = Utils.traverse_paths(
+        include_paths=["./tests/queries"],
+        exclude_paths=[],
+        file_suffixes=[".sql", ".sh", ".py", ".j2"],
+    )
+
+    results.append(
+        Result(
+            name="Read Files",
+            status=Result.Status.SUCCESS,
+            start_time=stop_watch.start_time,
+            duration=stop_watch.duration,
+        )
+    )
+
+    results.append(
+        run_check_concurrent(
+            check_name="Whitespace Check",
+            check_function=check_whitespaces,
+            files=cpp_files,
+        )
+    )
+    results.append(
+        run_check_concurrent(
+            check_name="YamlLint Check",
+            check_function=check_yamllint,
+            files=yaml_workflow_files,
+        )
+    )
+    results.append(
+        run_check_concurrent(
+            check_name="XmlLint Check",
+            check_function=check_xmllint,
+            files=xml_files,
+        )
+    )
+    results.append(
+        run_check_concurrent(
+            check_name="Functional Tests scripts smoke check",
+            check_function=check_functional_test_cases,
+            files=functional_test_files,
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Tests Numbers",
+            command=check_gaps_in_tests_numbers,
+            command_args=[functional_test_files],
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Broken Symlinks",
+            command=check_broken_links,
+            command_kwargs={
+                "path": "./",
+                "exclude_paths": ["contrib/", "metadata/", "programs/server/data"],
+            },
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check CPP code",
+            command=check_cpp_code,
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Submodules",
+            command=check_repo_submodules,
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check File Names",
+            command=check_file_names,
+            command_args=[all_files],
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Many Different Things",
+            command=check_other,
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Codespell",
+            command=check_codespell,
+        )
+    )
+    results.append(
+        Result.create_from_command_execution(
+            name="Check Aspell",
+            command=check_aspell,
+        )
+    )
+
+    Result.create_from(results=results, stopwatch=stop_watch).complete_job()

ci/jobs/fast_test.py

@@ -0,0 +1,232 @@
+import argparse
+
+from praktika.result import Result
+from praktika.settings import Settings
+from praktika.utils import MetaClasses, Shell, Utils
+
+from ci.jobs.scripts.clickhouse_proc import ClickHouseProc
+from ci.jobs.scripts.functional_tests_results import FTResultsProcessor
+
+
+def clone_submodules():
+    submodules_to_update = [
+        "contrib/sysroot",
+        "contrib/magic_enum",
+        "contrib/abseil-cpp",
+        "contrib/boost",
+        "contrib/zlib-ng",
+        "contrib/libxml2",
+        "contrib/libunwind",
+        "contrib/fmtlib",
+        "contrib/aklomp-base64",
+        "contrib/cctz",
+        "contrib/libcpuid",
+        "contrib/libdivide",
+        "contrib/double-conversion",
+        "contrib/llvm-project",
+        "contrib/lz4",
+        "contrib/zstd",
+        "contrib/fastops",
+        "contrib/rapidjson",
+        "contrib/re2",
+        "contrib/sparsehash-c11",
+        "contrib/croaring",
+        "contrib/miniselect",
+        "contrib/xz",
+        "contrib/dragonbox",
+        "contrib/fast_float",
+        "contrib/NuRaft",
+        "contrib/jemalloc",
+        "contrib/replxx",
+        "contrib/wyhash",
+        "contrib/c-ares",
+        "contrib/morton-nd",
+        "contrib/xxHash",
+        "contrib/expected",
+        "contrib/simdjson",
+        "contrib/liburing",
+        "contrib/libfiu",
+        "contrib/incbin",
+        "contrib/yaml-cpp",
+    ]
+
+    res = Shell.check("git submodule sync", verbose=True, strict=True)
+    res = res and Shell.check("git submodule init", verbose=True, strict=True)
+    res = res and Shell.check(
+        command=f"xargs --max-procs={min([Utils.cpu_count(), 20])} --null --no-run-if-empty --max-args=1 git submodule update --depth 1 --single-branch",
+        stdin_str="\0".join(submodules_to_update) + "\0",
+        timeout=120,
+        retries=3,
+        verbose=True,
+    )
+    res = res and Shell.check("git submodule foreach git reset --hard", verbose=True)
+    res = res and Shell.check("git submodule foreach git checkout @ -f", verbose=True)
+    res = res and Shell.check("git submodule foreach git clean -xfd", verbose=True)
+    return res
+
+
+def update_path_ch_config(config_file_path=""):
+    print("Updating path in clickhouse config")
+    config_file_path = (
+        config_file_path or f"{Settings.TEMP_DIR}/etc/clickhouse-server/config.xml"
+    )
+    ssl_config_file_path = (
+        f"{Settings.TEMP_DIR}/etc/clickhouse-server/config.d/ssl_certs.xml"
+    )
+    try:
+        with open(config_file_path, "r", encoding="utf-8") as file:
+            content = file.read()
+
+        with open(ssl_config_file_path, "r", encoding="utf-8") as file:
+            ssl_config_content = file.read()
+        content = content.replace(">/var/", f">{Settings.TEMP_DIR}/var/")
+        content = content.replace(">/etc/", f">{Settings.TEMP_DIR}/etc/")
+        ssl_config_content = ssl_config_content.replace(
+            ">/etc/", f">{Settings.TEMP_DIR}/etc/"
+        )
+        with open(config_file_path, "w", encoding="utf-8") as file:
+            file.write(content)
+        with open(ssl_config_file_path, "w", encoding="utf-8") as file:
+            file.write(ssl_config_content)
+    except Exception as e:
+        print(f"ERROR: failed to update config, exception: {e}")
+        return False
+    return True
+
+
+class JobStages(metaclass=MetaClasses.WithIter):
+    CHECKOUT_SUBMODULES = "checkout"
+    CMAKE = "cmake"
+    BUILD = "build"
+    CONFIG = "config"
+    TEST = "test"
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="ClickHouse Fast Test Job")
+    parser.add_argument("--param", help="Optional custom job start stage", default=None)
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    stop_watch = Utils.Stopwatch()
+
+    stages = list(JobStages)
+    stage = args.param or JobStages.CHECKOUT_SUBMODULES
+    if stage:
+        assert stage in JobStages, f"--param must be one of [{list(JobStages)}]"
+        print(f"Job will start from stage [{stage}]")
+        while stage in stages:
+            stages.pop(0)
+        stages.insert(0, stage)
+
+    current_directory = Utils.cwd()
+    build_dir = f"{Settings.TEMP_DIR}/build"
+
+    Utils.add_to_PATH(f"{build_dir}/programs:{current_directory}/tests")
+
+    res = True
+    results = []
+
+    if res and JobStages.CHECKOUT_SUBMODULES in stages:
+        Shell.check(f"rm -rf {build_dir} && mkdir -p {build_dir}")
+        results.append(
+            Result.create_from_command_execution(
+                name="Checkout Submodules",
+                command=clone_submodules,
+            )
+        )
+        res = results[-1].is_ok()
+
+    if res and JobStages.CMAKE in stages:
+        results.append(
+            Result.create_from_command_execution(
+                name="Cmake configuration",
+                command=f"cmake {current_directory} -DCMAKE_CXX_COMPILER=clang++-18 -DCMAKE_C_COMPILER=clang-18 \
+                -DCMAKE_TOOLCHAIN_FILE={current_directory}/cmake/linux/toolchain-x86_64-musl.cmake -DENABLE_LIBRARIES=0 \
+                -DENABLE_TESTS=0 -DENABLE_UTILS=0 -DENABLE_THINLTO=0 -DENABLE_NURAFT=1 -DENABLE_SIMDJSON=1 \
+                -DENABLE_JEMALLOC=1 -DENABLE_LIBURING=1 -DENABLE_YAML_CPP=1 -DCOMPILER_CACHE=sccache",
+                workdir=build_dir,
+                with_log=True,
+            )
+        )
+        res = results[-1].is_ok()
+
+    if res and JobStages.BUILD in stages:
+        Shell.check("sccache --show-stats")
+        results.append(
+            Result.create_from_command_execution(
+                name="Build ClickHouse",
+                command="ninja clickhouse-bundle clickhouse-stripped",
+                workdir=build_dir,
+                with_log=True,
+            )
+        )
+        Shell.check("sccache --show-stats")
+        res = results[-1].is_ok()
+
+    if res and JobStages.BUILD in stages:
+        commands = [
+            f"mkdir -p {Settings.OUTPUT_DIR}/binaries",
+            f"cp ./programs/clickhouse {Settings.OUTPUT_DIR}/binaries/clickhouse",
+            f"zstd --threads=0 --force programs/clickhouse-stripped -o {Settings.OUTPUT_DIR}/binaries/clickhouse-stripped.zst",
+            "sccache --show-stats",
+            "clickhouse-client --version",
+            "clickhouse-test --help",
+        ]
+        results.append(
+            Result.create_from_command_execution(
+                name="Check and Compress binary",
+                command=commands,
+                workdir=build_dir,
+                with_log=True,
+            )
+        )
+        res = results[-1].is_ok()
+
+    if res and JobStages.CONFIG in stages:
+        commands = [
+            f"rm -rf {Settings.TEMP_DIR}/etc/ && mkdir -p {Settings.TEMP_DIR}/etc/clickhouse-client {Settings.TEMP_DIR}/etc/clickhouse-server",
+            f"cp ./programs/server/config.xml ./programs/server/users.xml {Settings.TEMP_DIR}/etc/clickhouse-server/",
+            f"./tests/config/install.sh {Settings.TEMP_DIR}/etc/clickhouse-server {Settings.TEMP_DIR}/etc/clickhouse-client --fast-test",
+            # f"cp -a {current_directory}/programs/server/config.d/log_to_console.xml {Settings.TEMP_DIR}/etc/clickhouse-server/config.d/",
+            f"rm -f {Settings.TEMP_DIR}/etc/clickhouse-server/config.d/secure_ports.xml",
+            update_path_ch_config,
+        ]
+        results.append(
+            Result.create_from_command_execution(
+                name="Install ClickHouse Config",
+                command=commands,
+                with_log=True,
+            )
+        )
+        res = results[-1].is_ok()
+
+    CH = ClickHouseProc(fast_test=True)
+    if res and JobStages.TEST in stages:
+        stop_watch_ = Utils.Stopwatch()
+        step_name = "Start ClickHouse Server"
+        print(step_name)
+        res = CH.start()
+        res = res and CH.wait_ready()
+        results.append(
+            Result.create_from(name=step_name, status=res, stopwatch=stop_watch_)
+        )
+
+    if res and JobStages.TEST in stages:
+        stop_watch_ = Utils.Stopwatch()
+        step_name = "Tests"
+        print(step_name)
+        res = res and CH.run_fast_test()
+        if res:
+            results.append(FTResultsProcessor(wd=Settings.OUTPUT_DIR).run())
+        results[-1].set_timing(stopwatch=stop_watch_)
+
+    CH.terminate()
+
+    Result.create_from(results=results, stopwatch=stop_watch).complete_job()
+
+
+if __name__ == "__main__":
+    main()