Merge remote-tracking branch 'upstream/master' into named-collections-granular-access

.clang-tidy

@@ -23,9 +23,12 @@ Checks: '*,
     -bugprone-implicit-widening-of-multiplication-result,
     -bugprone-narrowing-conversions,
     -bugprone-not-null-terminated-result,
+    -bugprone-reserved-identifier,
     -bugprone-unchecked-optional-access,
 
     -cert-dcl16-c,
+    -cert-dcl37-c,
+    -cert-dcl51-cpp,
     -cert-err58-cpp,
     -cert-msc32-c,
     -cert-msc51-cpp,
@@ -38,6 +41,8 @@ Checks: '*,
     -clang-analyzer-security.insecureAPI.strcpy,
 
     -cppcoreguidelines-avoid-c-arrays,
+    -cppcoreguidelines-avoid-const-or-ref-data-members,
+    -cppcoreguidelines-avoid-do-while,
     -cppcoreguidelines-avoid-goto,
     -cppcoreguidelines-avoid-magic-numbers,
     -cppcoreguidelines-avoid-non-const-global-variables,
@@ -125,10 +130,12 @@ Checks: '*,
     -portability-simd-intrinsics,
 
     -readability-braces-around-statements,
+    -readability-convert-member-functions-to-static,
     -readability-else-after-return,
     -readability-function-cognitive-complexity,
     -readability-function-size,
     -readability-identifier-length,
+    -readability-identifier-naming,
     -readability-implicit-bool-conversion,
     -readability-isolate-declaration,
     -readability-magic-numbers,
@@ -158,56 +165,28 @@ Checks: '*,
 
 WarningsAsErrors: '*'
 
-# TODO: use dictionary syntax for CheckOptions when minimum clang-tidy level rose to 15
-#           some-check.SomeOption: 'some value'
-#       instead of
-#           - key:             some-check.SomeOption
-#             value:           'some value'
 CheckOptions:
-  - key: readability-identifier-naming.ClassCase
-    value: CamelCase
-  - key: readability-identifier-naming.EnumCase
-    value: CamelCase
-  - key: readability-identifier-naming.LocalVariableCase
-    value: lower_case
-  - key: readability-identifier-naming.StaticConstantCase
-    value: aNy_CasE
-  - key: readability-identifier-naming.MemberCase
-    value: lower_case
-  - key: readability-identifier-naming.PrivateMemberPrefix
-    value: ''
-  - key: readability-identifier-naming.ProtectedMemberPrefix
-    value: ''
-  - key: readability-identifier-naming.PublicMemberCase
-    value: lower_case
-  - key: readability-identifier-naming.MethodCase
-    value: camelBack
-  - key: readability-identifier-naming.PrivateMethodPrefix
-    value: ''
-  - key: readability-identifier-naming.ProtectedMethodPrefix
-    value: ''
-  - key: readability-identifier-naming.ParameterPackCase
-    value: lower_case
-  - key: readability-identifier-naming.StructCase
-    value: CamelCase
-  - key: readability-identifier-naming.TemplateTemplateParameterCase
-    value: CamelCase
-  - key: readability-identifier-naming.TemplateUsingCase
-    value: lower_case
-  - key: readability-identifier-naming.TypeTemplateParameterCase
-    value: CamelCase
-  - key: readability-identifier-naming.TypedefCase
-    value: CamelCase
-  - key: readability-identifier-naming.UnionCase
-    value: CamelCase
-  - key: readability-identifier-naming.UsingCase
-    value: CamelCase
-  - key: modernize-loop-convert.UseCxx20ReverseRanges
-    value: false
-  - key: performance-move-const-arg.CheckTriviallyCopyableMove
-    value: false
-    # Workaround clang-tidy bug: https://github.com/llvm/llvm-project/issues/46097
-  - key: readability-identifier-naming.TypeTemplateParameterIgnoredRegexp
-    value: expr-type
-  - key: cppcoreguidelines-avoid-do-while.IgnoreMacros
-    value: true
+  readability-identifier-naming.ClassCase: CamelCase
+  readability-identifier-naming.EnumCase: CamelCase
+  readability-identifier-naming.LocalVariableCase: lower_case
+  readability-identifier-naming.StaticConstantCase: aNy_CasE
+  readability-identifier-naming.MemberCase: lower_case
+  readability-identifier-naming.PrivateMemberPrefix: ''
+  readability-identifier-naming.ProtectedMemberPrefix: ''
+  readability-identifier-naming.PublicMemberCase: lower_case
+  readability-identifier-naming.MethodCase: camelBack
+  readability-identifier-naming.PrivateMethodPrefix: ''
+  readability-identifier-naming.ProtectedMethodPrefix: ''
+  readability-identifier-naming.ParameterPackCase: lower_case
+  readability-identifier-naming.StructCase: CamelCase
+  readability-identifier-naming.TemplateTemplateParameterCase: CamelCase
+  readability-identifier-naming.TemplateUsingCase: lower_case
+  readability-identifier-naming.TypeTemplateParameterCase: CamelCase
+  readability-identifier-naming.TypedefCase: CamelCase
+  readability-identifier-naming.UnionCase: CamelCase
+  readability-identifier-naming.UsingCase: CamelCase
+  modernize-loop-convert.UseCxx20ReverseRanges: false
+  performance-move-const-arg.CheckTriviallyCopyableMove: false
+  # Workaround clang-tidy bug: https://github.com/llvm/llvm-project/issues/46097
+  readability-identifier-naming.TypeTemplateParameterIgnoredRegexp: expr-type
+  cppcoreguidelines-avoid-do-while.IgnoreMacros: true

.github/workflows/backport_branches.yml

@@ -9,8 +9,22 @@ on: # yamllint disable-line rule:truthy
     branches:
       - 'backport/**'
 jobs:
+  CheckLabels:
+    runs-on: [self-hosted, style-checker]
+    # Run the first check always, even if the CI is cancelled
+    if: ${{ always() }}
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+      - name: Labels check
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 run_check.py
   PythonUnitTests:
     runs-on: [self-hosted, style-checker]
+    needs: CheckLabels
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
@@ -22,6 +36,7 @@ jobs:
           python3 -m unittest discover -s . -p '*_test.py'
   DockerHubPushAarch64:
     runs-on: [self-hosted, style-checker-aarch64]
+    needs: CheckLabels
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
@@ -38,6 +53,7 @@ jobs:
           path: ${{ runner.temp }}/docker_images_check/changed_images_aarch64.json
   DockerHubPushAmd64:
     runs-on: [self-hosted, style-checker]
+    needs: CheckLabels
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
@@ -79,7 +95,7 @@ jobs:
         with:
           name: changed_images
           path: ${{ runner.temp }}/changed_images.json
-  CompatibilityCheck:
+  CompatibilityCheckX86:
     needs: [BuilderDebRelease]
     runs-on: [self-hosted, style-checker]
     steps:
@@ -98,12 +114,43 @@ jobs:
         uses: actions/download-artifact@v3
         with:
           path: ${{ env.REPORTS_PATH }}
-      - name: CompatibilityCheck
+      - name: CompatibilityCheckX86
         run: |
           sudo rm -fr "$TEMP_PATH"
           mkdir -p "$TEMP_PATH"
           cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
+      - name: Cleanup
+        if: always()
+        run: |
+          docker ps --quiet | xargs --no-run-if-empty docker kill ||:
+          docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
+          sudo rm -fr "$TEMP_PATH"
+  CompatibilityCheckAarch64:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, style-checker]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/compatibility_check
+          REPO_COPY=${{runner.temp}}/compatibility_check/ClickHouse
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          EOF
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+      - name: Download json reports
+        uses: actions/download-artifact@v3
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: CompatibilityCheckAarch64
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
       - name: Cleanup
         if: always()
         run: |
@@ -421,7 +468,8 @@ jobs:
       - name: Check docker clickhouse/clickhouse-server building
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 docker_server.py --release-type head --no-push
+          python3 docker_server.py --release-type head --no-push \
+            --image-repo clickhouse/clickhouse-server --image-path docker/server
           python3 docker_server.py --release-type head --no-push --no-ubuntu \
             --image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
       - name: Cleanup
@@ -741,7 +789,8 @@ jobs:
       - FunctionalStatefulTestDebug
       - StressTestTsan
       - IntegrationTestsRelease
-      - CompatibilityCheck
+      - CompatibilityCheckX86
+      - CompatibilityCheckAarch64
     runs-on: [self-hosted, style-checker]
     steps:
       - name: Check out repository code

.github/workflows/cherry_pick.yml

@@ -35,7 +35,6 @@ jobs:
           fetch-depth: 0
       - name: Cherry pick
         run: |
-          sudo pip install GitPython
           cd "$GITHUB_WORKSPACE/tests/ci"
           python3 cherry_pick.py
       - name: Cleanup

.github/workflows/master.yml

@@ -110,7 +110,7 @@ jobs:
           docker ps --quiet | xargs --no-run-if-empty docker kill ||:
           docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
           sudo rm -fr "$TEMP_PATH"
-  CompatibilityCheck:
+  CompatibilityCheckX86:
     needs: [BuilderDebRelease]
     runs-on: [self-hosted, style-checker]
     steps:
@@ -129,12 +129,43 @@ jobs:
         uses: actions/download-artifact@v3
         with:
           path: ${{ env.REPORTS_PATH }}
-      - name: CompatibilityCheck
+      - name: CompatibilityCheckX86
         run: |
           sudo rm -fr "$TEMP_PATH"
           mkdir -p "$TEMP_PATH"
           cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
+      - name: Cleanup
+        if: always()
+        run: |
+          docker ps --quiet | xargs --no-run-if-empty docker kill ||:
+          docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
+          sudo rm -fr "$TEMP_PATH"
+  CompatibilityCheckAarch64:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, style-checker]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/compatibility_check
+          REPO_COPY=${{runner.temp}}/compatibility_check/ClickHouse
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          EOF
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+      - name: Download json reports
+        uses: actions/download-artifact@v3
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: CompatibilityCheckAarch64
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
       - name: Cleanup
         if: always()
         run: |
@@ -829,7 +860,8 @@ jobs:
       - name: Check docker clickhouse/clickhouse-server building
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 docker_server.py --release-type head
+          python3 docker_server.py --release-type head \
+            --image-repo clickhouse/clickhouse-server --image-path docker/server
           python3 docker_server.py --release-type head --no-ubuntu \
             --image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
       - name: Cleanup
@@ -3124,7 +3156,8 @@ jobs:
       - PerformanceComparisonX86-1
       - PerformanceComparisonX86-2
       - PerformanceComparisonX86-3
-      - CompatibilityCheck
+      - CompatibilityCheckX86
+      - CompatibilityCheckAarch64
       - ASTFuzzerTestDebug
       - ASTFuzzerTestAsan
       - ASTFuzzerTestTsan

.github/workflows/pull_request.yml

@@ -37,7 +37,6 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           python3 run_check.py
   PythonUnitTests:
-    needs: CheckLabels
     runs-on: [self-hosted, style-checker]
     steps:
       - name: Check out repository code
@@ -174,7 +173,7 @@ jobs:
           docker ps --quiet | xargs --no-run-if-empty docker kill ||:
           docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
           sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
-  CompatibilityCheck:
+  CompatibilityCheckX86:
     needs: [BuilderDebRelease]
     runs-on: [self-hosted, style-checker]
     steps:
@@ -193,12 +192,43 @@ jobs:
         uses: actions/download-artifact@v3
         with:
           path: ${{ env.REPORTS_PATH }}
-      - name: CompatibilityCheck
+      - name: CompatibilityCheckX86
         run: |
           sudo rm -fr "$TEMP_PATH"
           mkdir -p "$TEMP_PATH"
           cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
+      - name: Cleanup
+        if: always()
+        run: |
+          docker ps --quiet | xargs --no-run-if-empty docker kill ||:
+          docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
+          sudo rm -fr "$TEMP_PATH"
+  CompatibilityCheckAarch64:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, style-checker]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/compatibility_check
+          REPO_COPY=${{runner.temp}}/compatibility_check/ClickHouse
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          EOF
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+      - name: Download json reports
+        uses: actions/download-artifact@v3
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: CompatibilityCheckAarch64
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
       - name: Cleanup
         if: always()
         run: |
@@ -886,7 +916,8 @@ jobs:
       - name: Check docker clickhouse/clickhouse-server building
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 docker_server.py --release-type head --no-push
+          python3 docker_server.py --release-type head --no-push \
+            --image-repo clickhouse/clickhouse-server --image-path docker/server
           python3 docker_server.py --release-type head --no-push --no-ubuntu \
             --image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
       - name: Cleanup
@@ -4792,7 +4823,8 @@ jobs:
       - UnitTestsMsan
       - UnitTestsUBsan
       - UnitTestsReleaseClang
-      - CompatibilityCheck
+      - CompatibilityCheckX86
+      - CompatibilityCheckAarch64
       - IntegrationTestsFlakyCheck
       - SQLancerTestRelease
       - SQLancerTestDebug

.github/workflows/release.yml

@@ -7,15 +7,28 @@ on: # yamllint disable-line rule:truthy
   release:
     types:
     - published
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag'
+        required: true
+        type: string
 
 jobs:
   ReleasePublish:
     runs-on: [self-hosted, style-checker]
     steps:
+    - name: Set tag from input
+      if: github.event_name == 'workflow_dispatch'
+      run: |
+        echo "GITHUB_TAG=${{ github.event.inputs.tag }}" >> "$GITHUB_ENV"
+    - name: Set tag from REF
+      if: github.event_name == 'release'
+      run: |
+        echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
     - name: Deploy packages and assets
       run: |
-        GITHUB_TAG="${GITHUB_REF#refs/tags/}"
-        curl --silent --data '' \
+        curl --silent --data '' --no-buffer \
           '${{ secrets.PACKAGES_RELEASE_URL }}/release/'"${GITHUB_TAG}"'?binary=binary_darwin&binary=binary_darwin_aarch64&sync=true'
   ############################################################################################
   ##################################### Docker images  #######################################
@@ -23,16 +36,26 @@ jobs:
   DockerServerImages:
     runs-on: [self-hosted, style-checker]
     steps:
+    - name: Set tag from input
+      if: github.event_name == 'workflow_dispatch'
+      run: |
+        echo "GITHUB_TAG=${{ github.event.inputs.tag }}" >> "$GITHUB_ENV"
+    - name: Set tag from REF
+      if: github.event_name == 'release'
+      run: |
+        echo "GITHUB_TAG=${GITHUB_REF#refs/tags/}" >> "$GITHUB_ENV"
     - name: Check out repository code
       uses: ClickHouse/checkout@v1
       with:
         clear-repository: true
         fetch-depth: 0  # otherwise we will have no version info
+        ref: ${{ env.GITHUB_TAG }}
     - name: Check docker clickhouse/clickhouse-server building
       run: |
         cd "$GITHUB_WORKSPACE/tests/ci"
-        python3 docker_server.py --release-type auto --version "${{ github.ref }}"
-        python3 docker_server.py --release-type auto --version "${{ github.ref }}" --no-ubuntu \
+        python3 docker_server.py --release-type auto --version "$GITHUB_TAG" \
+          --image-repo clickhouse/clickhouse-server --image-path docker/server
+        python3 docker_server.py --release-type auto --version "$GITHUB_TAG" --no-ubuntu \
           --image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
     - name: Cleanup
       if: always()

.github/workflows/release_branches.yml

@@ -71,7 +71,7 @@ jobs:
         with:
           name: changed_images
           path: ${{ runner.temp }}/changed_images.json
-  CompatibilityCheck:
+  CompatibilityCheckX86:
     needs: [BuilderDebRelease]
     runs-on: [self-hosted, style-checker]
     steps:
@@ -90,12 +90,43 @@ jobs:
         uses: actions/download-artifact@v3
         with:
           path: ${{ env.REPORTS_PATH }}
-      - name: CompatibilityCheck
+      - name: CompatibilityCheckX86
         run: |
           sudo rm -fr "$TEMP_PATH"
           mkdir -p "$TEMP_PATH"
           cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (amd64)" --check-glibc --check-distributions
+      - name: Cleanup
+        if: always()
+        run: |
+          docker ps --quiet | xargs --no-run-if-empty docker kill ||:
+          docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
+          sudo rm -fr "$TEMP_PATH"
+  CompatibilityCheckAarch64:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, style-checker]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/compatibility_check
+          REPO_COPY=${{runner.temp}}/compatibility_check/ClickHouse
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          EOF
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+      - name: Download json reports
+        uses: actions/download-artifact@v3
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: CompatibilityCheckAarch64
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 compatibility_check.py --check-name "Compatibility check (aarch64)" --check-glibc
       - name: Cleanup
         if: always()
         run: |
@@ -494,7 +525,8 @@ jobs:
       - name: Check docker clickhouse/clickhouse-server building
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 docker_server.py --release-type head --no-push
+          python3 docker_server.py --release-type head --no-push \
+            --image-repo clickhouse/clickhouse-server --image-path docker/server
           python3 docker_server.py --release-type head --no-push --no-ubuntu \
             --image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
       - name: Cleanup
@@ -1947,7 +1979,8 @@ jobs:
       - IntegrationTestsTsan1
       - IntegrationTestsTsan2
       - IntegrationTestsTsan3
-      - CompatibilityCheck
+      - CompatibilityCheckX86
+      - CompatibilityCheckAarch64
     runs-on: [self-hosted, style-checker]
     steps:
       - name: Check out repository code

CMakeLists.txt

@@ -121,6 +121,7 @@ if (ENABLE_COLORED_BUILD AND CMAKE_GENERATOR STREQUAL "Ninja")
     set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-color=always")
     # ... such manually setting of flags can be removed once CMake supports a variable to
     # activate colors in *all* build systems: https://gitlab.kitware.com/cmake/cmake/-/issues/15502
+    # --> available since CMake 3.24: https://stackoverflow.com/a/73349744
 endif ()
 
 include (cmake/check_flags.cmake)
@@ -134,24 +135,15 @@ if (COMPILER_CLANG)
         set(COMPILER_FLAGS "${COMPILER_FLAGS} -gdwarf-aranges")
     endif ()
 
-    if (HAS_USE_CTOR_HOMING)
-        # For more info see https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
-        if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
-            set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -fuse-ctor-homing")
-            set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Xclang -fuse-ctor-homing")
-        endif()
+    # See https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
+    if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
+        set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -fuse-ctor-homing")
+        set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Xclang -fuse-ctor-homing")
     endif()
 
     no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
 endif ()
 
-# If compiler has support for -Wreserved-identifier. It is difficult to detect by clang version,
-# because there are two different branches of clang: clang and AppleClang.
-# (AppleClang is not supported by ClickHouse, but some developers have misfortune to use it).
-if (HAS_RESERVED_IDENTIFIER)
-    add_compile_definitions (HAS_RESERVED_IDENTIFIER)
-endif ()
-
 option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON)
 option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
 option(ENABLE_BENCHMARKS "Build all benchmark programs in 'benchmarks' subdirectories" OFF)
@@ -184,26 +176,12 @@ if (OS_DARWIN)
     set (ENABLE_CURL_BUILD OFF)
 endif ()
 
-# Ignored if `lld` is used
-option(ADD_GDB_INDEX_FOR_GOLD "Add .gdb-index to resulting binaries for gold linker.")
-
 if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
     # Can be lld or ld-lld or lld-13 or /path/to/lld.
     if (LINKER_NAME MATCHES "lld" AND OS_LINUX)
         set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
         set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,--gdb-index")
         message (STATUS "Adding .gdb-index via --gdb-index linker option.")
-    # we use another tool for gdb-index, because gold linker removes section .debug_aranges, which used inside clickhouse stacktraces
-    # http://sourceware-org.1504.n7.nabble.com/gold-No-debug-aranges-section-when-linking-with-gdb-index-td540965.html#a556932
-    elseif (LINKER_NAME MATCHES "gold$" AND ADD_GDB_INDEX_FOR_GOLD)
-        find_program (GDB_ADD_INDEX_EXE NAMES "gdb-add-index" DOC "Path to gdb-add-index executable")
-        if (NOT GDB_ADD_INDEX_EXE)
-            set (USE_GDB_ADD_INDEX 0)
-            message (WARNING "Cannot add gdb index to binaries, because gold linker is used, but gdb-add-index executable not found.")
-        else()
-            set (USE_GDB_ADD_INDEX 1)
-            message (STATUS "gdb-add-index found: ${GDB_ADD_INDEX_EXE}")
-        endif()
     endif ()
 endif()
 
@@ -301,16 +279,17 @@ if (ENABLE_BUILD_PROFILING)
      endif ()
 endif ()
 
-set (CMAKE_CXX_STANDARD 20)
-set (CMAKE_CXX_EXTENSIONS ON) # Same as gnu++2a (ON) vs c++2a (OFF): https://cmake.org/cmake/help/latest/prop_tgt/CXX_EXTENSIONS.html
+set (CMAKE_CXX_STANDARD 23)
+set (CMAKE_CXX_EXTENSIONS OFF)
 set (CMAKE_CXX_STANDARD_REQUIRED ON)
 
 set (CMAKE_C_STANDARD 11)
-set (CMAKE_C_EXTENSIONS ON)
+set (CMAKE_C_EXTENSIONS ON) # required by most contribs written in C
 set (CMAKE_C_STANDARD_REQUIRED ON)
 
 if (COMPILER_GCC OR COMPILER_CLANG)
     # Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
+    # See https://reviews.llvm.org/D112921
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
 endif ()
 
@@ -329,11 +308,7 @@ if (ARCH_AMD64)
         set(BRANCHES_WITHIN_32B_BOUNDARIES "-Wa,${BRANCHES_WITHIN_32B_BOUNDARIES}")
     endif()
 
-    include(CheckCXXCompilerFlag)
-    check_cxx_compiler_flag("${BRANCHES_WITHIN_32B_BOUNDARIES}" HAS_BRANCHES_WITHIN_32B_BOUNDARIES)
-    if (HAS_BRANCHES_WITHIN_32B_BOUNDARIES)
-        set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
-    endif()
+    set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
 endif()
 
 if (COMPILER_GCC)
@@ -375,7 +350,15 @@ set (CMAKE_ASM_FLAGS_DEBUG               "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_I
 if (COMPILER_CLANG)
     if (OS_DARWIN)
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
+
         set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
+
+        # The LLVM MachO linker (ld64.lld) generates by default unwind info in 'compact' format which the internal unwinder doesn't support
+        # and the server will not come up ('invalid compact unwind encoding'). Disable it.
+        # You will see warning during the build "ld64.lld: warning: Option `-no_compact_unwind' is undocumented. Should lld implement it?".
+        # Yes, ld64.lld does not document the option, likely for compat with Apple's system ld after which ld64.lld is modeled after and
+        # which also does not document it.
+        set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-no_compact_unwind")
     endif()
 
     # Display absolute paths in error messages. Otherwise KDevelop fails to navigate to correct file and opens a new file instead.
@@ -445,6 +428,7 @@ option(WERROR "Enable -Werror compiler option" ON)
 if (WERROR)
     # Don't pollute CMAKE_CXX_FLAGS with -Werror as it will break some CMake checks.
     # Instead, adopt modern cmake usage requirement.
+    # TODO: Set CMAKE_COMPILE_WARNING_AS_ERROR (cmake 3.24)
     target_compile_options(global-group INTERFACE "-Werror")
 endif ()
 

README.md

@@ -14,18 +14,17 @@ curl https://clickhouse.com/ | sh
 * [Tutorial](https://clickhouse.com/docs/en/getting_started/tutorial/) shows how to set up and query a small ClickHouse cluster.
 * [Documentation](https://clickhouse.com/docs/en/) provides more in-depth information.
 * [YouTube channel](https://www.youtube.com/c/ClickHouseDB) has a lot of content about ClickHouse in video format.
-* [Slack](https://join.slack.com/t/clickhousedb/shared_invite/zt-1gh9ds7f4-PgDhJAaF8ad5RbWBAAjzFg) and [Telegram](https://telegram.me/clickhouse_en) allow chatting with ClickHouse users in real-time.
+* [Slack](https://clickhouse.com/slack) and [Telegram](https://telegram.me/clickhouse_en) allow chatting with ClickHouse users in real-time.
 * [Blog](https://clickhouse.com/blog/) contains various ClickHouse-related articles, as well as announcements and reports about events.
 * [Code Browser (Woboq)](https://clickhouse.com/codebrowser/ClickHouse/index.html) with syntax highlight and navigation.
 * [Code Browser (github.dev)](https://github.dev/ClickHouse/ClickHouse) with syntax highlight, powered by github.dev.
 * [Contacts](https://clickhouse.com/company/contact) can help to get your questions answered if there are any.
 
 ## Upcoming Events
-* [**v23.2 Release Webinar**](https://clickhouse.com/company/events/v23-2-release-webinar?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-02) - Feb 23 - 23.2 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
-* [**ClickHouse Meetup in Amsterdam**](https://www.meetup.com/clickhouse-netherlands-user-group/events/291485868/) - Mar 9 - The first ClickHouse Amsterdam Meetup of 2023 is here! 🎉 Join us for short lightning talks and long discussions. Food, drinks & good times on us.
-* [**ClickHouse Meetup in SF Bay Area**](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/291490121/) - Mar 14 - A night to meet with ClickHouse team in the San Francisco area! Food and drink are a given...but networking is the primary focus.
-* [**ClickHouse Meetup in Austin**](https://www.meetup.com/clickhouse-austin-user-group/events/291486654/) - Mar 16 - The first ClickHouse Meetup in Austin is happening soon! Interested in speaking, let us know!
+* [**ClickHouse Meetup in Austin**](https://www.meetup.com/clickhouse-austin-user-group/events/291486654/) - Mar 30 - The first ClickHouse Meetup in Austin is happening soon! Interested in speaking, let us know!
+* [**v23.3 Release Webinar**](https://clickhouse.com/company/events/v23-3-release-webinar?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-02) - Mar 30 - 23.3 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
 
 ## Recent Recordings
 * **FOSDEM 2023**: In the "Fast and Streaming Data" room Alexey gave a talk entitled "Building Analytical Apps With ClickHouse" that looks at the landscape of data tools, an interesting data set, and how you can interact with data quickly. Check out the recording on **[YouTube](https://www.youtube.com/watch?v=JlcI2Vfz_uk)**.
-* **Recording available**: [**v23.1 Release Webinar**](https://www.youtube.com/watch?v=zYSZXBnTMSE) 23.1 is the ClickHouse New Year release. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release. Inverted indices, query cache, and so -- very -- much more.
+* **Recording available**: [**v23.2 Release Webinar**](https://www.youtube.com/watch?v=2o0vRMMIrkY) NTILE Window Function support, Partition Key for GROUP By, io_uring, Apache Iceberg support, Dynamic Disks, integrations updates! Watch it now!
+* **All release webinar recordings**: [YouTube playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3jAlSy1JxyP8zluvXaN3nxU)

base/base/CMakeLists.txt

@@ -2,6 +2,10 @@ if (USE_CLANG_TIDY)
     set (CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_PATH}")
 endif ()
 
+# TODO: Remove this. We like to compile with C++23 (set by top-level CMakeLists) but Clang crashes with our libcxx
+# when instantiated from JSON.cpp. Try again when libcxx(abi) and Clang are upgraded to 16.
+set (CMAKE_CXX_STANDARD 20)
+
 set (SRCS
     argsToConfig.cpp
     coverage.cpp

base/base/TypeList.h

@@ -4,7 +4,6 @@
 #include <type_traits>
 #include <utility>
 #include "defines.h"
-#include "TypePair.h"
 
 /// General-purpose typelist. Easy on compilation times as it does not use recursion.
 template <typename ...Args>
@@ -28,7 +27,7 @@ namespace TypeListUtils /// In some contexts it's more handy to use functions in
     constexpr Root<Args...> changeRoot(TypeList<Args...>) { return {}; }
 
     template <typename F, typename ...Args>
-    constexpr void forEach(TypeList<Args...>, F && f) { (std::forward<F>(f)(Id<Args>{}), ...); }
+    constexpr void forEach(TypeList<Args...>, F && f) { (std::forward<F>(f)(TypeList<Args>{}), ...); }
 }
 
 template <typename TypeListLeft, typename TypeListRight>

base/base/TypePair.h

@@ -1,4 +0,0 @@
-#pragma once
-
-template <typename T, typename V> struct TypePair {};
-template <typename T> struct Id {};

base/base/coverage.cpp

@@ -2,6 +2,8 @@
 
 #if WITH_COVERAGE
 
+#pragma GCC diagnostic ignored "-Wreserved-identifier"
+
 #    include <mutex>
 #    include <unistd.h>
 

base/base/find_symbols.h

@@ -159,22 +159,22 @@ inline const char * find_first_symbols_sse42(const char * const begin, const cha
 #endif
 
     for (; pos < end; ++pos)
-        if (   (num_chars >= 1 && maybe_negate<positive>(*pos == c01))
-            || (num_chars >= 2 && maybe_negate<positive>(*pos == c02))
-            || (num_chars >= 3 && maybe_negate<positive>(*pos == c03))
-            || (num_chars >= 4 && maybe_negate<positive>(*pos == c04))
-            || (num_chars >= 5 && maybe_negate<positive>(*pos == c05))
-            || (num_chars >= 6 && maybe_negate<positive>(*pos == c06))
-            || (num_chars >= 7 && maybe_negate<positive>(*pos == c07))
-            || (num_chars >= 8 && maybe_negate<positive>(*pos == c08))
-            || (num_chars >= 9 && maybe_negate<positive>(*pos == c09))
-            || (num_chars >= 10 && maybe_negate<positive>(*pos == c10))
-            || (num_chars >= 11 && maybe_negate<positive>(*pos == c11))
-            || (num_chars >= 12 && maybe_negate<positive>(*pos == c12))
-            || (num_chars >= 13 && maybe_negate<positive>(*pos == c13))
-            || (num_chars >= 14 && maybe_negate<positive>(*pos == c14))
-            || (num_chars >= 15 && maybe_negate<positive>(*pos == c15))
-            || (num_chars >= 16 && maybe_negate<positive>(*pos == c16)))
+        if (   (num_chars == 1 && maybe_negate<positive>(is_in<c01>(*pos)))
+            || (num_chars == 2 && maybe_negate<positive>(is_in<c01, c02>(*pos)))
+            || (num_chars == 3 && maybe_negate<positive>(is_in<c01, c02, c03>(*pos)))
+            || (num_chars == 4 && maybe_negate<positive>(is_in<c01, c02, c03, c04>(*pos)))
+            || (num_chars == 5 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05>(*pos)))
+            || (num_chars == 6 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06>(*pos)))
+            || (num_chars == 7 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07>(*pos)))
+            || (num_chars == 8 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08>(*pos)))
+            || (num_chars == 9 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09>(*pos)))
+            || (num_chars == 10 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10>(*pos)))
+            || (num_chars == 11 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11>(*pos)))
+            || (num_chars == 12 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12>(*pos)))
+            || (num_chars == 13 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12, c13>(*pos)))
+            || (num_chars == 14 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12, c13, c14>(*pos)))
+            || (num_chars == 15 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12, c13, c14, c15>(*pos)))
+            || (num_chars == 16 && maybe_negate<positive>(is_in<c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12, c13, c14, c15, c16>(*pos))))
             return pos;
     return return_mode == ReturnMode::End ? end : nullptr;
 }

base/base/hex.h

@@ -0,0 +1,215 @@
+#pragma once
+
+#include <bit>
+#include <cstring>
+#include "types.h"
+
+/// Maps 0..15 to 0..9A..F or 0..9a..f correspondingly.
+
+constexpr inline std::string_view hex_digit_to_char_uppercase_table = "0123456789ABCDEF";
+constexpr inline std::string_view hex_digit_to_char_lowercase_table = "0123456789abcdef";
+
+constexpr char hexDigitUppercase(unsigned char c)
+{
+    return hex_digit_to_char_uppercase_table[c];
+}
+constexpr char hexDigitLowercase(unsigned char c)
+{
+    return hex_digit_to_char_lowercase_table[c];
+}
+
+/// Maps 0..255 to 00..FF or 00..ff correspondingly
+
+constexpr inline std::string_view hex_byte_to_char_uppercase_table = //
+    "000102030405060708090A0B0C0D0E0F"
+    "101112131415161718191A1B1C1D1E1F"
+    "202122232425262728292A2B2C2D2E2F"
+    "303132333435363738393A3B3C3D3E3F"
+    "404142434445464748494A4B4C4D4E4F"
+    "505152535455565758595A5B5C5D5E5F"
+    "606162636465666768696A6B6C6D6E6F"
+    "707172737475767778797A7B7C7D7E7F"
+    "808182838485868788898A8B8C8D8E8F"
+    "909192939495969798999A9B9C9D9E9F"
+    "A0A1A2A3A4A5A6A7A8A9AAABACADAEAF"
+    "B0B1B2B3B4B5B6B7B8B9BABBBCBDBEBF"
+    "C0C1C2C3C4C5C6C7C8C9CACBCCCDCECF"
+    "D0D1D2D3D4D5D6D7D8D9DADBDCDDDEDF"
+    "E0E1E2E3E4E5E6E7E8E9EAEBECEDEEEF"
+    "F0F1F2F3F4F5F6F7F8F9FAFBFCFDFEFF";
+
+constexpr inline std::string_view hex_byte_to_char_lowercase_table = //
+    "000102030405060708090a0b0c0d0e0f"
+    "101112131415161718191a1b1c1d1e1f"
+    "202122232425262728292a2b2c2d2e2f"
+    "303132333435363738393a3b3c3d3e3f"
+    "404142434445464748494a4b4c4d4e4f"
+    "505152535455565758595a5b5c5d5e5f"
+    "606162636465666768696a6b6c6d6e6f"
+    "707172737475767778797a7b7c7d7e7f"
+    "808182838485868788898a8b8c8d8e8f"
+    "909192939495969798999a9b9c9d9e9f"
+    "a0a1a2a3a4a5a6a7a8a9aaabacadaeaf"
+    "b0b1b2b3b4b5b6b7b8b9babbbcbdbebf"
+    "c0c1c2c3c4c5c6c7c8c9cacbcccdcecf"
+    "d0d1d2d3d4d5d6d7d8d9dadbdcdddedf"
+    "e0e1e2e3e4e5e6e7e8e9eaebecedeeef"
+    "f0f1f2f3f4f5f6f7f8f9fafbfcfdfeff";
+
+inline void writeHexByteUppercase(UInt8 byte, void * out)
+{
+    memcpy(out, &hex_byte_to_char_uppercase_table[static_cast<size_t>(byte) * 2], 2);
+}
+
+inline void writeHexByteLowercase(UInt8 byte, void * out)
+{
+    memcpy(out, &hex_byte_to_char_lowercase_table[static_cast<size_t>(byte) * 2], 2);
+}
+
+constexpr inline std::string_view bin_byte_to_char_table = //
+    "0000000000000001000000100000001100000100000001010000011000000111"
+    "0000100000001001000010100000101100001100000011010000111000001111"
+    "0001000000010001000100100001001100010100000101010001011000010111"
+    "0001100000011001000110100001101100011100000111010001111000011111"
+    "0010000000100001001000100010001100100100001001010010011000100111"
+    "0010100000101001001010100010101100101100001011010010111000101111"
+    "0011000000110001001100100011001100110100001101010011011000110111"
+    "0011100000111001001110100011101100111100001111010011111000111111"
+    "0100000001000001010000100100001101000100010001010100011001000111"
+    "0100100001001001010010100100101101001100010011010100111001001111"
+    "0101000001010001010100100101001101010100010101010101011001010111"
+    "0101100001011001010110100101101101011100010111010101111001011111"
+    "0110000001100001011000100110001101100100011001010110011001100111"
+    "0110100001101001011010100110101101101100011011010110111001101111"
+    "0111000001110001011100100111001101110100011101010111011001110111"
+    "0111100001111001011110100111101101111100011111010111111001111111"
+    "1000000010000001100000101000001110000100100001011000011010000111"
+    "1000100010001001100010101000101110001100100011011000111010001111"
+    "1001000010010001100100101001001110010100100101011001011010010111"
+    "1001100010011001100110101001101110011100100111011001111010011111"
+    "1010000010100001101000101010001110100100101001011010011010100111"
+    "1010100010101001101010101010101110101100101011011010111010101111"
+    "1011000010110001101100101011001110110100101101011011011010110111"
+    "1011100010111001101110101011101110111100101111011011111010111111"
+    "1100000011000001110000101100001111000100110001011100011011000111"
+    "1100100011001001110010101100101111001100110011011100111011001111"
+    "1101000011010001110100101101001111010100110101011101011011010111"
+    "1101100011011001110110101101101111011100110111011101111011011111"
+    "1110000011100001111000101110001111100100111001011110011011100111"
+    "1110100011101001111010101110101111101100111011011110111011101111"
+    "1111000011110001111100101111001111110100111101011111011011110111"
+    "1111100011111001111110101111101111111100111111011111111011111111";
+
+inline void writeBinByte(UInt8 byte, void * out)
+{
+    memcpy(out, &bin_byte_to_char_table[static_cast<size_t>(byte) * 8], 8);
+}
+
+/// Produces hex representation of an unsigned int with leading zeros (for checksums)
+template <typename TUInt>
+inline void writeHexUIntImpl(TUInt uint_, char * out, std::string_view table)
+{
+    union
+    {
+        TUInt value;
+        UInt8 uint8[sizeof(TUInt)];
+    };
+
+    value = uint_;
+
+    for (size_t i = 0; i < sizeof(TUInt); ++i)
+    {
+        if constexpr (std::endian::native == std::endian::little)
+            memcpy(out + i * 2, &table[static_cast<size_t>(uint8[sizeof(TUInt) - 1 - i]) * 2], 2);
+        else
+            memcpy(out + i * 2, &table[static_cast<size_t>(uint8[i]) * 2], 2);
+    }
+}
+
+template <typename TUInt>
+inline void writeHexUIntUppercase(TUInt uint_, char * out)
+{
+    writeHexUIntImpl(uint_, out, hex_byte_to_char_uppercase_table);
+}
+
+template <typename TUInt>
+inline void writeHexUIntLowercase(TUInt uint_, char * out)
+{
+    writeHexUIntImpl(uint_, out, hex_byte_to_char_lowercase_table);
+}
+
+template <typename TUInt>
+std::string getHexUIntUppercase(TUInt uint_)
+{
+    std::string res(sizeof(TUInt) * 2, '\0');
+    writeHexUIntUppercase(uint_, res.data());
+    return res;
+}
+
+template <typename TUInt>
+std::string getHexUIntLowercase(TUInt uint_)
+{
+    std::string res(sizeof(TUInt) * 2, '\0');
+    writeHexUIntLowercase(uint_, res.data());
+    return res;
+}
+
+/// Maps 0..9, A..F, a..f to 0..15. Other chars are mapped to implementation specific value.
+
+constexpr inline std::string_view hex_char_to_digit_table
+    = {"\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\xff\xff\xff\xff\xff\xff" //0-9
+       "\xff\x0a\x0b\x0c\x0d\x0e\x0f\xff\xff\xff\xff\xff\xff\xff\xff\xff" //A-Z
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\x0a\x0b\x0c\x0d\x0e\x0f\xff\xff\xff\xff\xff\xff\xff\xff\xff" //a-z
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"
+       "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff",
+       256};
+
+constexpr UInt8 unhex(char c)
+{
+    return hex_char_to_digit_table[static_cast<UInt8>(c)];
+}
+
+constexpr UInt8 unhex2(const char * data)
+{
+    return static_cast<UInt8>(unhex(data[0])) * 0x10 + static_cast<UInt8>(unhex(data[1]));
+}
+
+constexpr UInt16 unhex4(const char * data)
+{
+    return static_cast<UInt16>(unhex(data[0])) * 0x1000 + static_cast<UInt16>(unhex(data[1])) * 0x100
+        + static_cast<UInt16>(unhex(data[2])) * 0x10 + static_cast<UInt16>(unhex(data[3]));
+}
+
+template <typename TUInt>
+constexpr TUInt unhexUInt(const char * data)
+{
+    TUInt res = 0;
+    if constexpr ((sizeof(TUInt) <= 8) || ((sizeof(TUInt) % 8) != 0))
+    {
+        for (size_t i = 0; i < sizeof(TUInt) * 2; ++i, ++data)
+        {
+            res <<= 4;
+            res += unhex(*data);
+        }
+    }
+    else
+    {
+        for (size_t i = 0; i < sizeof(TUInt) / 8; ++i, data += 16)
+        {
+            res <<= 64;
+            res += unhexUInt<UInt64>(data);
+        }
+    }
+    return res;
+}

base/base/interpolate.h

@@ -0,0 +1,13 @@
+#pragma once
+#include <cassert>
+#include <cmath>
+
+/** Linear interpolation in logarithmic coordinates.
+  * Exponential interpolation is related to linear interpolation
+  * exactly in same way as geometric mean is related to arithmetic mean.
+  */
+constexpr double interpolateExponential(double min, double max, double ratio)
+{
+    assert(min > 0 && ratio >= 0 && ratio <= 1);
+    return min * std::pow(max / min, ratio);
+}

base/base/phdr_cache.cpp

@@ -1,6 +1,4 @@
-#ifdef HAS_RESERVED_IDENTIFIER
 #pragma clang diagnostic ignored "-Wreserved-identifier"
-#endif
 
 /// This code was based on the code by Fedor Korotkiy https://www.linkedin.com/in/fedor-korotkiy-659a1838/
 

base/base/unit.h

@@ -5,10 +5,8 @@ constexpr size_t KiB = 1024;
 constexpr size_t MiB = 1024 * KiB;
 constexpr size_t GiB = 1024 * MiB;
 
-#ifdef HAS_RESERVED_IDENTIFIER
-#  pragma clang diagnostic push
-#  pragma clang diagnostic ignored "-Wreserved-identifier"
-#endif
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wreserved-identifier"
 
 // NOLINTBEGIN(google-runtime-int)
 constexpr size_t operator"" _KiB(unsigned long long val) { return val * KiB; }
@@ -16,6 +14,4 @@ constexpr size_t operator"" _MiB(unsigned long long val) { return val * MiB; }
 constexpr size_t operator"" _GiB(unsigned long long val) { return val * GiB; }
 // NOLINTEND(google-runtime-int)
 
-#ifdef HAS_RESERVED_IDENTIFIER
-#  pragma clang diagnostic pop
-#endif
+#pragma clang diagnostic pop

base/poco/Data/ODBC/include/Poco/Data/ODBC/Extractor.h

@@ -466,7 +466,7 @@ namespace Data
             bool extractManualImpl(std::size_t pos, T & val, SQLSMALLINT cType)
             {
                 SQLRETURN rc = 0;
-                T value = (T)0;
+                T value;
 
                 resizeLengths(pos);
 

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

@@ -105,6 +105,8 @@ public:
     const std::string & getText() const;
     /// Returns the text of the message.
 
+    void appendText(const std::string & text);
+
     void setPriority(Priority prio);
     /// Sets the priority of the message.
 

base/poco/Foundation/src/Message.cpp

@@ -27,8 +27,7 @@ Message::Message():
 	_tid(0), 
 	_file(0),
 	_line(0),
-	_pMap(0),
-    _fmt_str(0)
+	_pMap(0)
 {
 	init();
 }
@@ -157,6 +156,12 @@ void Message::setText(const std::string& text)
 }
 
 
+void Message::appendText(const std::string & text)
+{
+    _text.append(text);
+}
+
+
 void Message::setPriority(Priority prio)
 {
 	_prio = prio;

base/poco/MongoDB/include/Poco/MongoDB/Connection.h

@@ -90,6 +90,9 @@ namespace MongoDB
 
         Poco::Net::SocketAddress address() const;
         /// Returns the address of the MongoDB server.
+        
+        const std::string & uri() const;
+        /// Returns the uri on which the connection was made.
 
         void connect(const std::string & hostAndPort);
         /// Connects to the given MongoDB server.
@@ -148,6 +151,7 @@ namespace MongoDB
     private:
         Poco::Net::SocketAddress _address;
         Poco::Net::StreamSocket _socket;
+        std::string _uri;
     };
 
 
@@ -158,6 +162,10 @@ namespace MongoDB
     {
         return _address;
     }
+    inline const std::string & Connection::uri() const
+    {
+    	return _uri;
+    }
 
 
 }

base/poco/MongoDB/src/Connection.cpp

@@ -145,68 +145,155 @@ void Connection::connect(const Poco::Net::StreamSocket& socket)
 
 void Connection::connect(const std::string& uri, SocketFactory& socketFactory)
 {
-	Poco::URI theURI(uri);
-	if (theURI.getScheme() != "mongodb") throw Poco::UnknownURISchemeException(uri);
+    std::vector<std::string> strAddresses;
+    std::string newURI;
 
-	std::string userInfo = theURI.getUserInfo();
-	std::string host = theURI.getHost();
-	Poco::UInt16 port = theURI.getPort();
-	if (port == 0) port = 27017;
+    if (uri.find(',') != std::string::npos)
+    {
+        size_t pos;
+        size_t head = 0;
+        if ((pos = uri.find("@")) != std::string::npos)
+        {
+            head = pos + 1;
+        }
+        else if ((pos = uri.find("://")) != std::string::npos)
+        {
+            head = pos + 3;
+        }
 
-	std::string databaseName = theURI.getPath();
-	if (!databaseName.empty() && databaseName[0] == '/') databaseName.erase(0, 1);
-	if (databaseName.empty()) databaseName = "admin";
+        std::string tempstr;
+        std::string::const_iterator it = uri.begin();
+        it += head;
+        size_t tail = head;
+        for (;it != uri.end() && *it != '?' && *it != '/'; ++it)
+        {
+            tempstr += *it;
+            tail++;
+        }
 
-	bool ssl = false;
-	Poco::Timespan connectTimeout;
-	Poco::Timespan socketTimeout;
-	std::string authMechanism = Database::AUTH_SCRAM_SHA1;
+        it = tempstr.begin();
+        std::string token;
+        for (;it != tempstr.end(); ++it)
+        {
+            if (*it == ',')
+            {
+                newURI = uri.substr(0, head) + token + uri.substr(tail, uri.length());
+                strAddresses.push_back(newURI);
+                token = "";
+            }
+            else
+            {
+                token += *it;
+            }
+        }
+        newURI = uri.substr(0, head) + token + uri.substr(tail, uri.length());
+        strAddresses.push_back(newURI);
+    }
+    else
+    {
+        strAddresses.push_back(uri);
+    }
 
-	Poco::URI::QueryParameters params = theURI.getQueryParameters();
-	for (Poco::URI::QueryParameters::const_iterator it = params.begin(); it != params.end(); ++it)
-	{
-		if (it->first == "ssl")
-		{
-			ssl = (it->second == "true");
-		}
-		else if (it->first == "connectTimeoutMS")
-		{
-			connectTimeout = static_cast<Poco::Timespan::TimeDiff>(1000)*Poco::NumberParser::parse(it->second);
-		}
-		else if (it->first == "socketTimeoutMS")
-		{
-			socketTimeout = static_cast<Poco::Timespan::TimeDiff>(1000)*Poco::NumberParser::parse(it->second);
-		}
-		else if (it->first == "authMechanism")
-		{
-			authMechanism = it->second;
-		}
-	}
+    newURI = strAddresses.front();
+    Poco::URI theURI(newURI);
+    if (theURI.getScheme() != "mongodb") throw Poco::UnknownURISchemeException(uri);
 
-	connect(socketFactory.createSocket(host, port, connectTimeout, ssl));
+    std::string userInfo = theURI.getUserInfo();
+    std::string databaseName = theURI.getPath();
+    if (!databaseName.empty() && databaseName[0] == '/') databaseName.erase(0, 1);
+    if (databaseName.empty()) databaseName = "admin";
 
-	if (socketTimeout > 0)
-	{
-		_socket.setSendTimeout(socketTimeout);
-		_socket.setReceiveTimeout(socketTimeout);
-	}
+    bool ssl = false;
+    Poco::Timespan connectTimeout;
+    Poco::Timespan socketTimeout;
+    std::string authMechanism = Database::AUTH_SCRAM_SHA1;
+    std::string readPreference="primary";
 
-	if (!userInfo.empty())
-	{
-		std::string username;
-		std::string password;
-		std::string::size_type pos = userInfo.find(':');
-		if (pos != std::string::npos)
-		{
-			username.assign(userInfo, 0, pos++);
-			password.assign(userInfo, pos, userInfo.size() - pos);
-		}
-		else username = userInfo;
+    Poco::URI::QueryParameters params = theURI.getQueryParameters();
+    for (Poco::URI::QueryParameters::const_iterator it = params.begin(); it != params.end(); ++it)
+    {
+        if (it->first == "ssl")
+        {
+            ssl = (it->second == "true");
+        }
+        else if (it->first == "connectTimeoutMS")
+        {
+            connectTimeout = static_cast<Poco::Timespan::TimeDiff>(1000)*Poco::NumberParser::parse(it->second);
+        }
+        else if (it->first == "socketTimeoutMS")
+        {
+            socketTimeout = static_cast<Poco::Timespan::TimeDiff>(1000)*Poco::NumberParser::parse(it->second);
+        }
+        else if (it->first == "authMechanism")
+        {
+            authMechanism = it->second;
+        }
+        else if (it->first == "readPreference")
+        {
+            readPreference= it->second;
+        }
+    }
 
-		Database database(databaseName);
-		if (!database.authenticate(*this, username, password, authMechanism))
-			throw Poco::NoPermissionException(Poco::format("Access to MongoDB database %s denied for user %s", databaseName, username));
-	}
+    for (std::vector<std::string>::const_iterator it = strAddresses.cbegin();it != strAddresses.cend(); ++it)
+    {
+        newURI = *it;
+        theURI = Poco::URI(newURI);
+
+        std::string host = theURI.getHost();
+        Poco::UInt16 port = theURI.getPort();
+        if (port == 0) port = 27017;
+
+        connect(socketFactory.createSocket(host, port, connectTimeout, ssl));
+        _uri = newURI;
+        if (socketTimeout > 0)
+        {
+            _socket.setSendTimeout(socketTimeout);
+            _socket.setReceiveTimeout(socketTimeout);
+        }
+        if (strAddresses.size() > 1)
+        {
+            Poco::MongoDB::QueryRequest request("admin.$cmd");
+            request.setNumberToReturn(1);
+            request.selector().add("isMaster", 1);
+            Poco::MongoDB::ResponseMessage response;
+
+            sendRequest(request, response);
+            _uri = newURI;
+            if (!response.documents().empty())
+            {
+                Poco::MongoDB::Document::Ptr doc = response.documents()[0];
+                if (doc->get<bool>("ismaster") && readPreference == "primary")
+                {
+                    break;
+                }
+                else if (!doc->get<bool>("ismaster") && readPreference == "secondary")
+                {
+                    break;
+                }
+                else if (it + 1 == strAddresses.cend())
+                {
+                    throw Poco::URISyntaxException(uri);
+                }
+            }
+        }
+    }
+    if (!userInfo.empty())
+    {
+        std::string username;
+        std::string password;
+        std::string::size_type pos = userInfo.find(':');
+        if (pos != std::string::npos)
+        {
+            username.assign(userInfo, 0, pos++);
+            password.assign(userInfo, pos, userInfo.size() - pos);
+        }
+        else username = userInfo;
+
+        Database database(databaseName);
+
+        if (!database.authenticate(*this, username, password, authMechanism))
+            throw Poco::NoPermissionException(Poco::format("Access to MongoDB database %s denied for user %s", databaseName, username));
+    }
 }
 
 

base/poco/Util/src/XMLConfiguration.cpp

@@ -27,7 +27,7 @@
 #include "Poco/Exception.h"
 #include "Poco/NumberParser.h"
 #include "Poco/NumberFormatter.h"
-#include <set>
+#include <unordered_map>
 
 
 namespace Poco {

base/readpassphrase/readpassphrase.c

@@ -27,9 +27,7 @@
 #define _PATH_TTY "/dev/tty"
 #endif
 
-#ifdef HAS_RESERVED_IDENTIFIER
 #pragma clang diagnostic ignored "-Wreserved-identifier"
-#endif
 
 #include <termios.h>
 #include <signal.h>

cmake/check_flags.cmake

@@ -1,7 +1,5 @@
 include (CheckCXXCompilerFlag)
 include (CheckCCompilerFlag)
 
-check_cxx_compiler_flag("-Wreserved-identifier" HAS_RESERVED_IDENTIFIER)
-check_cxx_compiler_flag("-Wsuggest-destructor-override" HAS_SUGGEST_DESTRUCTOR_OVERRIDE)
-check_cxx_compiler_flag("-Wsuggest-override" HAS_SUGGEST_OVERRIDE)
-check_cxx_compiler_flag("-Xclang -fuse-ctor-homing" HAS_USE_CTOR_HOMING)
+# Set/unset variable based on existence of compiler flags. Example:
+# check_cxx_compiler_flag("-Wreserved-identifier" HAS_RESERVED_IDENTIFIER)

cmake/clang_tidy.cmake

@@ -5,14 +5,14 @@ if (ENABLE_CLANG_TIDY)
 
     find_program (CLANG_TIDY_CACHE_PATH NAMES "clang-tidy-cache")
     if (CLANG_TIDY_CACHE_PATH)
-        find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-15" "clang-tidy-14" "clang-tidy-13" "clang-tidy-12" "clang-tidy")
+        find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-16" "clang-tidy-15" "clang-tidy-14" "clang-tidy")
 
         # Why do we use ';' here?
         # It's a cmake black magic: https://cmake.org/cmake/help/latest/prop_tgt/LANG_CLANG_TIDY.html#prop_tgt:%3CLANG%3E_CLANG_TIDY
         # The CLANG_TIDY_PATH is passed to CMAKE_CXX_CLANG_TIDY, which follows CXX_CLANG_TIDY syntax.
         set (CLANG_TIDY_PATH "${CLANG_TIDY_CACHE_PATH};${_CLANG_TIDY_PATH}" CACHE STRING "A combined command to run clang-tidy with caching wrapper")
     else ()
-        find_program (CLANG_TIDY_PATH NAMES "clang-tidy-15" "clang-tidy-14" "clang-tidy-13" "clang-tidy-12" "clang-tidy")
+        find_program (CLANG_TIDY_PATH NAMES "clang-tidy-16" "clang-tidy-15" "clang-tidy-14" "clang-tidy")
     endif ()
 
     if (CLANG_TIDY_PATH)

cmake/tools.cmake

@@ -50,61 +50,47 @@ endif ()
 string (REGEX MATCHALL "[0-9]+" COMPILER_VERSION_LIST ${CMAKE_CXX_COMPILER_VERSION})
 list (GET COMPILER_VERSION_LIST 0 COMPILER_VERSION_MAJOR)
 
-# Example values: `lld-10`, `gold`.
+# Example values: `lld-10`
 option (LINKER_NAME "Linker name or full path")
 
-# s390x doesnt support lld
-if (NOT ARCH_S390X)
-    if (NOT LINKER_NAME)
-        if (COMPILER_GCC)
-            find_program (LLD_PATH NAMES "ld.lld")
-            find_program (GOLD_PATH NAMES "ld.gold")
-        elseif (COMPILER_CLANG)
-            # llvm lld is a generic driver.
-            # Invoke ld.lld (Unix), ld64.lld (macOS), lld-link (Windows), wasm-ld (WebAssembly) instead
-            if (OS_LINUX)
+if (LINKER_NAME MATCHES "gold")
+    message (FATAL_ERROR "Linking with gold is unsupported. Please use lld.")
+endif ()
+
+if (NOT LINKER_NAME)
+    if (COMPILER_GCC)
+        find_program (LLD_PATH NAMES "ld.lld")
+    elseif (COMPILER_CLANG)
+        # llvm lld is a generic driver.
+        # Invoke ld.lld (Unix), ld64.lld (macOS), lld-link (Windows), wasm-ld (WebAssembly) instead
+        if (OS_LINUX)
+            if (NOT ARCH_S390X) # s390x doesnt support lld
                 find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
-            elseif (OS_DARWIN)
-                find_program (LLD_PATH NAMES "ld64.lld-${COMPILER_VERSION_MAJOR}" "ld64.lld")
             endif ()
-            find_program (GOLD_PATH NAMES "ld.gold" "gold")
+        elseif (OS_DARWIN)
+            find_program (LLD_PATH NAMES "ld64.lld-${COMPILER_VERSION_MAJOR}" "ld64.lld")
+        endif ()
+    endif ()
+    if (OS_LINUX OR OS_DARWIN)
+        if (LLD_PATH)
+            if (COMPILER_GCC)
+                # GCC driver requires one of supported linker names like "lld".
+                set (LINKER_NAME "lld")
+            else ()
+                # Clang driver simply allows full linker path.
+                set (LINKER_NAME ${LLD_PATH})
+            endif ()
         endif ()
     endif()
 endif()
 
-if ((OS_LINUX OR OS_DARWIN) AND NOT LINKER_NAME)
-    # prefer lld linker over gold or ld on linux and macos
-    if (LLD_PATH)
-        if (COMPILER_GCC)
-            # GCC driver requires one of supported linker names like "lld".
-            set (LINKER_NAME "lld")
-        else ()
-            # Clang driver simply allows full linker path.
-            set (LINKER_NAME ${LLD_PATH})
-        endif ()
-    endif ()
-
-    if (NOT LINKER_NAME)
-        if (GOLD_PATH)
-            message (FATAL_ERROR "Linking with gold is unsupported. Please use lld.")
-            if (COMPILER_GCC)
-                set (LINKER_NAME "gold")
-            else ()
-                set (LINKER_NAME ${GOLD_PATH})
-            endif ()
-        endif ()
-    endif ()
-endif ()
-# TODO: allow different linker on != OS_LINUX
-
 if (LINKER_NAME)
+    find_program (LLD_PATH NAMES ${LINKER_NAME})
+    if (NOT LLD_PATH)
+        message (FATAL_ERROR "Using linker ${LINKER_NAME} but can't find its path.")
+    endif ()
     if (COMPILER_CLANG)
-        find_program (LLD_PATH NAMES ${LINKER_NAME})
-        if (NOT LLD_PATH)
-            message (FATAL_ERROR "Using linker ${LINKER_NAME} but can't find its path.")
-        endif ()
-
-        # This a temporary quirk to emit .debug_aranges with ThinLTO
+        # This a temporary quirk to emit .debug_aranges with ThinLTO, can be removed after upgrade to clang-16
         set (LLD_WRAPPER "${CMAKE_CURRENT_BINARY_DIR}/ld.lld")
         configure_file ("${CMAKE_CURRENT_SOURCE_DIR}/cmake/ld.lld.in" "${LLD_WRAPPER}" @ONLY)
 

contrib/arrow-cmake/CMakeLists.txt

@@ -115,6 +115,13 @@ configure_file("${ORC_SOURCE_SRC_DIR}/Adaptor.hh.in" "${ORC_BUILD_INCLUDE_DIR}/A
 
 # ARROW_ORC + adapters/orc/CMakefiles
 set(ORC_SRCS
+        "${CMAKE_CURRENT_BINARY_DIR}/orc_proto.pb.h"
+        "${ORC_SOURCE_SRC_DIR}/sargs/ExpressionTree.cc"
+        "${ORC_SOURCE_SRC_DIR}/sargs/Literal.cc"
+        "${ORC_SOURCE_SRC_DIR}/sargs/PredicateLeaf.cc"
+        "${ORC_SOURCE_SRC_DIR}/sargs/SargsApplier.cc"
+        "${ORC_SOURCE_SRC_DIR}/sargs/SearchArgument.cc"
+        "${ORC_SOURCE_SRC_DIR}/sargs/TruthValue.cc"
         "${ORC_SOURCE_SRC_DIR}/Exceptions.cc"
         "${ORC_SOURCE_SRC_DIR}/OrcFile.cc"
         "${ORC_SOURCE_SRC_DIR}/Reader.cc"
@@ -129,13 +136,20 @@ set(ORC_SRCS
         "${ORC_SOURCE_SRC_DIR}/MemoryPool.cc"
         "${ORC_SOURCE_SRC_DIR}/RLE.cc"
         "${ORC_SOURCE_SRC_DIR}/RLEv1.cc"
-        "${ORC_SOURCE_SRC_DIR}/RLEv2.cc"
+        "${ORC_SOURCE_SRC_DIR}/RleDecoderV2.cc"
+        "${ORC_SOURCE_SRC_DIR}/RleEncoderV2.cc"
+        "${ORC_SOURCE_SRC_DIR}/RLEV2Util.cc"
         "${ORC_SOURCE_SRC_DIR}/Statistics.cc"
         "${ORC_SOURCE_SRC_DIR}/StripeStream.cc"
         "${ORC_SOURCE_SRC_DIR}/Timezone.cc"
         "${ORC_SOURCE_SRC_DIR}/TypeImpl.cc"
         "${ORC_SOURCE_SRC_DIR}/Vector.cc"
         "${ORC_SOURCE_SRC_DIR}/Writer.cc"
+        "${ORC_SOURCE_SRC_DIR}/Adaptor.cc"
+        "${ORC_SOURCE_SRC_DIR}/BloomFilter.cc"
+        "${ORC_SOURCE_SRC_DIR}/Murmur3.cc"
+        "${ORC_SOURCE_SRC_DIR}/BlockBuffer.cc"
+        "${ORC_SOURCE_SRC_DIR}/wrap/orc-proto-wrapper.cc"
         "${ORC_SOURCE_SRC_DIR}/io/InputStream.cc"
         "${ORC_SOURCE_SRC_DIR}/io/OutputStream.cc"
         "${ORC_ADDITION_SOURCE_DIR}/orc_proto.pb.cc"
@@ -358,6 +372,9 @@ SET(ARROW_SRCS "${LIBRARY_DIR}/util/compression_zlib.cc" ${ARROW_SRCS})
 add_definitions(-DARROW_WITH_ZSTD)
 SET(ARROW_SRCS "${LIBRARY_DIR}/util/compression_zstd.cc" ${ARROW_SRCS})
 
+add_definitions(-DARROW_WITH_BROTLI)
+SET(ARROW_SRCS "${LIBRARY_DIR}/util/compression_brotli.cc" ${ARROW_SRCS})
+
 
 add_library(_arrow ${ARROW_SRCS})
 
@@ -372,6 +389,7 @@ target_link_libraries(_arrow PRIVATE
     ch_contrib::snappy
     ch_contrib::zlib
     ch_contrib::zstd
+    ch_contrib::brotli
 )
 target_link_libraries(_arrow PUBLIC _orc)
 

contrib/croaring

@@ -1 +1 @@
-Subproject commit 2c867e9f9c9e2a3a7032791f94c4c7ae3013f6e0
+Subproject commit f40ed52bcdd635840a79877cef4857315dba817c

contrib/croaring-cmake/CMakeLists.txt

@@ -17,7 +17,8 @@ set(SRCS
     "${LIBRARY_DIR}/src/containers/run.c"
     "${LIBRARY_DIR}/src/roaring.c"
     "${LIBRARY_DIR}/src/roaring_priority_queue.c"
-    "${LIBRARY_DIR}/src/roaring_array.c")
+    "${LIBRARY_DIR}/src/roaring_array.c"
+    "${LIBRARY_DIR}/src/memory.c")
 
 add_library(_roaring ${SRCS})
 

contrib/grpc-cmake/CMakeLists.txt

@@ -48,6 +48,9 @@ set(gRPC_ABSL_PROVIDER "clickhouse" CACHE STRING "" FORCE)
 # We don't want to build C# extensions.
 set(gRPC_BUILD_CSHARP_EXT OFF)
 
+# TODO: Remove this. We generally like to compile with C++23 but grpc isn't ready yet.
+set (CMAKE_CXX_STANDARD 20)
+
 set(_gRPC_CARES_LIBRARIES ch_contrib::c-ares)
 set(gRPC_CARES_PROVIDER "clickhouse" CACHE STRING "" FORCE)
 add_subdirectory("${_gRPC_SOURCE_DIR}" "${_gRPC_BINARY_DIR}")

contrib/krb5

@@ -1 +1 @@
-Subproject commit f8262a1b548eb29d97e059260042036255d07f8d
+Subproject commit 9453aec0d50e5aff9b189051611b321b40935d02

contrib/krb5-cmake/CMakeLists.txt

@@ -160,6 +160,8 @@ set(ALL_SRCS
 
     # "${KRB5_SOURCE_DIR}/lib/gssapi/spnego/negoex_trace.c"
 
+    "${KRB5_SOURCE_DIR}/lib/crypto/builtin/kdf.c"
+    "${KRB5_SOURCE_DIR}/lib/crypto/builtin/cmac.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/prng.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/enc_dk_cmac.c"
     # "${KRB5_SOURCE_DIR}/lib/crypto/krb/crc32.c"
@@ -183,7 +185,6 @@ set(ALL_SRCS
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/block_size.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/string_to_key.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/verify_checksum.c"
-    "${KRB5_SOURCE_DIR}/lib/crypto/krb/crypto_libinit.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/derive.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/random_to_key.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/verify_checksum_iov.c"
@@ -217,9 +218,7 @@ set(ALL_SRCS
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/s2k_rc4.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/valid_cksumtype.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/nfold.c"
-    "${KRB5_SOURCE_DIR}/lib/crypto/krb/prng_fortuna.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/encrypt_length.c"
-    "${KRB5_SOURCE_DIR}/lib/crypto/krb/cmac.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/keyblocks.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/prf_rc4.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/krb/s2k_pbkdf2.c"
@@ -228,11 +227,11 @@ set(ALL_SRCS
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/rc4.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/des3.c"
     #"${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/camellia.c"
+    "${KRB5_SOURCE_DIR}/lib/crypto/openssl/cmac.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/sha256.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/hmac.c"
+    "${KRB5_SOURCE_DIR}/lib/crypto/openssl/kdf.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/pbkdf2.c"
-    "${KRB5_SOURCE_DIR}/lib/crypto/openssl/init.c"
-    "${KRB5_SOURCE_DIR}/lib/crypto/openssl/stubs.c"
     # "${KRB5_SOURCE_DIR}/lib/crypto/openssl/hash_provider/hash_crc32.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/hash_provider/hash_evp.c"
     "${KRB5_SOURCE_DIR}/lib/crypto/openssl/des/des_keys.c"
@@ -312,7 +311,6 @@ set(ALL_SRCS
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/allow_weak.c"
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/mk_rep.c"
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/mk_priv.c"
-    "${KRB5_SOURCE_DIR}/lib/krb5/krb/s4u_authdata.c"
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/preauth_otp.c"
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/init_keyblock.c"
     "${KRB5_SOURCE_DIR}/lib/krb5/krb/ser_addr.c"
@@ -688,6 +686,7 @@ target_include_directories(_krb5 PRIVATE
 
 target_compile_definitions(_krb5 PRIVATE
     KRB5_PRIVATE
+    CRYPTO_OPENSSL
     _GSS_STATIC_LINK=1
     KRB5_DEPRECATED=1
     LOCALEDIR="/usr/local/share/locale"

contrib/libfarmhash/CMakeLists.txt

@@ -6,6 +6,10 @@ if (MSVC)
     target_compile_definitions (_farmhash PRIVATE FARMHASH_NO_BUILTIN_EXPECT=1)
 endif ()
 
+if (ARCH_S390X)
+    add_compile_definitions(WORDS_BIGENDIAN)
+endif ()
+
 target_include_directories (_farmhash BEFORE PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 
 add_library(ch_contrib::farmhash ALIAS _farmhash)

contrib/llvm-project

@@ -1 +1 @@
-Subproject commit a8bf69e9cd39a23140a2b633c172d201484172da
+Subproject commit d80af319f5f047067b956b2fe93a6c00038c1e0d

contrib/orc

@@ -1 +1 @@
-Subproject commit f9a393ed2433a60034795284f82d093b348f2102
+Subproject commit c5d7755ba0b9a95631c8daea4d094101f26ec761

docker/keeper/Dockerfile

@@ -29,7 +29,7 @@ RUN arch=${TARGETARCH:-amd64} \
     esac
 
 ARG REPOSITORY="https://s3.amazonaws.com/clickhouse-builds/22.4/31c367d3cd3aefd316778601ff6565119fe36682/package_release"
-ARG VERSION="23.2.1.2537"
+ARG VERSION="23.2.4.12"
 ARG PACKAGES="clickhouse-keeper"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.

docker/server/Dockerfile.alpine

@@ -33,7 +33,7 @@ RUN arch=${TARGETARCH:-amd64} \
 # lts / testing / prestable / etc
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
-ARG VERSION="23.2.1.2537"
+ARG VERSION="23.2.4.12"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.

docker/server/Dockerfile.ubuntu

@@ -22,7 +22,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
 
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="deb https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
-ARG VERSION="23.2.1.2537"
+ARG VERSION="23.2.4.12"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # set non-empty deb_location_url url to create a docker image

docker/test/stress/run.sh

@@ -41,9 +41,14 @@ if [ "$is_tsan_build" -eq "0" ]; then
     export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_TIME_US=10000
     export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_TIME_US=10000
     export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_TIME_US=10000
+
+    export THREAD_FUZZER_EXPLICIT_SLEEP_PROBABILITY=0.01
+    export THREAD_FUZZER_EXPLICIT_MEMORY_EXCEPTION_PROBABILITY=0.01
 fi
 
 export ZOOKEEPER_FAULT_INJECTION=1
+# Initial run without S3 to create system.*_log on local file system to make it
+# available for dump via clickhouse-local
 configure
 
 azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &

docker/test/upgrade/run.sh

@@ -49,19 +49,26 @@ echo -e "Successfully cloned previous release tests$OK" >> /test_output/test_res
 echo -e "Successfully downloaded previous release packages$OK" >> /test_output/test_results.tsv
 
 # Make upgrade check more funny by forcing Ordinary engine for system database
-mkdir /var/lib/clickhouse/metadata
+mkdir -p /var/lib/clickhouse/metadata
 echo "ATTACH DATABASE system ENGINE=Ordinary" > /var/lib/clickhouse/metadata/system.sql
 
 # Install previous release packages
 install_packages previous_release_package_folder
 
-# Start server from previous release
-# Let's enable S3 storage by default
-export USE_S3_STORAGE_FOR_MERGE_TREE=1
-# Previous version may not be ready for fault injections
-export ZOOKEEPER_FAULT_INJECTION=0
+# Initial run without S3 to create system.*_log on local file system to make it
+# available for dump via clickhouse-local
 configure
 
+start
+stop
+mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.initial.log
+
+# force_sync=false doesn't work correctly on some older versions
+sudo cat /etc/clickhouse-server/config.d/keeper_port.xml \
+  | sed "s|<force_sync>false</force_sync>|<force_sync>true</force_sync>|" \
+  > /etc/clickhouse-server/config.d/keeper_port.xml.tmp
+sudo mv /etc/clickhouse-server/config.d/keeper_port.xml.tmp /etc/clickhouse-server/config.d/keeper_port.xml
+
 # But we still need default disk because some tables loaded only into it
 sudo cat /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml \
   | sed "s|<main><disk>s3</disk></main>|<main><disk>s3</disk></main><default><disk>default</disk></default>|" \
@@ -69,6 +76,13 @@ sudo cat /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml \
 sudo chown clickhouse /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml
 sudo chgrp clickhouse /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml
 
+# Start server from previous release
+# Let's enable S3 storage by default
+export USE_S3_STORAGE_FOR_MERGE_TREE=1
+# Previous version may not be ready for fault injections
+export ZOOKEEPER_FAULT_INJECTION=0
+configure
+
 start
 
 clickhouse-client --query="SELECT 'Server version: ', version()"
@@ -161,8 +175,10 @@ rg -Fav -e "Code: 236. DB::Exception: Cancelled merging parts" \
            -e "Authentication failed" \
            -e "Cannot flush" \
            -e "Container already exists" \
-    /var/log/clickhouse-server/clickhouse-server.upgrade.log | zgrep -Fa "<Error>" > /test_output/upgrade_error_messages.txt \
-    && echo -e "Error message in clickhouse-server.log (see upgrade_error_messages.txt)$FAIL$(head_escaped /test_output/bc_check_error_messages.txt)" \
+    clickhouse-server.upgrade.log \
+    | grep -av -e "_repl_01111_.*Mapping for table with UUID" \
+    | zgrep -Fa "<Error>" > /test_output/upgrade_error_messages.txt \
+    && echo -e "Error message in clickhouse-server.log (see upgrade_error_messages.txt)$FAIL$(head_escaped /test_output/upgrade_error_messages.txt)" \
         >> /test_output/test_results.tsv \
     || echo -e "No Error messages after server upgrade$OK" >> /test_output/test_results.tsv
 
@@ -176,8 +192,6 @@ tar -chf /test_output/coordination.tar /var/lib/clickhouse/coordination ||:
 
 collect_query_and_trace_logs
 
-check_oom_in_dmesg
-
 mv /var/log/clickhouse-server/stderr.log /test_output/
 
 # Write check result into check_status.tsv

docs/_includes/install/universal.sh

@@ -85,9 +85,9 @@ echo
 echo "Successfully downloaded the ClickHouse binary, you can run it as:
     ./${clickhouse}"
 
-#if [ "${OS}" = "Linux" ]
-#then
-    #echo
-    #echo "You can also install it:
-    #sudo ./${clickhouse} install"
-#fi
+if [ "${OS}" = "Linux" ]
+then
+    echo
+    echo "You can also install it:
+    sudo ./${clickhouse} install"
+fi

docs/changelogs/v22.12.4.76-stable.md

@@ -0,0 +1,55 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v22.12.4.76-stable (cb5772db805) FIXME as compared to v22.12.3.5-stable (893de538f02)
+
+#### Performance Improvement
+* Backported in [#45704](https://github.com/ClickHouse/ClickHouse/issues/45704): Fixed performance of short `SELECT` queries that read from tables with large number of`Array`/`Map`/`Nested` columns. [#45630](https://github.com/ClickHouse/ClickHouse/pull/45630) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#46378](https://github.com/ClickHouse/ClickHouse/issues/46378): Fix too big memory usage for vertical merges on non-remote disk. Respect `max_insert_delayed_streams_for_parallel_write` for the remote disk. [#46275](https://github.com/ClickHouse/ClickHouse/pull/46275) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+
+#### Bug Fix
+* Backported in [#45672](https://github.com/ClickHouse/ClickHouse/issues/45672): Fix wiping sensitive info in logs. [#45603](https://github.com/ClickHouse/ClickHouse/pull/45603) ([Vitaly Baranov](https://github.com/vitlibar)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#45200](https://github.com/ClickHouse/ClickHouse/issues/45200): Fix zookeeper downloading, update the version, and optimize the image size. [#44853](https://github.com/ClickHouse/ClickHouse/pull/44853) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46116](https://github.com/ClickHouse/ClickHouse/issues/46116): Remove the dependency on the `adduser` tool from the packages, because we don't use it. This fixes [#44934](https://github.com/ClickHouse/ClickHouse/issues/44934). [#45011](https://github.com/ClickHouse/ClickHouse/pull/45011) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46035](https://github.com/ClickHouse/ClickHouse/issues/46035): Add systemd.service file for clickhouse-keeper. Fixes [#44293](https://github.com/ClickHouse/ClickHouse/issues/44293). [#45568](https://github.com/ClickHouse/ClickHouse/pull/45568) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46484](https://github.com/ClickHouse/ClickHouse/issues/46484): Get rid of unnecessary build for standalone clickhouse-keeper. [#46367](https://github.com/ClickHouse/ClickHouse/pull/46367) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46509](https://github.com/ClickHouse/ClickHouse/issues/46509): Some time ago the ccache compression was changed to `zst`, but `gz` archives are downloaded by default. It fixes it by prioritizing zst archive. [#46490](https://github.com/ClickHouse/ClickHouse/pull/46490) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#47058](https://github.com/ClickHouse/ClickHouse/issues/47058): Fix error during server startup on old distros (e.g. Amazon Linux 2) and on ARM that glibc 2.28 symbols are not found. [#47008](https://github.com/ClickHouse/ClickHouse/pull/47008) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#45904](https://github.com/ClickHouse/ClickHouse/issues/45904): Fixed bug with non-parsable default value for EPHEMERAL column in table metadata. [#44026](https://github.com/ClickHouse/ClickHouse/pull/44026) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#45321](https://github.com/ClickHouse/ClickHouse/issues/45321): Fixed a bug in normalization of a `DEFAULT` expression in `CREATE TABLE` statement. The second argument of function `in` (or the right argument of operator `IN`) might be replaced with the result of its evaluation during CREATE query execution. Fixes [#44496](https://github.com/ClickHouse/ClickHouse/issues/44496). [#44547](https://github.com/ClickHouse/ClickHouse/pull/44547) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#45000](https://github.com/ClickHouse/ClickHouse/issues/45000): Another fix for `Cannot read all data` error which could happen while reading `LowCardinality` dictionary from remote fs. Fixes [#44709](https://github.com/ClickHouse/ClickHouse/issues/44709). [#44875](https://github.com/ClickHouse/ClickHouse/pull/44875) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#45553](https://github.com/ClickHouse/ClickHouse/issues/45553): Fix `SELECT ... FROM system.dictionaries` exception when there is a dictionary with a bad structure (e.g. incorrect type in xml config). [#45399](https://github.com/ClickHouse/ClickHouse/pull/45399) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#46226](https://github.com/ClickHouse/ClickHouse/issues/46226): A couple of seg faults have been reported around `c-ares`. All of the recent stack traces observed fail on inserting into `std::unodered_set<>`. I believe I have found the root cause of this, it seems to be unprocessed queries. Prior to this PR, CH calls `poll` to wait on the file descriptors in the `c-ares` channel. According to the [poll docs](https://man7.org/linux/man-pages/man2/poll.2.html), a negative return value means an error has ocurred. Because of this, we would abort the execution and return failure. The problem is that `poll` will also return a negative value if a system interrupt occurs. A system interrupt does not mean the processing has failed or ended, but we would abort it anyways because we were checking for negative values. Once the execution is aborted, the whole stack is destroyed, which includes the `std::unordered_set<std::string>` passed to the `void *` parameter of the c-ares callback. Once c-ares completed the request, the callback would be invoked and would access an invalid memory address causing a segfault. [#45629](https://github.com/ClickHouse/ClickHouse/pull/45629) ([Arthur Passos](https://github.com/arthurpassos)).
+* Backported in [#46218](https://github.com/ClickHouse/ClickHouse/issues/46218): Fix reading of non existing nested columns with multiple level in compact parts. [#46045](https://github.com/ClickHouse/ClickHouse/pull/46045) ([Azat Khuzhin](https://github.com/azat)).
+* Backported in [#46446](https://github.com/ClickHouse/ClickHouse/issues/46446): Fix possible `LOGICAL_ERROR` in asynchronous inserts with invalid data sent in format `VALUES`. [#46350](https://github.com/ClickHouse/ClickHouse/pull/46350) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#46678](https://github.com/ClickHouse/ClickHouse/issues/46678): Fix an invalid processing of constant `LowCardinality` argument in function `arrayMap`. This bug could lead to a segfault in release, and logical error `Bad cast` in debug build. [#46569](https://github.com/ClickHouse/ClickHouse/pull/46569) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46872](https://github.com/ClickHouse/ClickHouse/issues/46872): Fix a bug in the `Map` data type. This closes [#46855](https://github.com/ClickHouse/ClickHouse/issues/46855). [#46856](https://github.com/ClickHouse/ClickHouse/pull/46856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46954](https://github.com/ClickHouse/ClickHouse/issues/46954): Fix result of LIKE predicates which translate to substring searches and contain quoted non-LIKE metacharacters. [#46875](https://github.com/ClickHouse/ClickHouse/pull/46875) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Automatically merge green backport PRs and green approved PRs [#41110](https://github.com/ClickHouse/ClickHouse/pull/41110) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Improve release scripts [#45074](https://github.com/ClickHouse/ClickHouse/pull/45074) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix wrong approved_at, simplify conditions [#45302](https://github.com/ClickHouse/ClickHouse/pull/45302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Get rid of artifactory in favor of r2 + ch-repos-manager [#45421](https://github.com/ClickHouse/ClickHouse/pull/45421) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Another attempt to fix automerge, or at least to have debug footprint [#45476](https://github.com/ClickHouse/ClickHouse/pull/45476) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Trim refs/tags/ from GITHUB_TAG in release workflow [#45636](https://github.com/ClickHouse/ClickHouse/pull/45636) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add check for running workflows to merge_pr.py [#45803](https://github.com/ClickHouse/ClickHouse/pull/45803) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Get rid of progress timestamps in release publishing [#45818](https://github.com/ClickHouse/ClickHouse/pull/45818) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add necessary dependency for sanitizers [#45959](https://github.com/ClickHouse/ClickHouse/pull/45959) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add helping logging to auto-merge script [#46080](https://github.com/ClickHouse/ClickHouse/pull/46080) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix write buffer destruction order for vertical merge. [#46205](https://github.com/ClickHouse/ClickHouse/pull/46205) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Improve install_check.py [#46458](https://github.com/ClickHouse/ClickHouse/pull/46458) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix dependencies for InstallPackagesTestAarch64 [#46597](https://github.com/ClickHouse/ClickHouse/pull/46597) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Get rid of legacy DocsReleaseChecks [#46665](https://github.com/ClickHouse/ClickHouse/pull/46665) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Reduce updates of Mergeable Check [#46781](https://github.com/ClickHouse/ClickHouse/pull/46781) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v22.12.5.34-stable.md

@@ -0,0 +1,29 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v22.12.5.34-stable (b82d6401ca1) FIXME as compared to v22.12.4.76-stable (cb5772db805)
+
+#### Improvement
+* Backported in [#46983](https://github.com/ClickHouse/ClickHouse/issues/46983): - Apply `ALTER TABLE table_name ON CLUSTER cluster MOVE PARTITION|PART partition_expr TO DISK|VOLUME 'disk_name'` to all replicas. Because `ALTER TABLE t MOVE` is not replicated. [#46402](https://github.com/ClickHouse/ClickHouse/pull/46402) ([lizhuoyu5](https://github.com/lzydmxy)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#45729](https://github.com/ClickHouse/ClickHouse/issues/45729): Fix key description when encountering duplicate primary keys. This can happen in projections. See [#45590](https://github.com/ClickHouse/ClickHouse/issues/45590) for details. [#45686](https://github.com/ClickHouse/ClickHouse/pull/45686) ([Amos Bird](https://github.com/amosbird)).
+* Backported in [#46398](https://github.com/ClickHouse/ClickHouse/issues/46398): Fix `SYSTEM UNFREEZE` queries failing with the exception `CANNOT_PARSE_INPUT_ASSERTION_FAILED`. [#46325](https://github.com/ClickHouse/ClickHouse/pull/46325) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#46903](https://github.com/ClickHouse/ClickHouse/issues/46903): - Fix incorrect alias recursion in QueryNormalizer. [#46609](https://github.com/ClickHouse/ClickHouse/pull/46609) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#47210](https://github.com/ClickHouse/ClickHouse/issues/47210): `INSERT` queries through native TCP protocol and HTTP protocol were not canceled correctly in some cases. It could lead to a partially applied query if a client canceled the query, or if a client died or, in rare cases, on network errors. As a result, it could lead to not working deduplication. Fixes [#27667](https://github.com/ClickHouse/ClickHouse/issues/27667) and [#45377](https://github.com/ClickHouse/ClickHouse/issues/45377). [#46681](https://github.com/ClickHouse/ClickHouse/pull/46681) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#47157](https://github.com/ClickHouse/ClickHouse/issues/47157): - Fix arithmetic operations in aggregate optimization with `min` and `max`. [#46705](https://github.com/ClickHouse/ClickHouse/pull/46705) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#46881](https://github.com/ClickHouse/ClickHouse/issues/46881): Fix MSan report in the `maxIntersections` function. This closes [#43126](https://github.com/ClickHouse/ClickHouse/issues/43126). [#46847](https://github.com/ClickHouse/ClickHouse/pull/46847) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#47359](https://github.com/ClickHouse/ClickHouse/issues/47359): Fix possible deadlock on distributed query cancellation. [#47161](https://github.com/ClickHouse/ClickHouse/pull/47161) ([Kruglov Pavel](https://github.com/Avogar)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Use /etc/default/clickhouse in systemd too [#47003](https://github.com/ClickHouse/ClickHouse/pull/47003) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Update typing for a new PyGithub version [#47123](https://github.com/ClickHouse/ClickHouse/pull/47123) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Follow-up to [#46681](https://github.com/ClickHouse/ClickHouse/issues/46681) [#47284](https://github.com/ClickHouse/ClickHouse/pull/47284) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Add a manual trigger for release workflow [#47302](https://github.com/ClickHouse/ClickHouse/pull/47302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v22.8.14.53-lts.md

@@ -0,0 +1,40 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v22.8.14.53-lts (4ea67c40077) FIXME as compared to v22.8.13.20-lts (e4817946d18)
+
+#### Performance Improvement
+* Backported in [#45845](https://github.com/ClickHouse/ClickHouse/issues/45845): Fixed performance of short `SELECT` queries that read from tables with large number of`Array`/`Map`/`Nested` columns. [#45630](https://github.com/ClickHouse/ClickHouse/pull/45630) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#46374](https://github.com/ClickHouse/ClickHouse/issues/46374): Fix too big memory usage for vertical merges on non-remote disk. Respect `max_insert_delayed_streams_for_parallel_write` for the remote disk. [#46275](https://github.com/ClickHouse/ClickHouse/pull/46275) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#46358](https://github.com/ClickHouse/ClickHouse/issues/46358): Allow using Vertical merge algorithm with parts in Compact format. This will allow ClickHouse server to use much less memory for background operations. This closes [#46084](https://github.com/ClickHouse/ClickHouse/issues/46084). [#46282](https://github.com/ClickHouse/ClickHouse/pull/46282) ([Anton Popov](https://github.com/CurtizJ)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#46112](https://github.com/ClickHouse/ClickHouse/issues/46112): Remove the dependency on the `adduser` tool from the packages, because we don't use it. This fixes [#44934](https://github.com/ClickHouse/ClickHouse/issues/44934). [#45011](https://github.com/ClickHouse/ClickHouse/pull/45011) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46482](https://github.com/ClickHouse/ClickHouse/issues/46482): Get rid of unnecessary build for standalone clickhouse-keeper. [#46367](https://github.com/ClickHouse/ClickHouse/pull/46367) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46505](https://github.com/ClickHouse/ClickHouse/issues/46505): Some time ago the ccache compression was changed to `zst`, but `gz` archives are downloaded by default. It fixes it by prioritizing zst archive. [#46490](https://github.com/ClickHouse/ClickHouse/pull/46490) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#45908](https://github.com/ClickHouse/ClickHouse/issues/45908): Fixed bug with non-parsable default value for EPHEMERAL column in table metadata. [#44026](https://github.com/ClickHouse/ClickHouse/pull/44026) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#46238](https://github.com/ClickHouse/ClickHouse/issues/46238): A couple of seg faults have been reported around `c-ares`. All of the recent stack traces observed fail on inserting into `std::unodered_set<>`. I believe I have found the root cause of this, it seems to be unprocessed queries. Prior to this PR, CH calls `poll` to wait on the file descriptors in the `c-ares` channel. According to the [poll docs](https://man7.org/linux/man-pages/man2/poll.2.html), a negative return value means an error has ocurred. Because of this, we would abort the execution and return failure. The problem is that `poll` will also return a negative value if a system interrupt occurs. A system interrupt does not mean the processing has failed or ended, but we would abort it anyways because we were checking for negative values. Once the execution is aborted, the whole stack is destroyed, which includes the `std::unordered_set<std::string>` passed to the `void *` parameter of the c-ares callback. Once c-ares completed the request, the callback would be invoked and would access an invalid memory address causing a segfault. [#45629](https://github.com/ClickHouse/ClickHouse/pull/45629) ([Arthur Passos](https://github.com/arthurpassos)).
+* Backported in [#45727](https://github.com/ClickHouse/ClickHouse/issues/45727): Fix key description when encountering duplicate primary keys. This can happen in projections. See [#45590](https://github.com/ClickHouse/ClickHouse/issues/45590) for details. [#45686](https://github.com/ClickHouse/ClickHouse/pull/45686) ([Amos Bird](https://github.com/amosbird)).
+* Backported in [#46394](https://github.com/ClickHouse/ClickHouse/issues/46394): Fix `SYSTEM UNFREEZE` queries failing with the exception `CANNOT_PARSE_INPUT_ASSERTION_FAILED`. [#46325](https://github.com/ClickHouse/ClickHouse/pull/46325) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#46442](https://github.com/ClickHouse/ClickHouse/issues/46442): Fix possible `LOGICAL_ERROR` in asynchronous inserts with invalid data sent in format `VALUES`. [#46350](https://github.com/ClickHouse/ClickHouse/pull/46350) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#46674](https://github.com/ClickHouse/ClickHouse/issues/46674): Fix an invalid processing of constant `LowCardinality` argument in function `arrayMap`. This bug could lead to a segfault in release, and logical error `Bad cast` in debug build. [#46569](https://github.com/ClickHouse/ClickHouse/pull/46569) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46879](https://github.com/ClickHouse/ClickHouse/issues/46879): Fix MSan report in the `maxIntersections` function. This closes [#43126](https://github.com/ClickHouse/ClickHouse/issues/43126). [#46847](https://github.com/ClickHouse/ClickHouse/pull/46847) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46871](https://github.com/ClickHouse/ClickHouse/issues/46871): Fix a bug in the `Map` data type. This closes [#46855](https://github.com/ClickHouse/ClickHouse/issues/46855). [#46856](https://github.com/ClickHouse/ClickHouse/pull/46856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Another attempt to fix automerge, or at least to have debug footprint [#45476](https://github.com/ClickHouse/ClickHouse/pull/45476) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add check for running workflows to merge_pr.py [#45803](https://github.com/ClickHouse/ClickHouse/pull/45803) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Get rid of progress timestamps in release publishing [#45818](https://github.com/ClickHouse/ClickHouse/pull/45818) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add necessary dependency for sanitizers [#45959](https://github.com/ClickHouse/ClickHouse/pull/45959) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add helping logging to auto-merge script [#46080](https://github.com/ClickHouse/ClickHouse/pull/46080) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix write buffer destruction order for vertical merge. [#46205](https://github.com/ClickHouse/ClickHouse/pull/46205) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Get rid of legacy DocsReleaseChecks [#46665](https://github.com/ClickHouse/ClickHouse/pull/46665) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v22.8.15.23-lts.md

@@ -0,0 +1,28 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v22.8.15.23-lts (d36fa168bbf) FIXME as compared to v22.8.14.53-lts (4ea67c40077)
+
+#### Improvement
+* Backported in [#46981](https://github.com/ClickHouse/ClickHouse/issues/46981): - Apply `ALTER TABLE table_name ON CLUSTER cluster MOVE PARTITION|PART partition_expr TO DISK|VOLUME 'disk_name'` to all replicas. Because `ALTER TABLE t MOVE` is not replicated. [#46402](https://github.com/ClickHouse/ClickHouse/pull/46402) ([lizhuoyu5](https://github.com/lzydmxy)).
+
+#### Bug Fix
+* Backported in [#47336](https://github.com/ClickHouse/ClickHouse/issues/47336): Sometimes after changing a role that could be not reflected on the access rights of a user who uses that role. This PR fixes that. [#46772](https://github.com/ClickHouse/ClickHouse/pull/46772) ([Vitaly Baranov](https://github.com/vitlibar)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#46901](https://github.com/ClickHouse/ClickHouse/issues/46901): - Fix incorrect alias recursion in QueryNormalizer. [#46609](https://github.com/ClickHouse/ClickHouse/pull/46609) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#47156](https://github.com/ClickHouse/ClickHouse/issues/47156): - Fix arithmetic operations in aggregate optimization with `min` and `max`. [#46705](https://github.com/ClickHouse/ClickHouse/pull/46705) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#46987](https://github.com/ClickHouse/ClickHouse/issues/46987): Fix result of LIKE predicates which translate to substring searches and contain quoted non-LIKE metacharacters. [#46875](https://github.com/ClickHouse/ClickHouse/pull/46875) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#47357](https://github.com/ClickHouse/ClickHouse/issues/47357): Fix possible deadlock on distributed query cancellation. [#47161](https://github.com/ClickHouse/ClickHouse/pull/47161) ([Kruglov Pavel](https://github.com/Avogar)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Reduce updates of Mergeable Check [#46781](https://github.com/ClickHouse/ClickHouse/pull/46781) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Update typing for a new PyGithub version [#47123](https://github.com/ClickHouse/ClickHouse/pull/47123) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add a manual trigger for release workflow [#47302](https://github.com/ClickHouse/ClickHouse/pull/47302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.1.4.58-stable.md

@@ -0,0 +1,47 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.1.4.58-stable (9ed562163a5) FIXME as compared to v23.1.3.5-stable (548b494bcce)
+
+#### Performance Improvement
+* Backported in [#46380](https://github.com/ClickHouse/ClickHouse/issues/46380): Fix too big memory usage for vertical merges on non-remote disk. Respect `max_insert_delayed_streams_for_parallel_write` for the remote disk. [#46275](https://github.com/ClickHouse/ClickHouse/pull/46275) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+
+#### Improvement
+* Backported in [#46985](https://github.com/ClickHouse/ClickHouse/issues/46985): - Apply `ALTER TABLE table_name ON CLUSTER cluster MOVE PARTITION|PART partition_expr TO DISK|VOLUME 'disk_name'` to all replicas. Because `ALTER TABLE t MOVE` is not replicated. [#46402](https://github.com/ClickHouse/ClickHouse/pull/46402) ([lizhuoyu5](https://github.com/lzydmxy)).
+* Backported in [#46778](https://github.com/ClickHouse/ClickHouse/issues/46778): Backward compatibility for T64 codec support for IPv4. [#46747](https://github.com/ClickHouse/ClickHouse/pull/46747) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#47020](https://github.com/ClickHouse/ClickHouse/issues/47020): Allow IPv4 in range(). [#46995](https://github.com/ClickHouse/ClickHouse/pull/46995) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#46031](https://github.com/ClickHouse/ClickHouse/issues/46031): Add systemd.service file for clickhouse-keeper. Fixes [#44293](https://github.com/ClickHouse/ClickHouse/issues/44293). [#45568](https://github.com/ClickHouse/ClickHouse/pull/45568) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46477](https://github.com/ClickHouse/ClickHouse/issues/46477): Get rid of unnecessary build for standalone clickhouse-keeper. [#46367](https://github.com/ClickHouse/ClickHouse/pull/46367) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#46511](https://github.com/ClickHouse/ClickHouse/issues/46511): Some time ago the ccache compression was changed to `zst`, but `gz` archives are downloaded by default. It fixes it by prioritizing zst archive. [#46490](https://github.com/ClickHouse/ClickHouse/pull/46490) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#46228](https://github.com/ClickHouse/ClickHouse/issues/46228): A couple of seg faults have been reported around `c-ares`. All of the recent stack traces observed fail on inserting into `std::unodered_set<>`. I believe I have found the root cause of this, it seems to be unprocessed queries. Prior to this PR, CH calls `poll` to wait on the file descriptors in the `c-ares` channel. According to the [poll docs](https://man7.org/linux/man-pages/man2/poll.2.html), a negative return value means an error has ocurred. Because of this, we would abort the execution and return failure. The problem is that `poll` will also return a negative value if a system interrupt occurs. A system interrupt does not mean the processing has failed or ended, but we would abort it anyways because we were checking for negative values. Once the execution is aborted, the whole stack is destroyed, which includes the `std::unordered_set<std::string>` passed to the `void *` parameter of the c-ares callback. Once c-ares completed the request, the callback would be invoked and would access an invalid memory address causing a segfault. [#45629](https://github.com/ClickHouse/ClickHouse/pull/45629) ([Arthur Passos](https://github.com/arthurpassos)).
+* Backported in [#46967](https://github.com/ClickHouse/ClickHouse/issues/46967): Backward compatibility - allow implicit narrowing conversion from UInt64 to IPv4 - required for "INSERT ... VALUES ..." expression. [#45865](https://github.com/ClickHouse/ClickHouse/pull/45865) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#46220](https://github.com/ClickHouse/ClickHouse/issues/46220): Fix reading of non existing nested columns with multiple level in compact parts. [#46045](https://github.com/ClickHouse/ClickHouse/pull/46045) ([Azat Khuzhin](https://github.com/azat)).
+* Backported in [#46751](https://github.com/ClickHouse/ClickHouse/issues/46751): Follow-up fix for Replace domain IP types (IPv4, IPv6) with native https://github.com/ClickHouse/ClickHouse/pull/43221. [#46087](https://github.com/ClickHouse/ClickHouse/pull/46087) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#46448](https://github.com/ClickHouse/ClickHouse/issues/46448): Fix possible `LOGICAL_ERROR` in asynchronous inserts with invalid data sent in format `VALUES`. [#46350](https://github.com/ClickHouse/ClickHouse/pull/46350) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#46680](https://github.com/ClickHouse/ClickHouse/issues/46680): Fix an invalid processing of constant `LowCardinality` argument in function `arrayMap`. This bug could lead to a segfault in release, and logical error `Bad cast` in debug build. [#46569](https://github.com/ClickHouse/ClickHouse/pull/46569) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46873](https://github.com/ClickHouse/ClickHouse/issues/46873): Fix a bug in the `Map` data type. This closes [#46855](https://github.com/ClickHouse/ClickHouse/issues/46855). [#46856](https://github.com/ClickHouse/ClickHouse/pull/46856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46956](https://github.com/ClickHouse/ClickHouse/issues/46956): Fix result of LIKE predicates which translate to substring searches and contain quoted non-LIKE metacharacters. [#46875](https://github.com/ClickHouse/ClickHouse/pull/46875) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Another attempt to fix automerge, or at least to have debug footprint [#45476](https://github.com/ClickHouse/ClickHouse/pull/45476) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Support DELETE ON CLUSTER [#45786](https://github.com/ClickHouse/ClickHouse/pull/45786) ([Alexander Gololobov](https://github.com/davenger)).
+* Add check for running workflows to merge_pr.py [#45803](https://github.com/ClickHouse/ClickHouse/pull/45803) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add necessary dependency for sanitizers [#45959](https://github.com/ClickHouse/ClickHouse/pull/45959) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Add helping logging to auto-merge script [#46080](https://github.com/ClickHouse/ClickHouse/pull/46080) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix write buffer destruction order for vertical merge. [#46205](https://github.com/ClickHouse/ClickHouse/pull/46205) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Wait for background tasks in ~UploadHelper [#46334](https://github.com/ClickHouse/ClickHouse/pull/46334) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Improve install_check.py [#46458](https://github.com/ClickHouse/ClickHouse/pull/46458) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Fix dependencies for InstallPackagesTestAarch64 [#46597](https://github.com/ClickHouse/ClickHouse/pull/46597) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Get rid of legacy DocsReleaseChecks [#46665](https://github.com/ClickHouse/ClickHouse/pull/46665) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Reduce updates of Mergeable Check [#46781](https://github.com/ClickHouse/ClickHouse/pull/46781) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.1.5.24-stable.md

@@ -0,0 +1,28 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.1.5.24-stable (0e51b53ba99) FIXME as compared to v23.1.4.58-stable (9ed562163a5)
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#47060](https://github.com/ClickHouse/ClickHouse/issues/47060): Fix error during server startup on old distros (e.g. Amazon Linux 2) and on ARM that glibc 2.28 symbols are not found. [#47008](https://github.com/ClickHouse/ClickHouse/pull/47008) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#46401](https://github.com/ClickHouse/ClickHouse/issues/46401): Fix `SYSTEM UNFREEZE` queries failing with the exception `CANNOT_PARSE_INPUT_ASSERTION_FAILED`. [#46325](https://github.com/ClickHouse/ClickHouse/pull/46325) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#46905](https://github.com/ClickHouse/ClickHouse/issues/46905): - Fix incorrect alias recursion in QueryNormalizer. [#46609](https://github.com/ClickHouse/ClickHouse/pull/46609) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#47211](https://github.com/ClickHouse/ClickHouse/issues/47211): `INSERT` queries through native TCP protocol and HTTP protocol were not canceled correctly in some cases. It could lead to a partially applied query if a client canceled the query, or if a client died or, in rare cases, on network errors. As a result, it could lead to not working deduplication. Fixes [#27667](https://github.com/ClickHouse/ClickHouse/issues/27667) and [#45377](https://github.com/ClickHouse/ClickHouse/issues/45377). [#46681](https://github.com/ClickHouse/ClickHouse/pull/46681) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#47118](https://github.com/ClickHouse/ClickHouse/issues/47118): - Fix arithmetic operations in aggregate optimization with `min` and `max`. [#46705](https://github.com/ClickHouse/ClickHouse/pull/46705) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#46883](https://github.com/ClickHouse/ClickHouse/issues/46883): Fix MSan report in the `maxIntersections` function. This closes [#43126](https://github.com/ClickHouse/ClickHouse/issues/43126). [#46847](https://github.com/ClickHouse/ClickHouse/pull/46847) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#47361](https://github.com/ClickHouse/ClickHouse/issues/47361): Fix possible deadlock on distributed query cancellation. [#47161](https://github.com/ClickHouse/ClickHouse/pull/47161) ([Kruglov Pavel](https://github.com/Avogar)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Use /etc/default/clickhouse in systemd too [#47003](https://github.com/ClickHouse/ClickHouse/pull/47003) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Update typing for a new PyGithub version [#47123](https://github.com/ClickHouse/ClickHouse/pull/47123) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Follow-up to [#46681](https://github.com/ClickHouse/ClickHouse/issues/46681) [#47284](https://github.com/ClickHouse/ClickHouse/pull/47284) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Add a manual trigger for release workflow [#47302](https://github.com/ClickHouse/ClickHouse/pull/47302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.2.2.20-stable.md

@@ -0,0 +1,30 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.2.2.20-stable (f6c269c8df2) FIXME as compared to v23.2.1.2537-stable (52bf836e03a)
+
+#### Improvement
+* Backported in [#46914](https://github.com/ClickHouse/ClickHouse/issues/46914): Allow PREWHERE for Merge with different DEFAULT expression for column. [#46831](https://github.com/ClickHouse/ClickHouse/pull/46831) ([Azat Khuzhin](https://github.com/azat)).
+* Backported in [#47022](https://github.com/ClickHouse/ClickHouse/issues/47022): Allow IPv4 in range(). [#46995](https://github.com/ClickHouse/ClickHouse/pull/46995) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+
+#### Bug Fix
+* Backported in [#46828](https://github.com/ClickHouse/ClickHouse/issues/46828): Combined PREWHERE column accumulated from multiple PREWHERE in some cases didn't contain 0's from previous steps. The fix is to apply final filter if we know that it wasn't applied from more than 1 last step. [#46785](https://github.com/ClickHouse/ClickHouse/pull/46785) ([Alexander Gololobov](https://github.com/davenger)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#47062](https://github.com/ClickHouse/ClickHouse/issues/47062): Fix error during server startup on old distros (e.g. Amazon Linux 2) and on ARM that glibc 2.28 symbols are not found. [#47008](https://github.com/ClickHouse/ClickHouse/pull/47008) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#46895](https://github.com/ClickHouse/ClickHouse/issues/46895): Fixed a bug in automatic retries of `DROP TABLE` query with `ReplicatedMergeTree` tables and `Atomic` databases. In rare cases it could lead to `Can't get data for node /zk_path/log_pointer` and `The specified key does not exist` errors if ZooKeeper session expired during DROP and a new replicated table with the same path in ZooKeeper was created in parallel. [#46384](https://github.com/ClickHouse/ClickHouse/pull/46384) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#46865](https://github.com/ClickHouse/ClickHouse/issues/46865): Fix a bug in the `Map` data type. This closes [#46855](https://github.com/ClickHouse/ClickHouse/issues/46855). [#46856](https://github.com/ClickHouse/ClickHouse/pull/46856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#46958](https://github.com/ClickHouse/ClickHouse/issues/46958): Fix result of LIKE predicates which translate to substring searches and contain quoted non-LIKE metacharacters. [#46875](https://github.com/ClickHouse/ClickHouse/pull/46875) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* More concise logging at trace level for PREWHERE steps [#46771](https://github.com/ClickHouse/ClickHouse/pull/46771) ([Alexander Gololobov](https://github.com/davenger)).
+* Reduce updates of Mergeable Check [#46781](https://github.com/ClickHouse/ClickHouse/pull/46781) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.2.3.17-stable.md

@@ -0,0 +1,23 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.2.3.17-stable (dec18bf7281) FIXME as compared to v23.2.2.20-stable (f6c269c8df2)
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#46907](https://github.com/ClickHouse/ClickHouse/issues/46907): - Fix incorrect alias recursion in QueryNormalizer. [#46609](https://github.com/ClickHouse/ClickHouse/pull/46609) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#47091](https://github.com/ClickHouse/ClickHouse/issues/47091): - Fix arithmetic operations in aggregate optimization with `min` and `max`. [#46705](https://github.com/ClickHouse/ClickHouse/pull/46705) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#46885](https://github.com/ClickHouse/ClickHouse/issues/46885): Fix MSan report in the `maxIntersections` function. This closes [#43126](https://github.com/ClickHouse/ClickHouse/issues/43126). [#46847](https://github.com/ClickHouse/ClickHouse/pull/46847) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#47067](https://github.com/ClickHouse/ClickHouse/issues/47067): Fix typo in systemd service, which causes the systemd service start to fail. [#47051](https://github.com/ClickHouse/ClickHouse/pull/47051) ([Palash Goel](https://github.com/palash-goel)).
+* Backported in [#47259](https://github.com/ClickHouse/ClickHouse/issues/47259): Fix concrete columns PREWHERE support. [#47154](https://github.com/ClickHouse/ClickHouse/pull/47154) ([Azat Khuzhin](https://github.com/azat)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Use /etc/default/clickhouse in systemd too [#47003](https://github.com/ClickHouse/ClickHouse/pull/47003) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* do flushUntrackedMemory when context switches [#47102](https://github.com/ClickHouse/ClickHouse/pull/47102) ([Sema Checherinda](https://github.com/CheSema)).
+* Update typing for a new PyGithub version [#47123](https://github.com/ClickHouse/ClickHouse/pull/47123) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.2.4.12-stable.md

@@ -0,0 +1,20 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.2.4.12-stable (8fe866cb035) FIXME as compared to v23.2.3.17-stable (dec18bf7281)
+
+#### Bug Fix (user-visible misbehavior in official stable or prestable release)
+
+* Backported in [#47277](https://github.com/ClickHouse/ClickHouse/issues/47277): Fix IPv4/IPv6 serialization/deserialization in binary formats that was broken in https://github.com/ClickHouse/ClickHouse/pull/43221. Closes [#46522](https://github.com/ClickHouse/ClickHouse/issues/46522). [#46616](https://github.com/ClickHouse/ClickHouse/pull/46616) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#47212](https://github.com/ClickHouse/ClickHouse/issues/47212): `INSERT` queries through native TCP protocol and HTTP protocol were not canceled correctly in some cases. It could lead to a partially applied query if a client canceled the query, or if a client died or, in rare cases, on network errors. As a result, it could lead to not working deduplication. Fixes [#27667](https://github.com/ClickHouse/ClickHouse/issues/27667) and [#45377](https://github.com/ClickHouse/ClickHouse/issues/45377). [#46681](https://github.com/ClickHouse/ClickHouse/pull/46681) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#47363](https://github.com/ClickHouse/ClickHouse/issues/47363): Fix possible deadlock on distributed query cancellation. [#47161](https://github.com/ClickHouse/ClickHouse/pull/47161) ([Kruglov Pavel](https://github.com/Avogar)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Follow-up to [#46681](https://github.com/ClickHouse/ClickHouse/issues/46681) [#47284](https://github.com/ClickHouse/ClickHouse/pull/47284) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Add a manual trigger for release workflow [#47302](https://github.com/ClickHouse/ClickHouse/pull/47302) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/en/development/architecture.md

@@ -172,7 +172,7 @@ Global thread pool is `GlobalThreadPool` singleton class. To allocate thread fro
 
 Global pool is universal and all pools described below are implemented on top of it. This can be thought of as a hierarchy of pools. Any specialized pool takes its threads from the global pool using `ThreadPool` class. So the main purpose of any specialized pool is to apply limit on the number of simultaneous jobs and do job scheduling. If there are more jobs scheduled than threads in a pool, `ThreadPool` accumulates jobs in a queue with priorities. Each job has an integer priority. Default priority is zero. All jobs with higher priority values are started before any job with lower priority value. But there is no difference between already executing jobs, thus priority matters only when the pool in overloaded.
 
-IO thread pool is implemented as a plain `ThreadPool` accessible via `IOThreadPool::get()` method. It is configured in the same way as global pool with `max_io_thread_pool_size`, `max_io_thread_pool_free_size` and `io_thread_pool_queue_size` settings. The main purpose of IO thread pool is to avoid exhaustion of the global pool with IO jobs, which could prevent queries from fully utilizing CPU.
+IO thread pool is implemented as a plain `ThreadPool` accessible via `IOThreadPool::get()` method. It is configured in the same way as global pool with `max_io_thread_pool_size`, `max_io_thread_pool_free_size` and `io_thread_pool_queue_size` settings. The main purpose of IO thread pool is to avoid exhaustion of the global pool with IO jobs, which could prevent queries from fully utilizing CPU. Backup to S3 does significant amount of IO operations and to avoid impact on interactive queries there is a separate `BackupsIOThreadPool` configured with `max_backups_io_thread_pool_size`, `max_backups_io_thread_pool_free_size` and `backups_io_thread_pool_queue_size` settings.
 
 For periodic task execution there is `BackgroundSchedulePool` class. You can register tasks using `BackgroundSchedulePool::TaskHolder` objects and the pool ensures that no task runs two jobs at the same time. It also allows you to postpone task execution to a specific instant in the future or temporarily deactivate task. Global `Context` provides a few instances of this class for different purposes. For general purpose tasks `Context::getSchedulePool()` is used.
 

docs/en/development/build-cross-s390x.md

@@ -0,0 +1,123 @@
+---
+slug: /en/development/build-cross-s390x
+sidebar_position: 69
+title: How to Build, Run and Debug ClickHouse on Linux for s390x (zLinux)
+sidebar_label: Build on Linux for s390x (zLinux)
+---
+
+As of writing (2023/3/10) building for s390x considered to be experimental. Not all features can be enabled, has broken features and is currently under active development. 
+
+
+## Building
+
+As s390x does not support boringssl, it uses OpenSSL and has two related build options. 
+- By default, the s390x build will dynamically link to OpenSSL libraries. It will build OpenSSL shared objects, so it's not necessary to install OpenSSL beforehand. (This option is recommended in all cases.)
+- Another option is to build OpenSSL in-tree. In this case two build flags need to be supplied to cmake
+```bash
+-DENABLE_OPENSSL_DYNAMIC=0 -DENABLE_OPENSSL=1
+```
+
+These instructions assume that the host machine is x86_64 and has all the tooling required to build natively based on the [build instructions](../development/build.md). It also assumes that the host is Ubuntu 22.04 but the following instructions should also work on Ubuntu 20.04.
+
+In addition to installing the tooling used to build natively, the following additional packages need to be installed:
+
+```bash
+apt-get install binutils-s390x-linux-gnu libc6-dev-s390x-cross gcc-s390x-linux-gnu binfmt-support qemu-user-static
+```
+
+If you wish to cross compile rust code install the rust cross compile target for s390x:
+```bash
+rustup target add s390x-unknown-linux-gnu
+```
+
+To build for s390x:
+```bash
+cmake -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-s390x.cmake ..
+ninja
+```
+
+## Running
+
+Once built, the binary can be run with, eg.:
+
+```bash
+qemu-s390x-static -L /usr/s390x-linux-gnu ./clickhouse
+```
+
+## Debugging
+
+Install LLDB:
+
+```bash
+apt-get install lldb-15
+```
+
+To Debug a s390x executable, run clickhouse using QEMU in debug mode:
+
+```bash
+qemu-s390x-static -g 31338 -L /usr/s390x-linux-gnu ./clickhouse
+```
+
+In another shell run LLDB and attach, replace `<Clickhouse Parent Directory>` and `<build directory>` with the values corresponding to your environment.
+```bash
+lldb-15
+(lldb) target create ./clickhouse
+Current executable set to '/<Clickhouse Parent Directory>/ClickHouse/<build directory>/programs/clickhouse' (s390x).
+(lldb) settings set target.source-map <build directory> /<Clickhouse Parent Directory>/ClickHouse
+(lldb) gdb-remote 31338
+Process 1 stopped
+* thread #1, stop reason = signal SIGTRAP
+    frame #0: 0x0000004020e74cd0
+->  0x4020e74cd0: lgr    %r2, %r15
+    0x4020e74cd4: aghi   %r15, -160
+    0x4020e74cd8: xc     0(8,%r15), 0(%r15)
+    0x4020e74cde: brasl  %r14, 275429939040
+(lldb) b main
+Breakpoint 1: 9 locations.
+(lldb) c
+Process 1 resuming
+Process 1 stopped
+* thread #1, stop reason = breakpoint 1.1
+    frame #0: 0x0000004005cd9fc0 clickhouse`main(argc_=1, argv_=0x0000004020e594a8) at main.cpp:450:17
+   447  #if !defined(FUZZING_MODE)
+   448  int main(int argc_, char ** argv_)
+   449  {
+-> 450      inside_main = true;
+   451      SCOPE_EXIT({ inside_main = false; });
+   452
+   453      /// PHDR cache is required for query profiler to work reliably
+```
+
+## Visual Studio Code integration
+
+- (CodeLLDB extension)[https://github.com/vadimcn/vscode-lldb] is required for visual debugging, the (Command Variable)[https://github.com/rioj7/command-variable] extension can help dynamic launches if using (cmake variants)[https://github.com/microsoft/vscode-cmake-tools/blob/main/docs/variants.md].
+- Make sure to set the backend to your llvm installation eg. `"lldb.library": "/usr/lib/x86_64-linux-gnu/liblldb-15.so"`
+- Launcher:
+```json
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Debug",
+            "type": "lldb",
+            "request": "custom",
+            "targetCreateCommands": ["target create ${command:cmake.launchTargetDirectory}/clickhouse"],
+            "processCreateCommands": ["settings set target.source-map ${input:targetdir} ${workspaceFolder}", "gdb-remote 31338"],
+            "sourceMap": { "${input:targetdir}": "${workspaceFolder}" },
+        }
+    ],
+	"inputs": [
+        {
+            "id": "targetdir",
+            "type": "command",
+            "command": "extension.commandvariable.transform",
+            "args": {
+                "text": "${command:cmake.launchTargetDirectory}",
+                "find": ".*/([^/]+)/[^/]+$",
+                "replace": "$1"
+            }
+        }
+    ]
+}
+```
+- Make sure to run the clickhouse executable in debug mode prior to launch. (It is also possible to create a `preLaunchTask` that automates this)

docs/en/development/build.md

@@ -159,4 +159,3 @@ The CI checks build the binaries on each commit to [ClickHouse](https://github.c
 1. Find the type of package for your operating system that you need and download the files.
 
 ![build artifact check](images/find-build-artifact.png)
-

docs/en/development/contrib.md

@@ -1,6 +1,6 @@
 ---
 slug: /en/development/contrib
-sidebar_position: 71
+sidebar_position: 72
 sidebar_label: Third-Party Libraries
 description: A list of third-party libraries used
 ---

docs/en/development/developer-instruction.md

@@ -67,7 +67,7 @@ It generally means that the SSH keys for connecting to GitHub are missing. These
 
 You can also clone the repository via https protocol:
 
-    git clone --recursive--shallow-submodules https://github.com/ClickHouse/ClickHouse.git
+    git clone --recursive --shallow-submodules https://github.com/ClickHouse/ClickHouse.git
 
 This, however, will not let you send your changes to the server. You can still use it temporarily and add the SSH keys later replacing the remote address of the repository with `git remote` command.
 

docs/en/development/style.md

@@ -1,6 +1,6 @@
 ---
 slug: /en/development/style
-sidebar_position: 69
+sidebar_position: 70
 sidebar_label: C++ Guide
 description: A list of recommendations regarding coding style, naming convention, formatting and more
 ---

docs/en/development/tests.md

@@ -1,6 +1,6 @@
 ---
 slug: /en/development/tests
-sidebar_position: 70
+sidebar_position: 71
 sidebar_label: Testing
 title: ClickHouse Testing
 description: Most of ClickHouse features can be tested with functional tests and they are mandatory to use for every change in ClickHouse code that can be tested that way.
@@ -31,6 +31,9 @@ folder and run the following command:
 PATH=$PATH:<path to clickhouse-client> tests/clickhouse-test 01428_hash_set_nan_key
 ```
 
+Test results (`stderr` and `stdout`) are written to files `01428_hash_set_nan_key.[stderr|stdout]` which
+are located near the test file itself (so for `queries/0_stateless/foo.sql` output will be in `queries/0_stateless/foo.stdout`).
+
 For more options, see `tests/clickhouse-test --help`. You can simply run all tests or run subset of tests filtered by substring in test name: `./clickhouse-test substring`. There are also options to run tests in parallel or in randomized order.
 
 ### Adding a New Test
@@ -68,7 +71,7 @@ SELECT 1
 | `global` | Same as `shard`. Prefer `shard` ||
 | `zookeeper` | Test requires Zookeeper or ClickHouse Keeper to run | Test uses `ReplicatedMergeTree` |
 | `replica` | Same as `zookeeper`. Prefer `zookeeper` ||
-| `no-fasttest`|  Test is not run under [Fast test](continuous-integration#fast-test) | Test uses `MySQL` table engine which is disabled in Fast test|
+| `no-fasttest`|  Test is not run under [Fast test](continuous-integration.md#fast-test) | Test uses `MySQL` table engine which is disabled in Fast test|
 | `no-[asan, tsan, msan, ubsan]` | Disables tests in build with [sanitizers](#sanitizers) | Test is run under QEMU which doesn't work with sanitizers |
 | `no-replicated-database` |||
 | `no-ordinary-database` |||

docs/en/engines/_category_.yml

@@ -4,5 +4,4 @@ collapsible: true
 collapsed: true
 link:
   type: generated-index
-  title: Database & Table Engines
   slug: /en/engines

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

@@ -19,8 +19,8 @@ Kafka lets you:
 ``` sql
 CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
 (
-    name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1],
-    name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2],
+    name1 [type1],
+    name2 [type2],
     ...
 ) ENGINE = Kafka()
 SETTINGS
@@ -113,6 +113,10 @@ Kafka(kafka_broker_list, kafka_topic_list, kafka_group_name, kafka_format
 
 </details>
 
+:::info
+The Kafka table engine doesn't support columns with [default value](../../../sql-reference/statements/create/table.md#default_value). If you need columns with default value, you can add them at materialized view level (see below).
+:::
+
 ## Description {#description}
 
 The delivered messages are tracked automatically, so each message in a group is only counted once. If you want to get the data twice, then create a copy of the table with another group name.

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

@@ -180,4 +180,4 @@ Default value: `300`.
 ## See Also {#see-also}
 
 -   [The mysql table function](../../../sql-reference/table-functions/mysql.md)
--   [Using MySQL as a dictionary source](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-mysql)
+-   [Using MySQL as a dictionary source](../../../sql-reference/dictionaries/index.md#dictionary-sources#dicts-external_dicts_dict_sources-mysql)

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

@@ -126,5 +126,5 @@ SELECT * FROM odbc_t
 
 ## See Also {#see-also}
 
--   [ODBC dictionaries](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-odbc)
+-   [ODBC dictionaries](../../../sql-reference/dictionaries/index.md#dictionary-sources#dicts-external_dicts_dict_sources-odbc)
 -   [ODBC table function](../../../sql-reference/table-functions/odbc.md)

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

@@ -174,7 +174,7 @@ CREATE TABLE pg_table_schema_with_dots (a UInt32)
 **See Also**
 
 -   [The `postgresql` table function](../../../sql-reference/table-functions/postgresql.md)
--   [Using PostgreSQL as a dictionary source](../../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md#dicts-external_dicts_dict_sources-postgresql)
+-   [Using PostgreSQL as a dictionary source](../../../sql-reference/dictionaries/index.md#dictionary-sources#dicts-external_dicts_dict_sources-postgresql)
 
 ## Related content
 - Blog: [ClickHouse and PostgreSQL - a match made in data heaven - part 1](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres)

docs/en/engines/table-engines/integrations/s3.md

@@ -150,6 +150,7 @@ The following settings can be specified in configuration file for given endpoint
 -   `use_environment_credentials` — If set to `true`, S3 client will try to obtain credentials from environment variables and [Amazon EC2](https://en.wikipedia.org/wiki/Amazon_Elastic_Compute_Cloud) metadata for given endpoint. Optional, default value is `false`.
 -   `region` — Specifies S3 region name. Optional.
 -   `use_insecure_imds_request` — If set to `true`, S3 client will use insecure IMDS request while obtaining credentials from Amazon EC2 metadata. Optional, default value is `false`.
+-   `expiration_window_seconds` — Grace period for checking if expiration-based credentials have expired. Optional, default value is `120`.
 -   `header` —  Adds specified HTTP header to a request to given endpoint. Optional, can be specified multiple times.
 -   `server_side_encryption_customer_key_base64` — If specified, required headers for accessing S3 objects with SSE-C encryption will be set. Optional.
 -   `max_single_read_retries` — The maximum number of attempts during single read. Default value is `4`. Optional.
@@ -166,6 +167,7 @@ The following settings can be specified in configuration file for given endpoint
         <!-- <region>us-west-1</region> -->
         <!-- <use_environment_credentials>false</use_environment_credentials> -->
         <!-- <use_insecure_imds_request>false</use_insecure_imds_request> -->
+        <!-- <expiration_window_seconds>120</expiration_window_seconds> -->
         <!-- <header>Authorization: Bearer SOME-TOKEN</header> -->
         <!-- <server_side_encryption_customer_key_base64>BASE64-ENCODED-KEY</server_side_encryption_customer_key_base64> -->
         <!-- <max_single_read_retries>4</max_single_read_retries> -->

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

@@ -450,29 +450,32 @@ INDEX sample_index3 (lower(str), str) TYPE ngrambf_v1(3, 256, 2, 0) GRANULARITY
 
 Conditions in the `WHERE` clause contains calls of the functions that operate with columns. If the column is a part of an index, ClickHouse tries to use this index when performing the functions. ClickHouse supports different subsets of functions for using indexes.
 
-The `set` index can be used with all functions. Function subsets for other indexes are shown in the table below.
+Indexes of type `set` can be utilized by all functions. The other index types are supported as follows:
 
 | Function (operator) / Index                                                                                | primary key | minmax | ngrambf_v1 | tokenbf_v1 | bloom_filter |
-|------------------------------------------------------------------------------------------------------------|-------------|--------|-------------|-------------|---------------|
-| [equals (=, ==)](/docs/en/sql-reference/functions/comparison-functions.md/#function-equals)                 | ✔           | ✔      | ✔           | ✔           | ✔             |
-| [notEquals(!=, <>)](/docs/en/sql-reference/functions/comparison-functions.md/#function-notequals)         | ✔           | ✔      | ✔           | ✔           | ✔             |
-| [like](/docs/en/sql-reference/functions/string-search-functions.md/#function-like)                          | ✔           | ✔      | ✔           | ✔           | ✗             |
-| [notLike](/docs/en/sql-reference/functions/string-search-functions.md/#function-notlike)                    | ✔           | ✔      | ✔           | ✔           | ✗             |
-| [startsWith](/docs/en/sql-reference/functions/string-functions.md/#startswith)                              | ✔           | ✔      | ✔           | ✔           | ✗             |
-| [endsWith](/docs/en/sql-reference/functions/string-functions.md/#endswith)                                  | ✗           | ✗      | ✔           | ✔           | ✗             |
-| [multiSearchAny](/docs/en/sql-reference/functions/string-search-functions.md/#function-multisearchany)      | ✗           | ✗      | ✔           | ✗           | ✗             |
-| [in](/docs/en/sql-reference/functions/in-functions#in-functions)                                        | ✔           | ✔      | ✔           | ✔           | ✔             |
-| [notIn](/docs/en/sql-reference/functions/in-functions#in-functions)                                     | ✔           | ✔      | ✔           | ✔           | ✔             |
-| [less (<)](/docs/en/sql-reference/functions/comparison-functions.md/#function-less)                        | ✔           | ✔      | ✗           | ✗           | ✗             |
-| [greater (>)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greater)                  | ✔           | ✔      | ✗           | ✗           | ✗             |
-| [lessOrEquals (<=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-lessorequals)       | ✔           | ✔      | ✗           | ✗           | ✗             |
-| [greaterOrEquals (>=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greaterorequals) | ✔           | ✔      | ✗           | ✗           | ✗             |
-| [empty](/docs/en/sql-reference/functions/array-functions#function-empty)                                | ✔           | ✔      | ✗           | ✗           | ✗             |
-| [notEmpty](/docs/en/sql-reference/functions/array-functions#function-notempty)                          | ✔           | ✔      | ✗           | ✗           | ✗             |
-| hasToken                                                                                                   | ✗           | ✗      | ✗           | ✔           | ✗             |
-| hasTokenOrNull                                                                                                   | ✗           | ✗      | ✗           | ✔           | ✗             |
-| hasTokenCaseInsensitive                                                                                                   | ✗           | ✗      | ✗           | ✔           | ✗             |
-| hasTokenCaseInsensitiveOrNull                                                                                                   | ✗           | ✗      | ✗           | ✔           | ✗             |
+|------------------------------------------------------------------------------------------------------------|-------------|--------|------------|------------|--------------|
+| [equals (=, ==)](/docs/en/sql-reference/functions/comparison-functions.md/#function-equals)                | ✔           | ✔      | ✔          | ✔          | ✔            |
+| [notEquals(!=, &lt;&gt;)](/docs/en/sql-reference/functions/comparison-functions.md/#function-notequals)    | ✔           | ✔      | ✔          | ✔          | ✔            |
+| [like](/docs/en/sql-reference/functions/string-search-functions.md/#function-like)                         | ✔           | ✔      | ✔          | ✔          | ✗            |
+| [notLike](/docs/en/sql-reference/functions/string-search-functions.md/#function-notlike)                   | ✔           | ✔      | ✔          | ✔          | ✗            |
+| [startsWith](/docs/en/sql-reference/functions/string-functions.md/#startswith)                             | ✔           | ✔      | ✔          | ✔          | ✗            |
+| [endsWith](/docs/en/sql-reference/functions/string-functions.md/#endswith)                                 | ✗           | ✗      | ✔          | ✔          | ✗            |
+| [multiSearchAny](/docs/en/sql-reference/functions/string-search-functions.md/#function-multisearchany)     | ✗           | ✗      | ✔          | ✗          | ✗            |
+| [in](/docs/en/sql-reference/functions/in-functions#in-functions)                                           | ✔           | ✔      | ✔          | ✔          | ✔            |
+| [notIn](/docs/en/sql-reference/functions/in-functions#in-functions)                                        | ✔           | ✔      | ✔          | ✔          | ✔            |
+| [less (<)](/docs/en/sql-reference/functions/comparison-functions.md/#function-less)                        | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [greater (>)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greater)                  | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [lessOrEquals (<=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-lessorequals)       | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [greaterOrEquals (>=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greaterorequals) | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [empty](/docs/en/sql-reference/functions/array-functions#function-empty)                                   | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [notEmpty](/docs/en/sql-reference/functions/array-functions#function-notempty)                             | ✔           | ✔      | ✗          | ✗          | ✗            |
+| [has](/docs/en/sql-reference/functions/array-functions#function-has)                                       | ✗           | ✗      | ✔          | ✔          | ✔            |
+| [hasAny](/docs/en/sql-reference/functions/array-functions#function-hasAny)                                 | ✗           | ✗      | ✗          | ✗          | ✔            |
+| [hasAll](/docs/en/sql-reference/functions/array-functions#function-hasAll)                                 | ✗           | ✗      | ✗          | ✗          | ✔            |
+| hasToken                                                                                                   | ✗           | ✗      | ✗          | ✔          | ✗            |
+| hasTokenOrNull                                                                                             | ✗           | ✗      | ✗          | ✔          | ✗            |
+| hasTokenCaseInsensitive                                                                                    | ✗           | ✗      | ✗          | ✔          | ✗            |
+| hasTokenCaseInsensitiveOrNull                                                                              | ✗           | ✗      | ✗          | ✔          | ✗            |
 
 Functions with a constant argument that is less than ngram size can’t be used by `ngrambf_v1` for query optimization.
 
@@ -898,7 +901,7 @@ User can assign new big parts to different disks of a [JBOD](https://en.wikipedi
 ## Using S3 for Data Storage {#table_engine-mergetree-s3}
 
 :::note
-Google Cloud Storage (GCS) is also supported using the type `s3`. See [GCS backed MergeTree](/docs/en/integrations/data-ingestion/s3/gcs-merge-tree.md).
+Google Cloud Storage (GCS) is also supported using the type `s3`. See [GCS backed MergeTree](/docs/en/integrations/gcs).
 :::
 
 `MergeTree` family table engines can store data to [S3](https://aws.amazon.com/s3/) using a disk with type `s3`.
@@ -957,6 +960,7 @@ Optional parameters:
 -   `support_batch_delete` — This controls the check to see if batch deletes are supported. Set this to `false` when using Google Cloud Storage (GCS) as GCS does not support batch deletes and preventing the checks will prevent error messages in the logs.
 -   `use_environment_credentials` — Reads AWS credentials from the Environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN if they exist. Default value is `false`.
 -   `use_insecure_imds_request` — If set to `true`, S3 client will use insecure IMDS request while obtaining credentials from Amazon EC2 metadata. Default value is `false`.
+-   `expiration_window_seconds` — Grace period for checking if expiration-based credentials have expired. Optional, default value is `120`.
 -   `proxy` — Proxy configuration for S3 endpoint. Each `uri` element inside `proxy` block should contain a proxy URL.
 -   `connect_timeout_ms` — Socket connect timeout in milliseconds. Default value is `10 seconds`.
 -   `request_timeout_ms` — Request timeout in milliseconds. Default value is `5 seconds`.

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

@@ -39,7 +39,7 @@ Compressed data for `INSERT` and `ALTER` queries is replicated (for more informa
 -   The `DROP TABLE` query deletes the replica located on the server where the query is run.
 -   The `RENAME` query renames the table on one of the replicas. In other words, replicated tables can have different names on different replicas.
 
-ClickHouse uses [ClickHouse Keeper](/docs/en/guides/sre/keeper/clickhouse-keeper.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
+ClickHouse uses [ClickHouse Keeper](/docs/en/guides/sre/keeper/index.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
 
 To use replication, set parameters in the [zookeeper](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings_zookeeper) server configuration section.
 
@@ -144,7 +144,7 @@ ENGINE = ReplicatedReplacingMergeTree
 The `Replicated` prefix is added to the table engine name. For example:`ReplicatedMergeTree`.
 
 :::tip
-Adding `Replicated` is optional in ClickHouse Cloud, as all of the tables are replicated.  
+Adding `Replicated` is optional in ClickHouse Cloud, as all of the tables are replicated.
 :::
 
 ### Replicated\*MergeTree parameters

docs/en/engines/table-engines/special/dictionary.md

@@ -6,7 +6,7 @@ sidebar_label: Dictionary
 
 # Dictionary Table Engine
 
-The `Dictionary` engine displays the [dictionary](../../../sql-reference/dictionaries/external-dictionaries/external-dicts.md) data as a ClickHouse table.
+The `Dictionary` engine displays the [dictionary](../../../sql-reference/dictionaries/index.md) data as a ClickHouse table.
 
 ## Example {#example}
 

docs/en/engines/table-engines/special/distributed.md

@@ -184,7 +184,7 @@ The parameters `host`, `port`, and optionally `user`, `password`, `secure`, `com
 
 - `host` – The address of the remote server. You can use either the domain or the IPv4 or IPv6 address. If you specify the domain, the server makes a DNS request when it starts, and the result is stored as long as the server is running. If the DNS request fails, the server does not start. If you change the DNS record, restart the server.
 - `port` – The TCP port for messenger activity (`tcp_port` in the config, usually set to 9000). Not to be confused with `http_port`.
-- `user` – Name of the user for connecting to a remote server. Default value is the `default` user. This user must have access to connect to the specified server. Access is configured in the `users.xml` file. For more information, see the section [Access rights](../../../operations/access-rights.md).
+- `user` – Name of the user for connecting to a remote server. Default value is the `default` user. This user must have access to connect to the specified server. Access is configured in the `users.xml` file. For more information, see the section [Access rights](../../../guides/sre/user-management/index.md).
 - `password` – The password for connecting to a remote server (not masked). Default value: empty string.
 - `secure` - Whether to use a secure SSL/TLS connection. Usually also requires specifying the port (the default secure port is `9440`). The server should listen on `<tcp_port_secure>9440</tcp_port_secure>` and be configured with correct certificates.
 - `compression` - Use data compression. Default value: `true`.

docs/en/getting-started/example-datasets/cell-towers.md

@@ -1,9 +1,10 @@
 ---
 slug: /en/getting-started/example-datasets/cell-towers
-sidebar_label: Cell Towers
+sidebar_label: Geo Data
 sidebar_position: 3
-title: "Cell Towers"
+title: "Geo Data using the Cell Tower Dataset"
 ---
+
 import ConnectionDetails from '@site/docs/en/_snippets/_gather_your_details_http.mdx';
 
 import Tabs from '@theme/Tabs';
@@ -163,7 +164,7 @@ SELECT mcc, count() FROM cell_towers GROUP BY mcc ORDER BY count() DESC LIMIT 10
 
 Based on the above query and the [MCC list](https://en.wikipedia.org/wiki/Mobile_country_code), the countries with the most cell towers are: the USA, Germany, and Russia.
 
-You may want to create a [Dictionary](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md) in ClickHouse to decode these values.
+You may want to create a [Dictionary](../../sql-reference/dictionaries/index.md) in ClickHouse to decode these values.
 
 ## Use case: Incorporate geo data {#use-case}
 

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

@@ -3,14 +3,56 @@ slug: /en/getting-started/example-datasets/criteo
 sidebar_label: Terabyte Click Logs from Criteo
 ---
 
-# Terabyte of Click Logs from Criteo 
+# Terabyte of Click Logs from Criteo
 
 Download the data from http://labs.criteo.com/downloads/download-terabyte-click-logs/
 
 Create a table to import the log to:
 
 ``` sql
-CREATE TABLE criteo_log (date Date, clicked UInt8, int1 Int32, int2 Int32, int3 Int32, int4 Int32, int5 Int32, int6 Int32, int7 Int32, int8 Int32, int9 Int32, int10 Int32, int11 Int32, int12 Int32, int13 Int32, cat1 String, cat2 String, cat3 String, cat4 String, cat5 String, cat6 String, cat7 String, cat8 String, cat9 String, cat10 String, cat11 String, cat12 String, cat13 String, cat14 String, cat15 String, cat16 String, cat17 String, cat18 String, cat19 String, cat20 String, cat21 String, cat22 String, cat23 String, cat24 String, cat25 String, cat26 String) ENGINE = Log
+CREATE TABLE criteo_log (
+    date Date,
+    clicked UInt8,
+    int1 Int32,
+    int2 Int32,
+    int3 Int32,
+    int4 Int32,
+    int5 Int32,
+    int6 Int32,
+    int7 Int32,
+    int8 Int32,
+    int9 Int32,
+    int10 Int32,
+    int11 Int32,
+    int12 Int32,
+    int13 Int32,
+    cat1 String,
+    cat2 String,
+    cat3 String,
+    cat4 String,
+    cat5 String,
+    cat6 String,
+    cat7 String,
+    cat8 String,
+    cat9 String,
+    cat10 String,
+    cat11 String,
+    cat12 String,
+    cat13 String,
+    cat14 String,
+    cat15 String,
+    cat16 String,
+    cat17 String,
+    cat18 String,
+    cat19 String,
+    cat20 String,
+    cat21 String,
+    cat22 String,
+    cat23 String,
+    cat24 String,
+    cat25 String,
+    cat26 String
+) ENGINE = Log;
 ```
 
 Download the data:
@@ -73,7 +115,52 @@ ORDER BY (date, icat1)
 Transform data from the raw log and put it in the second table:
 
 ``` sql
-INSERT INTO criteo SELECT date, clicked, int1, int2, int3, int4, int5, int6, int7, int8, int9, int10, int11, int12, int13, reinterpretAsUInt32(unhex(cat1)) AS icat1, reinterpretAsUInt32(unhex(cat2)) AS icat2, reinterpretAsUInt32(unhex(cat3)) AS icat3, reinterpretAsUInt32(unhex(cat4)) AS icat4, reinterpretAsUInt32(unhex(cat5)) AS icat5, reinterpretAsUInt32(unhex(cat6)) AS icat6, reinterpretAsUInt32(unhex(cat7)) AS icat7, reinterpretAsUInt32(unhex(cat8)) AS icat8, reinterpretAsUInt32(unhex(cat9)) AS icat9, reinterpretAsUInt32(unhex(cat10)) AS icat10, reinterpretAsUInt32(unhex(cat11)) AS icat11, reinterpretAsUInt32(unhex(cat12)) AS icat12, reinterpretAsUInt32(unhex(cat13)) AS icat13, reinterpretAsUInt32(unhex(cat14)) AS icat14, reinterpretAsUInt32(unhex(cat15)) AS icat15, reinterpretAsUInt32(unhex(cat16)) AS icat16, reinterpretAsUInt32(unhex(cat17)) AS icat17, reinterpretAsUInt32(unhex(cat18)) AS icat18, reinterpretAsUInt32(unhex(cat19)) AS icat19, reinterpretAsUInt32(unhex(cat20)) AS icat20, reinterpretAsUInt32(unhex(cat21)) AS icat21, reinterpretAsUInt32(unhex(cat22)) AS icat22, reinterpretAsUInt32(unhex(cat23)) AS icat23, reinterpretAsUInt32(unhex(cat24)) AS icat24, reinterpretAsUInt32(unhex(cat25)) AS icat25, reinterpretAsUInt32(unhex(cat26)) AS icat26 FROM criteo_log;
+INSERT INTO
+    criteo
+SELECT
+    date,
+    clicked,
+    int1,
+    int2,
+    int3,
+    int4,
+    int5,
+    int6,
+    int7,
+    int8,
+    int9,
+    int10,
+    int11,
+    int12,
+    int13,
+    reinterpretAsUInt32(unhex(cat1)) AS icat1,
+    reinterpretAsUInt32(unhex(cat2)) AS icat2,
+    reinterpretAsUInt32(unhex(cat3)) AS icat3,
+    reinterpretAsUInt32(unhex(cat4)) AS icat4,
+    reinterpretAsUInt32(unhex(cat5)) AS icat5,
+    reinterpretAsUInt32(unhex(cat6)) AS icat6,
+    reinterpretAsUInt32(unhex(cat7)) AS icat7,
+    reinterpretAsUInt32(unhex(cat8)) AS icat8,
+    reinterpretAsUInt32(unhex(cat9)) AS icat9,
+    reinterpretAsUInt32(unhex(cat10)) AS icat10,
+    reinterpretAsUInt32(unhex(cat11)) AS icat11,
+    reinterpretAsUInt32(unhex(cat12)) AS icat12,
+    reinterpretAsUInt32(unhex(cat13)) AS icat13,
+    reinterpretAsUInt32(unhex(cat14)) AS icat14,
+    reinterpretAsUInt32(unhex(cat15)) AS icat15,
+    reinterpretAsUInt32(unhex(cat16)) AS icat16,
+    reinterpretAsUInt32(unhex(cat17)) AS icat17,
+    reinterpretAsUInt32(unhex(cat18)) AS icat18,
+    reinterpretAsUInt32(unhex(cat19)) AS icat19,
+    reinterpretAsUInt32(unhex(cat20)) AS icat20,
+    reinterpretAsUInt32(unhex(cat21)) AS icat21,
+    reinterpretAsUInt32(unhex(cat22)) AS icat22,
+    reinterpretAsUInt32(unhex(cat23)) AS icat23,
+    reinterpretAsUInt32(unhex(cat24)) AS icat24,
+    reinterpretAsUInt32(unhex(cat25)) AS icat25,
+    reinterpretAsUInt32(unhex(cat26)) AS icat26
+FROM
+    criteo_log;
 
 DROP TABLE criteo_log;
 ```

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

@@ -1,12 +1,13 @@
 ---
 slug: /en/getting-started/example-datasets/github
-sidebar_label: GitHub Repo Analysis
+sidebar_label: Github Repo
+sidebar_position: 1
 description: Analyze the ClickHouse GitHub repo or any repository of your choosing
 ---
 
-# ClickHouse GitHub data
+# Writing Queries in ClickHouse using GitHub Data
 
-This dataset contains all of the commits and changes for the ClickHouse repository. It can be generated using the native `git-import` tool distributed with ClickHouse. 
+This dataset contains all of the commits and changes for the ClickHouse repository. It can be generated using the native `git-import` tool distributed with ClickHouse.
 
 The generated data provides a `tsv` file for each of the following tables:
 
@@ -323,7 +324,7 @@ Note a more complex variant of this query exists where we find the [line-by-line
 
 ## Find the current active files
 
-This is important for later analysis when we only want to consider the current files in the repository. We estimate this set as the files which haven't been renamed or deleted (and then re-added/re-named). 
+This is important for later analysis when we only want to consider the current files in the repository. We estimate this set as the files which haven't been renamed or deleted (and then re-added/re-named).
 
 **Note there appears to have been a broken commit history in relation to files under the `dbms`, `libs`, `tests/testflows/` directories during their renames. We also thus exclude these.**
 
@@ -417,7 +418,7 @@ git ls-files | grep -v -E 'generated\.cpp|^(contrib|docs?|website|libs/(libcityh
 
 The difference here is caused by a few factors:
 
-- A rename can occur alongside other modifications to the file. These are listed as separate events in file_changes but with the same time. The `argMax` function has no way of distinguishing these - it picks the first value. The natural ordering of the inserts (the only means of knowing the correct order) is not maintained across the union so modified events can be selected. For example, below the `src/Functions/geometryFromColumn.h` file has several modifications before being renamed to `src/Functions/geometryConverters.h`. Our current solution may pick a Modify event as the latest change causing `src/Functions/geometryFromColumn.h` to be retained. 
+- A rename can occur alongside other modifications to the file. These are listed as separate events in file_changes but with the same time. The `argMax` function has no way of distinguishing these - it picks the first value. The natural ordering of the inserts (the only means of knowing the correct order) is not maintained across the union so modified events can be selected. For example, below the `src/Functions/geometryFromColumn.h` file has several modifications before being renamed to `src/Functions/geometryConverters.h`. Our current solution may pick a Modify event as the latest change causing `src/Functions/geometryFromColumn.h` to be retained.
 
 [play](https://play.clickhouse.com/play?user=play#U0VMRUNUCiAgICAgIGNoYW5nZV90eXBlLAogICAgICBwYXRoLAogICAgICBvbGRfcGF0aCwKICAgICAgdGltZSwKICAgICAgY29tbWl0X2hhc2gKICBGUk9NIGdpdF9jbGlja2hvdXNlLmZpbGVfY2hhbmdlcwogIFdIRVJFIChwYXRoID0gJ3NyYy9GdW5jdGlvbnMvZ2VvbWV0cnlGcm9tQ29sdW1uLmgnKSBPUiAob2xkX3BhdGggPSAnc3JjL0Z1bmN0aW9ucy9nZW9tZXRyeUZyb21Db2x1bW4uaCcpCg==)
 
@@ -1386,7 +1387,7 @@ LIMIT 1 BY day_of_week
 7 rows in set. Elapsed: 0.004 sec. Processed 21.82 thousand rows, 140.02 KB (4.88 million rows/s., 31.29 MB/s.)
 ```
 
-This is still a little simple and doesn't reflect people's work. 
+This is still a little simple and doesn't reflect people's work.
 
 A better metric might be who is the top contributor each day as a fraction of the total work performed in the last year. Note that we treat the deletion and adding code equally.
 
@@ -1952,7 +1953,7 @@ SELECT
 
 Most contributors write more code than tests, as you'd expect.
 
-What about who adds the most comments when contributing code? 
+What about who adds the most comments when contributing code?
 
 [play](https://play.clickhouse.com/play?user=play#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)
 
@@ -2393,7 +2394,7 @@ WHERE (path = 'src/Storages/StorageReplicatedMergeTree.cpp') AND (change_type =
 
 This makes viewing the full history of a file challenging since we don't have a single value connecting all line or file changes.
 
-To address this, we can use User Defined Functions (UDFs). These cannot, currently, be recursive, so to identify the history of a file we must define a series of UDFs which call each other explicitly. 
+To address this, we can use User Defined Functions (UDFs). These cannot, currently, be recursive, so to identify the history of a file we must define a series of UDFs which call each other explicitly.
 
 This means we can only track renames to a maximum depth - the below example is 5 deep. It is unlikely a file will be renamed more times than this, so for now, this is sufficient.
 

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

@@ -84,7 +84,7 @@ clickhouse-client --query "SELECT COUNT(*) FROM datasets.visits_v1"
 1680609
 ```
 
-## An example JOIN 
+## An example JOIN
 
 The hits and visits dataset is used in the ClickHouse test
 routines, this is one of the queries from the test suite. The rest
@@ -131,10 +131,10 @@ FORMAT PrettyCompact"
 
 ## Next Steps
 
-[A Practical Introduction to Sparse Primary Indexes in ClickHouse](../../guides/improving-query-performance/sparse-primary-indexes/sparse-primary-indexes-intro.md) uses the hits dataset to discuss the differences in ClickHouse indexing compared to traditional relational databases, how ClickHouse builds and uses a sparse primary index, and indexing best practices.
+[A Practical Introduction to Sparse Primary Indexes in ClickHouse](/docs/en/guides/best-practices/sparse-primary-indexes.md) uses the hits dataset to discuss the differences in ClickHouse indexing compared to traditional relational databases, how ClickHouse builds and uses a sparse primary index, and indexing best practices.
 
 Additional examples of queries to these tables can be found among the ClickHouse [stateful tests](https://github.com/ClickHouse/ClickHouse/blob/d7129855757f38ceec3e4ecc6dafacdabe9b178f/tests/queries/1_stateful/00172_parallel_join.sql).
 
 :::note
-The test suite uses a database name `test`, and the tables are named `hits` and `visits`.  You can rename your database and tables, or edit the SQL from the test file.  
+The test suite uses a database name `test`, and the tables are named `hits` and `visits`.  You can rename your database and tables, or edit the SQL from the test file.
 :::

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

@@ -16,7 +16,7 @@ While working through this guide you will:
 
 The dataset used in this guide comes from the NYC Open Data team, and contains data about "all valid felony, misdemeanor, and violation crimes reported to the New York City Police Department (NYPD)". At the time of writing, the data file is 166MB, but it is updated regularly.
 
-**Source**: [data.cityofnewyork.us](https://data.cityofnewyork.us/Public-Safety/NYPD-Complaint-Data-Current-Year-To-Date-/5uac-w243)  
+**Source**: [data.cityofnewyork.us](https://data.cityofnewyork.us/Public-Safety/NYPD-Complaint-Data-Current-Year-To-Date-/5uac-w243)
 **Terms of use**: https://www1.nyc.gov/home/terms-of-use.page
 
 ## Prerequisites
@@ -35,7 +35,7 @@ The examples in this guide assume that you have saved the TSV file to `${HOME}/N
 
 ## Familiarize yourself with the TSV file
 
-Before starting to work with the ClickHouse database familiarize yourself with the data. 
+Before starting to work with the ClickHouse database familiarize yourself with the data.
 
 ### Look at the fields in the source TSV file
 
@@ -47,15 +47,15 @@ clickhouse-local --query \
 
 Sample response
 ```response
-CMPLNT_NUM                  Nullable(Float64)					
-ADDR_PCT_CD                 Nullable(Float64)					
-BORO_NM                     Nullable(String)					
-CMPLNT_FR_DT                Nullable(String)					
-CMPLNT_FR_TM                Nullable(String)					
+CMPLNT_NUM                  Nullable(Float64)
+ADDR_PCT_CD                 Nullable(Float64)
+BORO_NM                     Nullable(String)
+CMPLNT_FR_DT                Nullable(String)
+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](../../guides/developer/working-with-json/json-semi-structured.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](/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`
 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.
@@ -65,46 +65,46 @@ Run this command at your command prompt.  You will be using `clickhouse-local` t
 ```sh
 clickhouse-local --input_format_max_rows_to_read_for_schema_inference=2000 \
 --query \
-"describe file('${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv', 'TSVWithNames')" 
+"describe file('${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv', 'TSVWithNames')"
 ```
 
 Result:
 ```response
-CMPLNT_NUM        Nullable(String)					
-ADDR_PCT_CD       Nullable(Float64)					
-BORO_NM           Nullable(String)					
-CMPLNT_FR_DT      Nullable(String)					
-CMPLNT_FR_TM      Nullable(String)					
-CMPLNT_TO_DT      Nullable(String)					
-CMPLNT_TO_TM      Nullable(String)					
-CRM_ATPT_CPTD_CD  Nullable(String)					
-HADEVELOPT        Nullable(String)					
-HOUSING_PSA       Nullable(Float64)					
-JURISDICTION_CODE Nullable(Float64)					
-JURIS_DESC        Nullable(String)					
-KY_CD             Nullable(Float64)					
-LAW_CAT_CD        Nullable(String)					
-LOC_OF_OCCUR_DESC Nullable(String)					
-OFNS_DESC         Nullable(String)					
-PARKS_NM          Nullable(String)					
-PATROL_BORO       Nullable(String)					
-PD_CD             Nullable(Float64)					
-PD_DESC           Nullable(String)					
-PREM_TYP_DESC     Nullable(String)					
-RPT_DT            Nullable(String)					
-STATION_NAME      Nullable(String)					
-SUSP_AGE_GROUP    Nullable(String)					
-SUSP_RACE         Nullable(String)					
-SUSP_SEX          Nullable(String)					
-TRANSIT_DISTRICT  Nullable(Float64)					
-VIC_AGE_GROUP     Nullable(String)					
-VIC_RACE          Nullable(String)					
-VIC_SEX           Nullable(String)					
-X_COORD_CD        Nullable(Float64)					
-Y_COORD_CD        Nullable(Float64)					
-Latitude          Nullable(Float64)					
-Longitude         Nullable(Float64)					
-Lat_Lon           Tuple(Nullable(Float64), Nullable(Float64))					
+CMPLNT_NUM        Nullable(String)
+ADDR_PCT_CD       Nullable(Float64)
+BORO_NM           Nullable(String)
+CMPLNT_FR_DT      Nullable(String)
+CMPLNT_FR_TM      Nullable(String)
+CMPLNT_TO_DT      Nullable(String)
+CMPLNT_TO_TM      Nullable(String)
+CRM_ATPT_CPTD_CD  Nullable(String)
+HADEVELOPT        Nullable(String)
+HOUSING_PSA       Nullable(Float64)
+JURISDICTION_CODE Nullable(Float64)
+JURIS_DESC        Nullable(String)
+KY_CD             Nullable(Float64)
+LAW_CAT_CD        Nullable(String)
+LOC_OF_OCCUR_DESC Nullable(String)
+OFNS_DESC         Nullable(String)
+PARKS_NM          Nullable(String)
+PATROL_BORO       Nullable(String)
+PD_CD             Nullable(Float64)
+PD_DESC           Nullable(String)
+PREM_TYP_DESC     Nullable(String)
+RPT_DT            Nullable(String)
+STATION_NAME      Nullable(String)
+SUSP_AGE_GROUP    Nullable(String)
+SUSP_RACE         Nullable(String)
+SUSP_SEX          Nullable(String)
+TRANSIT_DISTRICT  Nullable(Float64)
+VIC_AGE_GROUP     Nullable(String)
+VIC_RACE          Nullable(String)
+VIC_SEX           Nullable(String)
+X_COORD_CD        Nullable(Float64)
+Y_COORD_CD        Nullable(Float64)
+Latitude          Nullable(Float64)
+Longitude         Nullable(Float64)
+Lat_Lon           Tuple(Nullable(Float64), Nullable(Float64))
 New Georeferenced Column Nullable(String)
 ```
 
@@ -362,7 +362,7 @@ The dates shown as `1925` above are from errors in the data.  There are several
 
 The decisions made above on the data types used for the columns are reflected in the table schema
 below. We also need to decide on the `ORDER BY` and `PRIMARY KEY` used for the table.  At least one
-of `ORDER BY` or `PRIMARY KEY` must be specified.  Here are some guidelines on deciding on the 
+of `ORDER BY` or `PRIMARY KEY` must be specified.  Here are some guidelines on deciding on the
 columns to includes in `ORDER BY`, and more information is in the *Next Steps* section at the end
 of this document.
 
@@ -420,7 +420,7 @@ ORDER BY ( borough, offense_description, date_reported )
 Putting together the changes to data types and the `ORDER BY` tuple gives this table structure:
 
 ```sql
-CREATE TABLE NYPD_Complaint ( 
+CREATE TABLE NYPD_Complaint (
     complaint_number     String,
     precinct             UInt8,
     borough              LowCardinality(String),
@@ -429,7 +429,7 @@ CREATE TABLE NYPD_Complaint (
     was_crime_completed  String,
     housing_authority    String,
     housing_level_code   UInt32,
-    jurisdiction_code    UInt8, 
+    jurisdiction_code    UInt8,
     jurisdiction         LowCardinality(String),
     offense_code         UInt8,
     offense_level        LowCardinality(String),
@@ -478,7 +478,7 @@ Query id: 6a5b10bf-9333-4090-b36e-c7f08b1d9e01
 
 Row 1:
 ──────
-partition_key: 
+partition_key:
 sorting_key:   borough, offense_description, date_reported
 primary_key:   borough, offense_description, date_reported
 table:         NYPD_Complaint
@@ -495,7 +495,7 @@ We will use `clickhouse-local` tool for data preprocessing and `clickhouse-clien
 :::tip
 `table='input'` appears in the arguments to clickhouse-local below.  clickhouse-local takes the provided input (`cat ${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv`) and inserts the input into a table.  By default the table is named `table`.  In this guide the name of the table is set to `input` to make the data flow clearer. The final argument to clickhouse-local is a query that selects from the table (`FROM input`) which is then piped to `clickhouse-client` to populate the table `NYPD_Complaint`.
 :::
-  
+
 ```sql
 cat ${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv \
   | clickhouse-local --table='input' --input-format='TSVWithNames' \
@@ -512,12 +512,12 @@ cat ${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv \
       CRM_ATPT_CPTD_CD                            AS was_crime_completed,
       HADEVELOPT                                  AS housing_authority_development,
       HOUSING_PSA                                 AS housing_level_code,
-      JURISDICTION_CODE                           AS jurisdiction_code, 
+      JURISDICTION_CODE                           AS jurisdiction_code,
       JURIS_DESC                                  AS jurisdiction,
       KY_CD                                       AS offense_code,
       LAW_CAT_CD                                  AS offense_level,
       LOC_OF_OCCUR_DESC                           AS location_descriptor,
-      OFNS_DESC                                   AS offense_description, 
+      OFNS_DESC                                   AS offense_description,
       PARKS_NM                                    AS park_name,
       PATROL_BORO                                 AS patrol_borough,
       PD_CD,
@@ -529,7 +529,7 @@ cat ${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv \
       SUSP_RACE                                   AS suspect_race,
       SUSP_SEX                                    AS suspect_sex,
       TRANSIT_DISTRICT                            AS transit_district,
-      VIC_AGE_GROUP                               AS victim_age_group,   
+      VIC_AGE_GROUP                               AS victim_age_group,
       VIC_RACE                                    AS victim_race,
       VIC_SEX                                     AS victim_sex,
       X_COORD_CD                                  AS NY_x_coordinate,
@@ -538,7 +538,7 @@ cat ${HOME}/NYPD_Complaint_Data_Current__Year_To_Date_.tsv \
       Longitude
     FROM input" \
   | clickhouse-client --query='INSERT INTO NYPD_Complaint FORMAT TSV'
-```  
+```
 
 ## Validate the Data {#validate-data}
 
@@ -560,7 +560,7 @@ Result:
 │  208993 │
 └─────────┘
 
-1 row in set. Elapsed: 0.001 sec. 
+1 row in set. Elapsed: 0.001 sec.
 ```
 
 The size of the dataset in ClickHouse is just 12% of the original TSV file, compare the size of the original TSV file with the size of the table:
@@ -651,4 +651,4 @@ Query id: 8cdcdfd4-908f-4be0-99e3-265722a2ab8d
 
 ## Next Steps
 
-[A Practical Introduction to Sparse Primary Indexes in ClickHouse](../../guides/improving-query-performance/sparse-primary-indexes/sparse-primary-indexes-intro.md) discusses the differences in ClickHouse indexing compared to traditional relational databases, how ClickHouse builds and uses a sparse primary index, and indexing best practices.
+[A Practical Introduction to Sparse Primary Indexes in ClickHouse](/docs/en/guides/best-practices/sparse-primary-indexes.md) discusses the differences in ClickHouse indexing compared to traditional relational databases, how ClickHouse builds and uses a sparse primary index, and indexing best practices.

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

@@ -80,7 +80,7 @@ Result:
 
 ### Top Components by the Number of Recipes:
 
-In this example we learn how to use [arrayJoin](../../sql-reference/functions/array-join/) function to expand an array into a set of rows.
+In this example we learn how to use [arrayJoin](../../sql-reference/functions/array-join.md) function to expand an array into a set of rows.
 
 Query:
 
@@ -185,7 +185,7 @@ Result:
 10 rows in set. Elapsed: 0.215 sec. Processed 2.23 million rows, 1.48 GB (10.35 million rows/s., 6.86 GB/s.)
 ```
 
-In this example, we involve [has](../../sql-reference/functions/array-functions/#hasarr-elem) function to filter by array elements and sort by the number of directions.
+In this example, we involve [has](../../sql-reference/functions/array-functions.md#hasarr-elem) function to filter by array elements and sort by the number of directions.
 
 There is a wedding cake that requires the whole 126 steps to produce! Show that directions:
 

docs/en/getting-started/example-datasets/uk-price-paid.md

@@ -1,17 +1,17 @@
 ---
 slug: /en/getting-started/example-datasets/uk-price-paid
-sidebar_label: UK Property Price Paid
+sidebar_label: UK Property Prices
 sidebar_position: 1
-title: "UK Property Price Paid"
 ---
 
-The dataset contains data about prices paid for real-estate property in England and Wales. The data is available since year 1995.
-The size of the dataset in uncompressed form is about 4 GiB and it will take about 278 MiB in ClickHouse.
+# The UK property prices dataset
 
-Source: https://www.gov.uk/government/statistical-data-sets/price-paid-data-downloads
-Description of the fields: https://www.gov.uk/guidance/about-the-price-paid-data
+Projections are a great way to improve the performance of queries that you run frequently. We will demonstrate the power of projections
+using the UK property dataset, which contains data about prices paid for real-estate property in England and Wales. The data is available since 1995, and the size of the dataset in uncompressed form is about 4 GiB (which will only take about 278 MiB in ClickHouse).
 
-Contains HM Land Registry data © Crown copyright and database right 2021. This data is licensed under the Open Government Licence v3.0.
+- Source: https://www.gov.uk/government/statistical-data-sets/price-paid-data-downloads
+- Description of the fields: https://www.gov.uk/guidance/about-the-price-paid-data
+- Contains HM Land Registry data © Crown copyright and database right 2021. This data is licensed under the Open Government Licence v3.0.
 
 ## Create the Table {#create-table}
 

docs/en/getting-started/install.md

@@ -14,75 +14,35 @@ import CodeBlock from '@theme/CodeBlock';
 You have three 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
-- **[Self-managed ClickHouse](#self-managed-install):** ClickHouse can run on any Linux, FreeBSD, or macOS with x86-64, ARM, or PowerPC64LE CPU architecture
-- **[Docker Image](https://hub.docker.com/r/clickhouse/clickhouse-server/):** Read the guide with the official image in Docker Hub
+- **[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
+- **[Docker Image](https://hub.docker.com/r/clickhouse/clickhouse-server/):** use the official Docker image in Docker Hub
 
 ## ClickHouse Cloud
 
 The quickest and easiest way to get up and running with ClickHouse is to create a new service in [ClickHouse Cloud](https://clickhouse.cloud/).
 
-## Self-Managed Install
+## Quick Install
 
 :::tip
 For production installs of a specific release version see the [installation options](#available-installation-options) down below.
 :::
 
-<Tabs>
-<TabItem value="linux" label="Linux" default>
+On Linux and macOS:
 
-1. The simplest way to download ClickHouse locally is to run the following command. If your operating system is supported, an appropriate ClickHouse binary will be downloaded and made runnable:
+1. If you are just getting started and want to see what ClickHouse can do, the simplest way to download ClickHouse locally is to run the following command. It downloads a single binary for your operating system that can be used to run the ClickHouse server, clickhouse-client, clickhouse-local,
+ClickHouse Keeper, and other tools:
 
   ```bash
   curl https://clickhouse.com/ | sh
   ```
 
-1. Run the `install` command, which defines a collection of useful symlinks along with the files and folders used by ClickHouse - all of which you can see in the output of the install script:
-
-  ```bash
-  sudo ./clickhouse install
-  ```
-
-1. At the end of the install script, you are prompted for a password for the `default` user. Feel free to enter a password, or you can optionally leave it blank:
-
-  ```response
-  Creating log directory /var/log/clickhouse-server.
-  Creating data directory /var/lib/clickhouse.
-  Creating pid directory /var/run/clickhouse-server.
-   chown -R clickhouse:clickhouse '/var/log/clickhouse-server'
-   chown -R clickhouse:clickhouse '/var/run/clickhouse-server'
-   chown  clickhouse:clickhouse '/var/lib/clickhouse'
-  Enter password for default user:
-  ```
-  You should see the following output:
-
-  ```response
-   ClickHouse has been successfully installed.
-
-   Start clickhouse-server with:
-    sudo clickhouse start
-
-   Start clickhouse-client with:
-    clickhouse-client
-  ```
-
 1. Run the following command to start the ClickHouse server:
     ```bash
-    sudo clickhouse start
+    ./clickhouse server
     ```
 
-</TabItem>
-<TabItem value="macos" label="macOS">
-
-1. The simplest way to download ClickHouse locally is to run the following command. If your operating system is supported, an appropriate ClickHouse binary will be downloaded and made runnable:
-  ```bash
-  curl https://clickhouse.com/ | sh
-  ```
-
-1. Run the ClickHouse server:
-
-  ```bash
-  ./clickhouse server
-  ```
+    The first time you run this script, the necessary files and folders are created in the current directory, then the server starts.
 
 1. Open a new terminal and use the **clickhouse-client** to connect to your service:
 
@@ -101,15 +61,14 @@ For production installs of a specific release version see the [installation opti
 
   You are ready to start sending DDL and SQL commands to ClickHouse!
 
-</TabItem>
-</Tabs>
-
 
 :::tip
-The [Quick Start](/docs/en/quick-start.mdx/#step-1-get-clickhouse) walks through the steps to download and run ClickHouse, connect to it, and insert data.
+The [Quick Start](/docs/en/quick-start.mdx) walks through the steps for creating tables and inserting data.
 :::
 
-## Available Installation Options {#available-installation-options}
+## Production Deployments {#available-installation-options}
+
+For production deployments of ClickHouse, choose from one of the following install options.
 
 ### From DEB Packages {#install-from-deb-packages}
 
@@ -174,7 +133,7 @@ clickhouse-client # or "clickhouse-client --password" if you set up a password.
 
 </details>
 
-You can replace `stable` with `lts` to use different [release kinds](/docs/en/faq/operations/production.md) based on your needs.
+You can replace `stable` with `lts` to use different [release kinds](/knowledgebase/production) based on your needs.
 
 You can also download and install packages manually from [here](https://packages.clickhouse.com/deb/pool/main/c/).
 
@@ -272,7 +231,7 @@ clickhouse-client # or "clickhouse-client --password" if you set up a password.
 
 </details>
 
-You can replace `stable` with `lts` to use different [release kinds](/docs/en/faq/operations/production.md) based on your needs.
+You can replace `stable` with `lts` to use different [release kinds](/knowledgebase/production) based on your needs.
 
 Then run these commands to install packages:
 

docs/en/getting-started/playground.md

@@ -1,5 +1,5 @@
 ---
-sidebar_label: Playground
+sidebar_label: ClickHouse Playground
 sidebar_position: 2
 keywords: [clickhouse, playground, getting, started, docs]
 description: The ClickHouse Playground allows people to experiment with ClickHouse by running queries instantly, without setting up their server or cluster.
@@ -11,7 +11,7 @@ slug: /en/getting-started/playground
 [ClickHouse Playground](https://play.clickhouse.com/play?user=play) allows people to experiment with ClickHouse by running queries instantly, without setting up their server or cluster.
 Several example datasets are available in Playground.
 
-You can make queries to Playground using any HTTP client, for example [curl](https://curl.haxx.se) or [wget](https://www.gnu.org/software/wget/), or set up a connection using [JDBC](../interfaces/jdbc.md) or [ODBC](../interfaces/odbc.md) drivers. More information about software products that support ClickHouse is available [here](../interfaces).
+You can make queries to Playground using any HTTP client, for example [curl](https://curl.haxx.se) or [wget](https://www.gnu.org/software/wget/), or set up a connection using [JDBC](../interfaces/jdbc.md) or [ODBC](../interfaces/odbc.md) drivers. More information about software products that support ClickHouse is available [here](../integrations/index.mdx).
 
 ## Credentials {#credentials}
 

docs/en/interfaces/formats.md

@@ -1,7 +1,7 @@
 ---
 slug: /en/interfaces/formats
 sidebar_position: 21
-sidebar_label: Input and Output Formats
+sidebar_label: View all formats...
 title: Formats for Input and Output Data
 ---
 
@@ -684,7 +684,7 @@ Example:
 ## JSONColumns {#jsoncolumns}
 
 :::tip
-The output of the JSONColumns* formats provides the ClickHouse field name and then the content of each row of the table for that field; 
+The output of the JSONColumns* formats provides the ClickHouse field name and then the content of each row of the table for that field;
 visually, the data is rotated 90 degrees to the left.
 :::
 
@@ -1232,50 +1232,52 @@ Each row is formatted as a single document and each column is formatted as a sin
 
 For output it uses the following correspondence between ClickHouse types and BSON types:
 
-| ClickHouse type                                                                                           | BSON Type                                                                                                 |
-|-----------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------|
-| [Bool](/docs/en/sql-reference/data-types/boolean.md)                                                            | `\x08` boolean                                                                                            |
-| [Int8/UInt8](/docs/en/sql-reference/data-types/int-uint.md)                                                     | `\x10` int32                                                                                              |
-| [Int16UInt16](/docs/en/sql-reference/data-types/int-uint.md)                                                    | `\x10` int32                                                                                              |
-| [Int32](/docs/en/sql-reference/data-types/int-uint.md)                                                          | `\x10` int32                                                                                              |
-| [UInt32](/docs/en/sql-reference/data-types/int-uint.md)                                                         | `\x12` int64                                                                                              |
-| [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md)                                                   | `\x12` int64                                                                                              |
-| [Float32/Float64](/docs/en/sql-reference/data-types/float.md)                                                   | `\x01` double                                                                                             |
-| [Date](/docs/en/sql-reference/data-types/date.md)/[Date32](/docs/en/sql-reference/data-types/date32.md)               | `\x10` int32                                                                                              |
-| [DateTime](/docs/en/sql-reference/data-types/datetime.md)                                                       | `\x12` int64                                                                                                |
-| [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)                                                   | `\x09` datetime                                                                                             |
-| [Decimal32](/docs/en/sql-reference/data-types/decimal.md)                                                       | `\x10` int32                                                                                                |
-| [Decimal64](/docs/en/sql-reference/data-types/decimal.md)                                                       | `\x12` int64                                                                                                |
-| [Decimal128](/docs/en/sql-reference/data-types/decimal.md)                                                      | `\x05` binary, `\x00` binary subtype, size = 16                                                               |
-| [Decimal256](/docs/en/sql-reference/data-types/decimal.md)                                                      | `\x05` binary, `\x00` binary subtype, size = 32                                                               |
-| [Int128/UInt128](/docs/en/sql-reference/data-types/int-uint.md)                                                 | `\x05` binary, `\x00` binary subtype, size = 16                                                               |
-| [Int256/UInt256](/docs/en/sql-reference/data-types/int-uint.md)                                                 | `\x05` binary, `\x00` binary subtype, size = 32                                                               |
+| ClickHouse type                                                                                                       | BSON Type                                                                                                     |
+|-----------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
+| [Bool](/docs/en/sql-reference/data-types/boolean.md)                                                                  | `\x08` boolean                                                                                                |
+| [Int8/UInt8](/docs/en/sql-reference/data-types/int-uint.md)                                                           | `\x10` int32                                                                                                  |
+| [Int16UInt16](/docs/en/sql-reference/data-types/int-uint.md)                                                          | `\x10` int32                                                                                                  |
+| [Int32](/docs/en/sql-reference/data-types/int-uint.md)                                                                | `\x10` int32                                                                                                  |
+| [UInt32](/docs/en/sql-reference/data-types/int-uint.md)                                                               | `\x12` int64                                                                                                  |
+| [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md)                                                         | `\x12` int64                                                                                                  |
+| [Float32/Float64](/docs/en/sql-reference/data-types/float.md)                                                         | `\x01` double                                                                                                 |
+| [Date](/docs/en/sql-reference/data-types/date.md)/[Date32](/docs/en/sql-reference/data-types/date32.md)               | `\x10` int32                                                                                                  |
+| [DateTime](/docs/en/sql-reference/data-types/datetime.md)                                                             | `\x12` int64                                                                                                  |
+| [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)                                                         | `\x09` datetime                                                                                               |
+| [Decimal32](/docs/en/sql-reference/data-types/decimal.md)                                                             | `\x10` int32                                                                                                  |
+| [Decimal64](/docs/en/sql-reference/data-types/decimal.md)                                                             | `\x12` int64                                                                                                  |
+| [Decimal128](/docs/en/sql-reference/data-types/decimal.md)                                                            | `\x05` binary, `\x00` binary subtype, size = 16                                                               |
+| [Decimal256](/docs/en/sql-reference/data-types/decimal.md)                                                            | `\x05` binary, `\x00` binary subtype, size = 32                                                               |
+| [Int128/UInt128](/docs/en/sql-reference/data-types/int-uint.md)                                                       | `\x05` binary, `\x00` binary subtype, size = 16                                                               |
+| [Int256/UInt256](/docs/en/sql-reference/data-types/int-uint.md)                                                       | `\x05` binary, `\x00` binary subtype, size = 32                                                               |
 | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `\x05` binary, `\x00` binary subtype or \x02 string if setting output_format_bson_string_as_string is enabled |
-| [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                               | `\x05` binary, `\x04` uuid subtype, size = 16                                                                 |
-| [Array](/docs/en/sql-reference/data-types/array.md)                                                             | `\x04` array                                                                                                |
-| [Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                             | `\x04` array                                                                                                |
-| [Named Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                       | `\x03` document                                                                                             |
-| [Map](/docs/en/sql-reference/data-types/map.md) (with String keys)                                              | `\x03` document                                                                                             |
+| [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                     | `\x05` binary, `\x04` uuid subtype, size = 16                                                                 |
+| [Array](/docs/en/sql-reference/data-types/array.md)                                                                   | `\x04` array                                                                                                  |
+| [Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                   | `\x04` array                                                                                                  |
+| [Named Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                             | `\x03` document                                                                                               |
+| [Map](/docs/en/sql-reference/data-types/map.md) (with String keys)                                                    | `\x03` document                                                                                               |
+| [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)                                                             | `\x10` int32                                                                                                  |
+| [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)                                                             | `\x05` binary, `\x00` binary subtype                                                                          |
 
 For input it uses the following correspondence between BSON types and ClickHouse types:
 
-| BSON Type                                | ClickHouse Type                                                                                                                                              |
-|------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `\x01` double                            | [Float32/Float64](/docs/en/sql-reference/data-types/float.md)                                                                                                      |
-| `\x02` string                            | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x03` document                          | [Map](/docs/en/sql-reference/data-types/map.md)/[Named Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                |
-| `\x04` array                             | [Array](/docs/en/sql-reference/data-types/array.md)/[Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                  |
-| `\x05` binary, `\x00` binary subtype     | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x05` binary, `\x02` old binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x05` binary, `\x03` old uuid subtype   | [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                                                                  |
-| `\x05` binary, `\x04` uuid subtype       | [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                                                                  |
-| `\x07` ObjectId                          | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x08` boolean                           | [Bool](/docs/en/sql-reference/data-types/boolean.md)                                                                                                               |
-| `\x09` datetime                          | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)                                                                                                      |
-| `\x0A` null value                        | [NULL](/docs/en/sql-reference/data-types/nullable.md)                                                                                                              |
-| `\x0D` JavaScript code                   | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x0E` symbol                            | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                    |
-| `\x10` int32                             | [Int32/UInt32](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal32](/docs/en/sql-reference/data-types/decimal.md)                                                         |
+| BSON Type                                | ClickHouse Type                                                                                                                                                                       |
+|------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `\x01` double                            | [Float32/Float64](/docs/en/sql-reference/data-types/float.md)                                                                                                                         |
+| `\x02` string                            | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                                 |
+| `\x03` document                          | [Map](/docs/en/sql-reference/data-types/map.md)/[Named Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                             |
+| `\x04` array                             | [Array](/docs/en/sql-reference/data-types/array.md)/[Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                               |
+| `\x05` binary, `\x00` binary subtype     | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)/[IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)       |
+| `\x05` binary, `\x02` old binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                                 |
+| `\x05` binary, `\x03` old uuid subtype   | [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                                                                                     |
+| `\x05` binary, `\x04` uuid subtype       | [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                                                                                     |
+| `\x07` ObjectId                          | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                                 |
+| `\x08` boolean                           | [Bool](/docs/en/sql-reference/data-types/boolean.md)                                                                                                                                  |
+| `\x09` datetime                          | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)                                                                                                                         |
+| `\x0A` null value                        | [NULL](/docs/en/sql-reference/data-types/nullable.md)                                                                                                                                 |
+| `\x0D` JavaScript code                   | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                                 |
+| `\x0E` symbol                            | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)                                                                 |
+| `\x10` int32                             | [Int32/UInt32](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal32](/docs/en/sql-reference/data-types/decimal.md)/[IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)     |
 | `\x12` int64                             | [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal64](/docs/en/sql-reference/data-types/decimal.md)/[DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
 
 Other BSON types are not supported. Also, it performs conversion between different integer types (for example, you can insert BSON int32 value into ClickHouse UInt8).
@@ -1608,23 +1610,25 @@ See also [Format Schema](#formatschema).
 
 The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
 
-| CapnProto data type (`INSERT`) | ClickHouse data type                                      | CapnProto data type (`SELECT`) |
-|--------------------------------|-----------------------------------------------------------|--------------------------------|
-| `UINT8`, `BOOL`                | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)          | `UINT8`                        |
-| `INT8`                         | [Int8](/docs/en/sql-reference/data-types/int-uint.md)           | `INT8`                         |
-| `UINT16`                       | [UInt16](/docs/en/sql-reference/data-types/int-uint.md), [Date](/docs/en/sql-reference/data-types/date.md)         | `UINT16`                       |
-| `INT16`                        | [Int16](/docs/en/sql-reference/data-types/int-uint.md)          | `INT16`                        |
-| `UINT32`                       | [UInt32](/docs/en/sql-reference/data-types/int-uint.md), [DateTime](/docs/en/sql-reference/data-types/datetime.md)         | `UINT32`                       |
-| `INT32`                        | [Int32](/docs/en/sql-reference/data-types/int-uint.md)          | `INT32`                        |
-| `UINT64`                       | [UInt64](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT64`                       |
-| `INT64`                        | [Int64](/docs/en/sql-reference/data-types/int-uint.md), [DateTime64](/docs/en/sql-reference/data-types/datetime.md)          | `INT64`                        |
-| `FLOAT32`                      | [Float32](/docs/en/sql-reference/data-types/float.md)           | `FLOAT32`                      |
-| `FLOAT64`                      | [Float64](/docs/en/sql-reference/data-types/float.md)           | `FLOAT64`                      |
-| `TEXT, DATA`                   | [String](/docs/en/sql-reference/data-types/string.md), [FixedString](/docs/en/sql-reference/data-types/fixedstring.md)               | `TEXT, DATA`                       |
-| `union(T, Void), union(Void, T)`          | [Nullable(T)](/docs/en/sql-reference/data-types/date.md)       | `union(T, Void), union(Void, T)`                       |
-| `ENUM`                         | [Enum(8\|16)](/docs/en/sql-reference/data-types/enum.md)        | `ENUM`                         |
-| `LIST`                         | [Array](/docs/en/sql-reference/data-types/array.md)             | `LIST`                         |
-| `STRUCT`                       | [Tuple](/docs/en/sql-reference/data-types/tuple.md)             | `STRUCT`                       |
+| CapnProto data type (`INSERT`)   | ClickHouse data type                                                                                                   | CapnProto data type (`SELECT`) |
+|----------------------------------|------------------------------------------------------------------------------------------------------------------------|------------------------------|
+| `UINT8`, `BOOL`                  | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)                                                                 | `UINT8`                      |
+| `INT8`                           | [Int8](/docs/en/sql-reference/data-types/int-uint.md)                                                                  | `INT8`                       |
+| `UINT16`                         | [UInt16](/docs/en/sql-reference/data-types/int-uint.md), [Date](/docs/en/sql-reference/data-types/date.md)             | `UINT16`                     |
+| `INT16`                          | [Int16](/docs/en/sql-reference/data-types/int-uint.md)                                                                 | `INT16`                      |
+| `UINT32`                         | [UInt32](/docs/en/sql-reference/data-types/int-uint.md), [DateTime](/docs/en/sql-reference/data-types/datetime.md)     | `UINT32`                     |
+| `INT32`                          | [Int32](/docs/en/sql-reference/data-types/int-uint.md)                                                                 | `INT32`                      |
+| `UINT64`                         | [UInt64](/docs/en/sql-reference/data-types/int-uint.md)                                                                | `UINT64`                     |
+| `INT64`                          | [Int64](/docs/en/sql-reference/data-types/int-uint.md), [DateTime64](/docs/en/sql-reference/data-types/datetime.md)    | `INT64`                      |
+| `FLOAT32`                        | [Float32](/docs/en/sql-reference/data-types/float.md)                                                                  | `FLOAT32`                    |
+| `FLOAT64`                        | [Float64](/docs/en/sql-reference/data-types/float.md)                                                                  | `FLOAT64`                    |
+| `TEXT, DATA`                     | [String](/docs/en/sql-reference/data-types/string.md), [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `TEXT, DATA`                 |
+| `union(T, Void), union(Void, T)` | [Nullable(T)](/docs/en/sql-reference/data-types/date.md)                                                               | `union(T, Void), union(Void, T)`                 |
+| `ENUM`                           | [Enum(8\                                                                                                               |16)](/docs/en/sql-reference/data-types/enum.md)  | `ENUM`                         |
+| `LIST`                           | [Array](/docs/en/sql-reference/data-types/array.md)                                                                    | `LIST`                       |
+| `STRUCT`                         | [Tuple](/docs/en/sql-reference/data-types/tuple.md)                                                                    | `STRUCT`                     |
+| `UINT32`                         | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)                                                              | `UINT32`                     |
+| `DATA`                           | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)                                                              | `DATA`                       |
 
 For working with `Enum` in CapnProto format use the [format_capn_proto_enum_comparising_mode](/docs/en/operations/settings/settings-formats.md/#format_capn_proto_enum_comparising_mode) setting.
 
@@ -1804,21 +1808,26 @@ ClickHouse Avro format supports reading and writing [Avro data files](https://av
 
 The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
 
-| Avro data type `INSERT`                     | ClickHouse data type                                                                               | Avro data type `SELECT`      |
-|---------------------------------------------|----------------------------------------------------------------------------------------------------|------------------------------|
-| `boolean`, `int`, `long`, `float`, `double` | [Int(8\|16\|32)](/docs/en/sql-reference/data-types/int-uint.md), [UInt(8\|16\|32)](/docs/en/sql-reference/data-types/int-uint.md) | `int`                        |
-| `boolean`, `int`, `long`, `float`, `double` | [Int64](/docs/en/sql-reference/data-types/int-uint.md), [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `long`                       |
-| `boolean`, `int`, `long`, `float`, `double` | [Float32](/docs/en/sql-reference/data-types/float.md)                                                    | `float`                      |
-| `boolean`, `int`, `long`, `float`, `double` | [Float64](/docs/en/sql-reference/data-types/float.md)                                                    | `double`                     |
-| `bytes`, `string`, `fixed`, `enum`          | [String](/docs/en/sql-reference/data-types/string.md)                                                    | `bytes` or `string` \*       |
-| `bytes`, `string`, `fixed`                  | [FixedString(N)](/docs/en/sql-reference/data-types/fixedstring.md)                                       | `fixed(N)`                   |
-| `enum`                                      | [Enum(8\|16)](/docs/en/sql-reference/data-types/enum.md)                                                                    | `enum`                       |
-| `array(T)`                                  | [Array(T)](/docs/en/sql-reference/data-types/array.md)                                                   | `array(T)`                   |
-| `union(null, T)`, `union(T, null)`          | [Nullable(T)](/docs/en/sql-reference/data-types/date.md)                                                 | `union(null, T)`             |
-| `null`                                      | [Nullable(Nothing)](/docs/en/sql-reference/data-types/special-data-types/nothing.md)                     | `null`                       |
-| `int (date)` \**                            | [Date](/docs/en/sql-reference/data-types/date.md)                                                        | `int (date)` \**             |
-| `long (timestamp-millis)` \**               | [DateTime64(3)](/docs/en/sql-reference/data-types/datetime.md)                                           | `long (timestamp-millis)` \* |
-| `long (timestamp-micros)` \**               | [DateTime64(6)](/docs/en/sql-reference/data-types/datetime.md)                                           | `long (timestamp-micros)` \* |
+| Avro data type `INSERT`                     | ClickHouse data type                                                                                                          | Avro data type `SELECT`       |
+|---------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|-------------------------------|
+| `boolean`, `int`, `long`, `float`, `double` | [Int(8\16\32)](/docs/en/sql-reference/data-types/int-uint.md), [UInt(8\16\32)](/docs/en/sql-reference/data-types/int-uint.md) | `int`                         |
+| `boolean`, `int`, `long`, `float`, `double` | [Int64](/docs/en/sql-reference/data-types/int-uint.md), [UInt64](/docs/en/sql-reference/data-types/int-uint.md)               | `long`                        |
+| `boolean`, `int`, `long`, `float`, `double` | [Float32](/docs/en/sql-reference/data-types/float.md)                                                                         | `float`                       |
+| `boolean`, `int`, `long`, `float`, `double` | [Float64](/docs/en/sql-reference/data-types/float.md)                                                                         | `double`                      |
+| `bytes`, `string`, `fixed`, `enum`          | [String](/docs/en/sql-reference/data-types/string.md)                                                                         | `bytes` or `string` \*        |
+| `bytes`, `string`, `fixed`                  | [FixedString(N)](/docs/en/sql-reference/data-types/fixedstring.md)                                                            | `fixed(N)`                    |
+| `enum`                                      | [Enum(8\16)](/docs/en/sql-reference/data-types/enum.md)                                                                       | `enum`                        |
+| `array(T)`                                  | [Array(T)](/docs/en/sql-reference/data-types/array.md)                                                                        | `array(T)`                    |
+| `union(null, T)`, `union(T, null)`          | [Nullable(T)](/docs/en/sql-reference/data-types/date.md)                                                                      | `union(null, T)`              |
+| `null`                                      | [Nullable(Nothing)](/docs/en/sql-reference/data-types/special-data-types/nothing.md)                                          | `null`                        |
+| `int (date)` \**                            | [Date](/docs/en/sql-reference/data-types/date.md), [Date32](docs/en/sql-reference/data-types/date32.md)                       | `int (date)` \**              |
+| `long (timestamp-millis)` \**               | [DateTime64(3)](/docs/en/sql-reference/data-types/datetime.md)                                                                | `long (timestamp-millis)` \** |
+| `long (timestamp-micros)` \**               | [DateTime64(6)](/docs/en/sql-reference/data-types/datetime.md)                                                                | `long (timestamp-micros)` \** |
+| `int`                                       | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)                                                                     | `int`                         |
+| `fixed(16)`                                 | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)                                                                     | `fixed(16)`                   |
+| `bytes (decimal)` \**                       | [Decimal(P, S)](/docs/en/sql-reference/data-types/decimal.md)                                                                | `bytes (decimal)` \**         |
+| `string (uuid)` \**                         | [UUID](/docs/en/sql-reference/data-types/uuid.md)                                                                            | `string (uuid)` \**           |
+
 
 \* `bytes` is default, controlled by [output_format_avro_string_column_pattern](/docs/en/operations/settings/settings-formats.md/#output_format_avro_string_column_pattern)
 \** [Avro logical types](https://avro.apache.org/docs/current/spec.html#Logical+Types)
@@ -1918,28 +1927,30 @@ Setting `format_avro_schema_registry_url` needs to be configured in `users.xml`
 
 The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
 
-| Parquet data type (`INSERT`)                  | ClickHouse data type                                            | Parquet data type (`SELECT`) |
-|-----------------------------------------------|-----------------------------------------------------------------|------------------------------|
-| `BOOL`                                        | [Bool](/docs/en/sql-reference/data-types/boolean.md)            | `BOOL`                       |
-| `UINT8`, `BOOL`                               | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)          | `UINT8`                      |
-| `INT8`                                        | [Int8](/docs/en/sql-reference/data-types/int-uint.md)           | `INT8`                       |
-| `UINT16`                                      | [UInt16](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT16`                     |
-| `INT16`                                       | [Int16](/docs/en/sql-reference/data-types/int-uint.md)          | `INT16`                      |
-| `UINT32`                                      | [UInt32](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT32`                     |
-| `INT32`                                       | [Int32](/docs/en/sql-reference/data-types/int-uint.md)          | `INT32`                      |
-| `UINT64`                                      | [UInt64](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT64`                     |
-| `INT64`                                       | [Int64](/docs/en/sql-reference/data-types/int-uint.md)          | `INT64`                      |
-| `FLOAT`                                       | [Float32](/docs/en/sql-reference/data-types/float.md)           | `FLOAT`                      |
-| `DOUBLE`                                      | [Float64](/docs/en/sql-reference/data-types/float.md)           | `DOUBLE`                     |
-| `DATE`                                        | [Date32](/docs/en/sql-reference/data-types/date.md)             | `DATE`                       |
-| `TIME (ms)`                                   | [DateTime](/docs/en/sql-reference/data-types/datetime.md)       | `UINT32`                     |
-| `TIMESTAMP`, `TIME (us, ns)`                  | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)   | `TIMESTAMP`                  |
-| `STRING`, `BINARY`                            | [String](/docs/en/sql-reference/data-types/string.md)           | `BINARY`                     |
-| `STRING`, `BINARY`, `FIXED_LENGTH_BYTE_ARRAY` | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_LENGTH_BYTE_ARRAY`    |
-| `DECIMAL`                                     | [Decimal](/docs/en/sql-reference/data-types/decimal.md)         | `DECIMAL`                    |
-| `LIST`                                        | [Array](/docs/en/sql-reference/data-types/array.md)             | `LIST`                       |
-| `STRUCT`                                      | [Tuple](/docs/en/sql-reference/data-types/tuple.md)             | `STRUCT`                     |
-| `MAP`                                         | [Map](/docs/en/sql-reference/data-types/map.md)                 | `MAP`                        |
+| Parquet data type (`INSERT`)                       | ClickHouse data type                                            | Parquet data type (`SELECT`) |
+|----------------------------------------------------|-----------------------------------------------------------------|------------------------------|
+| `BOOL`                                             | [Bool](/docs/en/sql-reference/data-types/boolean.md)            | `BOOL`                       |
+| `UINT8`, `BOOL`                                    | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)          | `UINT8`                      |
+| `INT8`                                             | [Int8](/docs/en/sql-reference/data-types/int-uint.md)           | `INT8`                       |
+| `UINT16`                                           | [UInt16](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT16`                     |
+| `INT16`                                            | [Int16](/docs/en/sql-reference/data-types/int-uint.md)          | `INT16`                      |
+| `UINT32`                                           | [UInt32](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT32`                     |
+| `INT32`                                            | [Int32](/docs/en/sql-reference/data-types/int-uint.md)          | `INT32`                      |
+| `UINT64`                                           | [UInt64](/docs/en/sql-reference/data-types/int-uint.md)         | `UINT64`                     |
+| `INT64`                                            | [Int64](/docs/en/sql-reference/data-types/int-uint.md)          | `INT64`                      |
+| `FLOAT`                                            | [Float32](/docs/en/sql-reference/data-types/float.md)           | `FLOAT`                      |
+| `DOUBLE`                                           | [Float64](/docs/en/sql-reference/data-types/float.md)           | `DOUBLE`                     |
+| `DATE`                                             | [Date32](/docs/en/sql-reference/data-types/date.md)             | `DATE`                       |
+| `TIME (ms)`                                        | [DateTime](/docs/en/sql-reference/data-types/datetime.md)       | `UINT32`                     |
+| `TIMESTAMP`, `TIME (us, ns)`                       | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md)   | `TIMESTAMP`                  |
+| `STRING`, `BINARY`                                 | [String](/docs/en/sql-reference/data-types/string.md)           | `BINARY`                     |
+| `STRING`, `BINARY`, `FIXED_LENGTH_BYTE_ARRAY`      | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_LENGTH_BYTE_ARRAY`    |
+| `DECIMAL`                                          | [Decimal](/docs/en/sql-reference/data-types/decimal.md)         | `DECIMAL`                    |
+| `LIST`                                             | [Array](/docs/en/sql-reference/data-types/array.md)             | `LIST`                       |
+| `STRUCT`                                           | [Tuple](/docs/en/sql-reference/data-types/tuple.md)             | `STRUCT`                     |
+| `MAP`                                              | [Map](/docs/en/sql-reference/data-types/map.md)                 | `MAP`                        |
+| `UINT32`                                           | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)       | `UINT32`                     |
+| `FIXED_LENGTH_BYTE_ARRAY`                          | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)       | `FIXED_LENGTH_BYTE_ARRAY`                     |
 
 Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
 
@@ -1973,6 +1984,7 @@ To exchange data with Hadoop, you can use [HDFS table engine](/docs/en/engines/t
 - [input_format_parquet_skip_columns_with_unsupported_types_in_schema_inference](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_skip_columns_with_unsupported_types_in_schema_inference) - allow skipping columns with unsupported types while schema inference for Parquet format. Default value - `false`.
 - [output_format_parquet_fixed_string_as_fixed_byte_array](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_fixed_string_as_fixed_byte_array) - use Parquet FIXED_LENGTH_BYTE_ARRAY type instead of Binary/String for FixedString columns. Default value - `true`.
 - [output_format_parquet_version](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_version) - The version of Parquet format used in output format. Default value - `2.latest`.
+- [output_format_parquet_compression_method](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_compression_method) - compression method used in output Parquet format. Default value - `snappy`.
 
 ## Arrow {#data-format-arrow}
 
@@ -2007,6 +2019,8 @@ The table below shows supported data types and how they match ClickHouse [data t
 | `LIST`                                  | [Array](/docs/en/sql-reference/data-types/array.md)             | `LIST`                     |
 | `STRUCT`                                | [Tuple](/docs/en/sql-reference/data-types/tuple.md)             | `STRUCT`                   |
 | `MAP`                                   | [Map](/docs/en/sql-reference/data-types/map.md)                 | `MAP`                      |
+| `UINT32`                                | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)       | `UINT32`                   |
+| `FIXED_SIZE_BINARY`, `BINARY`           | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md)       | `FIXED_SIZE_BINARY`        |
 
 Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
 
@@ -2041,6 +2055,7 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Arrow" > {filenam
 - [input_format_arrow_allow_missing_columns](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_allow_missing_columns) - allow missing columns while reading Arrow data. Default value - `false`.
 - [input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference) - allow skipping columns with unsupported types while schema inference for Arrow format. Default value - `false`.
 - [output_format_arrow_fixed_string_as_fixed_byte_array](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_fixed_string_as_fixed_byte_array) - use Arrow FIXED_SIZE_BINARY type instead of Binary/String for FixedString columns. Default value - `true`.
+- [output_format_arrow_compression_method](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_compression_method) - compression method used in output Arrow format. Default value - `none`.
 
 ## ArrowStream {#data-format-arrow-stream}
 
@@ -2054,8 +2069,8 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Arrow" > {filenam
 
 The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
 
-| ORC data type (`INSERT`)              | ClickHouse data type                                    | ORC data type (`SELECT`) |
-|---------------------------------------|---------------------------------------------------------|--------------------------|
+| ORC data type (`INSERT`)              | ClickHouse data type                                          | ORC data type (`SELECT`) |
+|---------------------------------------|---------------------------------------------------------------|--------------------------|
 | `Boolean`                             | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)        | `Boolean`                |
 | `Tinyint`                             | [Int8](/docs/en/sql-reference/data-types/int-uint.md)         | `Tinyint`                |
 | `Smallint`                            | [Int16](/docs/en/sql-reference/data-types/int-uint.md)        | `Smallint`               |
@@ -2070,6 +2085,7 @@ The table below shows supported data types and how they match ClickHouse [data t
 | `List`                                | [Array](/docs/en/sql-reference/data-types/array.md)           | `List`                   |
 | `Struct`                              | [Tuple](/docs/en/sql-reference/data-types/tuple.md)           | `Struct`                 |
 | `Map`                                 | [Map](/docs/en/sql-reference/data-types/map.md)               | `Map`                    |
+| `-`                                   | [IPv4](/docs/en/sql-reference/data-types/int-uint.md)         | `Int`                    |
 
 Other types are not supported.
 
@@ -2096,6 +2112,7 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT ORC" > {filename.
 ### Arrow format settings {#parquet-format-settings}
 
 - [output_format_arrow_string_as_string](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_string_as_string) - use Arrow String type instead of Binary for String columns. Default value - `false`.
+- [output_format_orc_compression_method](/docs/en/operations/settings/settings-formats.md/#output_format_orc_compression_method) - compression method used in output ORC format. Default value - `none`.
 - [input_format_arrow_import_nested](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_import_nested) - allow inserting array of structs into Nested table in Arrow input format. Default value - `false`.
 - [input_format_arrow_case_insensitive_column_matching](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_case_insensitive_column_matching) - ignore case when matching Arrow columns with ClickHouse columns. Default value - `false`.
 - [input_format_arrow_allow_missing_columns](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_allow_missing_columns) - allow missing columns while reading Arrow data. Default value - `false`.
@@ -2264,8 +2281,8 @@ ClickHouse supports reading and writing [MessagePack](https://msgpack.org/) data
 
 ### Data Types Matching {#data-types-matching-msgpack}
 
-| MessagePack data type (`INSERT`)                                   | ClickHouse data type                                      | MessagePack data type (`SELECT`)   |
-|--------------------------------------------------------------------|-----------------------------------------------------------|------------------------------------|
+| MessagePack data type (`INSERT`)                                   | ClickHouse data type                                            | MessagePack data type (`SELECT`)   |
+|--------------------------------------------------------------------|-----------------------------------------------------------------|------------------------------------|
 | `uint N`, `positive fixint`                                        | [UIntN](/docs/en/sql-reference/data-types/int-uint.md)          | `uint N`                           |
 | `int N`, `negative fixint`                                         | [IntN](/docs/en/sql-reference/data-types/int-uint.md)           | `int N`                            |
 | `bool`                                                             | [UInt8](/docs/en/sql-reference/data-types/int-uint.md)          | `uint 8`                           |
@@ -2278,6 +2295,8 @@ ClickHouse supports reading and writing [MessagePack](https://msgpack.org/) data
 | `uint 64`                                                          | [DateTime64](/docs/en/sql-reference/data-types/datetime.md)     | `uint 64`                          |
 | `fixarray`, `array 16`, `array 32`                                 | [Array](/docs/en/sql-reference/data-types/array.md)             | `fixarray`, `array 16`, `array 32` |
 | `fixmap`, `map 16`, `map 32`                                       | [Map](/docs/en/sql-reference/data-types/map.md)                 | `fixmap`, `map 16`, `map 32`       |
+| `uint 32`                                                          | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)       | `uint 32`                          |
+| `bin 8`                                                            | [String](/docs/en/sql-reference/data-types/string.md)           | `bin 8`                            |
 
 Example:
 

docs/en/interfaces/http.md

@@ -309,6 +309,7 @@ The HTTP interface allows passing external data (external temporary tables) for
 ## Response Buffering {#response-buffering}
 
 You can enable response buffering on the server-side. The `buffer_size` and `wait_end_of_query` URL parameters are provided for this purpose.
+Also settings `http_response_buffer_size` and `http_wait_end_of_query` can be used.
 
 `buffer_size` determines the number of bytes in the result to buffer in the server memory. If a result body is larger than this threshold, the buffer is written to the HTTP channel, and the remaining data is sent directly to the HTTP channel.
 

docs/en/interfaces/postgresql.md

@@ -8,7 +8,7 @@ sidebar_label: PostgreSQL Interface
 
 ClickHouse supports the PostgreSQL wire protocol, which allows you to use Postgres clients to connect to ClickHouse. In a sense, ClickHouse can pretend to be a PostgreSQL instance - allowing you to connect a PostgreSQL client application to ClickHouse that is not already directly supported by ClickHouse (for example, Amazon Redshift).
 
-To enable the PostgreSQL wire protocol, add the [postgresql_port](../operations/server-configuration-parameters/settings#server_configuration_parameters-postgresql_port) setting to your server's configuration file. For example, you could define the port in a new XML file in your `config.d` folder:
+To enable the PostgreSQL wire protocol, add the [postgresql_port](../operations/server-configuration-parameters/settings.md#server_configuration_parameters-postgresql_port) setting to your server's configuration file. For example, you could define the port in a new XML file in your `config.d` folder:
 
 ```xml
 <clickhouse>

docs/en/interfaces/schema-inference.md

@@ -117,7 +117,7 @@ clickhouse-local --file='hobbies.jsonl' --table='hobbies' --query='SELECT * FROM
 4	47	Brayan	['movies','skydiving']
 ```
 
-# Using structure from insertion table {#using-structure-from-insertion-table}
+## Using structure from insertion table {#using-structure-from-insertion-table}
 
 When table functions `file/s3/url/hdfs` are used to insert data into a table,
 there is an option to use the structure from the insertion table instead of extracting it from the data.
@@ -222,7 +222,7 @@ INSERT INTO hobbies4 SELECT id, empty(hobbies) ? NULL : hobbies[1] FROM file(hob
 
 In this case, there are some operations performed on the column `hobbies` in the `SELECT` query to insert it into the table, so ClickHouse cannot use the structure from the insertion table, and schema inference will be used.
 
-# Schema inference cache {#schema-inference-cache}
+## Schema inference cache {#schema-inference-cache}
 
 For most input formats schema inference reads some data to determine its structure and this process can take some time.
 To prevent inferring the same schema every time ClickHouse read the data from the same file, the inferred schema is cached and when accessing the same file again, ClickHouse will use the schema from the cache.
@@ -326,14 +326,14 @@ SELECT count() FROM system.schema_inference_cache WHERE storage='S3'
 └─────────┘
 ```
 
-# Text formats {#text-formats}
+## Text formats {#text-formats}
 
 For text formats, ClickHouse reads the data row by row, extracts column values according to the format,
 and then uses some recursive parsers and heuristics to determine the type for each value. The maximum number of rows read from the data in schema inference
 is controlled by the setting `input_format_max_rows_to_read_for_schema_inference` with default value 25000.
 By default, all inferred types are [Nullable](../sql-reference/data-types/nullable.md), but you can change this by setting `schema_inference_make_columns_nullable` (see examples in the [settings](#settings-for-text-formats) section).
 
-## JSON formats {#json-formats}
+### JSON formats {#json-formats}
 
 In JSON formats ClickHouse parses values according to the JSON specification and then tries to find the most appropriate data type for them.
 
@@ -464,9 +464,9 @@ most likely this column contains only Nulls or empty Arrays/Maps.
 ...
 ```
 
-### JSON settings {#json-settings}
+#### JSON settings {#json-settings}
 
-#### input_format_json_read_objects_as_strings
+##### input_format_json_read_objects_as_strings
 
 Enabling this setting allows reading nested JSON objects as strings.
 This setting can be used to read nested JSON objects without using JSON object type.
@@ -486,7 +486,7 @@ DESC format(JSONEachRow, $$
 └──────┴──────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-#### input_format_json_try_infer_numbers_from_strings
+##### input_format_json_try_infer_numbers_from_strings
 
 Enabling this setting allows inferring numbers from string values.
 
@@ -507,7 +507,7 @@ DESC format(JSONEachRow, $$
 └───────┴─────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-#### input_format_json_read_numbers_as_strings
+##### input_format_json_read_numbers_as_strings
 
 Enabling this setting allows reading numeric values as strings.
 
@@ -528,7 +528,7 @@ DESC format(JSONEachRow, $$
 └───────┴──────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-#### input_format_json_read_bools_as_numbers
+##### input_format_json_read_bools_as_numbers
 
 Enabling this setting allows reading Bool values as numbers.
 
@@ -549,7 +549,7 @@ DESC format(JSONEachRow, $$
 └───────┴─────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## CSV {#csv}
+### CSV {#csv}
 
 In CSV format ClickHouse extracts column values from the row according to delimiters. ClickHouse expects all types except numbers and strings to be enclosed in double quotes. If the value is in double quotes, ClickHouse tries to parse
 the data inside quotes using the recursive parser and then tries to find the most appropriate data type for it. If the value is not in double quotes, ClickHouse tries to parse it as a number,
@@ -726,7 +726,7 @@ $$)
 └──────────────┴───────────────┘
 ```
 
-## TSV/TSKV {#tsv-tskv}
+### TSV/TSKV {#tsv-tskv}
 
 In TSV/TSKV formats ClickHouse extracts column value from the row according to tabular delimiters and then parses extracted value using
 the recursive parser to determine the most appropriate type. If the type cannot be determined, ClickHouse treats this value as String.
@@ -1019,7 +1019,7 @@ DESC format(TSV, '[1,2,3]	42.42	Hello World!')
 └──────┴──────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## CustomSeparated {#custom-separated}
+### CustomSeparated {#custom-separated}
 
 In CustomSeparated format ClickHouse first extracts all column values from the row according to specified delimiters and then tries to infer
 the data type for each value according to escaping rule.
@@ -1080,7 +1080,7 @@ $$)
 └────────┴───────────────┴────────────┘
 ```
 
-## Template {#template}
+### Template {#template}
 
 In Template format ClickHouse first extracts all column values from the row according to the specified template and then tries to infer the 
 data type for each value according to its escaping rule.
@@ -1120,7 +1120,7 @@ $$)
 └──────────┴────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## Regexp {#regexp}
+### Regexp {#regexp}
 
 Similar to Template, in Regexp format ClickHouse first extracts all column values from the row according to specified regular expression and then tries to infer
 data type for each value according to the specified escaping rule.
@@ -1142,9 +1142,9 @@ Line: value_1=2, value_2="Some string 2", value_3="[4, 5, NULL]"$$)
 └──────┴────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## Settings for text formats {settings-for-text-formats}
+### Settings for text formats {#settings-for-text-formats}
 
-### input_format_max_rows_to_read_for_schema_inference
+#### input_format_max_rows_to_read_for_schema_inference
 
 This setting controls the maximum number of rows to be read while schema inference.
 The more rows are read, the more time is spent on schema inference, but the greater the chance to
@@ -1152,7 +1152,7 @@ correctly determine the types (especially when the data contains a lot of nulls)
 
 Default value: `25000`.
 
-### column_names_for_schema_inference
+#### column_names_for_schema_inference
 
 The list of column names to use in schema inference for formats without explicit column names. Specified names will be used instead of default `c1,c2,c3,...`. The format: `column1,column2,column3,...`.
 
@@ -1169,7 +1169,7 @@ DESC format(TSV, 'Hello, World!	42	[1, 2, 3]') settings column_names_for_schema_
 └──────┴────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-### schema_inference_hints
+#### schema_inference_hints
 
 The list of column names and types to use in schema inference instead of automatically determined types. The format: 'column_name1 column_type1, column_name2 column_type2, ...'.
 This setting can be used to specify the types of columns that could not be determined automatically or for optimizing the schema.
@@ -1189,7 +1189,7 @@ DESC format(JSONEachRow, '{"id" : 1, "age" : 25, "name" : "Josh", "status" : nul
 └─────────┴─────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-### schema_inference_make_columns_nullable
+#### schema_inference_make_columns_nullable
 
 Controls making inferred types `Nullable` in schema inference for formats without information about nullability.
 If the setting is enabled, all inferred type will be `Nullable`, if disabled, the inferred type will be `Nullable` only if the column contains `NULL` in a sample that is parsed during schema inference.
@@ -1232,7 +1232,7 @@ DESC format(JSONEachRow, $$
 └─────────┴──────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-### input_format_try_infer_integers
+#### input_format_try_infer_integers
 
 If enabled, ClickHouse will try to infer integers instead of floats in schema inference for text formats.
 If all numbers in the column from sample data are integers, the result type will be `Int64`, if at least one number is float, the result type will be `Float64`.
@@ -1289,7 +1289,7 @@ DESC format(JSONEachRow, $$
 └────────┴───────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-### input_format_try_infer_datetimes
+#### input_format_try_infer_datetimes
 
 If enabled, ClickHouse will try to infer type `DateTime64` from string fields in schema inference for text formats.
 If all fields from a column in sample data were successfully parsed as datetimes, the result type will be `DateTime64(9)`,
@@ -1337,7 +1337,7 @@ DESC format(JSONEachRow, $$
 
 Note: Parsing datetimes during schema inference respect setting [date_time_input_format](/docs/en/operations/settings/settings-formats.md#date_time_input_format)
 
-### input_format_try_infer_dates
+#### input_format_try_infer_dates
 
 If enabled, ClickHouse will try to infer type `Date` from string fields in schema inference for text formats.
 If all fields from a column in sample data were successfully parsed as dates, the result type will be `Date`,
@@ -1383,14 +1383,14 @@ DESC format(JSONEachRow, $$
 └──────┴──────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-# Self describing formats {#self-describing-formats}
+## Self describing formats {#self-describing-formats}
 
 Self-describing formats contain information about the structure of the data in the data itself,
 it can be some header with a description, a binary type tree, or some kind of table.
 To automatically infer a schema from files in such formats, ClickHouse reads a part of the data containing
 information about the types and converts it into a schema of the ClickHouse table.
 
-## Formats with -WithNamesAndTypes suffix {#formats-with-names-and-types}
+### Formats with -WithNamesAndTypes suffix {#formats-with-names-and-types}
 
 ClickHouse supports some text formats with the suffix -WithNamesAndTypes. This suffix means that the data contains two additional rows with column names and types before the actual data.
 While schema inference for such formats, ClickHouse reads the first two rows and extracts column names and types.
@@ -1412,7 +1412,7 @@ $$)
 └──────┴──────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## JSON formats with metadata {#json-with-metadata}
+### JSON formats with metadata {#json-with-metadata}
 
 Some JSON input formats ([JSON](formats.md#json), [JSONCompact](formats.md#json-compact), [JSONColumnsWithMetadata](formats.md#jsoncolumnswithmetadata)) contain metadata with column names and types.
 In schema inference for such formats, ClickHouse reads this metadata.
@@ -1465,7 +1465,7 @@ $$)
 └──────┴──────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## Avro {#avro}
+### Avro {#avro}
 
 In Avro format ClickHouse reads its schema from the data and converts it to ClickHouse schema using the following type matches:
 
@@ -1473,6 +1473,7 @@ In Avro format ClickHouse reads its schema from the data and converts it to Clic
 |------------------------------------|--------------------------------------------------------------------------------|
 | `boolean`                          | [Bool](../sql-reference/data-types/boolean.md)                                 |
 | `int`                              | [Int32](../sql-reference/data-types/int-uint.md)                               |
+| `int (date)` \*                    | [Date32](../sql-reference/data-types/date32.md)                                |
 | `long`                             | [Int64](../sql-reference/data-types/int-uint.md)                               |
 | `float`                            | [Float32](../sql-reference/data-types/float.md)                                |
 | `double`                           | [Float64](../sql-reference/data-types/float.md)                                |
@@ -1482,10 +1483,14 @@ In Avro format ClickHouse reads its schema from the data and converts it to Clic
 | `array(T)`                         | [Array(T)](../sql-reference/data-types/array.md)                               |
 | `union(null, T)`, `union(T, null)` | [Nullable(T)](../sql-reference/data-types/date.md)                             |
 | `null`                             | [Nullable(Nothing)](../sql-reference/data-types/special-data-types/nothing.md) |
+| `string (uuid)` \*                 | [UUID](../sql-reference/data-types/uuid.md)                                    |
+| `binary (decimal)` \*              | [Decimal(P, S)](../sql-reference/data-types/decimal.md)                         |
+
+\* [Avro logical types](https://avro.apache.org/docs/current/spec.html#Logical+Types)
 
 Other Avro types are not supported.
 
-## Parquet {#parquet}
+### Parquet {#parquet}
 
 In Parquet format ClickHouse reads its schema from the data and converts it to ClickHouse schema using the following type matches:
 
@@ -1513,7 +1518,7 @@ In Parquet format ClickHouse reads its schema from the data and converts it to C
 
 Other Parquet types are not supported. By default, all inferred types are inside `Nullable`, but it can be changed using the setting `schema_inference_make_columns_nullable`.
 
-## Arrow {#arrow}
+### Arrow {#arrow}
 
 In Arrow format ClickHouse reads its schema from the data and converts it to ClickHouse schema using the following type matches:
 
@@ -1541,7 +1546,7 @@ In Arrow format ClickHouse reads its schema from the data and converts it to Cli
 
 Other Arrow types are not supported. By default, all inferred types are inside `Nullable`, but it can be changed using the setting `schema_inference_make_columns_nullable`.
 
-## ORC {#orc}
+### ORC {#orc}
 
 In ORC format ClickHouse reads its schema from the data and converts it to ClickHouse schema using the following type matches:
 
@@ -1564,17 +1569,17 @@ In ORC format ClickHouse reads its schema from the data and converts it to Click
 
 Other ORC types are not supported. By default, all inferred types are inside `Nullable`, but it can be changed using the setting `schema_inference_make_columns_nullable`.
 
-## Native {#native}
+### Native {#native}
 
 Native format is used inside ClickHouse and contains the schema in the data.
 In schema inference, ClickHouse reads the schema from the data without any transformations.
 
-# Formats with external schema {#formats-with-external-schema}
+## Formats with external schema {#formats-with-external-schema}
 
 Such formats require a schema describing the data in a separate file in a specific schema language.
 To automatically infer a schema from files in such formats, ClickHouse reads external schema from a separate file and transforms it to a ClickHouse table schema.
 
-# Protobuf {#protobuf}
+### Protobuf {#protobuf}
 
 In schema inference for Protobuf format ClickHouse uses the following type matches:
 
@@ -1592,7 +1597,7 @@ In schema inference for Protobuf format ClickHouse uses the following type match
 | `repeated T`                  | [Array(T)](../sql-reference/data-types/array.md)  |
 | `message`, `group`            | [Tuple](../sql-reference/data-types/tuple.md)     |
 
-# CapnProto {#capnproto}
+### CapnProto {#capnproto}
 
 In schema inference for CapnProto format ClickHouse uses the following type matches:
 
@@ -1615,13 +1620,13 @@ In schema inference for CapnProto format ClickHouse uses the following type matc
 | `struct`                           | [Tuple](../sql-reference/data-types/tuple.md)          |
 | `union(T, Void)`, `union(Void, T)` | [Nullable(T)](../sql-reference/data-types/nullable.md) |
 
-# Strong-typed binary formats {#strong-typed-binary-formats}
+## Strong-typed binary formats {#strong-typed-binary-formats}
 
 In such formats, each serialized value contains information about its type (and possibly about its name), but there is no information about the whole table.
 In schema inference for such formats, ClickHouse reads data row by row (up to `input_format_max_rows_to_read_for_schema_inference` rows) and extracts
 the type (and possibly name) for each value from the data and then converts these types to ClickHouse types.
 
-## MsgPack {msgpack}
+### MsgPack {#msgpack}
 
 In MsgPack format there is no delimiter between rows, to use schema inference for this format you should specify the number of columns in the table
 using the setting `input_format_msgpack_number_of_columns`. ClickHouse uses the following type matches:
@@ -1641,7 +1646,7 @@ using the setting `input_format_msgpack_number_of_columns`. ClickHouse uses the
 
 By default, all inferred types are inside `Nullable`, but it can be changed using the setting `schema_inference_make_columns_nullable`.
 
-## BSONEachRow {#bsoneachrow}
+### BSONEachRow {#bsoneachrow}
 
 In BSONEachRow each row of data is presented as a BSON document. In schema inference ClickHouse reads BSON documents one by one and extracts
 values, names, and types from the data and then transforms these types to ClickHouse types using the following type matches:
@@ -1661,11 +1666,11 @@ values, names, and types from the data and then transforms these types to ClickH
 
 By default, all inferred types are inside `Nullable`, but it can be changed using the setting `schema_inference_make_columns_nullable`.
 
-# Formats with constant schema {#formats-with-constant-schema}
+## Formats with constant schema {#formats-with-constant-schema}
 
 Data in such formats always have the same schema.
 
-## LineAsString {#line-as-string}
+### LineAsString {#line-as-string}
 
 In this format, ClickHouse reads the whole line from the data into a single column with `String` data type. The inferred type for this format is always `String` and the column name is `line`.
 
@@ -1680,7 +1685,7 @@ DESC format(LineAsString, 'Hello\nworld!')
 └──────┴────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## JSONAsString {#json-as-string}
+### JSONAsString {#json-as-string}
 
 In this format, ClickHouse reads the whole JSON object from the data into a single column with `String` data type. The inferred type for this format is always `String` and the column name is `json`.
 
@@ -1695,7 +1700,7 @@ DESC format(JSONAsString, '{"x" : 42, "y" : "Hello, World!"}')
 └──────┴────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
 ```
 
-## JSONAsObject {#json-as-object}
+### JSONAsObject {#json-as-object}
 
 In this format, ClickHouse reads the whole JSON object from the data into a single column with `Object('json')` data type. Inferred type for this format is always `String` and the column name is `json`.
 

docs/en/operations/_category_.yml

@@ -2,7 +2,3 @@ position: 70
 label: 'Operations'
 collapsible: true
 collapsed: true
-link:
-  type: generated-index
-  title: Operations
-  slug: /en/operations

docs/en/operations/access-rights.md

@@ -1,152 +0,0 @@
----
-slug: /en/operations/access-rights
-sidebar_position: 48
-sidebar_label: Access Control and Account Management
-title: Access Control and Account Management
----
-
-ClickHouse supports access control management based on [RBAC](https://en.wikipedia.org/wiki/Role-based_access_control) approach.
-
-ClickHouse access entities:
-- [User account](#user-account-management)
-- [Role](#role-management)
-- [Row Policy](#row-policy-management)
-- [Settings Profile](#settings-profiles-management)
-- [Quota](#quotas-management)
-
-You can configure access entities using:
-
--   SQL-driven workflow.
-
-    You need to [enable](#enabling-access-control) this functionality.
-
--   Server [configuration files](../operations/configuration-files.md) `users.xml` and `config.xml`.
-
-We recommend using SQL-driven workflow. Both of the configuration methods work simultaneously, so if you use the server configuration files for managing accounts and access rights, you can smoothly switch to SQL-driven workflow.
-
-:::warning
-You can’t manage the same access entity by both configuration methods simultaneously.
-:::
-
-To see all users, roles, profiles, etc. and all their grants use [SHOW ACCESS](../sql-reference/statements/show.md#show-access-statement) statement.
-
-## Usage {#access-control-usage}
-
-By default, the ClickHouse server provides the `default` user account which is not allowed using SQL-driven access control and account management but has all the rights and permissions. The `default` user account is used in any cases when the username is not defined, for example, at login from client or in distributed queries. In distributed query processing a default user account is used, if the configuration of the server or cluster does not specify the [user and password](../engines/table-engines/special/distributed.md) properties.
-
-If you just started using ClickHouse, consider the following scenario:
-
-1.  [Enable](#enabling-access-control) SQL-driven access control and account management for the `default` user.
-2.  Log in to the `default` user account and create all the required users. Don’t forget to create an administrator account (`GRANT ALL ON *.* TO admin_user_account WITH GRANT OPTION`).
-3.  [Restrict permissions](../operations/settings/permissions-for-queries.md#permissions_for_queries) for the `default` user and disable SQL-driven access control and account management for it.
-
-### Properties of Current Solution {#access-control-properties}
-
--   You can grant permissions for databases and tables even if they do not exist.
--   If a table was deleted, all the privileges that correspond to this table are not revoked. This means that even if you create a new table with the same name later, all the privileges remain valid. To revoke privileges corresponding to the deleted table, you need to execute, for example, the `REVOKE ALL PRIVILEGES ON db.table FROM ALL` query.
--   There are no lifetime settings for privileges.
-
-## User Account {#user-account-management}
-
-A user account is an access entity that allows to authorize someone in ClickHouse. A user account contains:
-
--   Identification information.
--   [Privileges](../sql-reference/statements/grant.md#grant-privileges) that define a scope of queries the user can execute.
--   Hosts allowed to connect to the ClickHouse server.
--   Assigned and default roles.
--   Settings with their constraints applied by default at user login.
--   Assigned settings profiles.
-
-Privileges can be granted to a user account by the [GRANT](../sql-reference/statements/grant.md) query or by assigning [roles](#role-management). To revoke privileges from a user, ClickHouse provides the [REVOKE](../sql-reference/statements/revoke.md) query. To list privileges for a user, use the [SHOW GRANTS](../sql-reference/statements/show.md#show-grants-statement) statement.
-
-Management queries:
-
--   [CREATE USER](../sql-reference/statements/create/user.md)
--   [ALTER USER](../sql-reference/statements/alter/user.md#alter-user-statement)
--   [DROP USER](../sql-reference/statements/drop.md)
--   [SHOW CREATE USER](../sql-reference/statements/show.md#show-create-user-statement)
--   [SHOW USERS](../sql-reference/statements/show.md#show-users-statement)
-
-### Settings Applying {#access-control-settings-applying}
-
-Settings can be configured differently: for a user account, in its granted roles and in settings profiles. At user login, if a setting is configured for different access entities, the value and constraints of this setting are applied as follows (from higher to lower priority):
-
-1.  User account settings.
-2.  The settings of default roles of the user account. If a setting is configured in some roles, then order of the setting application is undefined.
-3.  The settings from settings profiles assigned to a user or to its default roles. If a setting is configured in some profiles, then order of setting application is undefined.
-4.  Settings applied to all the server by default or from the [default profile](../operations/server-configuration-parameters/settings.md#default-profile).
-
-## Role {#role-management}
-
-Role is a container for access entities that can be granted to a user account.
-
-Role contains:
-
--   [Privileges](../sql-reference/statements/grant.md#grant-privileges)
--   Settings and constraints
--   List of assigned roles
-
-Management queries:
-
--   [CREATE ROLE](../sql-reference/statements/create/role.md)
--   [ALTER ROLE](../sql-reference/statements/alter/role.md#alter-role-statement)
--   [DROP ROLE](../sql-reference/statements/drop.md)
--   [SET ROLE](../sql-reference/statements/set-role.md)
--   [SET DEFAULT ROLE](../sql-reference/statements/set-role.md#set-default-role-statement)
--   [SHOW CREATE ROLE](../sql-reference/statements/show.md#show-create-role-statement)
--   [SHOW ROLES](../sql-reference/statements/show.md#show-roles-statement)
-
-Privileges can be granted to a role by the [GRANT](../sql-reference/statements/grant.md) query. To revoke privileges from a role ClickHouse provides the [REVOKE](../sql-reference/statements/revoke.md) query.
-
-## Row Policy {#row-policy-management}
-
-Row policy is a filter that defines which of the rows are available to a user or a role. Row policy contains filters for one particular table, as well as a list of roles and/or users which should use this row policy.
-
-:::warning
-Row policies makes sense only for users with readonly access. If user can modify table or copy partitions between tables, it defeats the restrictions of row policies.
-:::
-
-Management queries:
-
--   [CREATE ROW POLICY](../sql-reference/statements/create/row-policy.md)
--   [ALTER ROW POLICY](../sql-reference/statements/alter/row-policy.md#alter-row-policy-statement)
--   [DROP ROW POLICY](../sql-reference/statements/drop.md#drop-row-policy-statement)
--   [SHOW CREATE ROW POLICY](../sql-reference/statements/show.md#show-create-row-policy-statement)
--   [SHOW POLICIES](../sql-reference/statements/show.md#show-policies-statement)
-
-## Settings Profile {#settings-profiles-management}
-
-Settings profile is a collection of [settings](../operations/settings/index.md). Settings profile contains settings and constraints, as well as a list of roles and/or users to which this profile is applied.
-
-Management queries:
-
--   [CREATE SETTINGS PROFILE](../sql-reference/statements/create/settings-profile.md#create-settings-profile-statement)
--   [ALTER SETTINGS PROFILE](../sql-reference/statements/alter/settings-profile.md#alter-settings-profile-statement)
--   [DROP SETTINGS PROFILE](../sql-reference/statements/drop.md#drop-settings-profile-statement)
--   [SHOW CREATE SETTINGS PROFILE](../sql-reference/statements/show.md#show-create-settings-profile-statement)
--   [SHOW PROFILES](../sql-reference/statements/show.md#show-profiles-statement)
-
-## Quota {#quotas-management}
-
-Quota limits resource usage. See [Quotas](../operations/quotas.md).
-
-Quota contains a set of limits for some durations, as well as a list of roles and/or users which should use this quota.
-
-Management queries:
-
--   [CREATE QUOTA](../sql-reference/statements/create/quota.md)
--   [ALTER QUOTA](../sql-reference/statements/alter/quota.md#alter-quota-statement)
--   [DROP QUOTA](../sql-reference/statements/drop.md#drop-quota-statement)
--   [SHOW CREATE QUOTA](../sql-reference/statements/show.md#show-create-quota-statement)
--   [SHOW QUOTA](../sql-reference/statements/show.md#show-quota-statement)
--   [SHOW QUOTAS](../sql-reference/statements/show.md#show-quotas-statement)
-
-## Enabling SQL-driven Access Control and Account Management {#enabling-access-control}
-
--   Setup a directory for configurations storage.
-
-    ClickHouse stores access entity configurations in the folder set in the [access_control_path](../operations/server-configuration-parameters/settings.md#access_control_path) server configuration parameter.
-
--   Enable SQL-driven access control and account management for at least one user account.
-
-    By default, SQL-driven access control and account management is disabled for all users. You need to configure at least one user in the `users.xml` configuration file and set the value of the [access_management](../operations/settings/settings-users.md#access_management-user-setting) setting to 1.

docs/en/operations/backup.md

@@ -1,5 +1,6 @@
 ---
 slug: /en/operations/backup
+description: In order to effectively mitigate possible human errors, you should carefully prepare a strategy for backing up and restoring your data.
 ---
 
 # Backup and Restore
@@ -213,7 +214,7 @@ To write backups to an S3 bucket you need three pieces of information:
   for example `Abc+123`
 
 :::note
-Creating an S3 bucket is covered in [Use S3 Object Storage as a ClickHouse disk](/docs/en/integrations/data-ingestion/s3/configuring-s3-for-clickhouse-use.md), just come back to this doc after saving the policy, there is no need to configure ClickHouse to use the S3 bucket.
+Creating an S3 bucket is covered in [Use S3 Object Storage as a ClickHouse disk](/docs/en/integrations/data-ingestion/s3/index.md#configuring-s3-for-clickhouse-use), just come back to this doc after saving the policy, there is no need to configure ClickHouse to use the S3 bucket.
 :::
 
 The destination for a backup will be specified like this:

docs/en/operations/caches.md

@@ -3,6 +3,7 @@ slug: /en/operations/caches
 sidebar_position: 65
 sidebar_label: Caches
 title: "Cache Types"
+description: When performing queries, ClickHouse uses different caches.
 ---
 
 When performing queries, ClickHouse uses different caches.

docs/en/operations/clickhouse-keeper.md

@@ -1,378 +0,0 @@
----
-slug: /en/operations/clickhouse-keeper
-sidebar_position: 66
-sidebar_label: ClickHouse Keeper
----
-
-# ClickHouse Keeper
-import SelfManaged from '@site/docs/en/_snippets/_self_managed_only_automated.md';
-
-<SelfManaged />
-
-ClickHouse Keeper provides the coordination system for data [replication](../engines/table-engines/mergetree-family/replication.md) and [distributed DDL](../sql-reference/distributed-ddl.md) queries execution. ClickHouse Keeper is compatible with ZooKeeper.
-
-## Implementation details {#implementation-details}
-
-ZooKeeper is one of the first well-known open-source coordination systems. It's implemented in Java, and has quite a simple and powerful data model. ZooKeeper's coordination algorithm, ZooKeeper Atomic Broadcast (ZAB), doesn't provide linearizability guarantees for reads, because each ZooKeeper node serves reads locally. Unlike ZooKeeper ClickHouse Keeper is written in C++ and uses the [RAFT algorithm](https://raft.github.io/) [implementation](https://github.com/eBay/NuRaft). This algorithm allows linearizability for reads and writes, and has several open-source implementations in different languages.
-
-By default, ClickHouse Keeper provides the same guarantees as ZooKeeper (linearizable writes, non-linearizable reads). It has a compatible client-server protocol, so any standard ZooKeeper client can be used to interact with ClickHouse Keeper. Snapshots and logs have an incompatible format with ZooKeeper, but the `clickhouse-keeper-converter` tool enables the conversion of ZooKeeper data to ClickHouse Keeper snapshots. The interserver protocol in ClickHouse Keeper is also incompatible with ZooKeeper so a mixed ZooKeeper / ClickHouse Keeper cluster is impossible.
-
-ClickHouse Keeper supports Access Control Lists (ACLs) the same way as [ZooKeeper](https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#sc_ZooKeeperAccessControl) does. ClickHouse Keeper supports the same set of permissions and has the identical built-in schemes: `world`, `auth` and `digest`. The digest authentication scheme uses the pair `username:password`, the password is encoded in Base64.
-
-:::note
-External integrations are not supported.
-:::
-
-## Configuration {#configuration}
-
-ClickHouse Keeper can be used as a standalone replacement for ZooKeeper or as an internal part of the ClickHouse server. In both cases the configuration is almost the same `.xml` file. The main ClickHouse Keeper configuration tag is `<keeper_server>`. Keeper configuration has the following parameters:
-
--    `tcp_port` — Port for a client to connect (default for ZooKeeper is `2181`).
--    `tcp_port_secure` — Secure port for an SSL connection between client and keeper-server.
--    `server_id` — Unique server id, each participant of the ClickHouse Keeper cluster must have a unique number (1, 2, 3, and so on).
--    `log_storage_path` — Path to coordination logs, just like ZooKeeper it is best to store logs on non-busy nodes.
--    `snapshot_storage_path` — Path to coordination snapshots.
-
-Other common parameters are inherited from the ClickHouse server config (`listen_host`, `logger`, and so on).
-
-Internal coordination settings are located in the `<keeper_server>.<coordination_settings>` section:
-
--    `operation_timeout_ms` — Timeout for a single client operation (ms) (default: 10000).
--    `min_session_timeout_ms` — Min timeout for client session (ms) (default: 10000).
--    `session_timeout_ms` — Max timeout for client session (ms) (default: 100000).
--    `dead_session_check_period_ms` — How often ClickHouse Keeper checks for dead sessions and removes them (ms) (default: 500).
--    `heart_beat_interval_ms` — How often a ClickHouse Keeper leader will send heartbeats to followers (ms) (default: 500).
--    `election_timeout_lower_bound_ms` — If the follower does not receive a heartbeat from the leader in this interval, then it can initiate leader election (default: 1000). Must be less than or equal to `election_timeout_upper_bound_ms`. Ideally they shouldn't be equal.
--    `election_timeout_upper_bound_ms` — If the follower does not receive a heartbeat from the leader in this interval, then it must initiate leader election (default: 2000).
--    `rotate_log_storage_interval` — How many log records to store in a single file (default: 100000).
--    `reserved_log_items` — How many coordination log records to store before compaction (default: 100000).
--    `snapshot_distance` — How often ClickHouse Keeper will create new snapshots (in the number of records in logs) (default: 100000).
--    `snapshots_to_keep` — How many snapshots to keep (default: 3).
--    `stale_log_gap` — Threshold when leader considers follower as stale and sends the snapshot to it instead of logs (default: 10000).
--    `fresh_log_gap` — When node became fresh (default: 200).
--    `max_requests_batch_size` - Max size of batch in requests count before it will be sent to RAFT (default: 100).
--    `force_sync` — Call `fsync` on each write to coordination log (default: true).
--    `quorum_reads` — Execute read requests as writes through whole RAFT consensus with similar speed (default: false).
--    `raft_logs_level` — Text logging level about coordination (trace, debug, and so on) (default: system default).
--    `auto_forwarding` — Allow to forward write requests from followers to the leader (default: true).
--    `shutdown_timeout` — Wait to finish internal connections and shutdown (ms) (default: 5000).
--    `startup_timeout` — If the server doesn't connect to other quorum participants in the specified timeout it will terminate (ms) (default: 30000).
--    `four_letter_word_white_list` — White list of 4lw commands (default: `conf,cons,crst,envi,ruok,srst,srvr,stat,wchs,dirs,mntr,isro,rcvr,apiv,csnp,lgif,rqld`).
-
-Quorum configuration is located in the `<keeper_server>.<raft_configuration>` section and contain servers description.
-
-The only parameter for the whole quorum is `secure`, which enables encrypted connection for communication between quorum participants. The parameter can be set `true` if SSL connection is required for internal communication between nodes, or left unspecified otherwise.
-
-The main parameters for each `<server>` are:
-
--    `id` — Server identifier in a quorum.
--    `hostname` — Hostname where this server is placed.
--    `port` — Port where this server listens for connections.
-
-:::note
-In the case of a change in the topology of your ClickHouse Keeper cluster (e.g., replacing a server), please make sure to keep the mapping of `server_id` to `hostname` consistent and avoid shuffling or reusing an existing `server_id` for different servers (e.g., it can happen if your rely on automation scripts to deploy ClickHouse Keeper)
-:::
-
-Examples of configuration for quorum with three nodes can be found in [integration tests](https://github.com/ClickHouse/ClickHouse/tree/master/tests/integration) with `test_keeper_` prefix. Example configuration for server #1:
-
-```xml
-<keeper_server>
-    <tcp_port>2181</tcp_port>
-    <server_id>1</server_id>
-    <log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
-    <snapshot_storage_path>/var/lib/clickhouse/coordination/snapshots</snapshot_storage_path>
-
-    <coordination_settings>
-        <operation_timeout_ms>10000</operation_timeout_ms>
-        <session_timeout_ms>30000</session_timeout_ms>
-        <raft_logs_level>trace</raft_logs_level>
-    </coordination_settings>
-
-    <raft_configuration>
-        <server>
-            <id>1</id>
-            <hostname>zoo1</hostname>
-            <port>9444</port>
-        </server>
-        <server>
-            <id>2</id>
-            <hostname>zoo2</hostname>
-            <port>9444</port>
-        </server>
-        <server>
-            <id>3</id>
-            <hostname>zoo3</hostname>
-            <port>9444</port>
-        </server>
-    </raft_configuration>
-</keeper_server>
-```
-
-## How to run {#how-to-run}
-
-ClickHouse Keeper is bundled into the ClickHouse server package, just add configuration of `<keeper_server>` and start ClickHouse server as always. If you want to run standalone ClickHouse Keeper you can start it in a similar way with:
-
-```bash
-clickhouse-keeper --config /etc/your_path_to_config/config.xml
-```
-
-If you don't have the symlink (`clickhouse-keeper`) you can create it or specify `keeper` as an argument to `clickhouse`:
-
-```bash
-clickhouse keeper --config /etc/your_path_to_config/config.xml
-```
-
-## Four Letter Word Commands {#four-letter-word-commands}
-
-ClickHouse Keeper also provides 4lw commands which are almost the same with Zookeeper. Each command is composed of four letters such as `mntr`, `stat` etc. There are some more interesting commands: `stat` gives some general information about the server and connected clients, while `srvr` and `cons` give extended details on server and connections respectively.
-
-The 4lw commands has a white list configuration `four_letter_word_white_list` which has default value `conf,cons,crst,envi,ruok,srst,srvr,stat,wchs,dirs,mntr,isro,rcvr,apiv,csnp,lgif,rqld`.
-
-You can issue the commands to ClickHouse Keeper via telnet or nc, at the client port.
-
-```
-echo mntr | nc localhost 9181
-```
-
-Bellow is the detailed 4lw commands:
-
-- `ruok`: Tests if server is running in a non-error state. The server will respond with `imok` if it is running. Otherwise it will not respond at all. A response of `imok` does not necessarily indicate that the server has joined the quorum, just that the server process is active and bound to the specified client port. Use "stat" for details on state wrt quorum and client connection information.
-
-```
-imok
-```
-
-- `mntr`: Outputs a list of variables that could be used for monitoring the health of the cluster.
-
-```
-zk_version      v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
-zk_avg_latency  0
-zk_max_latency  0
-zk_min_latency  0
-zk_packets_received     68
-zk_packets_sent 68
-zk_num_alive_connections        1
-zk_outstanding_requests 0
-zk_server_state leader
-zk_znode_count  4
-zk_watch_count  1
-zk_ephemerals_count     0
-zk_approximate_data_size        723
-zk_open_file_descriptor_count   310
-zk_max_file_descriptor_count    10240
-zk_followers    0
-zk_synced_followers     0
-```
-
-- `srvr`: Lists full details for the server.
-
-```
-ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
-Latency min/avg/max: 0/0/0
-Received: 2
-Sent : 2
-Connections: 1
-Outstanding: 0
-Zxid: 34
-Mode: leader
-Node count: 4
-```
-
-- `stat`: Lists brief details for the server and connected clients.
-
-```
-ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
-Clients:
- 192.168.1.1:52852(recved=0,sent=0)
- 192.168.1.1:52042(recved=24,sent=48)
-Latency min/avg/max: 0/0/0
-Received: 4
-Sent : 4
-Connections: 1
-Outstanding: 0
-Zxid: 36
-Mode: leader
-Node count: 4
-```
-
-- `srst`: Reset server statistics. The command will affect the result of `srvr`, `mntr` and `stat`.
-
-```
-Server stats reset.
-```
-
-- `conf`: Print details about serving configuration.
-
-```
-server_id=1
-tcp_port=2181
-four_letter_word_white_list=*
-log_storage_path=./coordination/logs
-snapshot_storage_path=./coordination/snapshots
-max_requests_batch_size=100
-session_timeout_ms=30000
-operation_timeout_ms=10000
-dead_session_check_period_ms=500
-heart_beat_interval_ms=500
-election_timeout_lower_bound_ms=1000
-election_timeout_upper_bound_ms=2000
-reserved_log_items=1000000000000000
-snapshot_distance=10000
-auto_forwarding=true
-shutdown_timeout=5000
-startup_timeout=240000
-raft_logs_level=information
-snapshots_to_keep=3
-rotate_log_storage_interval=100000
-stale_log_gap=10000
-fresh_log_gap=200
-max_requests_batch_size=100
-quorum_reads=false
-force_sync=false
-compress_logs=true
-compress_snapshots_with_zstd_format=true
-configuration_change_tries_count=20
-```
-
-- `cons`: List full connection/session details for all clients connected to this server. Includes information on numbers of packets received/sent, session id, operation latencies, last operation performed, etc...
-
-```
- 192.168.1.1:52163(recved=0,sent=0,sid=0xffffffffffffffff,lop=NA,est=1636454787393,to=30000,lzxid=0xffffffffffffffff,lresp=0,llat=0,minlat=0,avglat=0,maxlat=0)
- 192.168.1.1:52042(recved=9,sent=18,sid=0x0000000000000001,lop=List,est=1636454739887,to=30000,lcxid=0x0000000000000005,lzxid=0x0000000000000005,lresp=1636454739892,llat=0,minlat=0,avglat=0,maxlat=0)
-```
-
-- `crst`: Reset connection/session statistics for all connections.
-
-```
-Connection stats reset.
-```
-
-- `envi`: Print details about serving environment
-
-```
-Environment:
-clickhouse.keeper.version=v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
-host.name=ZBMAC-C02D4054M.local
-os.name=Darwin
-os.arch=x86_64
-os.version=19.6.0
-cpu.count=12
-user.name=root
-user.home=/Users/JackyWoo/
-user.dir=/Users/JackyWoo/project/jd/clickhouse/cmake-build-debug/programs/
-user.tmp=/var/folders/b4/smbq5mfj7578f2jzwn602tt40000gn/T/
-```
-
-
-- `dirs`: Shows the total size of snapshot and log files in bytes
-
-```
-snapshot_dir_size: 0
-log_dir_size: 3875
-```
-
-- `isro`: Tests if server is running in read-only mode. The server will respond with "ro" if in read-only mode or "rw" if not in read-only mode.
-
-```
-rw
-```
-
-- `wchs`: Lists brief information on watches for the server.
-
-```
-1 connections watching 1 paths
-Total watches:1
-```
-
-- `wchc`: Lists detailed information on watches for the server, by session. This outputs a list of sessions (connections) with associated watches (paths). Note, depending on the number of watches this operation may be expensive (ie impact server performance), use it carefully.
-
-```
-0x0000000000000001
-    /clickhouse/task_queue/ddl
-```
-
-- `wchp`: Lists detailed information on watches for the server, by path. This outputs a list of paths (znodes) with associated sessions. Note, depending on the number of watches this operation may be expensive (i. e. impact server performance), use it carefully.
-
-```
-/clickhouse/task_queue/ddl
-    0x0000000000000001
-```
-
-- `dump`: Lists the outstanding sessions and ephemeral nodes. This only works on the leader.
-
-```
-Sessions dump (2):
-0x0000000000000001
-0x0000000000000002
-Sessions with Ephemerals (1):
-0x0000000000000001
- /clickhouse/task_queue/ddl
-```
-
-- `csnp`: Schedule a snapshot creation task. Return the last committed log index of the scheduled snapshot if success or `Failed to schedule snapshot creation task.` if failed. Note that `lgif` command can help you determine whether the snapshot is done.
-
-```
-100
-```
-
-- `lgif`: Keeper log information. `first_log_idx` : my first log index in log store; `first_log_term` : my first log term; `last_log_idx` : my last log index in log store; `last_log_term` : my last log term; `last_committed_log_idx` : my last committed log index in state machine; `leader_committed_log_idx` : leader's committed log index from my perspective; `target_committed_log_idx` : target log index should be committed to; `last_snapshot_idx` : the largest committed log index in last snapshot.
-
-```
-first_log_idx   1
-first_log_term  1
-last_log_idx    101
-last_log_term   1
-last_committed_log_idx  100
-leader_committed_log_idx    101
-target_committed_log_idx    101
-last_snapshot_idx   50
-```
-
-- `rqld`: Request to become new leader. Return `Sent leadership request to leader.` if request sent or `Failed to send leadership request to leader.` if request not sent. Note that if node is already leader the outcome is same as the request is sent. 
-
-```
-Sent leadership request to leader.
-```
-
-## Migration from ZooKeeper {#migration-from-zookeeper}
-
-Seamlessly migration from ZooKeeper to ClickHouse Keeper is impossible you have to stop your ZooKeeper cluster, convert data and start ClickHouse Keeper. `clickhouse-keeper-converter` tool allows converting ZooKeeper logs and snapshots to ClickHouse Keeper snapshot. It works only with ZooKeeper > 3.4. Steps for migration:
-
-1. Stop all ZooKeeper nodes.
-
-2. Optional, but recommended: find ZooKeeper leader node, start and stop it again. It will force ZooKeeper to create a consistent snapshot.
-
-3. Run `clickhouse-keeper-converter` on a leader, for example:
-
-```bash
-clickhouse-keeper-converter --zookeeper-logs-dir /var/lib/zookeeper/version-2 --zookeeper-snapshots-dir /var/lib/zookeeper/version-2 --output-dir /path/to/clickhouse/keeper/snapshots
-```
-
-4. Copy snapshot to ClickHouse server nodes with a configured `keeper` or start ClickHouse Keeper instead of ZooKeeper. The snapshot must persist on all nodes, otherwise, empty nodes can be faster and one of them can become a leader.
-
-
-
-## Recovering after losing quorum
-
-Because ClickHouse Keeper uses Raft it can tolerate certain amount of node crashes depending on the cluster size. \
-E.g. for a 3-node cluster, it will continue working correctly if only 1 node crashes.
-
-Cluster configuration can be dynamically configured but there are some limitations. Reconfiguration relies on Raft also
-so to add/remove a node from the cluster you need to have a quorum. If you lose too many nodes in your cluster at the same time without any chance
-of starting them again, Raft will stop working and not allow you to reconfigure your cluster using the conventional way.
-
-Nevertheless, ClickHouse Keeper has a recovery mode which allows you to forcefully reconfigure your cluster with only 1 node.
-This should be done only as your last resort if you cannot start your nodes again, or start a new instance on the same endpoint.
-
-Important things to note before continuing:
-- Make sure that the failed nodes cannot connect to the cluster again.
-- Do not start any of the new nodes until it's specified in the steps.
-
-After making sure that the above things are true, you need to do following:
-1. Pick a single Keeper node to be your new leader. Be aware that the data of that node will be used for the entire cluster so we recommend to use a node with the most up to date state.
-2. Before doing anything else, make a backup of the `log_storage_path` and `snapshot_storage_path` folders of the picked node.
-3. Reconfigure the cluster on all of the nodes you want to use.
-4. Send the four letter command `rcvr` to the node you picked which will move the node to the recovery mode OR stop Keeper instance on the picked node and start it again with the `--force-recovery` argument.
-5. One by one, start Keeper instances on the new nodes making sure that `mntr` returns `follower` for the `zk_server_state` before starting the next one.
-6. While in the recovery mode, the leader node will return error message for `mntr` command until it achieves quorum with the new nodes and refuse any requests from the client and the followers.
-7. After quorum is achieved, the leader node will return to the normal mode of operation, accepting all the requests using Raft - verify with `mntr` which should return `leader` for the `zk_server_state`.

docs/en/operations/external-authenticators/kerberos.md

@@ -113,7 +113,7 @@ Note, that now, once user `my_user` uses `kerberos`, Kerberos must be enabled in
 
 ### Enabling Kerberos using SQL {#enabling-kerberos-using-sql}
 
-When [SQL-driven Access Control and Account Management](../access-rights.md#access-control) is enabled in ClickHouse, users identified by Kerberos can also be created using SQL statements.
+When [SQL-driven Access Control and Account Management](/docs/en/guides/sre/user-management/index.md#access-control) is enabled in ClickHouse, users identified by Kerberos can also be created using SQL statements.
 
 ```sql
 CREATE USER my_user IDENTIFIED WITH kerberos REALM 'EXAMPLE.COM'

docs/en/operations/external-authenticators/ldap.md

@@ -112,7 +112,7 @@ At each login attempt, ClickHouse tries to "bind" to the specified DN defined by
 
 Note, that user `my_user` refers to `my_ldap_server`. This LDAP server must be configured in the main `config.xml` file as described previously.
 
-When SQL-driven [Access Control and Account Management](../access-rights.md#access-control) is enabled, users that are authenticated by LDAP servers can also be created using the [CREATE USER](../../sql-reference/statements/create/user.md#create-user-statement) statement.
+When SQL-driven [Access Control and Account Management](/docs/en/guides/sre/user-management/index.md#access-control) is enabled, users that are authenticated by LDAP servers can also be created using the [CREATE USER](/docs/en/sql-reference/statements/create/user.md#create-user-statement) statement.
 
 Query:
 
@@ -124,7 +124,7 @@ CREATE USER my_user IDENTIFIED WITH ldap SERVER 'my_ldap_server';
 
 In addition to the locally defined users, a remote LDAP server can be used as a source of user definitions. To achieve this, specify previously defined LDAP server name (see [LDAP Server Definition](#ldap-server-definition)) in the `ldap` section inside the `users_directories` section of the `config.xml` file.
 
-At each login attempt, ClickHouse tries to find the user definition locally and authenticate it as usual. If the user is not defined, ClickHouse will assume the definition exists in the external LDAP directory and will try to "bind" to the specified DN at the LDAP server using the provided credentials. If successful, the user will be considered existing and authenticated. The user will be assigned roles from the list specified in the `roles` section. Additionally, LDAP "search" can be performed and results can be transformed and treated as role names and then be assigned to the user if the `role_mapping` section is also configured. All this implies that the SQL-driven [Access Control and Account Management](../access-rights.md#access-control) is enabled and roles are created using the [CREATE ROLE](../../sql-reference/statements/create/role.md#create-role-statement) statement.
+At each login attempt, ClickHouse tries to find the user definition locally and authenticate it as usual. If the user is not defined, ClickHouse will assume the definition exists in the external LDAP directory and will try to "bind" to the specified DN at the LDAP server using the provided credentials. If successful, the user will be considered existing and authenticated. The user will be assigned roles from the list specified in the `roles` section. Additionally, LDAP "search" can be performed and results can be transformed and treated as role names and then be assigned to the user if the `role_mapping` section is also configured. All this implies that the SQL-driven [Access Control and Account Management](/docs/en/guides/sre/user-management/index.md#access-control) is enabled and roles are created using the [CREATE ROLE](/docs/en/sql-reference/statements/create/role.md#create-role-statement) statement.
 
 **Example**
 
@@ -173,7 +173,7 @@ Note that `my_ldap_server` referred in the `ldap` section inside the `user_direc
 - `roles` — Section with a list of locally defined roles that will be assigned to each user retrieved from the LDAP server.
     - If no roles are specified here or assigned during role mapping (below), user will not be able to perform any actions after authentication.
 - `role_mapping` — Section with LDAP search parameters and mapping rules.
-    - When a user authenticates, while still bound to LDAP, an LDAP search is performed using `search_filter` and the name of the logged-in user. For each entry found during that search, the value of the specified attribute is extracted. For each attribute value that has the specified prefix, the prefix is removed, and the rest of the value becomes the name of a local role defined in ClickHouse, which is expected to be created beforehand by the [CREATE ROLE](../../sql-reference/statements/create/role.md#create-role-statement) statement.
+    - When a user authenticates, while still bound to LDAP, an LDAP search is performed using `search_filter` and the name of the logged-in user. For each entry found during that search, the value of the specified attribute is extracted. For each attribute value that has the specified prefix, the prefix is removed, and the rest of the value becomes the name of a local role defined in ClickHouse, which is expected to be created beforehand by the [CREATE ROLE](/docs/en/sql-reference/statements/create/role.md#create-role-statement) statement.
     - There can be multiple `role_mapping` sections defined inside the same `ldap` section. All of them will be applied.
         - `base_dn` — Template used to construct the base DN for the LDAP search.
             - The resulting DN will be constructed by replacing all `{user_name}`, `{bind_dn}`, and `{user_dn}` substrings of the template with the actual user name, bind DN, and user DN during each LDAP search.

docs/en/operations/monitoring.md

@@ -2,6 +2,7 @@
 slug: /en/operations/monitoring
 sidebar_position: 45
 sidebar_label: Monitoring
+description: You can monitor the utilization of hardware resources and also ClickHouse server metrics.
 ---
 
 # Monitoring

docs/en/operations/server-configuration-parameters/settings.md

@@ -2,6 +2,7 @@
 slug: /en/operations/server-configuration-parameters/settings
 sidebar_position: 57
 sidebar_label: Server Settings
+description: This section contains descriptions of server settings that cannot be changed at the session or query level.
 ---
 
 # Server Settings
@@ -275,7 +276,7 @@ Path:
 -   Specify the absolute path or the path relative to the server config file.
 -   The path can contain wildcards \* and ?.
 
-See also “[Dictionaries](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md)”.
+See also “[Dictionaries](../../sql-reference/dictionaries/index.md)”.
 
 **Example**
 
@@ -765,7 +766,7 @@ Default value: `0`.
 
 ## concurrent_threads_soft_limit_ratio_to_cores {#concurrent_threads_soft_limit_ratio_to_cores}
 The maximum number of query processing threads as multiple of number of logical cores.
-More details: [concurrent_threads_soft_limit_num](#concurrent-threads-soft-limit-num).
+More details: [concurrent_threads_soft_limit_num](#concurrent_threads_soft_limit_num).
 
 Possible values:
 
@@ -967,6 +968,7 @@ The maximum number of jobs that can be scheduled on the Global Thread pool. Incr
 Possible values:
 
 -   Positive integer.
+-   0 — No limit.
 
 Default value: `10000`.
 
@@ -976,6 +978,69 @@ Default value: `10000`.
 <thread_pool_queue_size>12000</thread_pool_queue_size>
 ```
 
+## max_io_thread_pool_size {#max-io-thread-pool-size}
+
+ClickHouse uses threads from the IO Thread pool to do some IO operations (e.g. to interact with S3). `max_io_thread_pool_size` limits the maximum number of threads in the pool.
+
+Possible values:
+
+-   Positive integer.
+
+Default value: `100`.
+
+## max_io_thread_pool_free_size {#max-io-thread-pool-free-size}
+
+If the number of **idle** threads in the IO Thread pool exceeds `max_io_thread_pool_free_size`, ClickHouse will release resources occupied by idling threads and decrease the pool size. Threads can be created again if necessary.
+
+Possible values:
+
+-   Positive integer.
+
+Default value: `0`.
+
+## io_thread_pool_queue_size {#io-thread-pool-queue-size}
+
+The maximum number of jobs that can be scheduled on the IO Thread pool.
+
+Possible values:
+
+-   Positive integer.
+-   0 — No limit.
+
+Default value: `10000`.
+
+## max_backups_io_thread_pool_size {#max-backups-io-thread-pool-size}
+
+ClickHouse uses threads from the Backups IO Thread pool to do S3 backup IO operations. `max_backups_io_thread_pool_size` limits the maximum number of threads in the pool.
+
+Possible values:
+
+-   Positive integer.
+
+Default value: `1000`.
+
+## max_backups_io_thread_pool_free_size {#max-backups-io-thread-pool-free-size}
+
+If the number of **idle** threads in the Backups IO Thread pool exceeds `max_backup_io_thread_pool_free_size`, ClickHouse will release resources occupied by idling threads and decrease the pool size. Threads can be created again if necessary.
+
+Possible values:
+
+-   Positive integer.
+-   Zero.
+
+Default value: `0`.
+
+## backups_io_thread_pool_queue_size {#backups-io-thread-pool-queue-size}
+
+The maximum number of jobs that can be scheduled on the Backups IO Thread pool. It is recommended to keep this queue unlimited due to the current S3 backup logic.
+
+Possible values:
+
+-   Positive integer.
+-   0 — No limit.
+
+Default value: `0`.
+
 ## background_pool_size {#background_pool_size}
 
 Sets the number of threads performing background merges and mutations for tables with MergeTree engines. This setting is also could be applied  at server startup from the `default` profile configuration for backward compatibility at the ClickHouse server start. You can only increase the number of threads at runtime. To lower the number of threads you have to restart the server. By adjusting this setting, you manage CPU and disk load. Smaller pool size utilizes less CPU and disk resources, but background processes advance slower which might eventually impact query performance.
@@ -1254,12 +1319,12 @@ Settings:
 
 ``` xml
  <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>8001</port>
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-    </prometheus>
+    <endpoint>/metrics</endpoint>
+    <port>9363</port>
+    <metrics>true</metrics>
+    <events>true</events>
+    <asynchronous_metrics>true</asynchronous_metrics>
+</prometheus>
 ```
 
 ## query_log {#server_configuration_parameters-query-log}
@@ -1853,7 +1918,7 @@ Default value: `/var/lib/clickhouse/access/`.
 
 **See also**
 
-- [Access Control and Account Management](../../operations/access-rights.md#access-control)
+- [Access Control and Account Management](../../guides/sre/user-management/index.md#access-control)
 
 ## user_directories {#user_directories}
 

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

@@ -1014,6 +1014,12 @@ Use Arrow FIXED_SIZE_BINARY type instead of Binary/String for FixedString column
 
 Enabled by default.
 
+### output_format_arrow_compression_method {#output_format_arrow_compression_method}
+
+Compression method used in output Arrow format. Supported codecs: `lz4_frame`, `zstd`, `none` (uncompressed)
+
+Default value: `none`.
+
 ## ORC format settings {#orc-format-settings}
 
 ### input_format_orc_import_nested {#input_format_orc_import_nested}
@@ -1057,6 +1063,12 @@ Use ORC String type instead of Binary for String columns.
 
 Disabled by default.
 
+### output_format_orc_compression_method {#output_format_orc_compression_method}
+
+Compression method used in output ORC format. Supported codecs: `lz4`, `snappy`, `zlib`, `zstd`, `none` (uncompressed)
+
+Default value: `none`.
+
 ## Parquet format settings {#parquet-format-settings}
 
 ### input_format_parquet_import_nested {#input_format_parquet_import_nested}
@@ -1112,6 +1124,12 @@ The version of Parquet format used in output format. Supported versions: `1.0`,
 
 Default value: `2.latest`.
 
+### output_format_parquet_compression_method {#output_format_parquet_compression_method}
+
+Compression method used in output Parquet format. Supported codecs: `snappy`, `lz4`, `brotli`, `zstd`, `gzip`, `none` (uncompressed)
+
+Default value: `snappy`.
+
 ## Hive format settings {#hive-format-settings}
 
 ### input_format_hive_text_fields_delimiter {#input_format_hive_text_fields_delimiter}
@@ -1474,7 +1492,7 @@ Default value: `65505`.
 
 The name of table that will be used in the output INSERT statement.
 
-Default value: `'table''`.
+Default value: `table`.
 
 ### output_format_sql_insert_include_column_names {#output_format_sql_insert_include_column_names}
 
@@ -1514,4 +1532,12 @@ Disabled by default.
 
 The maximum allowed size for String in RowBinary format. It prevents allocating large amount of memory in case of corrupted data. 0 means there is no limit.
 
-Default value: `1GiB`
+Default value: `1GiB`.
+
+## Native format settings {#native-format-settings}
+
+### input_format_native_allow_types_conversion {#input_format_native_allow_types_conversion}
+
+Allow types conversion in Native input format between columns from input data and requested columns. 
+
+Enabled by default.

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

@@ -9,7 +9,7 @@ sidebar_label: Settings Profiles
 A settings profile is a collection of settings grouped under the same name.
 
 :::note
-ClickHouse also supports [SQL-driven workflow](../../operations/access-rights.md#access-control) for managing settings profiles. We recommend using it.
+ClickHouse also supports [SQL-driven workflow](../../guides/sre/user-management/index.md#access-control) for managing settings profiles. We recommend using it.
 :::
 
 The profile can have any name. You can specify the same profile for different users. The most important thing you can write in the settings profile is `readonly=1`, which ensures read-only access.

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

@@ -9,7 +9,7 @@ sidebar_label: User Settings
 The `users` section of the `user.xml` configuration file contains user settings.
 
 :::note
-ClickHouse also supports [SQL-driven workflow](../../operations/access-rights.md#access-control) for managing users. We recommend using it.
+ClickHouse also supports [SQL-driven workflow](../../guides/sre/user-management/index.md#access-control) for managing users. We recommend using it.
 :::
 
 Structure of the `users` section:
@@ -77,7 +77,7 @@ Password can be specified in plaintext or in SHA256 (hex format).
 
 ### access_management {#access_management-user-setting}
 
-This setting enables or disables using of SQL-driven [access control and account management](../../operations/access-rights.md#access-control) for the user.
+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.
 
 Possible values:
 

docs/en/operations/settings/settings.md

@@ -966,10 +966,10 @@ This is an expert-level setting, and you shouldn't change it if you're just gett
 
 ## max_query_size {#settings-max_query_size}
 
-The maximum part of a query that can be taken to RAM for parsing with the SQL parser.
-The INSERT query also contains data for INSERT that is processed by a separate stream parser (that consumes O(1) RAM), which is not included in this restriction.
+The maximum number of bytes of a query string parsed by the SQL parser.
+Data in the VALUES clause of INSERT queries is processed by a separate stream parser (that consumes O(1) RAM) and not affected by this restriction.
 
-Default value: 256 KiB.
+Default value: 262144 (= 256 KiB).
 
 ## max_parser_depth {#max_parser_depth}
 
@@ -1248,7 +1248,9 @@ Possible values:
 Default value: 1.
 
 :::warning
-Disable this setting if you use [max_parallel_replicas](#settings-max_parallel_replicas).
+Disable this setting if you use [max_parallel_replicas](#settings-max_parallel_replicas) without [parallel_replicas_custom_key](#settings-parallel_replicas_custom_key).
+If [parallel_replicas_custom_key](#settings-parallel_replicas_custom_key) is set, disable this setting only if it's used on a cluster with multiple shards containing multiple replicas.
+If it's used on a cluster with a single shard and multiple replicas, disabling this setting will have negative effects.
 :::
 
 ## totals_mode {#totals-mode}
@@ -1273,16 +1275,47 @@ Default value: `1`.
 
 **Additional Info**
 
-This setting is useful for replicated tables with a sampling key. A query may be processed faster if it is executed on several servers in parallel. But the query performance may degrade in the following cases:
+This options will produce different results depending on the settings used.
+
+:::warning
+This setting will produce incorrect results when joins or subqueries are involved, and all tables don't meet certain requirements. See [Distributed Subqueries and max_parallel_replicas](../../sql-reference/operators/in.md/#max_parallel_replica-subqueries) for more details.
+:::
+
+### Parallel processing using `SAMPLE` key
+
+A query may be processed faster if it is executed on several servers in parallel. But the query performance may degrade in the following cases:
 
 - The position of the sampling key in the partitioning key does not allow efficient range scans.
 - Adding a sampling key to the table makes filtering by other columns less efficient.
 - The sampling key is an expression that is expensive to calculate.
 - The cluster latency distribution has a long tail, so that querying more servers increases the query overall latency.
 
-:::warning
-This setting will produce incorrect results when joins or subqueries are involved, and all tables don't meet certain requirements. See [Distributed Subqueries and max_parallel_replicas](../../sql-reference/operators/in.md/#max_parallel_replica-subqueries) for more details.
-:::
+### Parallel processing using [parallel_replicas_custom_key](#settings-parallel_replicas_custom_key)
+
+This setting is useful for any replicated table.
+
+## parallel_replicas_custom_key {#settings-parallel_replicas_custom_key}
+
+An arbitrary integer expression that can be used to split work between replicas for a specific table.
+The value can be any integer expression.
+A query may be processed faster if it is executed on several servers in parallel but it depends on the used [parallel_replicas_custom_key](#settings-parallel_replicas_custom_key)
+and [parallel_replicas_custom_key_filter_type](#settings-parallel_replicas_custom_key_filter_type).
+
+Simple expressions using primary keys are preferred.
+
+If the setting is used on a cluster that consists of a single shard with multiple replicas, those replicas will be converted into virtual shards.
+Otherwise, it will behave same as for `SAMPLE` key, it will use multiple replicas of each shard.
+
+## parallel_replicas_custom_key_filter_type {#settings-parallel_replicas_custom_key_filter_type}
+
+How to use `parallel_replicas_custom_key` expression for splitting work between replicas.
+
+Possible values:
+
+-   `default` — Use the default implementation using modulo operation on the `parallel_replicas_custom_key`.
+-   `range` — Split the entire value space of the expression in the ranges. This type of filtering is useful if values of `parallel_replicas_custom_key` are uniformly spread across the entire integer space, e.g. hash values.
+
+Default value: `default`.
 
 ## compile_expressions {#compile-expressions}
 
@@ -1515,7 +1548,7 @@ Enables or disables asynchronous inserts. This makes sense only for insertion ov
 
 If enabled, the data is combined into batches before the insertion into tables, so it is possible to do small and frequent insertions into ClickHouse (up to 15000 queries per second) without buffer tables.
 
-The data is inserted either after the [async_insert_max_data_size](#async-insert-max-data-size) is exceeded or after [async_insert_busy_timeout_ms](#async-insert-busy-timeout-ms) milliseconds since the first `INSERT` query. If the [async_insert_stale_timeout_ms](#async-insert-stale-timeout-ms) is set to a non-zero value, the data is inserted after `async_insert_stale_timeout_ms` milliseconds since the last query.
+The data is inserted either after the [async_insert_max_data_size](#async-insert-max-data-size) is exceeded or after [async_insert_busy_timeout_ms](#async-insert-busy-timeout-ms) milliseconds since the first `INSERT` query. If the [async_insert_stale_timeout_ms](#async-insert-stale-timeout-ms) is set to a non-zero value, the data is inserted after `async_insert_stale_timeout_ms` milliseconds since the last query. Also the buffer will be flushed to disk if at least [async_insert_max_query_number](#async-insert-max-query-number) async insert queries per block were received. This last setting takes effect only if [async_insert_deduplicate](#async-insert-deduplicate) is enabled.
 
 If [wait_for_async_insert](#wait-for-async-insert) is enabled, every client will wait for the data to be processed and flushed to the table. Otherwise, the query would be processed almost instantly, even if the data is not inserted.
 
@@ -2966,7 +2999,7 @@ It can be useful when merges are CPU bounded not IO bounded (performing heavy da
 
 ## max_final_threads {#max-final-threads}
 
-Sets the maximum number of parallel threads for the `SELECT` query data read phase with the [FINAL](../../sql-reference/statements/select/from.md/#select-from-final) modifier.
+Sets the maximum number of parallel threads for the `SELECT` query data read phase with the [FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier.
 
 Possible values:
 
@@ -3061,9 +3094,9 @@ Possible values:
 
 Default value: `0`.
 
-## s3_truncate_on_insert 
+## s3_truncate_on_insert
 
-Enables or disables truncate before inserts in s3 engine tables. If disabled, an exception will be thrown on insert attempts if an S3 object already exists. 
+Enables or disables truncate before inserts in s3 engine tables. If disabled, an exception will be thrown on insert attempts if an S3 object already exists.
 
 Possible values:
 - 0 — `INSERT` query appends new data to the end of the file.
@@ -3071,9 +3104,9 @@ Possible values:
 
 Default value: `0`.
 
-## hdfs_truncate_on_insert 
+## hdfs_truncate_on_insert
 
-Enables or disables truncation before an insert in hdfs engine tables. If disabled, an exception will be thrown on an attempt to insert if a file in HDFS already exists. 
+Enables or disables truncation before an insert in hdfs engine tables. If disabled, an exception will be thrown on an attempt to insert if a file in HDFS already exists.
 
 Possible values:
 - 0 — `INSERT` query appends new data to the end of the file.
@@ -3081,11 +3114,11 @@ Possible values:
 
 Default value: `0`.
 
-## engine_file_allow_create_multiple_files 
+## engine_file_allow_create_multiple_files
 
 Enables or disables creating a new file on each insert in file engine tables if the format has the suffix (`JSON`, `ORC`, `Parquet`, etc.). If enabled, on each insert a new file will be created with a name following this pattern:
 
-`data.Parquet` -> `data.1.Parquet` -> `data.2.Parquet`, etc. 
+`data.Parquet` -> `data.1.Parquet` -> `data.2.Parquet`, etc.
 
 Possible values:
 - 0 — `INSERT` query appends new data to the end of the file.
@@ -3093,11 +3126,11 @@ Possible values:
 
 Default value: `0`.
 
-## s3_create_new_file_on_insert 
+## s3_create_new_file_on_insert
 
 Enables or disables creating a new file on each insert in s3 engine tables. If enabled, on each insert a new S3 object will be created with the key, similar to this pattern:
 
-initial: `data.Parquet.gz` -> `data.1.Parquet.gz` -> `data.2.Parquet.gz`, etc. 
+initial: `data.Parquet.gz` -> `data.1.Parquet.gz` -> `data.2.Parquet.gz`, etc.
 
 Possible values:
 - 0 — `INSERT` query appends new data to the end of the file.
@@ -3109,7 +3142,7 @@ Default value: `0`.
 
 Enables or disables creating a new file on each insert in HDFS engine tables. If enabled, on each insert a new HDFS file will be created with the name, similar to this pattern:
 
-initial: `data.Parquet.gz` -> `data.1.Parquet.gz` -> `data.2.Parquet.gz`, etc. 
+initial: `data.Parquet.gz` -> `data.1.Parquet.gz` -> `data.2.Parquet.gz`, etc.
 
 Possible values:
 - 0 — `INSERT` query appends new data to the end of the file.
@@ -3720,7 +3753,7 @@ Default value: `1`.
 
 ## optimize_move_to_prewhere_if_final {#optimize_move_to_prewhere_if_final}
 
-Enables or disables automatic [PREWHERE](../../sql-reference/statements/select/prewhere.md) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries with [FINAL](../../sql-reference/statements/select/from.md/#select-from-final) modifier.
+Enables or disables automatic [PREWHERE](../../sql-reference/statements/select/prewhere.md) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries with [FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier.
 
 Works only for [*MergeTree](../../engines/table-engines/mergetree-family/index.md) tables.
 
@@ -3737,7 +3770,7 @@ Default value: `0`.
 
 ## optimize_using_constraints
 
-Use [constraints](../../sql-reference/statements/create/table#constraints) for query optimization. The default is `false`.
+Use [constraints](../../sql-reference/statements/create/table.md#constraints) for query optimization. The default is `false`.
 
 Possible values:
 
@@ -3745,7 +3778,7 @@ Possible values:
 
 ## optimize_append_index
 
-Use [constraints](../../sql-reference/statements/create/table#constraints) in order to append index condition. The default is `false`.
+Use [constraints](../../sql-reference/statements/create/table.md#constraints) in order to append index condition. The default is `false`.
 
 Possible values:
 
@@ -3753,7 +3786,7 @@ Possible values:
 
 ## optimize_substitute_columns
 
-Use [constraints](../../sql-reference/statements/create/table#constraints) for column substitution. The default is `false`.
+Use [constraints](../../sql-reference/statements/create/table.md#constraints) for column substitution. The default is `false`.
 
 Possible values:
 
@@ -3951,7 +3984,7 @@ Use this setting only for backward compatibility if your use cases depend on old
 
 ## final {#final}
 
-Automatically applies [FINAL](../../sql-reference/statements/select/from/#final-modifier) modifier to all tables in a query, to tables where [FINAL](../../sql-reference/statements/select/from/#final-modifier) is applicable, including joined tables and tables in sub-queries, and 
+Automatically applies [FINAL](../../sql-reference/statements/select/from.md#final-modifier) modifier to all tables in a query, to tables where [FINAL](../../sql-reference/statements/select/from.md#final-modifier) is applicable, including joined tables and tables in sub-queries, and
 distributed tables.
 
 Possible values:
@@ -3997,7 +4030,7 @@ SELECT * FROM test;
 
 ## asterisk_include_materialized_columns {#asterisk_include_materialized_columns}
 
-Include [MATERIALIZED](../../sql-reference/statements/create/table/#materialized) columns for wildcard query (`SELECT *`).
+Include [MATERIALIZED](../../sql-reference/statements/create/table.md#materialized) columns for wildcard query (`SELECT *`).
 
 Possible values:
 
@@ -4008,7 +4041,7 @@ Default value: `0`.
 
 ## asterisk_include_alias_columns {#asterisk_include_alias_columns}
 
-Include [ALIAS](../../sql-reference/statements/create/table/#alias) columns for wildcard query (`SELECT *`).
+Include [ALIAS](../../sql-reference/statements/create/table.md#alias) columns for wildcard query (`SELECT *`).
 
 Possible values:
 

docs/en/operations/storing-data.md

@@ -80,7 +80,7 @@ Required parameters:
 
 -   `type` — `encrypted`. Otherwise the encrypted disk is not created.
 -   `disk` — Type of disk for data storage.
--   `key` — The key for encryption and decryption. Type: [Uint64](/docs/en/sql-reference/data-types/int-uint.md). You can use `key_hex` parameter to encrypt in hexadecimal form.
+-   `key` — The key for encryption and decryption. Type: [Uint64](/docs/en/sql-reference/data-types/int-uint.md). You can use `key_hex` parameter to encode the key in hexadecimal form.
     You can specify multiple keys using the `id` attribute (see example above).
 
 Optional parameters:
@@ -135,11 +135,13 @@ Example of configuration for versions later or equal to 22.8:
             </cache>
         </disks>
         <policies>
-            <volumes>
-                <main>
-                    <disk>cache</disk>
-                </main>
-            </volumes>
+            <s3-cache>
+                <volumes>
+                    <main>
+                        <disk>cache</disk>
+                    </main>
+                </volumes>
+            </s3-cache>
         <policies>
     </storage_configuration>
 ```
@@ -159,11 +161,13 @@ Example of configuration for versions earlier than 22.8:
             </s3>
         </disks>
         <policies>
-            <volumes>
-                <main>
-                    <disk>s3</disk>
-                </main>
-            </volumes>
+            <s3-cache>
+                <volumes>
+                    <main>
+                        <disk>s3</disk>
+                    </main>
+                </volumes>
+            </s3-cache>
         <policies>
     </storage_configuration>
 ```

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

@@ -3,12 +3,12 @@ slug: /en/operations/system-tables/dictionaries
 ---
 # dictionaries
 
-Contains information about [dictionaries](../../sql-reference/dictionaries/external-dictionaries/external-dicts.md).
+Contains information about [dictionaries](../../sql-reference/dictionaries/index.md).
 
 Columns:
 
 -   `database` ([String](../../sql-reference/data-types/string.md)) — Name of the database containing the dictionary created by DDL query. Empty string for other dictionaries.
--   `name` ([String](../../sql-reference/data-types/string.md)) — [Dictionary name](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict.md).
+-   `name` ([String](../../sql-reference/data-types/string.md)) — [Dictionary name](../../sql-reference/dictionaries/index.md).
 -   `uuid` ([UUID](../../sql-reference/data-types/uuid.md)) — Dictionary UUID.
 -   `status` ([Enum8](../../sql-reference/data-types/enum.md)) — Dictionary status. Possible values:
     -   `NOT_LOADED` — Dictionary was not loaded because it was not used.
@@ -18,20 +18,20 @@ Columns:
     -   `LOADED_AND_RELOADING` — Dictionary is loaded successfully, and is being reloaded right now (frequent reasons: [SYSTEM RELOAD DICTIONARY](../../sql-reference/statements/system.md#query_language-system-reload-dictionary) query, timeout, dictionary config has changed).
     -   `FAILED_AND_RELOADING` — Could not load the dictionary as a result of an error and is loading now.
 -   `origin` ([String](../../sql-reference/data-types/string.md)) — Path to the configuration file that describes the dictionary.
--   `type` ([String](../../sql-reference/data-types/string.md)) — Type of a dictionary allocation. [Storing Dictionaries in Memory](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-layout.md).
--   `key.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of [key names](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-key) provided by the dictionary.
--   `key.types` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Corresponding array of [key types](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-key) provided by the dictionary.
--   `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of [attribute names](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-attributes) provided by the dictionary.
--   `attribute.types` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Corresponding array of [attribute types](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-structure.md#ext_dict_structure-attributes) provided by the dictionary.
+-   `type` ([String](../../sql-reference/data-types/string.md)) — Type of a dictionary allocation. [Storing Dictionaries in Memory](../../sql-reference/dictionaries/index.md#storig-dictionaries-in-memory).
+-   `key.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of [key names](../../sql-reference/dictionaries/index.md#dictionary-key-and-fields#ext_dict_structure-key) provided by the dictionary.
+-   `key.types` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Corresponding array of [key types](../../sql-reference/dictionaries/index.md#dictionary-key-and-fields#ext_dict_structure-key) provided by the dictionary.
+-   `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of [attribute names](../../sql-reference/dictionaries/index.md#dictionary-key-and-fields#ext_dict_structure-attributes) provided by the dictionary.
+-   `attribute.types` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Corresponding array of [attribute types](../../sql-reference/dictionaries/index.md#dictionary-key-and-fields#ext_dict_structure-attributes) provided by the dictionary.
 -   `bytes_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Amount of RAM allocated for the dictionary.
 -   `query_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of queries since the dictionary was loaded or since the last successful reboot.
 -   `hit_rate` ([Float64](../../sql-reference/data-types/float.md)) — For cache dictionaries, the percentage of uses for which the value was in the cache.
 -   `found_rate` ([Float64](../../sql-reference/data-types/float.md)) — The percentage of uses for which the value was found.
 -   `element_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of items stored in the dictionary.
 -   `load_factor` ([Float64](../../sql-reference/data-types/float.md)) — Percentage filled in the dictionary (for a hashed dictionary, the percentage filled in the hash table).
--   `source` ([String](../../sql-reference/data-types/string.md)) — Text describing the [data source](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md) for the dictionary.
--   `lifetime_min` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Minimum [lifetime](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-lifetime.md) of the dictionary in memory, after which ClickHouse tries to reload the dictionary (if `invalidate_query` is set, then only if it has changed). Set in seconds.
--   `lifetime_max` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Maximum [lifetime](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-lifetime.md) of the dictionary in memory, after which ClickHouse tries to reload the dictionary (if `invalidate_query` is set, then only if it has changed). Set in seconds.
+-   `source` ([String](../../sql-reference/data-types/string.md)) — Text describing the [data source](../../sql-reference/dictionaries/index.md#dictionary-sources) for the dictionary.
+-   `lifetime_min` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Minimum [lifetime](../../sql-reference/dictionaries/index.md#dictionary-updates) of the dictionary in memory, after which ClickHouse tries to reload the dictionary (if `invalidate_query` is set, then only if it has changed). Set in seconds.
+-   `lifetime_max` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Maximum [lifetime](../../sql-reference/dictionaries/index.md#dictionary-updates) of the dictionary in memory, after which ClickHouse tries to reload the dictionary (if `invalidate_query` is set, then only if it has changed). Set in seconds.
 -   `loading_start_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Start time for loading the dictionary.
 -   `last_successful_update_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — End time for loading or updating the dictionary. Helps to monitor some troubles with dictionary sources and investigate the causes.
 -   `loading_duration` ([Float32](../../sql-reference/data-types/float.md)) — Duration of a dictionary loading.

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

@@ -15,6 +15,13 @@ Columns:
 
 -   `operation_name` ([String](../../sql-reference/data-types/string.md)) — The name of the operation.
 
+-   `kind` ([Enum8](../../sql-reference/data-types/enum.md)) — The [SpanKind](https://opentelemetry.io/docs/reference/specification/trace/api/#spankind) of the span.
+    -   `INTERNAL` — Indicates that the span represents an internal operation within an application.
+    -   `SERVER` — Indicates that the span covers server-side handling of a synchronous RPC or other remote request.
+    -   `CLIENT` — Indicates that the span describes a request to some remote service.
+    -   `PRODUCER` — Indicates that the span describes the initiators of an asynchronous request. This parent span will often end before the corresponding child CONSUMER span, possibly even before the child span starts.
+    -   `CONSUMER` - Indicates that the span describes a child of an asynchronous PRODUCER request.
+
 -   `start_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The start time of the `trace span` (in microseconds).
 
 -   `finish_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The finish time of the `trace span` (in microseconds).
@@ -42,6 +49,7 @@ trace_id:         cdab0847-0d62-61d5-4d38-dd65b19a1914
 span_id:          701487461015578150
 parent_span_id:   2991972114672045096
 operation_name:   DB::Block DB::InterpreterSelectQuery::getSampleBlockImpl()
+kind:             INTERNAL
 start_time_us:    1612374594529090
 finish_time_us:   1612374594529108
 finish_date:      2021-02-03

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

@@ -20,7 +20,7 @@ Columns:
 - `apply_to_all` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Logical value. It shows which users the quota is applied to. Values:
     - `0` — The quota applies to users specify in the `apply_to_list`.
     - `1` — The quota applies to all users except those listed in `apply_to_except`.
-- `apply_to_list` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — List of user names/[roles](../../operations/access-rights.md#role-management) that the quota should be applied to.
+- `apply_to_list` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — List of user names/[roles](../../guides/sre/user-management/index.md#role-management) that the quota should be applied to.
 - `apply_to_except` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — List of user names/roles that the quota should not apply to.
 
 ## See Also {#see-also}