Merge branch 'ClickHouse:master' into func_overlay

.clang-tidy

@@ -27,6 +27,8 @@ Checks: [
   '-bugprone-not-null-terminated-result',
   '-bugprone-reserved-identifier', # useful but too slow, TODO retry when https://reviews.llvm.org/rG1c282052624f9d0bd273bde0b47b30c96699c6c7 is merged
   '-bugprone-unchecked-optional-access',
+  '-bugprone-crtp-constructor-accessibility',
+  '-bugprone-suspicious-stringview-data-usage',
 
   '-cert-dcl16-c',
   '-cert-dcl37-c',
@@ -36,6 +38,7 @@ Checks: [
   '-cert-msc51-cpp',
   '-cert-oop54-cpp',
   '-cert-oop57-cpp',
+  '-cert-err33-c', # Misreports on clang-19: it warns about all functions containing 'remove' in the name, not only about the standard library.
 
   '-clang-analyzer-optin.performance.Padding',
 
@@ -99,6 +102,7 @@ Checks: [
   '-modernize-use-emplace',
   '-modernize-use-nodiscard',
   '-modernize-use-trailing-return-type',
+  '-modernize-use-designated-initializers',
 
   '-performance-enum-size',
   '-performance-inefficient-string-concatenation',

.git-blame-ignore-revs

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

.github/actionlint.yml

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

.github/actions/release/action.yml

@@ -0,0 +1,168 @@
+name: Release
+
+description: Makes patch releases and creates new release branch
+
+inputs:
+  ref:
+    description: 'Git reference (branch or commit sha) from which to create the release'
+    required: true
+    type: string
+  type:
+    description: 'The type of release: "new" for a new release or "patch" for a patch release'
+    required: true
+    type: choice
+    options:
+      - patch
+      - new
+  dry-run:
+    description: 'Dry run'
+    required: false
+    default: true
+    type: boolean
+  token:
+    required: true
+    type: string
+
+runs:
+  using: "composite"
+  steps:
+    - name: Prepare Release Info
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --prepare-release-info \
+          --ref ${{ inputs.ref }} --release-type ${{ inputs.type }} \
+          ${{ inputs.dry-run && '--dry-run' || '' }}
+        echo "::group::Release Info"
+        python3 -m json.tool /tmp/release_info.json
+        echo "::endgroup::"
+        release_tag=$(jq -r '.release_tag' /tmp/release_info.json)
+        commit_sha=$(jq -r '.commit_sha' /tmp/release_info.json)
+        echo "Release Tag: $release_tag"
+        echo "RELEASE_TAG=$release_tag" >> "$GITHUB_ENV"
+        echo "COMMIT_SHA=$commit_sha" >> "$GITHUB_ENV"
+    - name: Download All Release Artifacts
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --download-packages ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Push Git Tag for the Release
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --push-release-tag ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Push New Release Branch
+      if: ${{ inputs.type == 'new' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --push-new-release-branch ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Bump CH Version and Update Contributors' List
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --create-bump-version-pr ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Bump Docker versions, Changelog, Security
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        git checkout master
+        python3 ./tests/ci/create_release.py --set-progress-started --progress "update changelog, docker version, security"
+        echo "List versions"
+        ./utils/list-versions/list-versions.sh > ./utils/list-versions/version_date.tsv
+        echo "Update docker version"
+        ./utils/list-versions/update-docker-version.sh
+        echo "Generate ChangeLog"
+        export CI=1
+        docker run -u "${UID}:${GID}" -e PYTHONUNBUFFERED=1 -e CI=1 --network=host \
+          --volume=".:/ClickHouse" clickhouse/style-test \
+          /ClickHouse/tests/ci/changelog.py -v --debug-helpers \
+          --gh-user-or-token=${{ inputs.token }} --jobs=5 \
+          --output="/ClickHouse/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 }}
+      uses: peter-evans/create-pull-request@v6
+      with:
+        author: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
+        token: ${{ inputs.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 }}
+        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: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/create_release.py --set-progress-completed
+        git reset --hard HEAD
+        git checkout "$GITHUB_REF_NAME"
+    - name: Create GH Release
+      shell: bash
+      if: ${{ inputs.type == 'patch' }}
+      run: |
+        python3 ./tests/ci/create_release.py --create-gh-release ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Export TGZ Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --export-tgz ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Test TGZ Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --test-tgz ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Export RPM Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --export-rpm ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Test RPM Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --test-rpm ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Export Debian Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --export-debian ${{ inputs.dry-run && '--dry-run' || '' }}
+    - name: Test Debian Packages
+      if: ${{ inputs.type == 'patch' }}
+      shell: bash
+      run: |
+        python3 ./tests/ci/artifactory.py --test-debian ${{ inputs.dry-run && '--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 --release-type auto --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 --release-type auto --version ${{ env.RELEASE_TAG }} --check-name "$CHECK_NAME" --sha ${{ env.COMMIT_SHA }} ${{ ! inputs.dry-run && '--push'  || '' }}
+        python3 ./create_release.py --set-progress-completed
+    - name: Set current Release progress to Completed with OK
+      shell: bash
+      run: |
+        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 && '--dry-run' || '' }}

.github/workflows/auto_release.yml

@@ -1,44 +1,110 @@
 name: AutoRelease
 
 env:
-  # Force the stdout and stderr streams to be unbuffered
   PYTHONUNBUFFERED: 1
+  DRY_RUN: true
 
 concurrency:
-  group: auto-release
+  group: release
 on: # yamllint disable-line rule:truthy
-  # schedule:
-  #   - cron: '0 10-16 * * 1-5'
+  # Workflow uses a test bucket for packages and dry run mode (no real releases)
+  schedule:
+    - cron: '0 9 * * *'
+    - cron: '0 15 * * *'
   workflow_dispatch:
+    inputs:
+      dry-run:
+        description: 'Dry run'
+        required: false
+        default: true
+        type: boolean
 
 jobs:
-  CherryPick:
-    runs-on: [self-hosted, style-checker-aarch64]
+  AutoRelease:
+    runs-on: [self-hosted, release-maker]
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - 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: Set DRY_RUN for schedule
+        if: ${{ github.event_name == 'schedule' }}
+        run: echo "DRY_RUN=true" >> "$GITHUB_ENV"
+      - name: Set DRY_RUN for dispatch
+        if: ${{ github.event_name == 'workflow_dispatch' }}
+        run: echo "DRY_RUN=${{ github.event.inputs.dry-run }}" >> "$GITHUB_ENV"
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
-          clear-repository: true
           token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
           fetch-depth: 0
-      - name: Auto-release
+      - name: Auto Release Prepare
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 auto_release.py --release-after-days=3
-      - name: Cleanup
-        if: always()
+          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_info.json
+              echo 'EOF'
+          } >> "$GITHUB_ENV"
+      - name: Post Release Branch statuses
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 auto_release.py --post-status
+      - name: Release ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[0].release_branch }}
+        if: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[0] && fromJson(env.AUTO_RELEASE_PARAMS).releases[0].ready }}
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[0].commit_sha }}
+          type: patch
+          dry-run: ${{ env.DRY_RUN }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+      - name: Release ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[1].release_branch }}
+        if: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[0] && fromJson(env.AUTO_RELEASE_PARAMS).releases[1].ready }}
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[1].commit_sha }}
+          type: patch
+          dry-run: ${{ env.DRY_RUN }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+      - name: Release ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[2].release_branch }}
+        if: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[2] && fromJson(env.AUTO_RELEASE_PARAMS).releases[2].ready }}
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[2].commit_sha }}
+          type: patch
+          dry-run: ${{ env.DRY_RUN }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+      - name: Release ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[3].release_branch }}
+        if: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[3] && fromJson(env.AUTO_RELEASE_PARAMS).releases[3].ready }}
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[3].commit_sha }}
+          type: patch
+          dry-run: ${{ env.DRY_RUN }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+      - name: Release ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[4].release_branch }}
+        if: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[4] && fromJson(env.AUTO_RELEASE_PARAMS).releases[4].ready }}
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ fromJson(env.AUTO_RELEASE_PARAMS).releases[4].commit_sha }}
+          type: patch
+          dry-run: ${{ env.DRY_RUN }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+      - name: Post Slack Message
+        if: ${{ !cancelled() }}
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 auto_release.py --post-auto-release-complete --wf-status ${{ job.status }}
+      - name: Clean up
         run: |
           docker ps --quiet | xargs --no-run-if-empty docker kill ||:
           docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:

.github/workflows/backport_branches.yml

@@ -36,10 +36,6 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           echo "Testing the main ci directory"
           python3 -m unittest discover -s . -p 'test_*.py'
-          for dir in *_lambda/; do
-            echo "Testing $dir"
-            python3 -m unittest discover -s "$dir" -p 'test_*.py'
-          done
       - name: PrepareRunConfig
         id: runconfig
         run: |
@@ -62,7 +58,7 @@ jobs:
   BuildDockers:
     needs: [RunConfig]
     if: ${{ !failure() && !cancelled() }}
-    uses: ./.github/workflows/reusable_docker.yml
+    uses: ./.github/workflows/docker_test_images.yml
     with:
       data: ${{ needs.RunConfig.outputs.data }}
   CompatibilityCheckX86:
@@ -245,8 +241,9 @@ jobs:
       runner_type: stress-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - Builds_Report
       - FunctionalStatelessTestAsan
       - FunctionalStatefulTestDebug
@@ -261,6 +258,7 @@ jobs:
         with:
           clear-repository: true
       - name: Finish label
+        if: ${{ !failure() }}
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
           # update mergeable check
@@ -268,3 +266,10 @@ jobs:
           # update overall ci report
           python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
           python3 merge_pr.py
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/create_release.yml

@@ -2,12 +2,11 @@ name: CreateRelease
 
 concurrency:
   group: release
-
 '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 +14,31 @@ concurrency:
         required: true
         type: choice
         options:
-          - new
           - patch
+          - new
+      dry-run:
+        description: 'Dry run'
+        required: false
+        default: true
+        type: boolean
 
 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: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
-      - name: Print greeting
-        run: |
-          python3 ./tests/ci/release.py --commit ${{ inputs.sha }} --type ${{ inputs.type }} --dry-run
+        with:
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
+          fetch-depth: 0
+      - name: Call Release Action
+        uses: ./.github/actions/release
+        with:
+          ref: ${{ inputs.ref }}
+          type: ${{ inputs.type }}
+          dry-run: ${{ inputs.dry-run }}
+          token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}

.github/workflows/jepsen.yml

@@ -9,19 +9,64 @@ on: # yamllint disable-line rule:truthy
     - cron: '0 */6 * * *'
   workflow_dispatch:
 jobs:
+  RunConfig:
+    runs-on: [self-hosted, style-checker-aarch64]
+    outputs:
+      data: ${{ steps.runconfig.outputs.CI_DATA }}
+    steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
+      - name: PrepareRunConfig
+        id: runconfig
+        run: |
+          echo "::group::configure CI run"
+          python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --workflow "$GITHUB_WORKFLOW" --outfile ${{ runner.temp }}/ci_run_data.json
+          echo "::endgroup::"
+          
+          echo "::group::CI run configure results"
+          python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
+          echo "::endgroup::"
+          {
+            echo 'CI_DATA<<EOF'
+            cat  ${{ runner.temp }}/ci_run_data.json
+            echo 'EOF'
+          } >> "$GITHUB_OUTPUT"
   KeeperJepsenRelease:
-    uses: ./.github/workflows/reusable_simple_job.yml
+    needs: [RunConfig]
+    uses: ./.github/workflows/reusable_test.yml
     with:
-      test_name: Jepsen keeper check
-      runner_type: style-checker
-      report_required: true
+      test_name: ClickHouse Keeper Jepsen
+      runner_type: style-checker-aarch64
+      data: ${{ needs.RunConfig.outputs.data }}
       run_command: |
         python3 jepsen_check.py keeper
-  # ServerJepsenRelease:
-  #   uses: ./.github/workflows/reusable_simple_job.yml
-  #   with:
-  #     test_name: Jepsen server check
-  #     runner_type: style-checker
-  #     run_command: |
-  #       cd "$REPO_COPY/tests/ci"
-  #       python3 jepsen_check.py server
+  ServerJepsenRelease:
+    if: false  # skip for server
+    needs: [RunConfig]
+    uses: ./.github/workflows/reusable_test.yml
+    with:
+      test_name: ClickHouse Server Jepsen
+      runner_type: style-checker-aarch64
+      data: ${{ needs.RunConfig.outputs.data }}
+      run_command: |
+        python3 jepsen_check.py server
+  CheckWorkflow:
+    if: ${{ !cancelled() }}
+    needs: [RunConfig, ServerJepsenRelease, KeeperJepsenRelease]
+    runs-on: [self-hosted, style-checker-aarch64]
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat >> "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/master.yml

@@ -33,10 +33,6 @@ jobs:
 #          cd "$GITHUB_WORKSPACE/tests/ci"
 #          echo "Testing the main ci directory"
 #          python3 -m unittest discover -s . -p 'test_*.py'
-#          for dir in *_lambda/; do
-#            echo "Testing $dir"
-#            python3 -m unittest discover -s "$dir" -p 'test_*.py'
-#          done
       - name: PrepareRunConfig
         id: runconfig
         run: |
@@ -58,7 +54,7 @@ jobs:
 #  BuildDockers:
 #    needs: [RunConfig]
 #    if: ${{ !failure() && !cancelled() }}
-#    uses: ./.github/workflows/reusable_docker.yml
+#    uses: ./.github/workflows/docker_test_images.yml
 #    with:
 #      data: ${{ needs.RunConfig.outputs.data }}
   # StyleCheck:
@@ -97,21 +93,21 @@ jobs:
     with:
       stage: Builds_2
       data: ${{ needs.RunConfig.outputs.data }}
-  Tests_2:
+  Tests_2_ww:
     needs: [RunConfig, Builds_2]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2_ww') }}
+    uses: ./.github/workflows/reusable_test_stage.yml
+    with:
+      stage: Tests_2_ww
+      data: ${{ needs.RunConfig.outputs.data }}
+  Tests_2:
+    # Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
+    needs: [RunConfig, Builds_1]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2') }}
     uses: ./.github/workflows/reusable_test_stage.yml
     with:
       stage: Tests_2
       data: ${{ needs.RunConfig.outputs.data }}
-  Tests_3:
-    # Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
-    needs: [RunConfig, Builds_1]
-    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
-    uses: ./.github/workflows/reusable_test_stage.yml
-    with:
-      stage: Tests_3
-      data: ${{ needs.RunConfig.outputs.data }}
 
   ################################# Reports #################################
   # Reports should run even if Builds_1/2 fail - run them separately, not in Tests_1/2/3
@@ -125,37 +121,9 @@ jobs:
       runner_type: style-checker-aarch64
       data: ${{ needs.RunConfig.outputs.data }}
 
-  MarkReleaseReady:
-    if: ${{ !failure() && !cancelled() }}
-    needs: [RunConfig, Builds_1, Builds_2]
-    runs-on: [self-hosted, style-checker-aarch64]
-    steps:
-      - name: Debug
-        run: |
-          echo need with different filters
-          cat << 'EOF'
-          ${{ toJSON(needs) }}
-          ${{ toJSON(needs.*.result) }}
-          no failures ${{ !contains(needs.*.result, 'failure') }}
-          no skips ${{ !contains(needs.*.result, 'skipped') }}
-          no both ${{ !(contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
-          EOF
-      - name: Not ready
-        # fail the job to be able to restart it
-        if: ${{ contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure') }}
-        run: exit 1
-      - name: Check out repository code
-        if: ${{ ! (contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
-        uses: ClickHouse/checkout@v1
-      - name: Mark Commit Release Ready
-        if: ${{ ! (contains(needs.*.result, 'skipped') || contains(needs.*.result, 'failure')) }}
-        run: |
-          cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 mark_release_ready.py
-
   FinishCheck:
     if: ${{ !cancelled() }}
-    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code
@@ -164,3 +132,11 @@ jobs:
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
           python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+      - name: Check Workflow results
+        if: ${{ !cancelled() }}
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/merge_queue.yml

@@ -30,10 +30,6 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           echo "Testing the main ci directory"
           python3 -m unittest discover -s . -p 'test_*.py'
-          for dir in *_lambda/; do
-            echo "Testing $dir"
-            python3 -m unittest discover -s "$dir" -p 'test_*.py'
-          done
       - name: PrepareRunConfig
         id: runconfig
         run: |
@@ -51,7 +47,7 @@ jobs:
   BuildDockers:
     needs: [RunConfig]
     if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
-    uses: ./.github/workflows/reusable_docker.yml
+    uses: ./.github/workflows/docker_test_images.yml
     with:
       data: ${{ needs.RunConfig.outputs.data }}
   StyleCheck:
@@ -97,7 +93,7 @@ jobs:
       data: ${{ needs.RunConfig.outputs.data }}
 
   CheckReadyForMerge:
-    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
+    if: ${{ !cancelled() }}
     # Test_2 or Test_3 must not have jobs required for Mergeable check
     needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Tests_1]
     runs-on: [self-hosted, style-checker-aarch64]
@@ -105,6 +101,14 @@ jobs:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
       - 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 ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/nightly.yml

@@ -40,7 +40,21 @@ jobs:
             } >> "$GITHUB_OUTPUT"
   BuildDockers:
     needs: [RunConfig]
-    uses: ./.github/workflows/reusable_docker.yml
+    uses: ./.github/workflows/docker_test_images.yml
     with:
       data: "${{ needs.RunConfig.outputs.data }}"
       set_latest: true
+  CheckWorkflow:
+    if: ${{ !cancelled() }}
+    needs: [RunConfig, BuildDockers]
+    runs-on: [self-hosted, style-checker-aarch64]
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/pull_request.yml

@@ -48,10 +48,6 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           echo "Testing the main ci directory"
           python3 -m unittest discover -s . -p 'test_*.py'
-          for dir in *_lambda/; do
-            echo "Testing $dir"
-            python3 -m unittest discover -s "$dir" -p 'test_*.py'
-          done
       - name: PrepareRunConfig
         id: runconfig
         run: |
@@ -72,7 +68,7 @@ jobs:
   BuildDockers:
     needs: [RunConfig]
     if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
-    uses: ./.github/workflows/reusable_docker.yml
+    uses: ./.github/workflows/docker_test_images.yml
     with:
       data: ${{ needs.RunConfig.outputs.data }}
   StyleCheck:
@@ -127,20 +123,20 @@ 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)
@@ -155,9 +151,10 @@ 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 +162,23 @@ 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 ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+          python3 ./tests/ci/ci_buddy.py --check-wf-status
 
   ################################# Stage Final #################################
   #
   FinishCheck:
-    if: ${{ !cancelled() }}
-    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_branches.yml

@@ -33,10 +33,6 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           echo "Testing the main ci directory"
           python3 -m unittest discover -s . -p 'test_*.py'
-          for dir in *_lambda/; do
-            echo "Testing $dir"
-            python3 -m unittest discover -s "$dir" -p 'test_*.py'
-          done
       - name: PrepareRunConfig
         id: runconfig
         run: |
@@ -57,7 +53,7 @@ jobs:
   BuildDockers:
     needs: [RunConfig]
     if: ${{ !failure() && !cancelled() }}
-    uses: ./.github/workflows/reusable_docker.yml
+    uses: ./.github/workflows/docker_test_images.yml
     with:
       data: ${{ needs.RunConfig.outputs.data }}
   CompatibilityCheckX86:
@@ -445,8 +441,9 @@ jobs:
       runner_type: stress-tester
       data: ${{ needs.RunConfig.outputs.data }}
   FinishCheck:
-    if: ${{ !failure() && !cancelled() }}
+    if: ${{ !cancelled() }}
     needs:
+      - RunConfig
       - DockerServerImage
       - DockerKeeperImage
       - Builds_Report
@@ -482,9 +479,18 @@ 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 ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+      - name: Check Workflow results
+        run: |
+          export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
+          cat > "$WORKFLOW_RESULT_FILE" << 'EOF'
+          ${{ toJson(needs) }}
+          EOF
+
+          python3 ./tests/ci/ci_buddy.py --check-wf-status

.github/workflows/reusable_test.yml

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

.yamllint

@@ -14,3 +14,9 @@ rules:
     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 +1,5 @@
 ### Table of Contents
+**[ClickHouse release v24.7, 2024-07-30](#247)**<br/>
 **[ClickHouse release v24.6, 2024-07-01](#246)**<br/>
 **[ClickHouse release v24.5, 2024-05-30](#245)**<br/>
 **[ClickHouse release v24.4, 2024-04-30](#244)**<br/>
@@ -9,6 +10,178 @@
 
 # 2024 Changelog
 
+### <a id="247"></a> ClickHouse release 24.7, 2024-07-30
+
+#### Backward Incompatible Change
+* Forbid `CRATE MATERIALIZED VIEW ... ENGINE Replicated*MergeTree POPULATE AS SELECT ...` with Replicated databases. [#63963](https://github.com/ClickHouse/ClickHouse/pull/63963) ([vdimir](https://github.com/vdimir)).
+* `clickhouse-keeper-client` will only accept paths in string literals, such as `ls '/hello/world'`, not bare strings such as `ls /hello/world`. [#65494](https://github.com/ClickHouse/ClickHouse/pull/65494) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Metric `KeeperOutstandingRequets` was renamed to `KeeperOutstandingRequests`. [#66206](https://github.com/ClickHouse/ClickHouse/pull/66206) ([Robert Schulze](https://github.com/rschu1ze)).
+* Remove `is_deterministic` field from the `system.functions` table. [#66630](https://github.com/ClickHouse/ClickHouse/pull/66630) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Function `tuple` will now try to construct named tuples in query (controlled by `enable_named_columns_in_function_tuple`). Introduce function `tupleNames` to extract names from tuples. [#54881](https://github.com/ClickHouse/ClickHouse/pull/54881) ([Amos Bird](https://github.com/amosbird)).
+
+#### New Feature
+* Add `ASOF JOIN` support for `full_sorting_join` algorithm. [#55051](https://github.com/ClickHouse/ClickHouse/pull/55051) ([vdimir](https://github.com/vdimir)).
+* Add new window function `percent_rank`. [#62747](https://github.com/ClickHouse/ClickHouse/pull/62747) ([lgbo](https://github.com/lgbo-ustc)).
+* 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)).
+
+#### Experimental Feature
+* Change binary serialization of 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 rocksdb as backend storage of 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
+* Enable `optimize_functions_to_subcolumns` by default. [#58661](https://github.com/ClickHouse/ClickHouse/pull/58661) ([Anton Popov](https://github.com/CurtizJ)).
+* 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) is 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 of 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
+* 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)).
+* Allow matching column names in a case insensitive manner when reading json files (`input_format_json_case_insensitive_column_matching`). [#61750](https://github.com/ClickHouse/ClickHouse/pull/61750) ([kevinyhzou](https://github.com/KevinyhZou)).
+* 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)).
+* 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)).
+* `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)).
+* 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)).
+* 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 support cancel. [#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 ``` sql :) 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 profile events. [#65999](https://github.com/ClickHouse/ClickHouse/pull/65999) ([alesapin](https://github.com/alesapin)).
+* Support ORC file read by writer time zone. [#66025](https://github.com/ClickHouse/ClickHouse/pull/66025) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Add settings to control connection to the PostgreSQL. * Setting `postgresql_connection_attempt_timeout` specifies the value passed to `connect_timeout` parameter of connection URL. * 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/input_wait_elapsed_us/elapsed_us. [#66239](https://github.com/ClickHouse/ClickHouse/pull/66239) ([Azat Khuzhin](https://github.com/azat)).
+* Improve FilesystemCache ProfileEvents. [#66249](https://github.com/ClickHouse/ClickHouse/pull/66249) ([zhukai](https://github.com/nauu)).
+* Add settings to ignore ON CLUSTER clause in queries for named collection management with 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. ### Documentation entry for user-facing changes. [#66595](https://github.com/ClickHouse/ClickHouse/pull/66595) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Fix unexpected size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
+* 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 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 SHOW MERGES remaining time. [#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 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 cancellation buffer when canceling a query. [#64478](https://github.com/ClickHouse/ClickHouse/pull/64478) ([Sema Checherinda](https://github.com/CheSema)).
+* Fix filling parts columns from metadata (when columns.txt does not exists). [#64757](https://github.com/ClickHouse/ClickHouse/pull/64757) ([Azat Khuzhin](https://github.com/azat)).
+* Fix crash for `ALTER TABLE ... ON CLUSTER ... MODIFY SQL SECURITY`. [#64957](https://github.com/ClickHouse/ClickHouse/pull/64957) ([pufit](https://github.com/pufit)).
+* Fix crash on destroying AccessControl: add explicit shutdown. [#64993](https://github.com/ClickHouse/ClickHouse/pull/64993) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Eliminate injective function in argument of functions `uniq*` recursively. This used to work correctly but was broken in the new analyzer. [#65140](https://github.com/ClickHouse/ClickHouse/pull/65140) ([Duc Canh Le](https://github.com/canhld94)).
+* Fix unexpected projection name when query with CTE. [#65267](https://github.com/ClickHouse/ClickHouse/pull/65267) ([wudidapaopao](https://github.com/wudidapaopao)).
+* Require `dictGet` privilege when accessing dictionaries via direct query or the `Dictionary` table engine. [#65359](https://github.com/ClickHouse/ClickHouse/pull/65359) ([Joe Lynch](https://github.com/joelynch)).
+* Fix user-specific S3 auth with incremental backups. [#65481](https://github.com/ClickHouse/ClickHouse/pull/65481) ([Antonio Andelic](https://github.com/antonio2368)).
+* Disable `non-intersecting-parts` optimization for queries with `FINAL` in case of `read-in-order` optimization was enabled. This could lead to an incorrect query result. As a workaround, disable `do_not_merge_across_partitions_select_final` and `split_parts_ranges_into_intersecting_and_non_intersecting_final` before this fix is merged. [#65505](https://github.com/ClickHouse/ClickHouse/pull/65505) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix getting exception `Index out of bound for blob metadata` in case all files from list batch were filtered out. [#65523](https://github.com/ClickHouse/ClickHouse/pull/65523) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix NOT_FOUND_COLUMN_IN_BLOCK for deduplicate merge of projection. [#65573](https://github.com/ClickHouse/ClickHouse/pull/65573) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Fixed bug in MergeJoin. Column in sparse serialisation might be treated as a column of its nested type though the required conversion wasn't performed. [#65632](https://github.com/ClickHouse/ClickHouse/pull/65632) ([Nikita Taranov](https://github.com/nickitat)).
+* Fixed a bug that compatibility level '23.4' was not properly applied. [#65737](https://github.com/ClickHouse/ClickHouse/pull/65737) ([cw5121](https://github.com/cw5121)).
+* Fix odbc table with nullable fields. [#65738](https://github.com/ClickHouse/ClickHouse/pull/65738) ([Rodolphe Dugé de Bernonville](https://github.com/RodolpheDuge)).
+* Fix data race in `TCPHandler`, which could happen on fatal error. [#65744](https://github.com/ClickHouse/ClickHouse/pull/65744) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix invalid exceptions in function `parseDateTime` with `%F` and `%D` placeholders. [#65768](https://github.com/ClickHouse/ClickHouse/pull/65768) ([Antonio Andelic](https://github.com/antonio2368)).
+* For queries that read from `PostgreSQL`, cancel the internal `PostgreSQL` query if the ClickHouse query is finished. Otherwise, `ClickHouse` query cannot be canceled until the internal `PostgreSQL` query is finished. [#65771](https://github.com/ClickHouse/ClickHouse/pull/65771) ([Maksim Kita](https://github.com/kitaisreal)).
+* Fix a bug in short circuit logic when old analyzer and dictGetOrDefault is used. [#65802](https://github.com/ClickHouse/ClickHouse/pull/65802) ([jsc0218](https://github.com/jsc0218)).
+* Fix a bug leads to EmbeddedRocksDB with TTL write corrupted SST files. [#65816](https://github.com/ClickHouse/ClickHouse/pull/65816) ([Duc Canh Le](https://github.com/canhld94)).
+* Functions `bitTest`, `bitTestAll`, and `bitTestAny` now return an error if the specified bit index is out-of-bounds [#65818](https://github.com/ClickHouse/ClickHouse/pull/65818) ([Pablo Marcos](https://github.com/pamarcos)).
+* Setting `join_any_take_last_row` is supported in any query with hash join. [#65820](https://github.com/ClickHouse/ClickHouse/pull/65820) ([vdimir](https://github.com/vdimir)).
+* Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
+* Functions `bitShiftLeft` and `bitShitfRight` return an error for out of bounds shift positions [#65838](https://github.com/ClickHouse/ClickHouse/pull/65838) ([Pablo Marcos](https://github.com/pamarcos)).
+* Fix growing memory usage in S3Queue. [#65839](https://github.com/ClickHouse/ClickHouse/pull/65839) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix tie handling in `arrayAUC` to match sklearn. [#65840](https://github.com/ClickHouse/ClickHouse/pull/65840) ([gabrielmcg44](https://github.com/gabrielmcg44)).
+* Fix possible issues with MySQL server protocol TLS connections. [#65917](https://github.com/ClickHouse/ClickHouse/pull/65917) ([Azat Khuzhin](https://github.com/azat)).
+* Fix possible issues with MySQL client protocol TLS connections. [#65938](https://github.com/ClickHouse/ClickHouse/pull/65938) ([Azat Khuzhin](https://github.com/azat)).
+* Fix handling of `SSL_ERROR_WANT_READ`/`SSL_ERROR_WANT_WRITE` with zero timeout. [#65941](https://github.com/ClickHouse/ClickHouse/pull/65941) ([Azat Khuzhin](https://github.com/azat)).
+* Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
+* Column _size in s3 engine and s3 table function denotes the size of a file inside the archive, not a size of the archive itself. [#65993](https://github.com/ClickHouse/ClickHouse/pull/65993) ([Daniil Ivanik](https://github.com/divanik)).
+* Fix resolving dynamic subcolumns in analyzer, avoid reading the whole column on dynamic subcolumn reading. [#66004](https://github.com/ClickHouse/ClickHouse/pull/66004) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix config merging for from_env with replace overrides. [#66034](https://github.com/ClickHouse/ClickHouse/pull/66034) ([Azat Khuzhin](https://github.com/azat)).
+* Fix a possible hanging in `GRPCServer` during shutdown. [#66061](https://github.com/ClickHouse/ClickHouse/pull/66061) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fixed several cases in function `has` with non-constant `LowCardinality` arguments. [#66088](https://github.com/ClickHouse/ClickHouse/pull/66088) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix for `groupArrayIntersect`. It had incorrect behavior in the `merge()` function. Also, fixed behavior in `deserialise()` for numeric and general data. [#66103](https://github.com/ClickHouse/ClickHouse/pull/66103) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
+* Disable the `merge-filters` optimization introduced in [#64760](https://github.com/ClickHouse/ClickHouse/issues/64760). It may cause an exception if optimization merges two filter expressions and does not apply a short-circuit evaluation. [#66126](https://github.com/ClickHouse/ClickHouse/pull/66126) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fixed the issue when the server failed to parse Avro files with negative block size arrays encoded, which is now allowed by the Avro specification. [#66130](https://github.com/ClickHouse/ClickHouse/pull/66130) ([Serge Klochkov](https://github.com/slvrtrn)).
+* Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix rare case with missing data in the result of distributed query. [#66174](https://github.com/ClickHouse/ClickHouse/pull/66174) ([vdimir](https://github.com/vdimir)).
+* Fix order of parsing metadata fields in StorageDeltaLake. [#66211](https://github.com/ClickHouse/ClickHouse/pull/66211) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Don't throw `TIMEOUT_EXCEEDED` for `none_only_active` mode of `distributed_ddl_output_mode`. [#66218](https://github.com/ClickHouse/ClickHouse/pull/66218) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
+* Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix error reporting while copying to S3 or AzureBlobStorage. [#66295](https://github.com/ClickHouse/ClickHouse/pull/66295) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Prevent watchdog from keeping descriptors of unlinked(rotated) log files. [#66334](https://github.com/ClickHouse/ClickHouse/pull/66334) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Fix the bug that logicalexpressionoptimizerpass lost logical type of constant. [#66344](https://github.com/ClickHouse/ClickHouse/pull/66344) ([pn](https://github.com/chloro-pn)).
+* Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix possible incorrect result for queries joining and filtering table external engine (like PostgreSQL), due to too aggressive filter pushdown. Since now, conditions from where section won't be send to external database in case of outer join with external table. [#66402](https://github.com/ClickHouse/ClickHouse/pull/66402) ([vdimir](https://github.com/vdimir)).
+* Added missing column materialization for cross join. [#66413](https://github.com/ClickHouse/ClickHouse/pull/66413) ([lgbo](https://github.com/lgbo-ustc)).
+* Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Avoid possible logical error during import from Npy format in case of bad array nesting level, fix testing of other kinds of errors. [#66461](https://github.com/ClickHouse/ClickHouse/pull/66461) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix wrong count() result when there is non-deterministic function in predicate. [#66510](https://github.com/ClickHouse/ClickHouse/pull/66510) ([Duc Canh Le](https://github.com/canhld94)).
+* Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix reading of uninitialized memory when hashing empty tuples. [#66562](https://github.com/ClickHouse/ClickHouse/pull/66562) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix removing named collections in local storage. [#66599](https://github.com/ClickHouse/ClickHouse/pull/66599) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix `column_length` is not updated in `ColumnTuple::insertManyFrom`. [#66626](https://github.com/ClickHouse/ClickHouse/pull/66626) ([lgbo](https://github.com/lgbo-ustc)).
+* Fix `Unknown identifier` and `Column is not under aggregate function` errors for queries with the expression `(column IS NULL).` The bug was triggered by [#65088](https://github.com/ClickHouse/ClickHouse/issues/65088), with the disabled analyzer only. [#66654](https://github.com/ClickHouse/ClickHouse/pull/66654) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix rare case of stuck merge after drop column. [#66707](https://github.com/ClickHouse/ClickHouse/pull/66707) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix assertion `isUniqTypes` when insert select from remote sources. [#66722](https://github.com/ClickHouse/ClickHouse/pull/66722) ([Sema Checherinda](https://github.com/CheSema)).
+* Fix logical error in PrometheusRequestHandler. [#66621](https://github.com/ClickHouse/ClickHouse/pull/66621) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix `indexHint` function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix AST formatting of 'create table b empty as a'. [#64951](https://github.com/ClickHouse/ClickHouse/pull/64951) ([Michael Kolupaev](https://github.com/al13n321)).
+
+#### Build/Testing/Packaging Improvement
+* Instantiate template methods ahead in different .cpp files, avoid too large translation units during compiling. [#64818](https://github.com/ClickHouse/ClickHouse/pull/64818) ([lgbo](https://github.com/lgbo-ustc)).
+
 ### <a id="246"></a> ClickHouse release 24.6, 2024-07-01
 
 #### Backward Incompatible Change

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
     }
@@ -33,8 +34,9 @@ bool cgroupsV2MemoryControllerEnabled()
     /// According to https://docs.kernel.org/admin-guide/cgroup-v2.html, file "cgroup.controllers" defines which controllers are available
     /// for the current + child cgroups. The set of available controllers can be restricted from level to level using file
     /// "cgroups.subtree_control". It is therefore sufficient to check the bottom-most nested "cgroup.controllers" file.
-    std::string cgroup = cgroupV2OfProcess();
-    auto cgroup_dir = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
+    fs::path cgroup_dir = cgroupV2PathOfProcess();
+    if (cgroup_dir.empty())
+        return false;
     std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
     if (!controllers_file.is_open())
         return false;
@@ -46,7 +48,7 @@ bool cgroupsV2MemoryControllerEnabled()
 #endif
 }
 
-std::string cgroupV2OfProcess()
+fs::path cgroupV2PathOfProcess()
 {
 #if defined(OS_LINUX)
     chassert(cgroupsV2Enabled());
@@ -54,17 +56,18 @@ std::string cgroupV2OfProcess()
     /// A simpler way to get the membership is:
     std::ifstream cgroup_name_file("/proc/self/cgroup");
     if (!cgroup_name_file.is_open())
-        return "";
+        return {};
     /// With cgroups v2, there will be a *single* line with prefix "0::/"
     /// (see https://docs.kernel.org/admin-guide/cgroup-v2.html)
     std::string cgroup;
     std::getline(cgroup_name_file, cgroup);
     static const std::string v2_prefix = "0::/";
     if (!cgroup.starts_with(v2_prefix))
-        return "";
+        return {};
     cgroup = cgroup.substr(v2_prefix.length());
-    return cgroup;
+    /// Note: The 'root' cgroup can have an empty cgroup name, this is valid
+    return default_cgroups_mount / cgroup;
 #else
-    return "";
+    return {};
 #endif
 }

base/base/cgroupsv2.h

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

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

base/base/demangle.h

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

base/base/extended_types.h

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

base/base/getMemoryAmount.cpp

@@ -23,8 +23,9 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
     if (!cgroupsV2MemoryControllerEnabled())
         return {};
 
-    std::string cgroup = cgroupV2OfProcess();
-    auto current_cgroup = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
+    std::filesystem::path current_cgroup = cgroupV2PathOfProcess();
+    if (current_cgroup.empty())
+        return {};
 
     /// Open the bottom-most nested memory limit setting file. If there is no such file at the current
     /// level, try again at the parent level as memory settings are inherited.

base/base/isSharedPtrUnique.h

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

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

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

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

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

base/poco/Foundation/src/Format.cpp

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

base/poco/MongoDB/src/ObjectId.cpp

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

base/poco/MongoDB/src/OpMsgCursor.cpp

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

base/poco/Net/src/HTTPMessage.cpp

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

cmake/autogenerated_versions.txt

@@ -2,11 +2,11 @@
 
 # NOTE: VERSION_REVISION has nothing common with DBMS_TCP_PROTOCOL_VERSION,
 # only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
-SET(VERSION_REVISION 54488)
+SET(VERSION_REVISION 54489)
 SET(VERSION_MAJOR 24)
-SET(VERSION_MINOR 7)
+SET(VERSION_MINOR 8)
 SET(VERSION_PATCH 1)
-SET(VERSION_GITHASH aa023477a9265e403982fca5ee29a714db5133d9)
-SET(VERSION_DESCRIBE v24.7.1.1-testing)
-SET(VERSION_STRING 24.7.1.1)
+SET(VERSION_GITHASH 3f8b27d7accd2b5ec4afe7d0dd459115323304af)
+SET(VERSION_DESCRIBE v24.8.1.1-testing)
+SET(VERSION_STRING 24.8.1.1)
 # end of autochange

cmake/limit_jobs.cmake

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

contrib/azure

@@ -1 +1 @@
-Subproject commit 92c94d7f37a43cc8fc4d466884a95f610c0593bf
+Subproject commit ea3e19a7be08519134c643177d56c7484dfec884

contrib/datasketches-cpp-cmake/CMakeLists.txt

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

contrib/grpc

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

contrib/jemalloc-cmake/CMakeLists.txt

@@ -34,11 +34,7 @@ if (OS_LINUX)
     # avoid spurious latencies and additional work associated with
     # MADV_DONTNEED. See
     # https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
-    if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
-        set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
-    else()
-        set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
-    endif()
+    set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
 else()
     set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
 endif()
@@ -179,12 +175,19 @@ endif ()
 
 target_compile_definitions(_jemalloc PRIVATE -DJEMALLOC_PROF=1)
 
-# jemalloc provides support for two different libunwind flavors: the original HP libunwind and the one coming with gcc / g++ / libstdc++.
-# The latter is identified by `JEMALLOC_PROF_LIBGCC` and uses `_Unwind_Backtrace` method instead of `unw_backtrace`.
-# At the time ClickHouse uses LLVM libunwind which follows libgcc's way of backtracking.
+# jemalloc provides support two unwind flavors:
+# - JEMALLOC_PROF_LIBUNWIND - unw_backtrace() - gnu libunwind (compatible with llvm libunwind)
+# - JEMALLOC_PROF_LIBGCC - _Unwind_Backtrace() - the original HP libunwind and the one coming with gcc / g++ / libstdc++.
 #
-# ClickHouse has to provide `unw_backtrace` method by the means of [commit 8e2b31e](https://github.com/ClickHouse/libunwind/commit/8e2b31e766dd502f6df74909e04a7dbdf5182eb1).
-target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBGCC=1)
+# But for JEMALLOC_PROF_LIBGCC it also calls _Unwind_Backtrace() during
+# bootstraping of jemalloc, which may lead to deadlock, if the dlsym will do
+# allocations somewhere (like glibc does prio 2.34, see [1]).
+#
+#  [1]: https://sourceware.org/git/?p=glibc.git;a=commit;h=fada9018199c21c469ff0e731ef75c6020074ac9
+#
+# And since ClickHouse unwind already supports unw_backtrace() we can safely
+# switch to it to avoid this deadlock.
+target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBUNWIND=1)
 target_link_libraries (_jemalloc PRIVATE unwind)
 
 # for RTLD_NEXT

contrib/jemalloc-cmake/README

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

contrib/libunwind

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

contrib/libunwind-cmake/CMakeLists.txt

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

contrib/openssl

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

contrib/openssl-cmake/CMakeLists.txt

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

contrib/pocketfft

@@ -1 +1 @@
-Subproject commit 9efd4da52cf8d28d14531d14e43ad9d913807546
+Subproject commit f4c1aa8aa9ce79ad39e80f2c9c41b92ead90fda3

contrib/rocksdb

@@ -1 +1 @@
-Subproject commit 078fa5638690004e1f744076d1bdcc4e93767304
+Subproject commit be366233921293bd07a84dc4ea6991858665f202

contrib/rocksdb-cmake/CMakeLists.txt

@@ -5,20 +5,13 @@ if (NOT ENABLE_ROCKSDB)
   return()
 endif()
 
-## this file is extracted from `contrib/rocksdb/CMakeLists.txt`
-set(ROCKSDB_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/rocksdb")
-list(APPEND CMAKE_MODULE_PATH "${ROCKSDB_SOURCE_DIR}/cmake/modules/")
-
-set(PORTABLE ON)
-## always disable jemalloc for rocksdb by default
-## because it introduces non-standard jemalloc APIs
+# Always disable jemalloc for rocksdb by default because it introduces non-standard jemalloc APIs
 option(WITH_JEMALLOC "build with JeMalloc" OFF)
-set(USE_SNAPPY OFF)
-if (TARGET ch_contrib::snappy)
-  set(USE_SNAPPY ON)
-endif()
-option(WITH_SNAPPY "build with SNAPPY" ${USE_SNAPPY})
-## lz4, zlib, zstd is enabled in ClickHouse by default
+
+option(WITH_LIBURING "build with liburing" OFF) # TODO could try to enable this conditionally, depending on ClickHouse's ENABLE_LIBURING
+
+# ClickHouse cannot be compiled without snappy, lz4, zlib, zstd
+option(WITH_SNAPPY "build with SNAPPY" ON)
 option(WITH_LZ4 "build with lz4" ON)
 option(WITH_ZLIB "build with zlib" ON)
 option(WITH_ZSTD "build with zstd" ON)
@@ -26,78 +19,46 @@ option(WITH_ZSTD "build with zstd" ON)
 # third-party/folly is only validated to work on Linux and Windows for now.
 # So only turn it on there by default.
 if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
-  if(MSVC AND MSVC_VERSION LESS 1910)
-    # Folly does not compile with MSVC older than VS2017
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-  else()
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
-  endif()
+  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
 else()
   option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
 endif()
 
-if( NOT DEFINED CMAKE_CXX_STANDARD )
-  set(CMAKE_CXX_STANDARD 11)
+if(WITH_SNAPPY)
+  add_definitions(-DSNAPPY)
+  list(APPEND THIRDPARTY_LIBS ch_contrib::snappy)
 endif()
 
-if(MSVC)
-  option(WITH_XPRESS "build with windows built in compression" OFF)
-  include("${ROCKSDB_SOURCE_DIR}/thirdparty.inc")
-else()
-  if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD" AND NOT CMAKE_SYSTEM_NAME MATCHES "kFreeBSD")
-    # FreeBSD has jemalloc as default malloc
-    # but it does not have all the jemalloc files in include/...
-    set(WITH_JEMALLOC ON)
-  else()
-    if(WITH_JEMALLOC AND TARGET ch_contrib::jemalloc)
-      add_definitions(-DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE)
-      list(APPEND THIRDPARTY_LIBS ch_contrib::jemalloc)
-    endif()
-  endif()
-
-  if(WITH_SNAPPY)
-    add_definitions(-DSNAPPY)
-    list(APPEND THIRDPARTY_LIBS ch_contrib::snappy)
-  endif()
-
-  if(WITH_ZLIB)
-    add_definitions(-DZLIB)
-    list(APPEND THIRDPARTY_LIBS ch_contrib::zlib)
-  endif()
-
-  if(WITH_LZ4)
-    add_definitions(-DLZ4)
-    list(APPEND THIRDPARTY_LIBS ch_contrib::lz4)
-  endif()
-
-  if(WITH_ZSTD)
-    add_definitions(-DZSTD)
-    list(APPEND THIRDPARTY_LIBS ch_contrib::zstd)
-  endif()
+if(WITH_ZLIB)
+  add_definitions(-DZLIB)
+  list(APPEND THIRDPARTY_LIBS ch_contrib::zlib)
 endif()
 
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
-  if(POWER9)
-    set(HAS_POWER9 1)
-    set(HAS_ALTIVEC 1)
-  else()
-    set(HAS_POWER8 1)
-    set(HAS_ALTIVEC 1)
-  endif(POWER9)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
+if(WITH_LZ4)
+  add_definitions(-DLZ4)
+  list(APPEND THIRDPARTY_LIBS ch_contrib::lz4)
+endif()
 
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm64|ARM64")
-  set(HAS_ARMV8_CRC 1)
-  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm64|ARM64")
+if(WITH_ZSTD)
+  add_definitions(-DZSTD)
+  list(APPEND THIRDPARTY_LIBS ch_contrib::zstd)
+endif()
 
+option(PORTABLE "build a portable binary" ON)
 
-if(ENABLE_AVX2 AND ENABLE_PCLMULQDQ)
+if(ENABLE_SSE42 AND ENABLE_PCLMULQDQ)
   add_definitions(-DHAVE_SSE42)
   add_definitions(-DHAVE_PCLMUL)
 endif()
 
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
+  set (HAS_ARMV8_CRC 1)
+  # the original build descriptions set specific flags for ARM. These flags are already subsumed by ClickHouse's general
+  # ARM flags, see cmake/cpu_features.cmake
+  # set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
+  # set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
+endif()
+
 set (HAVE_THREAD_LOCAL 1)
 if(HAVE_THREAD_LOCAL)
   add_definitions(-DROCKSDB_SUPPORT_THREAD_LOCAL)
@@ -107,8 +68,6 @@ if(CMAKE_SYSTEM_NAME MATCHES "Darwin")
   add_definitions(-DOS_MACOSX)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
   add_definitions(-DOS_LINUX)
-elseif(CMAKE_SYSTEM_NAME MATCHES "SunOS")
-  add_definitions(-DOS_SOLARIS)
 elseif(CMAKE_SYSTEM_NAME MATCHES "FreeBSD")
   add_definitions(-DOS_FREEBSD)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Android")
@@ -123,12 +82,10 @@ endif()
 
 if (OS_LINUX)
   add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
-  add_definitions(-DROCKSDB_AUXV_SYSAUXV_PRESENT)
   add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
-elseif (OS_FREEBSD)
-  add_definitions(-DROCKSDB_AUXV_SYSAUXV_PRESENT)
 endif()
 
+set(ROCKSDB_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/rocksdb")
 
 include_directories(${ROCKSDB_SOURCE_DIR})
 include_directories("${ROCKSDB_SOURCE_DIR}/include")
@@ -136,11 +93,11 @@ if(WITH_FOLLY_DISTRIBUTED_MUTEX)
   include_directories("${ROCKSDB_SOURCE_DIR}/third-party/folly")
 endif()
 
-# Main library source code
-
 set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/cache/cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/cache_entry_roles.cc
+    ${ROCKSDB_SOURCE_DIR}/cache/cache_key.cc
+    ${ROCKSDB_SOURCE_DIR}/cache/cache_reservation_manager.cc
     ${ROCKSDB_SOURCE_DIR}/cache/clock_cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/lru_cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/sharded_cache.cc
@@ -156,6 +113,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_format.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_sequential_reader.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_writer.cc
+    ${ROCKSDB_SOURCE_DIR}/db/blob/prefetch_buffer_collection.cc
     ${ROCKSDB_SOURCE_DIR}/db/builder.cc
     ${ROCKSDB_SOURCE_DIR}/db/c.cc
     ${ROCKSDB_SOURCE_DIR}/db/column_family.cc
@@ -229,6 +187,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/env/file_system_tracer.cc
     ${ROCKSDB_SOURCE_DIR}/env/fs_remap.cc
     ${ROCKSDB_SOURCE_DIR}/env/mock_env.cc
+    ${ROCKSDB_SOURCE_DIR}/env/unique_id_gen.cc
     ${ROCKSDB_SOURCE_DIR}/file/delete_scheduler.cc
     ${ROCKSDB_SOURCE_DIR}/file/file_prefetch_buffer.cc
     ${ROCKSDB_SOURCE_DIR}/file/file_util.cc
@@ -247,6 +206,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/memory/concurrent_arena.cc
     ${ROCKSDB_SOURCE_DIR}/memory/jemalloc_nodump_allocator.cc
     ${ROCKSDB_SOURCE_DIR}/memory/memkind_kmem_allocator.cc
+    ${ROCKSDB_SOURCE_DIR}/memory/memory_allocator.cc
     ${ROCKSDB_SOURCE_DIR}/memtable/alloc_tracker.cc
     ${ROCKSDB_SOURCE_DIR}/memtable/hash_linklist_rep.cc
     ${ROCKSDB_SOURCE_DIR}/memtable/hash_skiplist_rep.cc
@@ -322,6 +282,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/table/table_factory.cc
     ${ROCKSDB_SOURCE_DIR}/table/table_properties.cc
     ${ROCKSDB_SOURCE_DIR}/table/two_level_iterator.cc
+    ${ROCKSDB_SOURCE_DIR}/table/unique_id.cc
     ${ROCKSDB_SOURCE_DIR}/test_util/sync_point.cc
     ${ROCKSDB_SOURCE_DIR}/test_util/sync_point_impl.cc
     ${ROCKSDB_SOURCE_DIR}/test_util/testutil.cc
@@ -333,9 +294,12 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/tools/ldb_tool.cc
     ${ROCKSDB_SOURCE_DIR}/tools/sst_dump_tool.cc
     ${ROCKSDB_SOURCE_DIR}/tools/trace_analyzer_tool.cc
-    ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc
     ${ROCKSDB_SOURCE_DIR}/trace_replay/block_cache_tracer.cc
     ${ROCKSDB_SOURCE_DIR}/trace_replay/io_tracer.cc
+    ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record_handler.cc
+    ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record_result.cc
+    ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record.cc
+    ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc
     ${ROCKSDB_SOURCE_DIR}/util/coding.cc
     ${ROCKSDB_SOURCE_DIR}/util/compaction_job_stats_impl.cc
     ${ROCKSDB_SOURCE_DIR}/util/comparator.cc
@@ -347,6 +311,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/util/murmurhash.cc
     ${ROCKSDB_SOURCE_DIR}/util/random.cc
     ${ROCKSDB_SOURCE_DIR}/util/rate_limiter.cc
+    ${ROCKSDB_SOURCE_DIR}/util/regex.cc
     ${ROCKSDB_SOURCE_DIR}/util/ribbon_config.cc
     ${ROCKSDB_SOURCE_DIR}/util/slice.cc
     ${ROCKSDB_SOURCE_DIR}/util/file_checksum_helper.cc
@@ -362,18 +327,23 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl_filesnapshot.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_dump_tool.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_file.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/cache_dump_load.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/cache_dump_load_impl.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/cassandra_compaction_filter.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/format.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/merge_operator.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/checkpoint/checkpoint_impl.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/debug.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/env_mirror.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/env_timed.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_env.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_fs.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_secondary_cache.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/leveldb_options/leveldb_options.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/memory/memory_util.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/bytesxor.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/max.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/put.cc
@@ -393,6 +363,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/sim_cache.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/table_properties_collectors/compact_on_deletion_collector.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/trace/file_trace_reader_writer.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/trace/replayer_impl.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/lock_manager.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_tracker.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_manager.cc
@@ -411,6 +382,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn_db.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/ttl/db_ttl_impl.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/wal_filter.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index_internal.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc
@@ -425,7 +397,7 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/standalone_port.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/dbt.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/memarena.cc
-    rocksdb_build_version.cc)
+    build_version.cc) # generated by hand
 
 if(ENABLE_SSE42 AND ENABLE_PCLMULQDQ)
   set_source_files_properties(
@@ -462,5 +434,6 @@ endif()
 add_library(_rocksdb ${SOURCES})
 add_library(ch_contrib::rocksdb ALIAS _rocksdb)
 target_link_libraries(_rocksdb PRIVATE ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+
 # SYSTEM is required to overcome some issues
 target_include_directories(_rocksdb SYSTEM BEFORE INTERFACE "${ROCKSDB_SOURCE_DIR}/include")

docker/test/base/Dockerfile

@@ -23,15 +23,17 @@ RUN apt-get update \
 # and MEMORY_LIMIT_EXCEEDED exceptions in Functional tests (total memory limit in Functional tests is ~55.24 GiB).
 # TSAN will flush shadow memory when reaching this limit.
 # It may cause false-negatives, but it's better than OOM.
-RUN echo "TSAN_OPTIONS='verbosity=1000 halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'" >> /etc/environment
-RUN echo "UBSAN_OPTIONS='print_stacktrace=1'" >> /etc/environment
-RUN echo "MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'" >> /etc/environment
-RUN echo "LSAN_OPTIONS='suppressions=/usr/share/clickhouse-test/config/lsan_suppressions.txt'" >> /etc/environment
+#  max_allocation_size_mb is set to 32GB, so we have much bigger chance to run into memory limit than the limitation of the sanitizers
+RUN echo "TSAN_OPTIONS='verbosity=1000 halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1 max_allocation_size_mb=32768'" >> /etc/environment
+RUN echo "UBSAN_OPTIONS='print_stacktrace=1 max_allocation_size_mb=32768'" >> /etc/environment
+RUN echo "MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1 max_allocation_size_mb=32768'" >> /etc/environment
+RUN echo "LSAN_OPTIONS='suppressions=/usr/share/clickhouse-test/config/lsan_suppressions.txt max_allocation_size_mb=32768'" >> /etc/environment
 # Sanitizer options for current shell (not current, but the one that will be spawned on "docker run")
 # (but w/o verbosity for TSAN, otherwise test.reference will not match)
-ENV TSAN_OPTIONS='halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'
-ENV UBSAN_OPTIONS='print_stacktrace=1'
-ENV MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'
+ENV TSAN_OPTIONS='halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1 max_allocation_size_mb=32768'
+ENV UBSAN_OPTIONS='print_stacktrace=1 max_allocation_size_mb=32768'
+ENV MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1 max_allocation_size_mb=32768'
+ENV LSAN_OPTIONS='max_allocation_size_mb=32768'
 
 # for external_symbolizer_path
 RUN ln -s /usr/bin/llvm-symbolizer-${LLVM_VERSION} /usr/bin/llvm-symbolizer

docker/test/fasttest/Dockerfile

@@ -26,7 +26,10 @@ RUN apt-get update \
         zstd \
         --yes --no-install-recommends \
     && apt-get clean \
-    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
+    && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/* \
+    && groupadd --system --gid 1000 clickhouse \
+    && useradd --system --gid 1000 --uid 1000 -m clickhouse
+# ^ For some reason, groupadd and useradd are needed for tests with 'expect', but I don't know, why.
 
 COPY requirements.txt /
 RUN pip3 install --no-cache-dir -r /requirements.txt

docker/test/fasttest/run.sh

@@ -9,7 +9,7 @@ trap 'kill $(jobs -pr) ||:' EXIT
 stage=${stage:-}
 
 # Compiler version, normally set by Dockerfile
-export LLVM_VERSION=${LLVM_VERSION:-17}
+export LLVM_VERSION=${LLVM_VERSION:-18}
 
 # A variable to pass additional flags to CMake.
 # Here we explicitly default it to nothing so that bash doesn't complain about
@@ -261,9 +261,12 @@ function timeout_with_logging() {
 
     timeout -s TERM --preserve-status "${@}" || exit_code="${?}"
 
+    echo "Checking if it is a timeout. The code 124 will indicate a timeout."
     if [[ "${exit_code}" -eq "124" ]]
     then
-      echo "The command 'timeout ${*}' has been killed by timeout"
+        echo "The command 'timeout ${*}' has been killed by timeout."
+    else
+        echo "No, it isn't a timeout."
     fi
 
     return $exit_code
@@ -284,6 +287,11 @@ function run_tests
       NPROC=1
     fi
 
+    export CLICKHOUSE_CONFIG_DIR=$FASTTEST_DATA
+    export CLICKHOUSE_CONFIG="$FASTTEST_DATA/config.xml"
+    export CLICKHOUSE_USER_FILES="$FASTTEST_DATA/user_files"
+    export CLICKHOUSE_SCHEMA_FILES="$FASTTEST_DATA/format_schemas"
+
     local test_opts=(
         --hung-check
         --fast-tests-only

docker/test/fuzzer/query-fuzzer-tweaks-users.xml

@@ -20,7 +20,7 @@
                 </max_execution_time>
 
                 <max_memory_usage>
-                    <max>10G</max>
+                    <max>5G</max>
                 </max_memory_usage>
 
                 <table_function_remote_max_addresses>

docker/test/fuzzer/run-fuzzer.sh

@@ -208,7 +208,6 @@ handle SIGPIPE nostop noprint pass
 handle SIGTERM nostop noprint pass
 handle SIGUSR1 nostop noprint pass
 handle SIGUSR2 nostop noprint pass
-handle SIGSEGV nostop pass
 handle SIG$RTMIN nostop noprint pass
 info signals
 continue

docker/test/libfuzzer/Dockerfile

@@ -33,13 +33,9 @@ RUN apt-get update \
 COPY requirements.txt /
 RUN pip3 install --no-cache-dir -r /requirements.txt
 
-COPY * /
-
 ENV FUZZER_ARGS="-max_total_time=60"
 
 SHELL ["/bin/bash", "-c"]
-CMD set -o pipefail \
-    && timeout -s 9 1h /run_libfuzzer.py 2>&1 | ts "$(printf '%%Y-%%m-%%d %%H:%%M:%%S\t')" | tee main.log
 
 # docker run --network=host --volume <workspace>:/workspace -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/libfuzzer
 

docker/test/sqlancer/Dockerfile

@@ -6,7 +6,7 @@ ARG apt_archive="http://archive.ubuntu.com"
 RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
 
 RUN apt-get update --yes \
-    && env DEBIAN_FRONTEND=noninteractive apt-get install wget git default-jdk maven python3 --yes --no-install-recommends  \
+    && env DEBIAN_FRONTEND=noninteractive apt-get install wget git python3 default-jdk maven --yes --no-install-recommends  \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 

docker/test/stateful/run.sh

@@ -4,6 +4,9 @@
 source /setup_export_logs.sh
 set -e -x
 
+MAX_RUN_TIME=${MAX_RUN_TIME:-3600}
+MAX_RUN_TIME=$((MAX_RUN_TIME == 0 ? 3600 : MAX_RUN_TIME))
+
 # Choose random timezone for this test run
 TZ="$(rg -v '#' /usr/share/zoneinfo/zone.tab | awk '{print $3}' | shuf | head -n1)"
 echo "Choosen random timezone $TZ"
@@ -16,11 +19,17 @@ dpkg -i package_folder/clickhouse-client_*.deb
 
 ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
 
+# shellcheck disable=SC1091
+source /utils.lib
+
 # install test configs
 /usr/share/clickhouse-test/config/install.sh
 
 azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --silent --inMemoryPersistence &
+
 ./setup_minio.sh stateful
+./mc admin trace clickminio > /test_output/minio.log &
+MC_ADMIN_PID=$!
 
 config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
 
@@ -182,8 +191,8 @@ else
             ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
             SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192, storage_policy='s3_cache'"
 
-        clickhouse-client --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0"
-        clickhouse-client --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0"
+        clickhouse-client --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+        clickhouse-client --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
         clickhouse-client --query "DROP TABLE datasets.visits_v1 SYNC"
         clickhouse-client --query "DROP TABLE datasets.hits_v1 SYNC"
     else
@@ -191,7 +200,7 @@ else
         clickhouse-client --query "RENAME TABLE datasets.visits_v1 TO test.visits"
     fi
     clickhouse-client --query "CREATE TABLE test.hits_s3  (WatchID UInt64, JavaEnable UInt8, Title String, GoodEvent Int16, EventTime DateTime, EventDate Date, CounterID UInt32, ClientIP UInt32, ClientIP6 FixedString(16), RegionID UInt32, UserID UInt64, CounterClass Int8, OS UInt8, UserAgent UInt8, URL String, Referer String, URLDomain String, RefererDomain String, Refresh UInt8, IsRobot UInt8, RefererCategories Array(UInt16), URLCategories Array(UInt16), URLRegions Array(UInt32), RefererRegions Array(UInt32), ResolutionWidth UInt16, ResolutionHeight UInt16, ResolutionDepth UInt8, FlashMajor UInt8, FlashMinor UInt8, FlashMinor2 String, NetMajor UInt8, NetMinor UInt8, UserAgentMajor UInt16, UserAgentMinor FixedString(2), CookieEnable UInt8, JavascriptEnable UInt8, IsMobile UInt8, MobilePhone UInt8, MobilePhoneModel String, Params String, IPNetworkID UInt32, TraficSourceID Int8, SearchEngineID UInt16, SearchPhrase String, AdvEngineID UInt8, IsArtifical UInt8, WindowClientWidth UInt16, WindowClientHeight UInt16, ClientTimeZone Int16, ClientEventTime DateTime, SilverlightVersion1 UInt8, SilverlightVersion2 UInt8, SilverlightVersion3 UInt32, SilverlightVersion4 UInt16, PageCharset String, CodeVersion UInt32, IsLink UInt8, IsDownload UInt8, IsNotBounce UInt8, FUniqID UInt64, HID UInt32, IsOldCounter UInt8, IsEvent UInt8, IsParameter UInt8, DontCountHits UInt8, WithHash UInt8, HitColor FixedString(1), UTCEventTime DateTime, Age UInt8, Sex UInt8, Income UInt8, Interests UInt16, Robotness UInt8, GeneralInterests Array(UInt16), RemoteIP UInt32, RemoteIP6 FixedString(16), WindowName Int32, OpenerName Int32, HistoryLength Int16, BrowserLanguage FixedString(2), BrowserCountry FixedString(2), SocialNetwork String, SocialAction String, HTTPError UInt16, SendTiming Int32, DNSTiming Int32, ConnectTiming Int32, ResponseStartTiming Int32, ResponseEndTiming Int32, FetchTiming Int32, RedirectTiming Int32, DOMInteractiveTiming Int32, DOMContentLoadedTiming Int32, DOMCompleteTiming Int32, LoadEventStartTiming Int32, LoadEventEndTiming Int32, NSToDOMContentLoadedTiming Int32, FirstPaintTiming Int32, RedirectCount Int8, SocialSourceNetworkID UInt8, SocialSourcePage String, ParamPrice Int64, ParamOrderID String, ParamCurrency FixedString(3), ParamCurrencyID UInt16, GoalsReached Array(UInt32), OpenstatServiceName String, OpenstatCampaignID String, OpenstatAdID String, OpenstatSourceID String, UTMSource String, UTMMedium String, UTMCampaign String, UTMContent String, UTMTerm String, FromTag String, HasGCLID UInt8, RefererHash UInt64, URLHash UInt64, CLID UInt32, YCLID UInt64, ShareService String, ShareURL String, ShareTitle String, ParsedParams Nested(Key1 String, Key2 String, Key3 String, Key4 String, Key5 String, ValueDouble Float64), IslandID FixedString(16), RequestNum UInt32, RequestTry UInt8) ENGINE = MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDate, intHash32(UserID)) SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192, storage_policy='s3_cache'"
-    clickhouse-client --query "INSERT INTO test.hits_s3 SELECT * FROM test.hits SETTINGS enable_filesystem_cache_on_write_operations=0"
+    clickhouse-client --query "INSERT INTO test.hits_s3 SELECT * FROM test.hits SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
 fi
 
 clickhouse-client --query "SHOW TABLES FROM test"
@@ -236,7 +245,25 @@ function run_tests()
 }
 
 export -f run_tests
-timeout "$MAX_RUN_TIME" bash -c run_tests ||:
+
+function timeout_with_logging() {
+    local exit_code=0
+
+    timeout -s TERM --preserve-status "${@}" || exit_code="${?}"
+
+    echo "Checking if it is a timeout. The code 124 will indicate a timeout."
+    if [[ "${exit_code}" -eq "124" ]]
+    then
+        echo "The command 'timeout ${*}' has been killed by timeout."
+    else
+        echo "No, it isn't a timeout."
+    fi
+
+    return $exit_code
+}
+
+TIMEOUT=$((MAX_RUN_TIME - 700))
+timeout_with_logging "$TIMEOUT" bash -c run_tests ||:
 
 echo "Files in current directory"
 ls -la ./
@@ -251,6 +278,8 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
     sudo clickhouse stop --pid-path /var/run/clickhouse-server2 ||:
 fi
 
+# Kill minio admin client to stop collecting logs
+kill $MC_ADMIN_PID
 rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server.log ||:
 
 zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst ||:
@@ -272,3 +301,5 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
     mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
     mv /var/log/clickhouse-server/stderr2.log /test_output/ ||:
 fi
+
+collect_core_dumps

docker/test/stateless/Dockerfile

@@ -86,6 +86,7 @@ RUN curl -L --no-verbose -O 'https://archive.apache.org/dist/hadoop/common/hadoo
 ENV MINIO_ROOT_USER="clickhouse"
 ENV MINIO_ROOT_PASSWORD="clickhouse"
 ENV EXPORT_S3_STORAGE_POLICIES=1
+ENV CLICKHOUSE_GRPC_CLIENT="/usr/share/clickhouse-utils/grpc-client/clickhouse-grpc-client.py"
 
 RUN npm install -g azurite@3.30.0 \
     && npm install -g tslib && npm install -g node

docker/test/stateless/attach_gdb.lib

@@ -20,7 +20,6 @@ handle SIGPIPE nostop noprint pass
 handle SIGTERM nostop noprint pass
 handle SIGUSR1 nostop noprint pass
 handle SIGUSR2 nostop noprint pass
-handle SIGSEGV nostop pass
 handle SIG$RTMIN nostop noprint pass
 info signals
 continue

docker/test/stateless/requirements.txt

@@ -8,6 +8,7 @@ cryptography==3.4.8
 dbus-python==1.2.18
 distro==1.7.0
 docutils==0.17.1
+grpcio==1.47.0
 gyp==0.1
 httplib2==0.20.2
 idna==3.3
@@ -28,6 +29,7 @@ packaging==24.1
 pandas==1.5.3
 pip==24.1.1
 pipdeptree==2.23.0
+protobuf==4.25.3
 pyarrow==15.0.0
 pyasn1==0.4.8
 PyJWT==2.3.0

docker/test/stateless/run.sh

@@ -6,8 +6,11 @@ source /setup_export_logs.sh
 # fail on errors, verbose and export all env variables
 set -e -x -a
 
-MAX_RUN_TIME=${MAX_RUN_TIME:-10800}
-MAX_RUN_TIME=$((MAX_RUN_TIME == 0 ? 10800 : MAX_RUN_TIME))
+MAX_RUN_TIME=${MAX_RUN_TIME:-9000}
+MAX_RUN_TIME=$((MAX_RUN_TIME == 0 ? 9000 : MAX_RUN_TIME))
+
+USE_DATABASE_REPLICATED=${USE_DATABASE_REPLICATED:=0}
+USE_SHARED_CATALOG=${USE_SHARED_CATALOG:=0}
 
 # Choose random timezone for this test run.
 #
@@ -45,6 +48,9 @@ source /utils.lib
 /usr/share/clickhouse-test/config/install.sh
 
 ./setup_minio.sh stateless
+./mc admin trace clickminio > /test_output/minio.log &
+MC_ADMIN_PID=$!
+
 ./setup_hdfs_minicluster.sh
 
 config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
@@ -92,7 +98,7 @@ fi
 # simplest way to forward env variables to server
 sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
 
-if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
     sudo sed -i "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" /etc/clickhouse-server1/config.d/filesystem_caches_path.xml
 
     sudo sed -i "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_2/</filesystem_caches_path>|" /etc/clickhouse-server2/config.d/filesystem_caches_path.xml
@@ -124,12 +130,9 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
     --keeper_server.tcp_port 29181 --keeper_server.server_id 3 \
     --prometheus.port 29988 \
     --macros.shard s2   # It doesn't work :(
-
-    MAX_RUN_TIME=$((MAX_RUN_TIME < 9000 ? MAX_RUN_TIME : 9000))  # min(MAX_RUN_TIME, 2.5 hours)
-    MAX_RUN_TIME=$((MAX_RUN_TIME != 0 ? MAX_RUN_TIME : 9000))    # set to 2.5 hours if 0 (unlimited)
 fi
 
-if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
     sudo cat /etc/clickhouse-server1/config.d/filesystem_caches_path.xml \
     | sed "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" \
     > /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp
@@ -151,9 +154,6 @@ if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
     --keeper_server.tcp_port 19181 --keeper_server.server_id 2 \
     --prometheus.port 19988 \
     --macros.replica r2   # It doesn't work :(
-
-    MAX_RUN_TIME=$((MAX_RUN_TIME < 9000 ? MAX_RUN_TIME : 9000))  # min(MAX_RUN_TIME, 2.5 hours)
-    MAX_RUN_TIME=$((MAX_RUN_TIME != 0 ? MAX_RUN_TIME : 9000))    # set to 2.5 hours if 0 (unlimited)
 fi
 
 # Wait for the server to start, but not for too long.
@@ -164,7 +164,6 @@ do
 done
 
 setup_logs_replication
-
 attach_gdb_to_clickhouse || true  # FIXME: to not break old builds, clean on 2023-09-01
 
 function fn_exists() {
@@ -209,15 +208,15 @@ function run_tests()
         ADDITIONAL_OPTIONS+=('--no-random-merge-tree-settings')
     fi
 
-    if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+    if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
         ADDITIONAL_OPTIONS+=('--shared-catalog')
     fi
 
-    if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+    if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
         ADDITIONAL_OPTIONS+=('--replicated-database')
         # Too many tests fail for DatabaseReplicated in parallel.
         ADDITIONAL_OPTIONS+=('--jobs')
-        ADDITIONAL_OPTIONS+=('2')
+        ADDITIONAL_OPTIONS+=('3')
     elif [[ 1 == $(clickhouse-client --query "SELECT value LIKE '%SANITIZE_COVERAGE%' FROM system.build_options WHERE name = 'CXX_FLAGS'") ]]; then
         # Coverage on a per-test basis could only be collected sequentially.
         # Do not set the --jobs parameter.
@@ -248,24 +247,34 @@ function run_tests()
 
     try_run_with_retry 10 clickhouse-client -q "insert into system.zookeeper (name, path, value) values ('auxiliary_zookeeper2', '/test/chroot/', '')"
 
+    TIMEOUT=$((MAX_RUN_TIME - 800 > 8400 ? 8400 : MAX_RUN_TIME - 800))
+    START_TIME=${SECONDS}
     set +e
-    timeout -s TERM --preserve-status 120m clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
-         --no-drop-if-fail --test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
+    timeout --preserve-status --signal TERM --kill-after 60m ${TIMEOUT}s \
+        clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
+            --no-drop-if-fail --test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
     | ts '%Y-%m-%d %H:%M:%S' \
     | tee -a test_output/test_result.txt
     set -e
+    DURATION=$((START_TIME - SECONDS))
+
+    echo "Elapsed ${DURATION} seconds."
+    if [[ $DURATION -ge $TIMEOUT ]]
+    then
+        echo "It looks like the command is terminated by the timeout, which is ${TIMEOUT} seconds."
+    fi
 }
 
 export -f run_tests
 
 
 # This should be enough to setup job and collect artifacts
-TIMEOUT=$((MAX_RUN_TIME - 300))
+TIMEOUT=$((MAX_RUN_TIME - 700))
 if [ "$NUM_TRIES" -gt "1" ]; then
     # We don't run tests with Ordinary database in PRs, only in master.
     # So run new/changed tests with Ordinary at least once in flaky check.
     timeout_with_logging "$TIMEOUT" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
-      | sed 's/All tests have finished//' | sed 's/No tests were run//' ||:
+      | sed 's/All tests have finished/Redacted: a message about tests finish is deleted/' | sed 's/No tests were run/Redacted: a message about no tests run is deleted/' ||:
 fi
 
 timeout_with_logging "$TIMEOUT" bash -c run_tests ||:
@@ -289,7 +298,7 @@ do
     err=$(clickhouse-client -q "select * from system.$table into outfile '/test_output/$table.tsv.gz' format TSVWithNamesAndTypes")
     echo "$err"
     [[ "0" != "${#err}"  ]] && failed_to_save_logs=1
-    if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+    if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
         err=$( { clickhouse-client --port 19000 -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst; } 2>&1 )
         echo "$err"
         [[ "0" != "${#err}"  ]] && failed_to_save_logs=1
@@ -298,7 +307,7 @@ do
         [[ "0" != "${#err}"  ]] && failed_to_save_logs=1
     fi
 
-    if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+    if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
         err=$( { clickhouse-client --port 19000 -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst; } 2>&1 )
         echo "$err"
         [[ "0" != "${#err}"  ]] && failed_to_save_logs=1
@@ -309,15 +318,20 @@ done
 # Why do we read data with clickhouse-local?
 # Because it's the simplest way to read it when server has crashed.
 sudo clickhouse stop ||:
-if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+
+
+if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
     sudo clickhouse stop --pid-path /var/run/clickhouse-server1 ||:
     sudo clickhouse stop --pid-path /var/run/clickhouse-server2 ||:
 fi
 
-if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
     sudo clickhouse stop --pid-path /var/run/clickhouse-server1 ||:
 fi
 
+# Kill minio admin client to stop collecting logs
+kill $MC_ADMIN_PID
+
 rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server.log ||:
 rg -A50 -Fa "============" /var/log/clickhouse-server/stderr.log ||:
 zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst &
@@ -341,12 +355,13 @@ if [ $failed_to_save_logs -ne 0 ]; then
     for table in query_log zookeeper_log trace_log transactions_info_log metric_log blob_storage_log error_log
     do
         clickhouse-local "$data_path_config" --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst ||:
-        if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+
+        if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
             clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
             clickhouse-local --path /var/lib/clickhouse2/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.2.tsv.zst ||:
         fi
 
-        if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+        if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
             clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
         fi
     done
@@ -382,7 +397,8 @@ rm -rf /var/lib/clickhouse/data/system/*/
 tar -chf /test_output/store.tar /var/lib/clickhouse/store ||:
 tar -chf /test_output/metadata.tar /var/lib/clickhouse/metadata/*.sql ||:
 
-if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+
+if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
     rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server1.log ||:
     rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server2.log ||:
     zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
@@ -393,9 +409,11 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
     tar -chf /test_output/coordination2.tar /var/lib/clickhouse2/coordination ||:
 fi
 
-if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
+if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
     rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server1.log ||:
     zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
     mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
     tar -chf /test_output/coordination1.tar /var/lib/clickhouse1/coordination ||:
 fi
+
+collect_core_dumps

docker/test/stateless/setup_hdfs_minicluster.sh

@@ -10,7 +10,7 @@ cd hadoop-3.3.1
 export JAVA_HOME=/usr
 mkdir -p target/test/data
 chown clickhouse ./target/test/data
-sudo -E -u clickhouse bin/mapred minicluster -format -nomr -nnport 12222 >> /test_output/garbage.log 2>&1 &
+sudo -E -u clickhouse bin/mapred minicluster -format -nomr -nnport 12222 >> /test_output/hdfs_minicluster.log 2>&1 &
 
 while ! nc -z localhost 12222; do
   sleep 1

docker/test/stateless/stress_tests.lib

@@ -1,8 +1,5 @@
 #!/bin/bash
 
-# core.COMM.PID-TID
-sysctl kernel.core_pattern='core.%e.%p-%P'
-
 OK="\tOK\t\\N\t"
 FAIL="\tFAIL\t\\N\t"
 
@@ -315,12 +312,4 @@ function collect_query_and_trace_logs()
     done
 }
 
-function collect_core_dumps()
-{
-  find . -type f -maxdepth 1 -name 'core.*' | while read -r core; do
-      zstd --threads=0 "$core"
-      mv "$core.zst" /test_output/
-  done
-}
-
 # vi: ft=bash

docker/test/stateless/utils.lib

@@ -1,5 +1,10 @@
 #!/bin/bash
 
+# core.COMM.PID-TID
+sysctl kernel.core_pattern='core.%e.%p-%P'
+# ASAN doesn't work with suid_dumpable=2
+sysctl fs.suid_dumpable=1
+
 function run_with_retry()
 {
     if [[ $- =~ e ]]; then
@@ -40,12 +45,23 @@ function timeout_with_logging() {
 
     timeout -s TERM --preserve-status "${@}" || exit_code="${?}"
 
+    echo "Checking if it is a timeout. The code 124 will indicate a timeout."
     if [[ "${exit_code}" -eq "124" ]]
     then
-      echo "The command 'timeout ${*}' has been killed by timeout"
+        echo "The command 'timeout ${*}' has been killed by timeout."
+    else
+        echo "No, it isn't a timeout."
     fi
 
     return $exit_code
 }
 
+function collect_core_dumps()
+{
+  find . -type f -maxdepth 1 -name 'core.*' | while read -r core; do
+      zstd --threads=0 "$core"
+      mv "$core.zst" /test_output/
+  done
+}
+
 # vi: ft=bash

docker/test/stress/run.sh

@@ -21,6 +21,9 @@ source /attach_gdb.lib
 # shellcheck source=../stateless/stress_tests.lib
 source /stress_tests.lib
 
+# shellcheck disable=SC1091
+source /utils.lib
+
 install_packages package_folder
 
 # Thread Fuzzer allows to check more permutations of possible thread scheduling
@@ -206,9 +209,9 @@ clickhouse-client --query "CREATE TABLE test.visits (CounterID UInt32,  StartDat
     ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
     SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192, storage_policy='$TEMP_POLICY'"
 
-clickhouse-client --query "INSERT INTO test.hits_s3 SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0"
-clickhouse-client --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0"
-clickhouse-client --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0"
+clickhouse-client --query "INSERT INTO test.hits_s3 SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+clickhouse-client --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+clickhouse-client --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
 
 clickhouse-client --query "DROP TABLE datasets.visits_v1 SYNC"
 clickhouse-client --query "DROP TABLE datasets.hits_v1 SYNC"

docker/test/style/requirements.txt

@@ -3,7 +3,7 @@ aiosignal==1.3.1
 astroid==3.1.0
 async-timeout==4.0.3
 attrs==23.2.0
-black==23.12.0
+black==24.4.2
 boto3==1.34.131
 botocore==1.34.131
 certifi==2024.6.2

docker/test/util/Dockerfile

@@ -17,6 +17,7 @@ ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=18
 
 RUN apt-get update \
     && apt-get install \
+        sudo \
         apt-transport-https \
         apt-utils \
         ca-certificates \

docker/test/util/process_functional_tests_result.py

@@ -11,6 +11,8 @@ TIMEOUT_SIGN = "[ Timeout! "
 UNKNOWN_SIGN = "[ UNKNOWN "
 SKIPPED_SIGN = "[ SKIPPED "
 HUNG_SIGN = "Found hung queries in processlist"
+SERVER_DIED_SIGN = "Server died, terminating all processes"
+SERVER_DIED_SIGN2 = "Server does not respond to health check"
 DATABASE_SIGN = "Database: "
 
 SUCCESS_FINISH_SIGNS = ["All tests have finished", "No tests were run"]
@@ -25,6 +27,7 @@ def process_test_log(log_path, broken_tests):
     failed = 0
     success = 0
     hung = False
+    server_died = False
     retries = False
     success_finish = False
     test_results = []
@@ -41,6 +44,8 @@ def process_test_log(log_path, broken_tests):
             if HUNG_SIGN in line:
                 hung = True
                 break
+            if SERVER_DIED_SIGN in line or SERVER_DIED_SIGN2 in line:
+                server_died = True
             if RETRIES_SIGN in line:
                 retries = True
             if any(
@@ -107,12 +112,12 @@ def process_test_log(log_path, broken_tests):
     # Python does not support TSV, so we have to escape '\t' and '\n' manually
     # and hope that complex escape sequences will not break anything
     test_results = [
-        (
+        [
             test[0],
             test[1],
             test[2],
             "".join(test[3])[:4096].replace("\t", "\\t").replace("\n", "\\n"),
-        )
+        ]
         for test in test_results
     ]
 
@@ -123,6 +128,7 @@ def process_test_log(log_path, broken_tests):
         failed,
         success,
         hung,
+        server_died,
         success_finish,
         retries,
         test_results,
@@ -150,6 +156,7 @@ def process_result(result_path, broken_tests):
             failed,
             success,
             hung,
+            server_died,
             success_finish,
             retries,
             test_results,
@@ -164,14 +171,23 @@ def process_result(result_path, broken_tests):
         if hung:
             description = "Some queries hung, "
             state = "failure"
-            test_results.append(("Some queries hung", "FAIL", "0", ""))
+            test_results.append(["Some queries hung", "FAIL", "0", ""])
+        elif server_died:
+            description = "Server died, "
+            state = "failure"
+            # When ClickHouse server crashes, some tests are still running
+            # and fail because they cannot connect to server
+            for result in test_results:
+                if result[1] == "FAIL":
+                    result[1] = "SERVER_DIED"
+            test_results.append(["Server died", "FAIL", "0", ""])
         elif not success_finish:
             description = "Tests are not finished, "
             state = "failure"
-            test_results.append(("Tests are not finished", "FAIL", "0", ""))
+            test_results.append(["Tests are not finished", "FAIL", "0", ""])
         elif retries:
             description = "Some tests restarted, "
-            test_results.append(("Some tests restarted", "SKIPPED", "0", ""))
+            test_results.append(["Some tests restarted", "SKIPPED", "0", ""])
         else:
             description = ""
 
@@ -218,5 +234,21 @@ if __name__ == "__main__":
     state, description, test_results = process_result(args.in_results_dir, broken_tests)
     logging.info("Result parsed")
     status = (state, description)
+
+    def test_result_comparator(item):
+        # sort by status then by check name
+        order = {
+            "FAIL": 0,
+            "SERVER_DIED": 1,
+            "Timeout": 2,
+            "NOT_FAILED": 3,
+            "BROKEN": 4,
+            "OK": 5,
+            "SKIPPED": 6,
+        }
+        return order.get(item[1], 10), str(item[0]), item[1]
+
+    test_results.sort(key=test_result_comparator)
+
     write_results(args.out_results_file, args.out_status_file, test_results, status)
     logging.info("Result written")

docs/en/development/build-cross-riscv.md

@@ -11,7 +11,7 @@ This is for the case when you have Linux machine and want to use it to build `cl
 
 The cross-build for RISC-V 64 is based on the [Build instructions](../development/build.md), follow them first.
 
-## Install Clang-16
+## Install Clang-18
 
 Follow the instructions from https://apt.llvm.org/ for your Ubuntu or Debian setup or do
 ```

docs/en/development/developer-instruction.md

@@ -226,15 +226,59 @@ Other IDEs you can use are [Sublime Text](https://www.sublimetext.com/), [Visual
 
 ## Writing Code {#writing-code}
 
-The description of ClickHouse architecture can be found here: https://clickhouse.com/docs/en/development/architecture/
+Below you can find some quick links which may be useful when writing code for ClickHouse:
 
-The Code Style Guide: https://clickhouse.com/docs/en/development/style/
+- [ClickHouse architecture description](https://clickhouse.com/docs/en/development/architecture/). 
+- [The code style guide](https://clickhouse.com/docs/en/development/style/).
+- [Adding third-party libraries](https://clickhouse.com/docs/en/development/contrib/#adding-third-party-libraries)
+- [Writing tests](https://clickhouse.com/docs/en/development/tests/)
+- [List of open issues](https://github.com/ClickHouse/ClickHouse/issues?q=is%3Aopen+is%3Aissue+label%3Ahacktoberfest)
 
-Adding third-party libraries: https://clickhouse.com/docs/en/development/contrib/#adding-third-party-libraries
+## Writing Documentation {#writing-documentation}
 
-Writing tests: https://clickhouse.com/docs/en/development/tests/
+As part of every pull request which adds a new feature, it is necessary to write documentation for it. If you'd like to preview your documentation changes the instructions for how to build the documentation page locally are available in the README.md file [here](https://github.com/ClickHouse/clickhouse-docs). When adding a new function to ClickHouse you can use the template below as a guide:
 
-List of tasks: https://github.com/ClickHouse/ClickHouse/issues?q=is%3Aopen+is%3Aissue+label%3Ahacktoberfest
+```markdown
+# newFunctionName
+
+A short description of the function goes here. It should describe briefly what it does and a typical usage case.
+
+**Syntax**
+
+\```sql
+newFunctionName(arg1, arg2[, arg3])
+\```
+
+**Arguments**
+
+- `arg1` — Description of the argument. [DataType](../data-types/float.md)
+- `arg2` — Description of the argument. [DataType](../data-types/float.md)
+- `arg3` — Description of optional argument (optional). [DataType](../data-types/float.md)
+
+**Implementation Details**
+
+A description of implementation details if relevant.
+
+**Returned value**
+
+- Returns {insert what the function returns here}. [DataType](../data-types/float.md)
+
+**Example**
+
+Query:
+
+\```sql
+SELECT 'write your example query here';
+\```
+
+Response:
+
+\```response
+┌───────────────────────────────────┐
+│ the result of the query           │
+└───────────────────────────────────┘
+\```
+```
 
 ## Test Data {#test-data}
 

docs/en/engines/table-engines/integrations/s3queue.md

@@ -75,7 +75,7 @@ SETTINGS
 Possible values:
 
 - unordered — With unordered mode, the set of all already processed files is tracked with persistent nodes in ZooKeeper.
-- ordered — With ordered mode, only the max name of the successfully consumed file, and the names of files that will be retried after unsuccessful loading attempt are being stored in ZooKeeper.
+- ordered — With ordered mode, the files are processed in lexicographic order. It means that if file named 'BBB' was processed at some point and later on a file named 'AA' is added to the bucket, it will be ignored. Only the max name (in lexicographic sense) of the successfully consumed file, and the names of files that will be retried after unsuccessful loading attempt are being stored in ZooKeeper.
 
 Default value: `ordered` in versions before 24.6. Starting with 24.6 there is no default value, the setting becomes required to be specified manually. For tables created on earlier versions the default value will remain `Ordered` for compatibility.
 

docs/en/engines/table-engines/mergetree-family/mergetree.md

@@ -999,6 +999,10 @@ They can be used for prewhere optimization only if we enable `set allow_statisti
 
     [HyperLogLog](https://en.wikipedia.org/wiki/HyperLogLog) sketches which provide an estimation how many distinct values a column contains.
 
+- `count_min`
+
+    [Count-min](https://en.wikipedia.org/wiki/Count%E2%80%93min_sketch) sketches which provide an approximate count of the frequency of each value in a column.
+
 ## Column-level Settings {#column-level-settings}
 
 Certain MergeTree settings can be override at column level:

docs/en/getting-started/example-datasets/nypd_complaint_data.md

@@ -55,7 +55,7 @@ CMPLNT_FR_TM                Nullable(String)
 ```
 
 :::tip
-Most of the time the above command will let you know which fields in the input data are numeric, and which are strings, and which are tuples.  This is not always the case.  Because ClickHouse is routineley used with datasets containing billions of records there is a default number (100) of rows examined to [infer the schema](/docs/en/integrations/data-ingestion/data-formats/json.md#relying-on-schema-inference) in order to avoid parsing billions of rows to infer the schema. The response below may not match what you see, as the dataset is updated several times each year. Looking at the Data Dictionary you can see that CMPLNT_NUM is specified as text, and not numeric.  By overriding the default of 100 rows for inference with the setting `SETTINGS input_format_max_rows_to_read_for_schema_inference=2000`
+Most of the time the above command will let you know which fields in the input data are numeric, and which are strings, and which are tuples.  This is not always the case.  Because ClickHouse is routineley used with datasets containing billions of records there is a default number (100) of rows examined to [infer the schema](/en/integrations/data-formats/json/inference) in order to avoid parsing billions of rows to infer the schema. The response below may not match what you see, as the dataset is updated several times each year. Looking at the Data Dictionary you can see that CMPLNT_NUM is specified as text, and not numeric.  By overriding the default of 100 rows for inference with the setting `SETTINGS input_format_max_rows_to_read_for_schema_inference=2000`
 you can get a better idea of the content.
 
 Note: as of version 22.5 the default is now 25,000 rows for inferring the schema, so only change the setting if you are on an older version or if you need more than 25,000 rows to be sampled.

docs/en/getting-started/install.md

@@ -15,7 +15,7 @@ You have four options for getting up and running with ClickHouse:
 
 - **[ClickHouse Cloud](https://clickhouse.com/cloud/):** The official ClickHouse as a service, - built by, maintained and supported by the creators of ClickHouse
 - **[Quick Install](#quick-install):** an easy-to-download binary for testing and developing with ClickHouse
-- **[Production Deployments](#available-installation-options):** ClickHouse can run on any Linux, FreeBSD, or macOS with x86-64, ARM, or PowerPC64LE CPU architecture
+- **[Production Deployments](#available-installation-options):** ClickHouse can run on any Linux, FreeBSD, or macOS with x86-64, modern ARM (ARMv8.2-A up), or PowerPC64LE CPU architecture
 - **[Docker Image](https://hub.docker.com/r/clickhouse/clickhouse-server/):** use the official Docker image in Docker Hub
 
 ## ClickHouse Cloud

docs/en/interfaces/cli.md

@@ -185,6 +185,7 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va
 - `--format, -f` – Use the specified default format to output the result.
 - `--vertical, -E` – If specified, use the [Vertical format](../interfaces/formats.md#vertical) by default to output the result. This is the same as `–format=Vertical`. In this format, each value is printed on a separate line, which is helpful when displaying wide tables.
 - `--time, -t` – If specified, print the query execution time to ‘stderr’ in non-interactive mode.
+- `--memory-usage` – If specified, print memory usage to ‘stderr’ in non-interactive mode]. Possible values: 'none' - do not print memory usage, 'default' - print number of bytes, 'readable' - print memory usage in human-readable format.
 - `--stacktrace` – If specified, also print the stack trace if an exception occurs.
 - `--config-file` – The name of the configuration file.
 - `--secure` – If specified, will connect to server over secure connection (TLS). You might need to configure your CA certificates in the [configuration file](#configuration_files). The available configuration settings are the same as for [server-side TLS configuration](../operations/server-configuration-parameters/settings.md#server_configuration_parameters-openssl).
@@ -339,7 +340,7 @@ clickhouse-client clickhouse://some_user%40some_mail.com@localhost:9000
 Connect to one of provides hosts: `192.168.1.15`, `192.168.1.25`.
 
 ``` bash
-clickhouse-client clickhouse://192.168.1.15,192.168.1.25 
+clickhouse-client clickhouse://192.168.1.15,192.168.1.25
 ```
 
 ### Configuration Files {#configuration_files}
@@ -367,7 +368,7 @@ Example of a config file:
 ```
 
 Or the same config in a YAML format:
- 
+
 ```yaml
 user: username
 password: 'password'

docs/en/interfaces/formats.md

@@ -67,6 +67,7 @@ The supported formats are:
 | [Prometheus](#prometheus)                                                                 | ✗    | ✔     |
 | [Protobuf](#protobuf)                                                                     | ✔    | ✔     |
 | [ProtobufSingle](#protobufsingle)                                                         | ✔    | ✔     |
+| [ProtobufList](#protobuflist)								    | ✔    | ✔     |
 | [Avro](#data-format-avro)                                                                 | ✔    | ✔     |
 | [AvroConfluent](#data-format-avro-confluent)                                              | ✔    | ✗     |
 | [Parquet](#data-format-parquet)                                                           | ✔    | ✔     |
@@ -1535,6 +1536,10 @@ the columns from input data will be mapped to the columns from the table by thei
 Otherwise, the first row will be skipped.
 If setting [input_format_with_types_use_header](/docs/en/operations/settings/settings-formats.md/#input_format_with_types_use_header) is set to 1,
 the types from input data will be compared with the types of the corresponding columns from the table. Otherwise, the second row will be skipped.
+If setting [output_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#output_format_binary_encode_types_in_binary_format) is set to 1,
+the types in header will be written using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes output format.
+If setting [input_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#input_format_binary_encode_types_in_binary_format) is set to 1,
+the types in header will be read using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes input format.
 :::
 
 ## RowBinaryWithDefaults {#rowbinarywithdefaults}
@@ -1948,6 +1953,35 @@ SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf
 
 Same as [Protobuf](#protobuf) but for storing/parsing single Protobuf message without length delimiters.
 
+## ProtobufList {#protobuflist}
+
+Similar to Protobuf but rows are represented as a sequence of sub-messages contained in a message with fixed name "Envelope".
+
+Usage example:
+
+``` sql
+SELECT * FROM test.table FORMAT ProtobufList SETTINGS format_schema = 'schemafile:MessageType'
+```
+
+``` bash
+cat protobuflist_messages.bin | clickhouse-client --query "INSERT INTO test.table FORMAT ProtobufList SETTINGS format_schema='schemafile:MessageType'"
+```
+
+where the file `schemafile.proto` looks like this:
+
+``` capnp
+syntax = "proto3";
+message Envelope {
+  message MessageType {
+    string name = 1;
+    string surname = 2;
+    uint32 birthDate = 3;
+    repeated string phoneNumbers = 4;
+  };
+  MessageType row = 1;
+};
+```
+
 ## Avro {#data-format-avro}
 
 [Apache Avro](https://avro.apache.org/) is a row-oriented data serialization framework developed within Apache’s Hadoop project.

docs/en/interfaces/mysql.md

@@ -6,7 +6,20 @@ sidebar_label: MySQL Interface
 
 # MySQL Interface
 
-ClickHouse supports the MySQL wire protocol. This allow tools that are MySQL-compatible to interact with ClickHouse seamlessly (e.g. [Looker Studio](../integrations/data-visualization/looker-studio-and-clickhouse.md)).
+ClickHouse supports the MySQL wire protocol. This allows certain clients that do not have native ClickHouse connectors leverage the MySQL protocol instead, and it has been validated with the following BI tools:
+
+- [Looker Studio](../integrations/data-visualization/looker-studio-and-clickhouse.md)
+- [Tableau Online](../integrations/tableau-online)
+- [QuickSight](../integrations/quicksight)
+
+If you are trying other untested clients or integrations, keep in mind that there could be the following limitations:
+
+- SSL implementation might not be fully compatible; there could be potential [TLS SNI](https://www.cloudflare.com/learning/ssl/what-is-sni/) issues.
+- A particular tool might require dialect features (e.g., MySQL-specific functions or settings) that are not implemented yet.
+
+If there is a native driver available (e.g., [DBeaver](../integrations/dbeaver)), it is always preferred to use it instead of the MySQL interface. Additionally, while most of the MySQL language clients should work fine, MySQL interface is not guaranteed to be a drop-in replacement for a codebase with existing MySQL queries.
+
+If your use case involves a particular tool that does not have a native ClickHouse driver, and you would like to use it via the MySQL interface and you found certain incompatibilities - please [create an issue](https://github.com/ClickHouse/ClickHouse/issues) in the ClickHouse repository.
 
 ## Enabling the MySQL Interface On ClickHouse Cloud
 

docs/en/operations/configuration-files.md

@@ -124,7 +124,7 @@ which is equal to
 
 #### Default values for from_env and from_zk attributes
 
-It's possible to set the default value and substitute it only if the environment variable or zookeeper node is set using `replace="1"`.
+It's possible to set the default value and substitute it only if the environment variable or zookeeper node is set using `replace="1"` (must be declared before from_env).
 
 With previous example, but `MAX_QUERY_SIZE` is unset:
 
@@ -132,7 +132,7 @@ With previous example, but `MAX_QUERY_SIZE` is unset:
 <clickhouse>
     <profiles>
         <default>
-            <max_query_size from_env="MAX_QUERY_SIZE" replace="1">150000</max_query_size>
+            <max_query_size replace="1" from_env="MAX_QUERY_SIZE">150000</max_query_size>
         </default>
     </profiles>
 </clickhouse>

docs/en/operations/opentelemetry.md

@@ -2,15 +2,11 @@
 slug: /en/operations/opentelemetry
 sidebar_position: 62
 sidebar_label: Tracing ClickHouse with OpenTelemetry
-title: "[experimental] Tracing ClickHouse with OpenTelemetry"
+title: "Tracing ClickHouse with OpenTelemetry"
 ---
 
 [OpenTelemetry](https://opentelemetry.io/) is an open standard for collecting traces and metrics from the distributed application. ClickHouse has some support for OpenTelemetry.
 
-:::note    
-This is an experimental feature that will change in backwards-incompatible ways in future releases.
-:::
-
 ## Supplying Trace Context to ClickHouse
 
 ClickHouse accepts trace context HTTP headers, as described by the [W3C recommendation](https://www.w3.org/TR/trace-context/). It also accepts trace context over a native protocol that is used for communication between ClickHouse servers or between the client and server. For manual testing, trace context headers conforming to the Trace Context recommendation can be supplied to `clickhouse-client` using `--opentelemetry-traceparent` and `--opentelemetry-tracestate` flags.

docs/en/operations/settings/merge-tree-settings.md

@@ -1030,7 +1030,7 @@ A table with no primary key represents the extreme case of a single equivalence
 
 The fewer and the larger the equivalence classes are, the higher the degree of freedom when re-shuffling rows.
 
-The heuristics applied to find the best row order within each equivalence class is suggested by D. Lemir, O. Kaser in [Reordering columns for smaller indexes](https://doi.org/10.1016/j.ins.2011.02.002) and based on sorting the rows within each equivalence class by ascending cardinality of the non-primary key columns.
+The heuristics applied to find the best row order within each equivalence class is suggested by D. Lemire, O. Kaser in [Reordering columns for smaller indexes](https://doi.org/10.1016/j.ins.2011.02.002) and based on sorting the rows within each equivalence class by ascending cardinality of the non-primary key columns.
 It performs three steps:
 1. Find all equivalence classes based on the row values in primary key columns.
 2. For each equivalence class, calculate (usually estimate) the cardinalities of the non-primary-key columns.

docs/en/operations/settings/settings-formats.md

@@ -1951,6 +1951,18 @@ The maximum allowed size for String in RowBinary format. It prevents allocating
 
 Default value: `1GiB`.
 
+### output_format_binary_encode_types_in_binary_format {#output_format_binary_encode_types_in_binary_format}
+
+Write data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in RowBinaryWithNamesAndTypes output format.
+
+Disabled by default.
+
+### input_format_binary_decode_types_in_binary_format {#input_format_binary_decode_types_in_binary_format}
+
+Read data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in RowBinaryWithNamesAndTypes input format.
+
+Disabled by default.
+
 ## Native format settings {#native-format-settings}
 
 ### input_format_native_allow_types_conversion {#input_format_native_allow_types_conversion}
@@ -1958,3 +1970,15 @@ Default value: `1GiB`.
 Allow types conversion in Native input format between columns from input data and requested columns.
 
 Enabled by default.
+
+### output_format_native_encode_types_in_binary_format {#output_format_native_encode_types_in_binary_format}
+
+Write data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in Native output format.
+
+Disabled by default.
+
+### input_format_native_decode_types_in_binary_format {#input_format_native_decode_types_in_binary_format}
+
+Read data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in Native input format.
+
+Disabled by default.

docs/en/operations/settings/settings-users.md

@@ -22,6 +22,21 @@ Structure of the `users` section:
         <!-- Or -->
         <password_sha256_hex></password_sha256_hex>
 
+        <ssh_keys>
+            <ssh_key>
+                <type>ssh-ed25519</type>
+                <base64_key>AAAAC3NzaC1lZDI1NTE5AAAAIDNf0r6vRl24Ix3tv2IgPmNPO2ATa2krvt80DdcTatLj</base64_key>
+            </ssh_key>
+            <ssh_key>
+                <type>ecdsa-sha2-nistp256</type>
+                <base64_key>AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBNxeV2uN5UY6CUbCzTA1rXfYimKQA5ivNIqxdax4bcMXz4D0nSk2l5E1TkR5mG8EBWtmExSPbcEPJ8V7lyWWbA8=</base64_key>
+            </ssh_key>
+            <ssh_key>
+                <type>ssh-rsa</type>
+                <base64_key>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</base64_key>
+            </ssh_key>
+        </ssh_keys>
+
         <access_management>0|1</access_management>
 
         <networks incl="networks" replace="replace">
@@ -79,6 +94,24 @@ Password can be specified in plaintext or in SHA256 (hex format).
 
     The first line of the result is the password. The second line is the corresponding double SHA1 hash.
 
+### username/ssh-key {#user-sshkey}
+
+This setting allows authenticating with SSH keys.
+
+Given a SSH key (as generated by `ssh-keygen`) like
+```
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDNf0r6vRl24Ix3tv2IgPmNPO2ATa2krvt80DdcTatLj john@example.com
+```
+The `ssh_key` element is expected to be
+```
+<ssh_key>
+     <type>ssh-ed25519</type>
+     <base64_key>AAAAC3NzaC1lZDI1NTE5AAAAIDNf0r6vRl24Ix3tv2IgPmNPO2ATa2krvt80DdcTatLj</base64_key>
+ </ssh_key>
+```
+
+Substitute `ssh-ed25519` with `ssh-rsa` or `ecdsa-sha2-nistp256` for the other supported algorithms.
+
 ### access_management {#access_management-user-setting}
 
 This setting enables or disables using of SQL-driven [access control and account management](../../guides/sre/user-management/index.md#access-control) for the user.

docs/en/operations/settings/settings.md

@@ -1358,12 +1358,25 @@ Connection pool size for PostgreSQL table engine and database engine.
 
 Default value: 16
 
+## postgresql_connection_attempt_timeout {#postgresql-connection-attempt-timeout}
+
+Connection timeout in seconds of a single attempt to connect PostgreSQL end-point.
+The value is passed as a `connect_timeout` parameter of the connection URL.
+
+Default value: `2`.
+
 ## postgresql_connection_pool_wait_timeout {#postgresql-connection-pool-wait-timeout}
 
 Connection pool push/pop timeout on empty pool for PostgreSQL table engine and database engine. By default it will block on empty pool.
 
 Default value: 5000
 
+## postgresql_connection_pool_retries {#postgresql-connection-pool-retries}
+
+The maximum number of retries to establish a connection with the PostgreSQL end-point.
+
+Default value: `2`.
+
 ## postgresql_connection_pool_auto_close_connection {#postgresql-connection-pool-auto-close-connection}
 
 Close connection before returning connection to the pool.

docs/en/operations/system-tables/detached_tables.md

@@ -0,0 +1,35 @@
+---
+slug: /en/operations/system-tables/detached_tables
+---
+# detached_tables
+
+Contains information of each detached table.
+
+Columns:
+
+- `database` ([String](../../sql-reference/data-types/string.md)) — The name of the database the table is in.
+
+- `table` ([String](../../sql-reference/data-types/string.md)) — Table name.
+
+- `uuid` ([UUID](../../sql-reference/data-types/uuid.md)) — Table uuid (Atomic database).
+
+- `metadata_path` ([String](../../sql-reference/data-types/string.md)) - Path to the table metadata in the file system.
+
+- `is_permanently` ([UInt8](../../sql-reference/data-types/int-uint.md)) - Flag indicates that the table was detached PERMANENTLY.
+
+
+**Example**
+
+```sql
+SELECT * FROM system.detached_tables FORMAT Vertical;
+```
+
+```text
+Row 1:
+──────
+database:                   base
+table:                      t1
+uuid:                       81b1c20a-b7c6-4116-a2ce-7583fb6b6736
+metadata_path:              /var/lib/clickhouse/store/461/461cf698-fd0b-406d-8c01-5d8fd5748a91/t1.sql
+is_permanently:             1
+```

docs/en/operations/system-tables/functions.md

@@ -9,7 +9,6 @@ Columns:
 
 - `name` ([String](../../sql-reference/data-types/string.md)) – The name of the function.
 - `is_aggregate` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Whether the function is an aggregate function.
-- `is_deterministic` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt8](../../sql-reference/data-types/int-uint.md))) - Whether the function is deterministic.
 - `case_insensitive`, ([UInt8](../../sql-reference/data-types/int-uint.md)) - Whether the function name can be used case-insensitively.
 - `alias_to`, ([String](../../sql-reference/data-types/string.md)) - The original function name, if the function name is an alias.
 - `create_query`, ([String](../../sql-reference/data-types/enum.md)) - Unused.

docs/en/operations/utilities/clickhouse-local.md

@@ -16,7 +16,7 @@ sidebar_label: clickhouse-local
 
 While `clickhouse-local` is a great tool for development and testing purposes, and for processing files, it is not suitable for serving end users or applications. In these scenarios, it is recommended to use the open-source [ClickHouse](https://clickhouse.com/docs/en/install). ClickHouse is a powerful OLAP database that is designed to handle large-scale analytical workloads. It provides fast and efficient processing of complex queries on large datasets, making it ideal for use in production environments where high-performance is critical. Additionally, ClickHouse offers a wide range of features such as replication, sharding, and high availability, which are essential for scaling up to handle large datasets and serving applications. If you need to handle larger datasets or serve end users or applications, we recommend using open-source ClickHouse instead of `clickhouse-local`.
 
-Please read the docs below that show example use cases for `clickhouse-local`, such as [querying local CSVs](#query-data-in-a-csv-file-using-sql) or [reading a parquet file in S3](#query-data-in-a-parquet-file-in-aws-s3).
+Please read the docs below that show example use cases for `clickhouse-local`, such as [querying local file](#query_data_in_file) or [reading a parquet file in S3](#query-data-in-a-parquet-file-in-aws-s3).
 
 ## Download clickhouse-local
 

docs/en/sql-reference/aggregate-functions/index.md

@@ -18,7 +18,7 @@ ClickHouse also supports:
 
 During aggregation, all `NULL` arguments are skipped. If the aggregation has several arguments it will ignore any row in which one or more of them are NULL.
 
-There is an exception to this rule, which are the functions [`first_value`](../../sql-reference/aggregate-functions/reference/first_value.md), [`last_value`](../../sql-reference/aggregate-functions/reference/last_value.md) and their aliases when followed by the modifier `RESPECT NULLS`: `FIRST_VALUE(b) RESPECT NULLS`.
+There is an exception to this rule, which are the functions [`first_value`](../../sql-reference/aggregate-functions/reference/first_value.md), [`last_value`](../../sql-reference/aggregate-functions/reference/last_value.md) and their aliases (`any` and `anyLast` respectively) when followed by the modifier `RESPECT NULLS`. For example, `FIRST_VALUE(b) RESPECT NULLS`.
 
 **Examples:**
 

docs/en/sql-reference/aggregate-functions/reference/any.md

@@ -5,12 +5,12 @@ sidebar_position: 102
 
 # any
 
-Selects the first encountered value of a column.
+Selects the first encountered value of a column, ignoring any `NULL` values.
 
 **Syntax**
 
 ```sql
-any(column)
+any(column) [RESPECT NULLS]
 ```
 
 Aliases: `any_value`, [`first_value`](../reference/first_value.md).
@@ -20,7 +20,9 @@ Aliases: `any_value`, [`first_value`](../reference/first_value.md).
 
 **Returned value**
 
-By default, it ignores NULL values and returns the first NOT NULL value found in the column. Like [`first_value`](../../../sql-reference/aggregate-functions/reference/first_value.md) it supports `RESPECT NULLS`, in which case it will select the first value passed, independently on whether it's NULL or not.
+:::note
+Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the first value passed, regardless of whether it is `NULL` or not.
+:::
 
 :::note
 The return type of the function is the same as the input, except for LowCardinality which is discarded. This means that given no rows as input it will return the default value of that type (0 for integers, or Null for a Nullable() column). You might use the `-OrNull` [combinator](../../../sql-reference/aggregate-functions/combinators.md) ) to modify this behaviour.

docs/en/sql-reference/aggregate-functions/reference/any_respect_nulls.md

@@ -1,44 +0,0 @@
----
-slug: /en/sql-reference/aggregate-functions/reference/any_respect_nulls
-sidebar_position: 103
----
-
-# any_respect_nulls
-
-Selects the first encountered value of a column, irregardless of whether it is a `NULL` value or not.
-
-Alias: `any_value_respect_nulls`, `first_value_repect_nulls`.
-
-**Syntax**
-
-```sql
-any_respect_nulls(column)
-```
-
-**Parameters**
-- `column`: The column name. 
-
-**Returned value**
-
-- The last value encountered, irregardless of whether it is a `NULL` value or not.
-
-**Example**
-
-Query:
-
-```sql
-CREATE TABLE any_nulls (city Nullable(String)) ENGINE=Log;
-
-INSERT INTO any_nulls (city) VALUES (NULL), ('Amsterdam'), ('New York'), ('Tokyo'), ('Valencia'), (NULL);
-
-SELECT any(city), any_respect_nulls(city) FROM any_nulls;
-```
-
-```response
-┌─any(city)─┬─any_respect_nulls(city)─┐
-│ Amsterdam │ ᴺᵁᴸᴸ                    │
-└───────────┴─────────────────────────┘
-```
-
-**See Also**
-- [any](../reference/any.md)

docs/en/sql-reference/aggregate-functions/reference/anylast.md

@@ -5,17 +5,21 @@ sidebar_position: 105
 
 # anyLast
 
-Selects the last value encountered. The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
+Selects the last value encountered, ignoring any `NULL` values by default. The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
 
 **Syntax**
 
 ```sql
-anyLast(column)
+anyLast(column) [RESPECT NULLS]
 ```
 
 **Parameters**
 - `column`: The column name. 
 
+:::note
+Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the first value passed, regardless of whether it is `NULL` or not.
+:::
+
 **Returned value**
 
 - The last value encountered.

docs/en/sql-reference/aggregate-functions/reference/anylast_respect_nulls.md

@@ -1,39 +0,0 @@
----
-slug: /en/sql-reference/aggregate-functions/reference/anylast_respect_nulls
-sidebar_position: 106
----
-
-# anyLast_respect_nulls
-
-Selects the last value encountered, irregardless of whether it is `NULL` or not.
-
-**Syntax**
-
-```sql
-anyLast_respect_nulls(column)
-```
-
-**Parameters**
-- `column`: The column name. 
-
-**Returned value**
-
-- The last value encountered, irregardless of whether it is `NULL` or not.
-
-**Example**
-
-Query:
-
-```sql
-CREATE TABLE any_last_nulls (city Nullable(String)) ENGINE=Log;
-
-INSERT INTO any_last_nulls (city) VALUES ('Amsterdam'),(NULL),('New York'),('Tokyo'),('Valencia'),(NULL);
-
-SELECT anyLast(city), anyLast_respect_nulls(city) FROM any_last_nulls;
-```
-
-```response
-┌─anyLast(city)─┬─anyLast_respect_nulls(city)─┐
-│ Valencia      │ ᴺᵁᴸᴸ                        │
-└───────────────┴─────────────────────────────┘
-```

docs/en/sql-reference/aggregate-functions/reference/index.md

@@ -45,10 +45,9 @@ ClickHouse-specific aggregate functions:
 
 - [aggThrow](../reference/aggthrow.md)
 - [analysisOfVariance](../reference/analysis_of_variance.md)
-- [any](../reference/any_respect_nulls.md)
+- [any](../reference/any.md)
 - [anyHeavy](../reference/anyheavy.md)
 - [anyLast](../reference/anylast.md)
-- [anyLast](../reference/anylast_respect_nulls.md)
 - [boundingRatio](../reference/boundrat.md)
 - [first_value](../reference/first_value.md)
 - [last_value](../reference/last_value.md)

docs/en/sql-reference/aggregate-functions/reference/singlevalueornull.md

@@ -16,7 +16,7 @@ singleValueOrNull(x)
 
 **Parameters**
 
-- `x` — Column of any [data type](../../data-types/index.md).
+- `x` — Column of any [data type](../../data-types/index.md) (except [Map](../../data-types/map.md), [Array](../../data-types/array.md) or [Tuple](../../data-types/tuple) which cannot be of type [Nullable](../../data-types/nullable.md)).
 
 **Returned values**
 

docs/en/sql-reference/data-types/array.md

@@ -96,3 +96,22 @@ Result:
 │         1 │ [2]       │ [[4,1]]   │
 └───────────┴───────────┴───────────┘
 ```
+
+## Reading nested subcolumns from Array
+
+If nested type `T` inside `Array` has subcolumns (for example, if it's a [named tuple](./tuple.md)), you can read its subcolumns from an `Array(T)` type with the same subcolumn names. The type of a subcolumn will be `Array` of the type of original subcolumn.
+
+**Example**
+
+```sql
+CREATE TABLE t_arr (arr Array(Tuple(field1 UInt32, field2 String))) ENGINE = MergeTree ORDER BY tuple();
+INSERT INTO t_arr VALUES ([(1, 'Hello'), (2, 'World')]), ([(3, 'This'), (4, 'is'), (5, 'subcolumn')]);
+SELECT arr.field1, toTypeName(arr.field1), arr.field2, toTypeName(arr.field2) from t_arr;
+```
+
+```test
+┌─arr.field1─┬─toTypeName(arr.field1)─┬─arr.field2────────────────┬─toTypeName(arr.field2)─┐
+│ [1,2]      │ Array(UInt32)          │ ['Hello','World']         │ Array(String)          │
+│ [3,4,5]    │ Array(UInt32)          │ ['This','is','subcolumn'] │ Array(String)          │
+└────────────┴────────────────────────┴───────────────────────────┴────────────────────────┘
+```

docs/en/sql-reference/data-types/data-types-binary-encoding.md

@@ -0,0 +1,115 @@
+---
+slug: /en/sql-reference/data-types/data-types-binary-encoding
+sidebar_position: 56
+sidebar_label: Data types binary encoding specification.
+---
+
+
+# Data types binary encoding specification
+
+This specification describes the binary format that can be used for binary encoding and decoding of ClickHouse data types. This format is used in `Dynamic` column [binary serialization](dynamic.md#binary-output-format) and can be used in input/output formats [RowBinaryWithNamesAndTypes](../../interfaces/formats.md#rowbinarywithnamesandtypes) and [Native](../../interfaces/formats.md#native) under corresponding settings.
+
+The table below describes how each data type is represented in binary format. Each data type encoding consist of 1 byte that indicates the type and some optional additional information.
+`var_uint` in the binary encoding means that the size is encoded using Variable-Length Quantity compression.
+
+| ClickHouse data type                                                                 | Binary encoding                                                                                                                                                                                                                                                                                                        |
+|--------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `Nothing`                                                                            | `0x00`                                                                                                                                                                                                                                                                                                                 |
+| `UInt8`                                                                              | `0x01`                                                                                                                                                                                                                                                                                                                 |
+| `UInt16`                                                                             | `0x02`                                                                                                                                                                                                                                                                                                                 |
+| `UInt32`                                                                             | `0x03`                                                                                                                                                                                                                                                                                                                 |
+| `UInt64`                                                                             | `0x04`                                                                                                                                                                                                                                                                                                                 |
+| `UInt128`                                                                            | `0x05`                                                                                                                                                                                                                                                                                                                 |
+| `UInt256`                                                                            | `0x06`                                                                                                                                                                                                                                                                                                                 |
+| `Int8`                                                                               | `0x07`                                                                                                                                                                                                                                                                                                                 |
+| `Int16`                                                                              | `0x08`                                                                                                                                                                                                                                                                                                                 |
+| `Int32`                                                                              | `0x09`                                                                                                                                                                                                                                                                                                                 |
+| `Int64`                                                                              | `0x0A`                                                                                                                                                                                                                                                                                                                 |
+| `Int128`                                                                             | `0x0B`                                                                                                                                                                                                                                                                                                                 |
+| `Int256`                                                                             | `0x0C`                                                                                                                                                                                                                                                                                                                 |
+| `Float32`                                                                            | `0x0D`                                                                                                                                                                                                                                                                                                                 |
+| `Float64`                                                                            | `0x0E`                                                                                                                                                                                                                                                                                                                 |
+| `Date`                                                                               | `0x0F`                                                                                                                                                                                                                                                                                                                 |
+| `Date32`                                                                             | `0x10`                                                                                                                                                                                                                                                                                                                 |
+| `DateTime`                                                                           | `0x11`                                                                                                                                                                                                                                                                                                                 |
+| `DateTime(time_zone)`                                                                | `0x12<var_uint_time_zone_name_size><time_zone_name_data>`                                                                                                                                                                                                                                                              |
+| `DateTime64(P)`                                                                      | `0x13<uint8_precision>`                                                                                                                                                                                                                                                                                                |
+| `DateTime64(P, time_zone)`                                                           | `0x14<uint8_precision><var_uint_time_zone_name_size><time_zone_name_data>`                                                                                                                                                                                                                                             |
+| `String`                                                                             | `0x15`                                                                                                                                                                                                                                                                                                                 |
+| `FixedString(N)`                                                                     | `0x16<var_uint_size>`                                                                                                                                                                                                                                                                                                  |
+| `Enum8`                                                                              | `0x17<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><int8_value_1>...<var_uint_name_size_N><name_data_N><int8_value_N>`                                                                                                                                                                               |
+| `Enum16`                                                                             | `0x18<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><int16_little_endian_value_1>...><var_uint_name_size_N><name_data_N><int16_little_endian_value_N>`                                                                                                                                                |
+| `Decimal32(P, S)`                                                                    | `0x19<uint8_precision><uint8_scale>`                                                                                                                                                                                                                                                                                   |
+| `Decimal64(P, S)`                                                                    | `0x1A<uint8_precision><uint8_scale>`                                                                                                                                                                                                                                                                                   |
+| `Decimal128(P, S)`                                                                   | `0x1B<uint8_precision><uint8_scale>`                                                                                                                                                                                                                                                                                   |
+| `Decimal256(P, S)`                                                                   | `0x1C<uint8_precision><uint8_scale>`                                                                                                                                                                                                                                                                                   |
+| `UUID`                                                                               | `0x1D`                                                                                                                                                                                                                                                                                                                 |
+| `Array(T)`                                                                           | `0x1E<nested_type_encoding>`                                                                                                                                                                                                                                                                                           |
+| `Tuple(T1, ..., TN)`                                                                 | `0x1F<var_uint_number_of_elements><nested_type_encoding_1>...<nested_type_encoding_N>`                                                                                                                                                                                                                                 |
+| `Tuple(name1 T1, ..., nameN TN)`                                                     | `0x20<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><nested_type_encoding_1>...<var_uint_name_size_N><name_data_N><nested_type_encoding_N>`                                                                                                                                                           |
+| `Set`                                                                                | `0x21`                                                                                                                                                                                                                                                                                                                 |
+| `Interval`                                                                           | `0x22<interval_kind>` (see [interval kind binary encoding](#interval-kind-binary-encoding))                                                                                                                                                                                                                            |
+| `Nullable(T)`                                                                        | `0x23<nested_type_encoding>`                                                                                                                                                                                                                                                                                           |
+| `Function`                                                                           | `0x24<var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N><return_type_encoding>`                                                                                                                                                                                                      |
+| `AggregateFunction(function_name(param_1, ..., param_N), arg_T1, ..., arg_TN)`       | `0x25<var_uint_version><var_uint_function_name_size><function_name_data><var_uint_number_of_parameters><param_1>...<param_N><var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N>` (see [aggregate function parameter binary encoding](#aggregate-function-parameter-binary-encoding)) |
+| `LowCardinality(T)`                                                                  | `0x26<nested_type_encoding>`                                                                                                                                                                                                                                                                                           |
+| `Map(K, V)`                                                                          | `0x27<key_type_encoding><value_type_encoding>`                                                                                                                                                                                                                                                                         |
+| `IPv4`                                                                               | `0x28`                                                                                                                                                                                                                                                                                                                 |
+| `IPv6`                                                                               | `0x29`                                                                                                                                                                                                                                                                                                                 |
+| `Variant(T1, ..., TN)`                                                               | `0x2A<var_uint_number_of_variants><variant_type_encoding_1>...<variant_type_encoding_N>`                                                                                                                                                                                                                               |
+| `Dynamic(max_types=N)`                                                               | `0x2B<uint8_max_types>`                                                                                                                                                                                                                                                                                                |
+| `Custom type` (`Ring`, `Polygon`, etc)                                               | `0x2C<var_uint_type_name_size><type_name_data>`                                                                                                                                                                                                                                                                        |
+| `Bool`                                                                               | `0x2D`                                                                                                                                                                                                                                                                                                                 |
+| `SimpleAggregateFunction(function_name(param_1, ..., param_N), arg_T1, ..., arg_TN)` | `0x2E<var_uint_function_name_size><function_name_data><var_uint_number_of_parameters><param_1>...<param_N><var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N>` (see [aggregate function parameter binary encoding](#aggregate-function-parameter-binary-encoding))                   |
+| `Nested(name1 T1, ..., nameN TN)`                                                    | `0x2F<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><nested_type_encoding_1>...<var_uint_name_size_N><name_data_N><nested_type_encoding_N>`                                                                                                                                                           |
+
+
+### Interval kind binary encoding
+
+The table below describes how different interval kinds of `Interval` data type are encoded.
+
+| Interval kind | Binary encoding |
+|---------------|-----------------|
+| `Nanosecond`  | `0x00`          |
+| `Microsecond` | `0x01`          |
+| `Millisecond` | `0x02`          |
+| `Second`      | `0x03`          |
+| `Minute`      | `0x04`          |
+| `Hour`        | `0x05`          |
+| `Day`         | `0x06`          |
+| `Week`        | `0x07`          |
+| `Month`       | `0x08`          |
+| `Quarter`     | `0x09`          |
+| `Year`        | `0x1A`          |
+
+### Aggregate function parameter binary encoding
+
+The table below describes how parameters of `AggragateFunction` and `SimpleAggregateFunction` are encoded.
+The encoding of a parameter consists of 1 byte indicating the type of the parameter and the value itself.
+
+| Parameter type           | Binary encoding                                                                                                                |
+|--------------------------|--------------------------------------------------------------------------------------------------------------------------------|
+| `Null`                   | `0x00`                                                                                                                         |
+| `UInt64`                 | `0x01<var_uint_value>`                                                                                                         |
+| `Int64`                  | `0x02<var_int_value>`                                                                                                          |
+| `UInt128`                | `0x03<uint128_little_endian_value>`                                                                                            |
+| `Int128`                 | `0x04<int128_little_endian_value>`                                                                                             |
+| `UInt128`                | `0x05<uint128_little_endian_value>`                                                                                            |
+| `Int128`                 | `0x06<int128_little_endian_value>`                                                                                             |
+| `Float64`                | `0x07<float64_little_endian_value>`                                                                                            |
+| `Decimal32`              | `0x08<var_uint_scale><int32_little_endian_value>`                                                                              |
+| `Decimal64`              | `0x09<var_uint_scale><int64_little_endian_value>`                                                                              |
+| `Decimal128`             | `0x0A<var_uint_scale><int128_little_endian_value>`                                                                             |
+| `Decimal256`             | `0x0B<var_uint_scale><int256_little_endian_value>`                                                                             |
+| `String`                 | `0x0C<var_uint_size><data>`                                                                                                    |
+| `Array`                  | `0x0D<var_uint_size><value_encoding_1>...<value_encoding_N>`                                                                   |
+| `Tuple`                  | `0x0E<var_uint_size><value_encoding_1>...<value_encoding_N>`                                                                   |
+| `Map`                    | `0x0F<var_uint_size><key_encoding_1><value_encoding_1>...<key_endoding_N><value_encoding_N>`                                   |
+| `IPv4`                   | `0x10<uint32_little_endian_value>`                                                                                             |
+| `IPv6`                   | `0x11<uint128_little_endian_value>`                                                                                            |
+| `UUID`                   | `0x12<uuid_value>`                                                                                                             |
+| `Bool`                   | `0x13<bool_value>`                                                                                                             |
+| `Object`                 | `0x14<var_uint_size><var_uint_key_size_1><key_data_1><value_encoding_1>...<var_uint_key_size_N><key_data_N><value_encoding_N>` |
+| `AggregateFunctionState` | `0x15<var_uint_name_size><name_data><var_uint_data_size><data>`                                                                |
+| `Negative infinity`      | `0xFE`                                                                                                                         |
+| `Positive infinity`      | `0xFF`                                                                                                                         |

docs/en/sql-reference/data-types/dynamic.md

@@ -1,6 +1,6 @@
 ---
 slug: /en/sql-reference/data-types/dynamic
-sidebar_position: 56
+sidebar_position: 62
 sidebar_label: Dynamic
 ---
 
@@ -493,3 +493,44 @@ SELECT count(), dynamicType(d), _part FROM test GROUP BY _part, dynamicType(d) O
 ```
 
 As we can see, ClickHouse kept the most frequent types `UInt64` and `Array(UInt64)` and casted all other types to `String`.
+
+## JSONExtract functions with Dynamic
+
+All `JSONExtract*` functions support `Dynamic` type:
+
+```sql
+SELECT JSONExtract('{"a" : [1, 2, 3]}', 'a', 'Dynamic') AS dynamic, dynamicType(dynamic) AS dynamic_type;
+```
+
+```text
+┌─dynamic─┬─dynamic_type───────────┐
+│ [1,2,3] │ Array(Nullable(Int64)) │
+└─────────┴────────────────────────┘
+```
+
+```sql
+SELECT JSONExtract('{"obj" : {"a" : 42, "b" : "Hello", "c" : [1,2,3]}}', 'obj', 'Map(String, Variant(UInt32, String, Array(UInt32)))') AS map_of_dynamics, mapApply((k, v) -> (k, variantType(v)), map_of_dynamics) AS map_of_dynamic_types```
+
+```text
+┌─map_of_dynamics──────────────────┬─map_of_dynamic_types────────────────────────────┐
+│ {'a':42,'b':'Hello','c':[1,2,3]} │ {'a':'UInt32','b':'String','c':'Array(UInt32)'} │
+└──────────────────────────────────┴─────────────────────────────────────────────────┘
+```
+
+```sql
+SELECT JSONExtractKeysAndValues('{"a" : 42, "b" : "Hello", "c" : [1,2,3]}', 'Variant(UInt32, String, Array(UInt32))') AS dynamics, arrayMap(x -> (x.1, variantType(x.2)), dynamics) AS dynamic_types```
+```
+
+```text
+┌─dynamics───────────────────────────────┬─dynamic_types─────────────────────────────────────────┐
+│ [('a',42),('b','Hello'),('c',[1,2,3])] │ [('a','UInt32'),('b','String'),('c','Array(UInt32)')] │
+└────────────────────────────────────────┴───────────────────────────────────────────────────────┘
+```
+
+### Binary output format
+
+In RowBinary format values of `Dynamic` type are serialized in the following format:
+
+```text
+<binary_encoded_data_type><value_in_binary_format_according_to_the_data_type>
+```

docs/en/sql-reference/data-types/json.md

@@ -5,11 +5,11 @@ sidebar_label: Object Data Type
 keywords: [object, data type]
 ---
 
-# Object Data Type
+# Object Data Type (deprecated)
 
-:::note
-This feature is not production-ready and is now deprecated. If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-ingestion/data-formats/json) instead. A new implementation to support JSON object is in progress and can be tracked [here](https://github.com/ClickHouse/ClickHouse/issues/54864)
-:::
+**This feature is not production-ready and is now deprecated.** If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-formats/json/overview) instead. A new implementation to support JSON object is in progress and can be tracked [here](https://github.com/ClickHouse/ClickHouse/issues/54864).
+
+<hr />
 
 Stores JavaScript Object Notation (JSON) documents in a single column.