Merged with master

2024-11-22 15:42:02 +00:00 · 2022-06-04 17:22:22 +00:00 · 2022-06-04 17:22:22 +00:00 · 0246a3f415
commit 0246a3f415
parent 2232d47c5a 295f0a0557
1267 changed files with 13229 additions and 8627 deletions
--- a/.clang-tidy
+++ b/.clang-tidy
@ -62,6 +62,7 @@ Checks: '*,

    -google-build-using-namespace,
    -google-readability-braces-around-statements,
+    -google-readability-casting,
    -google-readability-function-size,
    -google-readability-namespace-comments,
    -google-readability-todo,
--- a/.github/workflows/master.yml
+++ b/.github/workflows/master.yml
@ -2911,7 +2911,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=0
          RUN_BY_HASH_TOTAL=4
@ -2949,7 +2949,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=1
          RUN_BY_HASH_TOTAL=4
@ -2987,7 +2987,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=2
          RUN_BY_HASH_TOTAL=4
@ -3025,7 +3025,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=3
          RUN_BY_HASH_TOTAL=4
--- a/.github/workflows/nightly.yml
+++ b/.github/workflows/nightly.yml
@ -81,7 +81,6 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          BUILD_NAME=coverity
          CACHES_PATH=${{runner.temp}}/../ccaches
-          CHECK_NAME=ClickHouse build check (actions)
          IMAGES_PATH=${{runner.temp}}/images_path
          REPO_COPY=${{runner.temp}}/build_check/ClickHouse
          TEMP_PATH=${{runner.temp}}/build_check
@ -99,13 +98,15 @@ jobs:
        id: coverity-checkout
        uses: actions/checkout@v2
        with:
-          submodules: 'true'
+          fetch-depth: 0 # otherwise we will have no info about contributors
      - name: Build
        run: |
+          git -C "$GITHUB_WORKSPACE" submodule sync
+          git -C "$GITHUB_WORKSPACE" submodule update --depth=1 --init --jobs=10
          sudo rm -fr "$TEMP_PATH"
          mkdir -p "$TEMP_PATH"
          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 build_check.py "$CHECK_NAME" "$BUILD_NAME"
+          cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
      - name: Upload Coverity Analysis
        if: ${{ success() || failure() }}
        run: |
--- a/.github/workflows/pull_request.yml
+++ b/.github/workflows/pull_request.yml
@ -3127,7 +3127,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=0
          RUN_BY_HASH_TOTAL=4
@ -3165,7 +3165,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=1
          RUN_BY_HASH_TOTAL=4
@ -3203,7 +3203,7 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=2
          RUN_BY_HASH_TOTAL=4
@ -3241,7 +3241,159 @@ jobs:
          cat >> "$GITHUB_ENV" << 'EOF'
          TEMP_PATH=${{runner.temp}}/performance_comparison
          REPORTS_PATH=${{runner.temp}}/reports_dir
-          CHECK_NAME=Performance Comparison (actions)
+          CHECK_NAME=Performance Comparison
+          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
+          RUN_BY_HASH_NUM=3
+          RUN_BY_HASH_TOTAL=4
+          EOF
+      - name: Download json reports
+        uses: actions/download-artifact@v2
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: Clear repository
+        run: |
+          sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
+      - name: Check out repository code
+        uses: actions/checkout@v2
+      - name: Performance Comparison
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci"
+          python3 performance_comparison_check.py "$CHECK_NAME"
+      - name: Cleanup
+        if: always()
+        run: |
+          # shellcheck disable=SC2046
+          docker kill $(docker ps -q) ||:
+          # shellcheck disable=SC2046
+          docker rm -f $(docker ps -a -q) ||:
+          sudo rm -fr "$TEMP_PATH"
+  PerformanceComparisonAarch0:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, func-tester-aarch64]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/performance_comparison
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          CHECK_NAME=Performance Comparison Aarch64
+          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
+          RUN_BY_HASH_NUM=0
+          RUN_BY_HASH_TOTAL=4
+          EOF
+      - name: Download json reports
+        uses: actions/download-artifact@v2
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: Clear repository
+        run: |
+          sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
+      - name: Check out repository code
+        uses: actions/checkout@v2
+      - name: Performance Comparison
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci"
+          python3 performance_comparison_check.py "$CHECK_NAME"
+      - name: Cleanup
+        if: always()
+        run: |
+          # shellcheck disable=SC2046
+          docker kill $(docker ps -q) ||:
+          # shellcheck disable=SC2046
+          docker rm -f $(docker ps -a -q) ||:
+          sudo rm -fr "$TEMP_PATH"
+  PerformanceComparisonAarch1:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, func-tester-aarch64]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/performance_comparison
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          CHECK_NAME=Performance Comparison Aarch64
+          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
+          RUN_BY_HASH_NUM=1
+          RUN_BY_HASH_TOTAL=4
+          EOF
+      - name: Download json reports
+        uses: actions/download-artifact@v2
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: Clear repository
+        run: |
+          sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
+      - name: Check out repository code
+        uses: actions/checkout@v2
+      - name: Performance Comparison
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci"
+          python3 performance_comparison_check.py "$CHECK_NAME"
+      - name: Cleanup
+        if: always()
+        run: |
+          # shellcheck disable=SC2046
+          docker kill $(docker ps -q) ||:
+          # shellcheck disable=SC2046
+          docker rm -f $(docker ps -a -q) ||:
+          sudo rm -fr "$TEMP_PATH"
+  PerformanceComparisonAarch2:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, func-tester-aarch64]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/performance_comparison
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          CHECK_NAME=Performance Comparison Aarch64
+          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
+          RUN_BY_HASH_NUM=2
+          RUN_BY_HASH_TOTAL=4
+          EOF
+      - name: Download json reports
+        uses: actions/download-artifact@v2
+        with:
+          path: ${{ env.REPORTS_PATH }}
+      - name: Clear repository
+        run: |
+          sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
+      - name: Check out repository code
+        uses: actions/checkout@v2
+      - name: Performance Comparison
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci"
+          python3 performance_comparison_check.py "$CHECK_NAME"
+      - name: Cleanup
+        if: always()
+        run: |
+          # shellcheck disable=SC2046
+          docker kill $(docker ps -q) ||:
+          # shellcheck disable=SC2046
+          docker rm -f $(docker ps -a -q) ||:
+          sudo rm -fr "$TEMP_PATH"
+  PerformanceComparisonAarch3:
+    needs: [BuilderDebAarch64]
+    runs-on: [self-hosted, func-tester-aarch64]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/performance_comparison
+          REPORTS_PATH=${{runner.temp}}/reports_dir
+          CHECK_NAME=Performance Comparison Aarch64
          REPO_COPY=${{runner.temp}}/performance_comparison/ClickHouse
          RUN_BY_HASH_NUM=3
          RUN_BY_HASH_TOTAL=4
@ -3333,6 +3485,10 @@ jobs:
      - PerformanceComparison1
      - PerformanceComparison2
      - PerformanceComparison3
+      - PerformanceComparisonAarch0
+      - PerformanceComparisonAarch1
+      - PerformanceComparisonAarch2
+      - PerformanceComparisonAarch3
      - UnitTestsAsan
      - UnitTestsTsan
      - UnitTestsMsan
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@ -36,7 +36,7 @@ set_property(GLOBAL PROPERTY USE_FOLDERS ON)

 # Check that submodules are present
 if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/sysroot/README.md")
-    message (FATAL_ERROR "Submodules are not initialized. Run\n\tgit submodule update --init --recursive")
+    message (FATAL_ERROR "Submodules are not initialized. Run\n\tgit submodule update --init")
 endif ()

 # Take care to add prlimit in command line before ccache, or else ccache thinks that
--- a/README.md
+++ b/README.md
@ -13,3 +13,7 @@ ClickHouse® is an open-source column-oriented database management system that a
 * [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
+
+* [ClickHouse Meetup Amsterdam (in-person and online)](https://www.meetup.com/clickhouse-netherlands-user-group/events/286017044/) on June 8th, 2022
--- a/base/base/CMakeLists.txt
+++ b/base/base/CMakeLists.txt
@ -17,15 +17,12 @@ set (SRCS
    sleep.cpp
    terminalColors.cpp
    errnoToString.cpp
+    ReplxxLineReader.cpp
    StringRef.cpp
    safeExit.cpp
    throwError.cpp
 )

-if (ENABLE_REPLXX)
-    list (APPEND SRCS ReplxxLineReader.cpp)
-endif ()
-
 if (USE_DEBUG_HELPERS)
    get_target_property(MAGIC_ENUM_INCLUDE_DIR ch_contrib::magic_enum INTERFACE_INCLUDE_DIRECTORIES)
    # CMake generator expression will do insane quoting when it encounters special character like quotes, spaces, etc.
--- a/base/base/ReplxxLineReader.cpp
+++ b/base/base/ReplxxLineReader.cpp
@ -45,14 +45,16 @@ std::string replxx_now_ms_str()
    time_t t = ms.count() / 1000;
    tm broken;
    if (!localtime_r(&t, &broken))
-    {
-        return std::string();
-    }
+        return {};

    static int const BUFF_SIZE(32);
    char str[BUFF_SIZE];
-    strftime(str, BUFF_SIZE, "%Y-%m-%d %H:%M:%S.", &broken);
-    snprintf(str + sizeof("YYYY-mm-dd HH:MM:SS"), 5, "%03d", static_cast<int>(ms.count() % 1000));
+    if (strftime(str, BUFF_SIZE, "%Y-%m-%d %H:%M:%S.", &broken) <= 0)
+        return {};
+
+    if (snprintf(str + sizeof("YYYY-mm-dd HH:MM:SS"), 5, "%03d", static_cast<int>(ms.count() % 1000)) <= 0)
+        return {};
+
    return str;
 }

--- a/base/base/wide_integer_impl.h
+++ b/base/base/wide_integer_impl.h
@ -576,8 +576,8 @@ private:
        else if constexpr (Bits == 128 && sizeof(base_type) == 8)
        {
            using CompilerUInt128 = unsigned __int128;
-            CompilerUInt128 a = (CompilerUInt128(lhs.items[1]) << 64) + lhs.items[0];
-            CompilerUInt128 b = (CompilerUInt128(rhs.items[1]) << 64) + rhs.items[0];
+            CompilerUInt128 a = (CompilerUInt128(lhs.items[1]) << 64) + lhs.items[0]; // NOLINT(clang-analyzer-core.UndefinedBinaryOperatorResult)
+            CompilerUInt128 b = (CompilerUInt128(rhs.items[1]) << 64) + rhs.items[0]; // NOLINT(clang-analyzer-core.UndefinedBinaryOperatorResult)
            CompilerUInt128 c = a * b;
            integer<Bits, Signed> res;
            res.items[0] = c;
@ -841,8 +841,8 @@ public:
        {
            using CompilerUInt128 = unsigned __int128;

-            CompilerUInt128 a = (CompilerUInt128(numerator.items[1]) << 64) + numerator.items[0];
-            CompilerUInt128 b = (CompilerUInt128(denominator.items[1]) << 64) + denominator.items[0];
+            CompilerUInt128 a = (CompilerUInt128(numerator.items[1]) << 64) + numerator.items[0]; // NOLINT(clang-analyzer-core.UndefinedBinaryOperatorResult)
+            CompilerUInt128 b = (CompilerUInt128(denominator.items[1]) << 64) + denominator.items[0]; // NOLINT(clang-analyzer-core.UndefinedBinaryOperatorResult)
            CompilerUInt128 c = a / b; // NOLINT

            integer<Bits, Signed> res;
@ -1204,7 +1204,7 @@ constexpr integer<Bits, Signed>::operator T() const noexcept

    UnsignedT res{};
    for (unsigned i = 0; i < _impl::item_count && i < (sizeof(T) + sizeof(base_type) - 1) / sizeof(base_type); ++i)
-        res += UnsignedT(items[i]) << (sizeof(base_type) * 8 * i);
+        res += UnsignedT(items[i]) << (sizeof(base_type) * 8 * i); // NOLINT(clang-analyzer-core.UndefinedBinaryOperatorResult)

    return res;
 }
--- a/contrib/abseil-cpp-cmake/CMakeLists.txt
+++ b/contrib/abseil-cpp-cmake/CMakeLists.txt
@ -1,7 +1,4 @@
 set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
-if(NOT EXISTS "${ABSL_ROOT_DIR}/CMakeLists.txt")
-  message(FATAL_ERROR " submodule third_party/abseil-cpp is missing. To fix try run: \n git submodule update --init --recursive")
-endif()
 set(BUILD_TESTING OFF)
 set(ABSL_PROPAGATE_CXX_STD ON)
 add_subdirectory("${ABSL_ROOT_DIR}" "${ClickHouse_BINARY_DIR}/contrib/abseil-cpp")
--- a/contrib/amqpcpp-cmake/CMakeLists.txt
+++ b/contrib/amqpcpp-cmake/CMakeLists.txt
@ -5,6 +5,12 @@ if (NOT ENABLE_AMQPCPP)
    return()
 endif()

+# can be removed once libuv build on MacOS with GCC is possible
+if (NOT TARGET ch_contrib::uv)
+    message(STATUS "Not using AMQP-CPP because libuv is disabled")
+    return()
+endif()
+
 set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/AMQP-CPP")

 set (SRCS
@ -32,21 +38,6 @@ set (SRCS

 add_library(_amqp-cpp ${SRCS})

-target_compile_options (_amqp-cpp
-    PRIVATE
-        -Wno-old-style-cast
-        -Wno-inconsistent-missing-destructor-override
-        -Wno-deprecated
-        -Wno-unused-parameter
-        -Wno-shadow
-        -Wno-tautological-type-limit-compare
-        -Wno-extra-semi
-# NOTE: disable all warnings at last because the warning:
-        #       "conversion function converting 'XXX' to itself will never be used"
-        #       doesn't have it's own diagnostic flag yet.
-        -w
-)
-
 target_include_directories (_amqp-cpp SYSTEM BEFORE PUBLIC "${LIBRARY_DIR}/include" "${LIBRARY_DIR}")
 target_link_libraries (_amqp-cpp PUBLIC OpenSSL::Crypto OpenSSL::SSL ch_contrib::uv)
 add_library (ch_contrib::amqp_cpp ALIAS _amqp-cpp)
--- a/contrib/arrow-cmake/CMakeLists.txt
+++ b/contrib/arrow-cmake/CMakeLists.txt
@ -20,7 +20,7 @@ endif()
 option (ENABLE_PARQUET "Enable parquet" ${ENABLE_PARQUET_DEFAULT})

 if (NOT ENABLE_PARQUET)
-    message(STATUS "Building without Parquet support")
+    message(STATUS "Not using parquet")
    return()
 endif()

--- a/contrib/avro-cmake/CMakeLists.txt
+++ b/contrib/avro-cmake/CMakeLists.txt
@ -60,14 +60,6 @@ target_compile_definitions (_avrocpp PUBLIC SNAPPY_CODEC_AVAILABLE)
 target_include_directories (_avrocpp PRIVATE ${SNAPPY_INCLUDE_DIR})
 target_link_libraries (_avrocpp PRIVATE ch_contrib::snappy)

-if (COMPILER_GCC)
-    set (SUPPRESS_WARNINGS -Wno-non-virtual-dtor)
-elseif (COMPILER_CLANG)
-    set (SUPPRESS_WARNINGS -Wno-non-virtual-dtor)
-endif ()
-
-target_compile_options(_avrocpp PRIVATE ${SUPPRESS_WARNINGS})
-
 # create a symlink to include headers with <avro/...>
 set(AVRO_INCLUDE_DIR "${CMAKE_CURRENT_BINARY_DIR}/include")
 ADD_CUSTOM_TARGET(avro_symlink_headers ALL
--- a/contrib/azure-cmake/CMakeLists.txt
+++ b/contrib/azure-cmake/CMakeLists.txt
@ -52,20 +52,6 @@ include("${AZURE_DIR}/cmake-modules/AzureTransportAdapters.cmake")

 add_library(_azure_sdk ${AZURE_SDK_UNIFIED_SRC})

-if (COMPILER_CLANG)
-    target_compile_options(_azure_sdk PRIVATE
-        -Wno-deprecated-copy-dtor
-        -Wno-extra-semi
-        -Wno-suggest-destructor-override
-        -Wno-inconsistent-missing-destructor-override
-        -Wno-error=unknown-warning-option
-    )
-
-    if (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 13)
-        target_compile_options(_azure_sdk PRIVATE -Wno-reserved-identifier)
-    endif()
-endif()
-
 # Originally, on Windows azure-core is built with bcrypt and crypt32 by default
 if (TARGET OpenSSL::SSL)
    target_link_libraries(_azure_sdk PRIVATE OpenSSL::Crypto OpenSSL::SSL)
--- a/contrib/boringssl-cmake/CMakeLists.txt
+++ b/contrib/boringssl-cmake/CMakeLists.txt
@ -1,7 +1,12 @@
 # Needed for:
 # - securely connecting to an external server, e.g. clickhouse-client --host ... --secure
 # - lots of thirdparty libraries
-option(ENABLE_SSL "Enable ssl" ${ENABLE_LIBRARIES})
+
+# Actually, so many 3rd party libraries + unit tests need SSL that we cannot disable it
+# without breaking the build ...
+option(ENABLE_SSL "Enable ssl" ON) # breaks if OFF
+# TODO: Making SSL dependent on ENABLE_LIBRARIES is desirable but needs fixing dependent libs + tests.
+# option(ENABLE_SSL "Enable ssl" ${ENABLE_LIBRARIES})

 if(NOT ENABLE_SSL)
  message(STATUS "Not using openssl")
--- a/contrib/brotli-cmake/CMakeLists.txt
+++ b/contrib/brotli-cmake/CMakeLists.txt
@ -45,7 +45,4 @@ add_library(ch_contrib::brotli ALIAS _brotli)

 target_include_directories(_brotli SYSTEM BEFORE PUBLIC "${BROTLI_SOURCE_DIR}/include")

-if(M_LIBRARY)
-    target_link_libraries(_brotli PRIVATE ${M_LIBRARY})
-endif()
 target_compile_definitions(_brotli PRIVATE BROTLI_BUILD_PORTABLE=1)
--- a/contrib/bzip2-cmake/CMakeLists.txt
+++ b/contrib/bzip2-cmake/CMakeLists.txt
@ -1,6 +1,6 @@
 option(ENABLE_BZIP2 "Enable bzip2 compression support" ${ENABLE_LIBRARIES})
 if (NOT ENABLE_BZIP2)
-    message (STATUS "bzip2 compression disabled")
+    message (STATUS "Not using bzip2")
    return()
 endif()

@ -26,8 +26,4 @@ configure_file (

 add_library(_bzip2 ${SRCS})
 add_library(ch_contrib::bzip2 ALIAS _bzip2)
-# To avoid -Wreserved-id-macro we use SYSTEM:
-#
-#     clickhouse/contrib/bzip2/bzlib.h:23:9: error: macro name is a reserved identifier [-Werror,-Wreserved-id-macro]
-#     #define _BZLIB_H
 target_include_directories(_bzip2 SYSTEM BEFORE PUBLIC "${BZIP2_SOURCE_DIR}" "${BZIP2_BINARY_DIR}")
--- a/contrib/capnproto-cmake/CMakeLists.txt
+++ b/contrib/capnproto-cmake/CMakeLists.txt
@ -81,16 +81,12 @@ set (CAPNPC_SRCS
 add_library(_capnpc ${CAPNPC_SRCS})
 target_link_libraries(_capnpc PUBLIC _capnp)

-# The library has substandard code
-if (COMPILER_GCC)
-    set (SUPPRESS_WARNINGS -w)
-elseif (COMPILER_CLANG)
-    set (SUPPRESS_WARNINGS -w)
+if (COMPILER_CLANG)
    set (CAPNP_PRIVATE_CXX_FLAGS -fno-char8_t)
 endif ()

-target_compile_options(_kj PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS})
-target_compile_options(_capnp PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS})
-target_compile_options(_capnpc PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS})
+target_compile_options(_kj PRIVATE ${CAPNP_PRIVATE_CXX_FLAGS})
+target_compile_options(_capnp PRIVATE ${CAPNP_PRIVATE_CXX_FLAGS})
+target_compile_options(_capnpc PRIVATE ${CAPNP_PRIVATE_CXX_FLAGS})

 add_library(ch_contrib::capnp ALIAS _capnpc)
--- a/contrib/cassandra-cmake/CMakeLists.txt
+++ b/contrib/cassandra-cmake/CMakeLists.txt
@ -5,6 +5,12 @@ if (NOT ENABLE_CASSANDRA)
    return()
 endif()

+# can be removed once libuv build on MacOS with GCC is possible
+if (NOT TARGET ch_contrib::uv)
+    message(STATUS "Not using cassandra because libuv is disabled")
+    return()
+endif()
+
 if (APPLE)
    set(CMAKE_MACOSX_RPATH ON)
 endif()
--- a/contrib/cppkafka-cmake/CMakeLists.txt
+++ b/contrib/cppkafka-cmake/CMakeLists.txt
@ -1,5 +1,5 @@
 if (NOT ENABLE_KAFKA)
-    message(STATUS "Not using librdkafka (skip cppkafka)")
+    message(STATUS "Not using kafka")
    return()
 endif()

--- a/contrib/fastops-cmake/CMakeLists.txt
+++ b/contrib/fastops-cmake/CMakeLists.txt
@ -5,7 +5,7 @@ elseif(ENABLE_FASTOPS)
 endif()

 if(NOT ENABLE_FASTOPS)
-    message(STATUS "Not using fast vectorized mathematical functions library by Mikhail Parakhin")
+    message(STATUS "Not using fastops")
    return()
 endif()

--- a/contrib/fmtlib-cmake/CMakeLists.txt
+++ b/contrib/fmtlib-cmake/CMakeLists.txt
@ -1,22 +1,24 @@
+set(FMT_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/fmtlib")
+
 set (SRCS
    # NOTE: do not build module for now:
    # ../fmtlib/src/fmt.cc
-    ../fmtlib/src/format.cc
-    ../fmtlib/src/os.cc
+    ${FMT_SOURCE_DIR}/src/format.cc
+    ${FMT_SOURCE_DIR}/src/os.cc

-    ../fmtlib/include/fmt/args.h
-    ../fmtlib/include/fmt/chrono.h
-    ../fmtlib/include/fmt/color.h
-    ../fmtlib/include/fmt/compile.h
-    ../fmtlib/include/fmt/core.h
-    ../fmtlib/include/fmt/format.h
-    ../fmtlib/include/fmt/format-inl.h
-    ../fmtlib/include/fmt/locale.h
-    ../fmtlib/include/fmt/os.h
-    ../fmtlib/include/fmt/ostream.h
-    ../fmtlib/include/fmt/printf.h
-    ../fmtlib/include/fmt/ranges.h
-    ../fmtlib/include/fmt/xchar.h
+    ${FMT_SOURCE_DIR}/include/fmt/args.h
+    ${FMT_SOURCE_DIR}/include/fmt/chrono.h
+    ${FMT_SOURCE_DIR}/include/fmt/color.h
+    ${FMT_SOURCE_DIR}/include/fmt/compile.h
+    ${FMT_SOURCE_DIR}/include/fmt/core.h
+    ${FMT_SOURCE_DIR}/include/fmt/format.h
+    ${FMT_SOURCE_DIR}/include/fmt/format-inl.h
+    ${FMT_SOURCE_DIR}/include/fmt/locale.h
+    ${FMT_SOURCE_DIR}/include/fmt/os.h
+    ${FMT_SOURCE_DIR}/include/fmt/ostream.h
+    ${FMT_SOURCE_DIR}/include/fmt/printf.h
+    ${FMT_SOURCE_DIR}/include/fmt/ranges.h
+    ${FMT_SOURCE_DIR}/include/fmt/xchar.h
 )

 add_library(_fmt ${SRCS})
--- a/contrib/h3-cmake/CMakeLists.txt
+++ b/contrib/h3-cmake/CMakeLists.txt
@ -9,23 +9,23 @@ set(H3_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/h3/src/h3lib")
 set(H3_BINARY_DIR "${ClickHouse_BINARY_DIR}/contrib/h3/src/h3lib")

 set(SRCS
-"${H3_SOURCE_DIR}/lib/algos.c"
-"${H3_SOURCE_DIR}/lib/coordijk.c"
-"${H3_SOURCE_DIR}/lib/bbox.c"
-"${H3_SOURCE_DIR}/lib/polygon.c"
-"${H3_SOURCE_DIR}/lib/h3Index.c"
-"${H3_SOURCE_DIR}/lib/vec2d.c"
-"${H3_SOURCE_DIR}/lib/vec3d.c"
-"${H3_SOURCE_DIR}/lib/vertex.c"
-"${H3_SOURCE_DIR}/lib/linkedGeo.c"
-"${H3_SOURCE_DIR}/lib/localij.c"
-"${H3_SOURCE_DIR}/lib/latLng.c"
-"${H3_SOURCE_DIR}/lib/directedEdge.c"
-"${H3_SOURCE_DIR}/lib/mathExtensions.c"
-"${H3_SOURCE_DIR}/lib/iterators.c"
-"${H3_SOURCE_DIR}/lib/vertexGraph.c"
-"${H3_SOURCE_DIR}/lib/faceijk.c"
-"${H3_SOURCE_DIR}/lib/baseCells.c"
+    "${H3_SOURCE_DIR}/lib/algos.c"
+    "${H3_SOURCE_DIR}/lib/coordijk.c"
+    "${H3_SOURCE_DIR}/lib/bbox.c"
+    "${H3_SOURCE_DIR}/lib/polygon.c"
+    "${H3_SOURCE_DIR}/lib/h3Index.c"
+    "${H3_SOURCE_DIR}/lib/vec2d.c"
+    "${H3_SOURCE_DIR}/lib/vec3d.c"
+    "${H3_SOURCE_DIR}/lib/vertex.c"
+    "${H3_SOURCE_DIR}/lib/linkedGeo.c"
+    "${H3_SOURCE_DIR}/lib/localij.c"
+    "${H3_SOURCE_DIR}/lib/latLng.c"
+    "${H3_SOURCE_DIR}/lib/directedEdge.c"
+    "${H3_SOURCE_DIR}/lib/mathExtensions.c"
+    "${H3_SOURCE_DIR}/lib/iterators.c"
+    "${H3_SOURCE_DIR}/lib/vertexGraph.c"
+    "${H3_SOURCE_DIR}/lib/faceijk.c"
+    "${H3_SOURCE_DIR}/lib/baseCells.c"
 )

 configure_file("${H3_SOURCE_DIR}/include/h3api.h.in" "${H3_BINARY_DIR}/include/h3api.h")
@ -34,8 +34,5 @@ add_library(_h3 ${SRCS})
 target_include_directories(_h3 SYSTEM PUBLIC "${H3_SOURCE_DIR}/include")
 target_include_directories(_h3 SYSTEM PUBLIC "${H3_BINARY_DIR}/include")
 target_compile_definitions(_h3 PRIVATE H3_HAVE_VLA)
-if(M_LIBRARY)
-    target_link_libraries(_h3 PRIVATE ${M_LIBRARY})
-endif()

 add_library(ch_contrib::h3 ALIAS _h3)
--- a/contrib/hive-metastore-cmake/CMakeLists.txt
+++ b/contrib/hive-metastore-cmake/CMakeLists.txt
@ -5,7 +5,7 @@ elseif(ENABLE_HIVE)
 endif()

 if (NOT ENABLE_HIVE)
-    message("Hive disabled")
+    message(STATUS "Not using hive")
    return()
 endif()

--- a/contrib/icu-cmake/CMakeLists.txt
+++ b/contrib/icu-cmake/CMakeLists.txt
@ -481,10 +481,6 @@ target_include_directories(_icui18n SYSTEM PUBLIC "${ICU_SOURCE_DIR}/i18n/")
 target_compile_definitions(_icuuc PRIVATE -DU_COMMON_IMPLEMENTATION)
 target_compile_definitions(_icui18n PRIVATE -DU_I18N_IMPLEMENTATION)

-if (COMPILER_CLANG)
-    target_compile_options(_icudata PRIVATE -Wno-unused-command-line-argument)
-endif ()
-
 add_library(_icu INTERFACE)
 target_link_libraries(_icu INTERFACE _icui18n _icuuc _icudata)
 add_library(ch_contrib::icu ALIAS _icu)
--- a/contrib/jemalloc-cmake/CMakeLists.txt
+++ b/contrib/jemalloc-cmake/CMakeLists.txt
@ -180,7 +180,6 @@ if (USE_UNWIND)
    target_link_libraries (_jemalloc PRIVATE unwind)
 endif ()

-target_compile_options(_jemalloc PRIVATE -Wno-redundant-decls)
 # for RTLD_NEXT
 target_compile_options(_jemalloc PRIVATE -D_GNU_SOURCE)

--- a/contrib/libcpuid-cmake/CMakeLists.txt
+++ b/contrib/libcpuid-cmake/CMakeLists.txt
@ -6,7 +6,7 @@ elseif(ENABLE_CPUID)
 endif()

 if (NOT ENABLE_CPUID)
-    message("Not using cpuid")
+    message(STATUS "Not using cpuid")
    return()
 endif()

@ -27,8 +27,5 @@ add_library (_cpuid ${SRCS})

 target_include_directories (_cpuid SYSTEM PUBLIC "${LIBRARY_DIR}")
 target_compile_definitions (_cpuid PRIVATE VERSION="v0.4.1")
-if (COMPILER_CLANG)
-    target_compile_options (_cpuid PRIVATE -Wno-reserved-id-macro)
-endif ()

 add_library(ch_contrib::cpuid ALIAS _cpuid)
--- a/contrib/libgsasl-cmake/CMakeLists.txt
+++ b/contrib/libgsasl-cmake/CMakeLists.txt
@ -1,7 +1,7 @@
 option(ENABLE_GSASL_LIBRARY "Enable gsasl library" ${ENABLE_LIBRARIES})

 if (NOT ENABLE_GSASL_LIBRARY)
-    message(STATUS "Not using gsasl library")
+    message(STATUS "Not using gsasl")
    return()
 endif()

--- a/contrib/libuv-cmake/CMakeLists.txt
+++ b/contrib/libuv-cmake/CMakeLists.txt
@ -1,3 +1,4 @@
+# once fixed, please remove similar places in CMakeLists of libuv users (search "ch_contrib::uv")
 if (OS_DARWIN AND COMPILER_GCC)
    message (WARNING "libuv cannot be built with GCC in macOS due to a bug: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93082")
    return()
--- a/contrib/libxml2
+++ b/contrib/libxml2
@ -1 +1 @@
-Subproject commit a075d256fd9ff15590b86d981b75a50ead124fca
+Subproject commit 7846b0a677f8d3ce72486125fa281e92ac9970e8
--- a/contrib/libxml2-cmake/CMakeLists.txt
+++ b/contrib/libxml2-cmake/CMakeLists.txt
@ -53,9 +53,6 @@ set(SRCS
 add_library(_libxml2 ${SRCS})

 target_link_libraries(_libxml2 PRIVATE ch_contrib::zlib)
-if(M_LIBRARY)
-    target_link_libraries(_libxml2 PRIVATE ${M_LIBRARY})
-endif()

 target_include_directories(_libxml2 BEFORE PUBLIC "${CMAKE_CURRENT_SOURCE_DIR}/linux_x86_64/include")
 target_include_directories(_libxml2 BEFORE PUBLIC "${LIBXML2_SOURCE_DIR}/include")
--- a/contrib/minizip-ng-cmake/CMakeLists.txt
+++ b/contrib/minizip-ng-cmake/CMakeLists.txt
@ -1,6 +1,6 @@
 option(ENABLE_MINIZIP "Enable minizip-ng the zip manipulation library" ${ENABLE_LIBRARIES})
 if (NOT ENABLE_MINIZIP)
-    message (STATUS "minizip-ng disabled")
+    message (STATUS "Not using minizip-ng")
    return()
 endif()

--- a/contrib/nanodbc-cmake/CMakeLists.txt
+++ b/contrib/nanodbc-cmake/CMakeLists.txt
@ -2,12 +2,12 @@ if (NOT ENABLE_ODBC)
    return ()
 endif ()

-set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/nanodbc")
-
 if (NOT TARGET ch_contrib::unixodbc)
    message(FATAL_ERROR "Configuration error: unixodbc is not a target")
 endif()

+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/nanodbc")
+
 set (SRCS
    "${LIBRARY_DIR}/nanodbc/nanodbc.cpp"
 )
--- a/contrib/replxx-cmake/CMakeLists.txt
+++ b/contrib/replxx-cmake/CMakeLists.txt
@ -1,10 +1,3 @@
-option (ENABLE_REPLXX "Enable replxx support" ${ENABLE_LIBRARIES})
-
-if (NOT ENABLE_REPLXX)
-    message (STATUS "Not using replxx")
-    return()
-endif()
-
 set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/replxx")

 set(SRCS
@ -22,9 +15,4 @@ set(SRCS

 add_library (_replxx ${SRCS})
 target_include_directories(_replxx SYSTEM PUBLIC "${LIBRARY_DIR}/include")
-
-if (COMPILER_CLANG)
-    target_compile_options(_replxx PRIVATE -Wno-documentation)
-endif ()
-
 add_library(ch_contrib::replxx ALIAS _replxx)
--- a/contrib/s2geometry-cmake/CMakeLists.txt
+++ b/contrib/s2geometry-cmake/CMakeLists.txt
@ -149,7 +149,3 @@ target_link_libraries(_s2 PRIVATE

 target_include_directories(_s2 SYSTEM BEFORE PUBLIC "${S2_SOURCE_DIR}/")
 target_include_directories(_s2 SYSTEM PUBLIC "${ABSL_SOURCE_DIR}")
-
-if(M_LIBRARY)
-    target_link_libraries(_s2 PRIVATE ${M_LIBRARY})
-endif()
--- a/contrib/thrift-cmake/CMakeLists.txt
+++ b/contrib/thrift-cmake/CMakeLists.txt
@ -1,7 +1,7 @@
 option(ENABLE_THRIFT "Enable Thrift" ${ENABLE_LIBRARIES})

 if (NOT ENABLE_THRIFT)
-    message (STATUS "thrift disabled")
+    message (STATUS "Not using thrift")
    return()
 endif()

--- a/contrib/unixodbc-cmake/CMakeLists.txt
+++ b/contrib/unixodbc-cmake/CMakeLists.txt
@ -294,14 +294,6 @@ target_include_directories (_unixodbc
        "${LIBRARY_DIR}/include"
 )
 target_compile_definitions (_unixodbc PRIVATE -DHAVE_CONFIG_H)
-target_compile_options (_unixodbc
-    PRIVATE
-        -Wno-dangling-else
-        -Wno-parentheses
-        -Wno-misleading-indentation
-        -Wno-unknown-warning-option
-        -Wno-reserved-id-macro
-        -O2
-)
+target_compile_options (_unixodbc PRIVATE -O2) # intended?

 add_library (ch_contrib::unixodbc ALIAS _unixodbc)
--- a/docker/docs/builder/run.sh
+++ b/docker/docs/builder/run.sh
@ -8,6 +8,8 @@ if [ "$GIT_DOCS_BRANCH" ] && ! [ "$GIT_DOCS_BRANCH" == "$GIT_BRANCH" ]; then
  git fetch origin --depth=1 -- "$GIT_DOCS_BRANCH:$GIT_DOCS_BRANCH"
  git checkout "$GIT_DOCS_BRANCH"
 else
+  # Untracked yarn.lock could cause pull to fail
+  git clean -fdx
  # Update docs repo
  git pull
 fi
--- a/docker/packager/binary/Dockerfile
+++ b/docker/packager/binary/Dockerfile
@ -6,7 +6,7 @@ FROM ubuntu:20.04
 ARG apt_archive="http://archive.ubuntu.com"
 RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list

-ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=13
+ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=14

 RUN apt-get update \
    && apt-get install \
--- a/docker/packager/packager
+++ b/docker/packager/packager
@ -319,25 +319,16 @@ if __name__ == "__main__":
    )
    parser.add_argument("--output-dir", type=dir_name, required=True)
    parser.add_argument("--build-type", choices=("debug", ""), default="")
+
    parser.add_argument(
        "--compiler",
        choices=(
-            "clang-11",
-            "clang-11-darwin",
-            "clang-11-darwin-aarch64",
-            "clang-11-aarch64",
-            "clang-12",
-            "clang-12-darwin",
-            "clang-12-darwin-aarch64",
-            "clang-12-aarch64",
-            "clang-13",
-            "clang-13-darwin",
-            "clang-13-darwin-aarch64",
-            "clang-13-aarch64",
-            "clang-13-ppc64le",
-            "clang-11-freebsd",
-            "clang-12-freebsd",
-            "clang-13-freebsd",
+            "clang-14",
+            "clang-14-darwin",
+            "clang-14-darwin-aarch64",
+            "clang-14-aarch64",
+            "clang-14-ppc64le",
+            "clang-14-freebsd",
            "gcc-11",
        ),
        default="clang-13",
@ -348,6 +339,7 @@ if __name__ == "__main__":
        choices=("address", "thread", "memory", "undefined", ""),
        default="",
    )
+
    parser.add_argument("--split-binary", action="store_true")
    parser.add_argument("--clang-tidy", action="store_true")
    parser.add_argument("--cache", choices=("ccache", "distcc", ""), default="")
--- a/docker/test/base/Dockerfile
+++ b/docker/test/base/Dockerfile
@ -7,7 +7,7 @@ FROM clickhouse/test-util:$FROM_TAG
 ARG apt_archive="http://archive.ubuntu.com"
 RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list

-ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=13
+ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=14

 RUN apt-get update \
    && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \
--- a/docker/test/codebrowser/Dockerfile
+++ b/docker/test/codebrowser/Dockerfile
@ -8,14 +8,18 @@ FROM clickhouse/binary-builder:$FROM_TAG
 ARG apt_archive="http://archive.ubuntu.com"
 RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list

-RUN apt-get update && apt-get --yes --allow-unauthenticated install clang-13 libllvm13 libclang-13-dev libmlir-13-dev
+RUN apt-get update && apt-get --yes --allow-unauthenticated install clang-14 libllvm14 libclang-14-dev libmlir-14-dev

 # repo versions doesn't work correctly with C++17
 # also we push reports to s3, so we add index.html to subfolder urls
 # https://github.com/ClickHouse-Extras/woboq_codebrowser/commit/37e15eaf377b920acb0b48dbe82471be9203f76b
-RUN git clone https://github.com/ClickHouse-Extras/woboq_codebrowser
-
-RUN cd woboq_codebrowser && cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=clang\+\+-13 -DCMAKE_C_COMPILER=clang-13 && make -j
+# TODO: remove branch in a few weeks after merge, e.g. in May or June 2022
+RUN git clone https://github.com/ClickHouse-Extras/woboq_codebrowser --branch llvm-14 \
+  && cd woboq_codebrowser \
+  && cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=clang\+\+-14 -DCMAKE_C_COMPILER=clang-14 \
+  && make -j \
+  && cd .. \
+  && rm -rf woboq_codebrowser

 ENV CODEGEN=/woboq_codebrowser/generator/codebrowser_generator
 ENV CODEINDEX=/woboq_codebrowser/indexgenerator/codebrowser_indexgenerator
@ -28,7 +32,7 @@ ENV SHA=nosha
 ENV DATA="https://s3.amazonaws.com/clickhouse-test-reports/codebrowser/data"

 CMD mkdir -p $BUILD_DIRECTORY && cd $BUILD_DIRECTORY && \
-    cmake $SOURCE_DIRECTORY -DCMAKE_CXX_COMPILER=/usr/bin/clang\+\+-13 -DCMAKE_C_COMPILER=/usr/bin/clang-13 -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DENABLE_EMBEDDED_COMPILER=0 -DENABLE_S3=0 && \
+    cmake $SOURCE_DIRECTORY -DCMAKE_CXX_COMPILER=/usr/bin/clang\+\+-14 -DCMAKE_C_COMPILER=/usr/bin/clang-14 -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DENABLE_EMBEDDED_COMPILER=0 -DENABLE_S3=0 && \
    mkdir -p $HTML_RESULT_DIRECTORY && \
    $CODEGEN -b $BUILD_DIRECTORY -a -o $HTML_RESULT_DIRECTORY -p ClickHouse:$SOURCE_DIRECTORY:$SHA -d $DATA | ts '%Y-%m-%d %H:%M:%S' && \
    cp -r $STATIC_DATA $HTML_RESULT_DIRECTORY/ &&\
--- a/docker/test/fasttest/Dockerfile
+++ b/docker/test/fasttest/Dockerfile
@ -7,7 +7,7 @@ FROM clickhouse/test-util:$FROM_TAG
 ARG apt_archive="http://archive.ubuntu.com"
 RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list

-ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=13
+ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=14

 RUN apt-get update \
    && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \
--- a/docker/test/fuzzer/run-fuzzer.sh
+++ b/docker/test/fuzzer/run-fuzzer.sh
@ -12,7 +12,7 @@ stage=${stage:-}
 script_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 echo "$script_dir"
 repo_dir=ch
-BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-13_debug_none_bundled_unsplitted_disable_False_binary"}
+BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-14_debug_none_bundled_unsplitted_disable_False_binary"}
 BINARY_URL_TO_DOWNLOAD=${BINARY_URL_TO_DOWNLOAD:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/$BINARY_TO_DOWNLOAD/clickhouse"}

 function clone
@ -355,22 +355,8 @@ fi
 cat > report.html <<EOF ||:
 <!DOCTYPE html>
 <html lang="en">
-<link rel="preload" as="font" href="https://yastatic.net/adv-www/_/sUYVCPUAQE7ExrvMS7FoISoO83s.woff2" type="font/woff2" crossorigin="anonymous"/>
  <style>
-@font-face {
-    font-family:'Yandex Sans Display Web';
-    src:url(https://yastatic.net/adv-www/_/H63jN0veW07XQUIA2317lr9UIm8.eot);
-    src:url(https://yastatic.net/adv-www/_/H63jN0veW07XQUIA2317lr9UIm8.eot?#iefix) format('embedded-opentype'),
-            url(https://yastatic.net/adv-www/_/sUYVCPUAQE7ExrvMS7FoISoO83s.woff2) format('woff2'),
-            url(https://yastatic.net/adv-www/_/v2Sve_obH3rKm6rKrtSQpf-eB7U.woff) format('woff'),
-            url(https://yastatic.net/adv-www/_/PzD8hWLMunow5i3RfJ6WQJAL7aI.ttf) format('truetype'),
-            url(https://yastatic.net/adv-www/_/lF_KG5g4tpQNlYIgA0e77fBSZ5s.svg#YandexSansDisplayWeb-Regular) format('svg');
-    font-weight:400;
-    font-style:normal;
-    font-stretch:normal
-}
-
-body { font-family: "Yandex Sans Display Web", Arial, sans-serif; background: #EEE; }
+body { font-family: "DejaVu Sans", "Noto Sans", Arial, sans-serif; background: #EEE; }
 h1 { margin-left: 10px; }
 th, td { border: 0; padding: 5px 10px 5px 10px; text-align: left; vertical-align: top; line-height: 1.5; background-color: #FFF;
 td { white-space: pre; font-family: Monospace, Courier New; }
@ -378,7 +364,6 @@ border: 0; box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.05), 0 8px 25px -5px rgba(0, 0,
 a { color: #06F; text-decoration: none; }
 a:hover, a:active { color: #F40; text-decoration: underline; }
 table { border: 0; }
-.main { margin-left: 10%; }
 p.links a { padding: 5px; margin: 3px; background: #FFF; line-height: 2; white-space: nowrap; box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.05), 0 8px 25px -5px rgba(0, 0, 0, 0.1); }
 th { cursor: pointer; }

--- a/docker/test/keeper-jepsen/run.sh
+++ b/docker/test/keeper-jepsen/run.sh
@ -2,7 +2,7 @@
 set -euo pipefail


-CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-13_relwithdebuginfo_none_bundled_unsplitted_disable_False_binary/clickhouse"}
+CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-14_relwithdebuginfo_none_bundled_unsplitted_disable_False_binary/clickhouse"}
 CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}


--- a/docker/test/performance-comparison/compare.sh
+++ b/docker/test/performance-comparison/compare.sh
@ -207,6 +207,13 @@ function run_tests
        test_files=($(ls "$test_prefix"/*.xml))
    fi

+    # We can filter out certain tests
+    if [ -v CHPC_TEST_GREP_EXCLUDE ]; then
+        # filter tests array in bash https://stackoverflow.com/a/40375567
+        filtered_test_files=( $( for i in ${test_files[@]} ; do echo $i ; done | grep -v ${CHPC_TEST_GREP_EXCLUDE} ) )
+        test_files=("${filtered_test_files[@]}")
+    fi
+
    # We split perf tests into multiple checks to make them faster
    if [ -v CHPC_TEST_RUN_BY_HASH_TOTAL ]; then
        # filter tests array in bash https://stackoverflow.com/a/40375567
--- a/docker/test/stateful/Dockerfile
+++ b/docker/test/stateful/Dockerfile
@ -17,8 +17,7 @@ ENV EXPORT_S3_STORAGE_POLICIES=1

 # Download Minio-related binaries
 RUN arch=${TARGETARCH:-amd64} \
-    && wget "https://dl.min.io/server/minio/release/linux-${arch}/minio" \
-    && chmod +x ./minio \
+    && if [ "$arch" = "amd64" ] ; then wget "https://dl.min.io/server/minio/release/linux-${arch}/archive/minio-20220103182258.0.0.x86_64.rpm"; else wget "https://dl.min.io/server/minio/release/linux-${arch}/archive/minio-20220103182258.0.0.aarch64.rpm" ; fi \
    && wget "https://dl.min.io/client/mc/release/linux-${arch}/mc" \
    && chmod +x ./mc
 ENV MINIO_ROOT_USER="clickhouse"
--- a/docker/test/stateful/setup_minio.sh
+++ b/docker/test/stateful/setup_minio.sh
@ -9,6 +9,10 @@

 set -e -x -a -u

+rpm2cpio ./minio-20220103182258.0.0.*.rpm | cpio -i --make-directories
+find / -name minio
+cp ./usr/local/bin/minio ./
+
 ls -lha

 mkdir -p ./minio_data
@ -27,12 +31,19 @@ fi
 MINIO_ROOT_USER=${MINIO_ROOT_USER:-clickhouse}
 MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-clickhouse}

+./minio --version
 ./minio server --address ":11111" ./minio_data &

+i=0
 while ! curl -v --silent http://localhost:11111 2>&1 | grep AccessDenied
 do
+  if [[ $i == 60 ]]; then
+    echo "Failed to setup minio"
+    exit 0
+  fi
  echo "Trying to connect to minio"
  sleep 1
+  i=$((i + 1))
 done

 lsof -i :11111
--- a/docker/test/stateless/Dockerfile
+++ b/docker/test/stateless/Dockerfile
@ -32,7 +32,11 @@ RUN apt-get update -y \
            mysql-client=8.0* \
            postgresql-client \
            sqlite3 \
-            awscli
+            awscli \
+            openjdk-11-jre-headless \
+            rpm2cpio \
+            cpio
+

 RUN pip3 install numpy scipy pandas Jinja2

@ -53,15 +57,20 @@ ARG TARGETARCH

 # Download Minio-related binaries
 RUN arch=${TARGETARCH:-amd64} \
-    && wget "https://dl.min.io/server/minio/release/linux-${arch}/minio" \
-    && chmod +x ./minio \
+    && if [ "$arch" = "amd64" ] ; then wget "https://dl.min.io/server/minio/release/linux-${arch}/archive/minio-20220103182258.0.0.x86_64.rpm"; else wget "https://dl.min.io/server/minio/release/linux-${arch}/archive/minio-20220103182258.0.0.aarch64.rpm" ; fi \
    && wget "https://dl.min.io/client/mc/release/linux-${arch}/mc" \
    && chmod +x ./mc

+
+RUN wget 'https://dlcdn.apache.org/hadoop/common/hadoop-3.3.1/hadoop-3.3.1.tar.gz' \
+    && tar -xvf hadoop-3.3.1.tar.gz \
+    && rm -rf hadoop-3.3.1.tar.gz
+
 ENV MINIO_ROOT_USER="clickhouse"
 ENV MINIO_ROOT_PASSWORD="clickhouse"
 ENV EXPORT_S3_STORAGE_POLICIES=1

 COPY run.sh /
 COPY setup_minio.sh /
+COPY setup_hdfs_minicluster.sh /
 CMD ["/bin/bash", "/run.sh"]
--- a/docker/test/stateless/run.sh
+++ b/docker/test/stateless/run.sh
@ -19,6 +19,7 @@ ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
 /usr/share/clickhouse-test/config/install.sh

 ./setup_minio.sh
+./setup_hdfs_minicluster.sh

 # For flaky check we also enable thread fuzzer
 if [ "$NUM_TRIES" -gt "1" ]; then
@ -92,8 +93,6 @@ function run_tests()

    if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
        ADDITIONAL_OPTIONS+=('--replicated-database')
-        # Cannot be used with replicated database, due to distributed_ddl_output_mode=none
-        ADDITIONAL_OPTIONS+=('--no-left-queries-check')
        ADDITIONAL_OPTIONS+=('--jobs')
        ADDITIONAL_OPTIONS+=('2')
    else
--- a/docker/test/stateless/setup_hdfs_minicluster.sh
+++ b/docker/test/stateless/setup_hdfs_minicluster.sh
@ -0,0 +1,20 @@
+#!/bin/bash
+
+set -e -x -a -u
+
+ls -lha
+
+cd hadoop-3.3.1
+
+export JAVA_HOME=/usr
+mkdir -p target/test/data
+chown clickhouse ./target/test/data
+sudo -E -u clickhouse bin/mapred minicluster -format -nomr -nnport 12222 &
+
+while ! nc -z localhost 12222; do
+  sleep 1
+done
+
+lsof -i :12222
+
+sleep 5
--- a/docker/test/stateless/setup_minio.sh
+++ b/docker/test/stateless/setup_minio.sh
@ -7,6 +7,10 @@

 set -e -x -a -u

+rpm2cpio ./minio-20220103182258.0.0.*.rpm | cpio -i --make-directories
+find / -name minio
+cp ./usr/local/bin/minio ./
+
 ls -lha

 mkdir -p ./minio_data
@ -25,12 +29,19 @@ fi
 MINIO_ROOT_USER=${MINIO_ROOT_USER:-clickhouse}
 MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-clickhouse}

+./minio --version
 ./minio server --address ":11111" ./minio_data &

+i=0
 while ! curl -v --silent http://localhost:11111 2>&1 | grep AccessDenied
 do
+  if [[ $i == 60 ]]; then
+    echo "Failed to setup minio"
+    exit 0
+  fi
  echo "Trying to connect to minio"
  sleep 1
+  i=$((i + 1))
 done

 lsof -i :11111
--- a/docker/test/stress/run.sh
+++ b/docker/test/stress/run.sh
@ -338,6 +338,7 @@ then
               -e "Code: 1000, e.code() = 111, Connection refused" \
               -e "UNFINISHED" \
               -e "Renaming unexpected part" \
+               -e "PART_IS_TEMPORARILY_LOCKED" \
        /var/log/clickhouse-server/clickhouse-server.backward.clean.log | zgrep -Fa "<Error>" > /test_output/bc_check_error_messages.txt \
        && echo -e 'Backward compatibility check: Error message in clickhouse-server.log (see bc_check_error_messages.txt)\tFAIL' >> /test_output/test_results.tsv \
        || echo -e 'Backward compatibility check: No Error messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv
--- a/docs/_includes/cmake_in_clickhouse_header.md
+++ b/docs/_includes/cmake_in_clickhouse_header.md
@ -6,8 +6,8 @@ Minimal ClickHouse build example:

 ```bash
 cmake .. \
-    -DCMAKE_C_COMPILER=$(which clang-13) \
-    -DCMAKE_CXX_COMPILER=$(which clang++-13) \
+    -DCMAKE_C_COMPILER=$(which clang-14) \
+    -DCMAKE_CXX_COMPILER=$(which clang++-14) \
    -DCMAKE_BUILD_TYPE=Debug \
    -DENABLE_UTILS=OFF \
    -DENABLE_TESTS=OFF
--- a/docs/en/development/build-cross-arm.md
+++ b/docs/en/development/build-cross-arm.md
@ -10,7 +10,7 @@ This is intended for continuous integration checks that run on Linux servers.

 The cross-build for AARCH64 is based on the [Build instructions](../development/build.md), follow them first.

-## Install Clang-13
+## Install Clang-14 or newer

 Follow the instructions from https://apt.llvm.org/ for your Ubuntu or Debian setup or do
 ```
@ -31,7 +31,7 @@ tar xJf gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz -C build-aarch64/cma
 ``` bash
 cd ClickHouse
 mkdir build-arm64
-CC=clang-13 CXX=clang++-13 cmake . -Bbuild-arm64 -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-aarch64.cmake
+CC=clang-14 CXX=clang++-14 cmake . -Bbuild-arm64 -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-aarch64.cmake
 ninja -C build-arm64
 ```

--- a/docs/en/development/build-cross-osx.md
+++ b/docs/en/development/build-cross-osx.md
@ -10,14 +10,14 @@ This is intended for continuous integration checks that run on Linux servers. If

 The cross-build for Mac OS X is based on the [Build instructions](../development/build.md), follow them first.

-## Install Clang-13
+## Install Clang-14

 Follow the instructions from https://apt.llvm.org/ for your Ubuntu or Debian setup.
 For example the commands for Bionic are like:

 ``` bash
-sudo echo "deb [trusted=yes] http://apt.llvm.org/bionic/ llvm-toolchain-bionic-13 main" >> /etc/apt/sources.list
-sudo apt-get install clang-13
+sudo echo "deb [trusted=yes] http://apt.llvm.org/bionic/ llvm-toolchain-bionic-14 main" >> /etc/apt/sources.list
+sudo apt-get install clang-14
 ```

 ## Install Cross-Compilation Toolset {#install-cross-compilation-toolset}
--- a/docs/en/development/build-cross-riscv.md
+++ b/docs/en/development/build-cross-riscv.md
@ -23,7 +23,7 @@ sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"
 ``` bash
 cd ClickHouse
 mkdir build-riscv64
-CC=clang-13 CXX=clang++-13 cmake . -Bbuild-riscv64 -G Ninja -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-riscv64.cmake -DGLIBC_COMPATIBILITY=OFF -DENABLE_LDAP=OFF  -DOPENSSL_NO_ASM=ON -DENABLE_JEMALLOC=ON -DENABLE_PARQUET=OFF -DENABLE_ORC=OFF -DUSE_UNWIND=OFF -DENABLE_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
+CC=clang-14 CXX=clang++-14 cmake . -Bbuild-riscv64 -G Ninja -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-riscv64.cmake -DGLIBC_COMPATIBILITY=OFF -DENABLE_LDAP=OFF  -DOPENSSL_NO_ASM=ON -DENABLE_JEMALLOC=ON -DENABLE_PARQUET=OFF -DENABLE_ORC=OFF -DUSE_UNWIND=OFF -DENABLE_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
 ninja -C build-riscv64
 ```

--- a/docs/en/development/build.md
+++ b/docs/en/development/build.md
@ -77,7 +77,7 @@ The build requires the following components:
 -   Git (is used only to checkout the sources, it’s not needed for the build)
 -   CMake 3.14 or newer
 -   Ninja
-   C++ compiler: clang-13 or newer
+-   C++ compiler: clang-14 or newer
 -   Linker: lld

 If all the components are installed, you may build in the same way as the steps above.
--- a/docs/en/development/contrib.md
+++ b/docs/en/development/contrib.md
@ -1,10 +1,10 @@
 ---
 sidebar_position: 71
 sidebar_label: Third-Party Libraries
-description: A list of third-party libraries used 
+description: A list of third-party libraries used
 ---

-# Third-Party Libraries Used 
+# Third-Party Libraries Used

 The list of third-party libraries:

--- a/docs/en/development/developer-instruction.md
+++ b/docs/en/development/developer-instruction.md
@ -155,7 +155,7 @@ While inside the `build` directory, configure your build by running CMake. Befor
    export CC=clang CXX=clang++
    cmake ..

-If you installed clang using the automatic installation script above, also specify the version of clang installed in the first command, e.g. `export CC=clang-13 CXX=clang++-13`. The clang version will be in the script output.
+If you installed clang using the automatic installation script above, also specify the version of clang installed in the first command, e.g. `export CC=clang-14 CXX=clang++-14`. The clang version will be in the script output.

 The `CC` variable specifies the compiler for C (short for C Compiler), and `CXX` variable instructs which C++ compiler is to be used for building.

--- a/docs/en/development/index.md
+++ b/docs/en/development/index.md
@ -3,6 +3,6 @@ sidebar_label: Development
 sidebar_position: 58
 ---

-# ClickHouse Development {#clickhouse-development}
+# ClickHouse Development

 [Original article](https://clickhouse.com/docs/en/development/) <!--hide-->
--- a/docs/en/development/tests.md
+++ b/docs/en/development/tests.md
@ -81,7 +81,7 @@ $ ./src/unit_tests_dbms --gtest_filter=LocalAddress*

 ## Performance Tests {#performance-tests}

-Performance tests allow to measure and compare performance of some isolated part of ClickHouse on synthetic queries. Tests are located at `tests/performance`. Each test is represented by `.xml` file with description of test case. Tests are run with `docker/tests/performance-comparison` tool . See the readme file for invocation.
+Performance tests allow to measure and compare performance of some isolated part of ClickHouse on synthetic queries. Tests are located at `tests/performance`. Each test is represented by `.xml` file with description of test case. Tests are run with `docker/test/performance-comparison` tool . See the readme file for invocation.

 Each test run one or multiple queries (possibly with combinations of parameters) in a loop.

--- a/docs/en/engines/database-engines/index.md
+++ b/docs/en/engines/database-engines/index.md
@ -4,7 +4,7 @@ toc_priority: 27
 toc_title: Introduction
 ---

-# Database Engines {#database-engines}
+# Database Engines

 Database engines allow you to work with tables. By default, ClickHouse uses the [Atomic](../../engines/database-engines/atomic.md) database engine, which provides configurable [table engines](../../engines/table-engines/index.md) and an [SQL dialect](../../sql-reference/syntax.md).

--- a/docs/en/engines/database-engines/lazy.md
+++ b/docs/en/engines/database-engines/lazy.md
@ -3,7 +3,7 @@ sidebar_label: Lazy
 sidebar_position: 20
 ---

-# Lazy {#lazy}
+# Lazy

 Keeps tables in RAM only `expiration_time_in_seconds` seconds after last access. Can be used only with \*Log tables.

--- a/docs/en/engines/database-engines/materialized-postgresql.md
+++ b/docs/en/engines/database-engines/materialized-postgresql.md
@ -3,7 +3,7 @@ sidebar_label: MaterializedPostgreSQL
 sidebar_position: 60
 ---

-# [experimental] MaterializedPostgreSQL {#materialize-postgresql}
+# [experimental] MaterializedPostgreSQL

 Creates a ClickHouse database with tables from PostgreSQL database. Firstly, database with engine `MaterializedPostgreSQL` creates a snapshot of PostgreSQL database and loads required tables. Required tables can include any subset of tables from any subset of schemas from specified database. Along with the snapshot database engine acquires LSN and once initial dump of tables is performed - it starts pulling updates from WAL. After database is created, newly added tables to PostgreSQL database are not automatically added to replication. They have to be added manually with `ATTACH TABLE db.table` query.

--- a/docs/en/engines/database-engines/postgresql.md
+++ b/docs/en/engines/database-engines/postgresql.md
@ -3,7 +3,7 @@ sidebar_position: 40
 sidebar_label: PostgreSQL
 ---

-# PostgreSQL {#postgresql}
+# PostgreSQL

 Allows to connect to databases on a remote [PostgreSQL](https://www.postgresql.org) server. Supports read and write operations (`SELECT` and `INSERT` queries) to exchange data between ClickHouse and PostgreSQL.

--- a/docs/en/engines/database-engines/replicated.md
+++ b/docs/en/engines/database-engines/replicated.md
@ -3,7 +3,7 @@ sidebar_position: 30
 sidebar_label: Replicated
 ---

-# [experimental] Replicated {#replicated}
+# [experimental] Replicated

 The engine is based on the [Atomic](../../engines/database-engines/atomic.md) engine. It supports replication of metadata via DDL log being written to ZooKeeper and executed on all of the replicas for a given database.

@ -20,7 +20,7 @@ One ClickHouse server can have multiple replicated databases running and updatin
 -   `shard_name` — Shard name. Database replicas are grouped into shards by `shard_name`.
 -   `replica_name` — Replica name. Replica names must be different for all replicas of the same shard.

-:::warning    
+:::warning
 For [ReplicatedMergeTree](../table-engines/mergetree-family/replication.md#table_engines-replication) tables if no arguments provided, then default arguments are used: `/clickhouse/tables/{uuid}/{shard}` and `{replica}`. These can be changed in the server settings [default_replica_path](../../operations/server-configuration-parameters/settings.md#default_replica_path) and [default_replica_name](../../operations/server-configuration-parameters/settings.md#default_replica_name). Macro `{uuid}` is unfolded to table's uuid, `{shard}` and `{replica}` are unfolded to values from server config, not from database engine arguments. But in the future, it will be possible to use `shard_name` and `replica_name` of Replicated database.
 :::

--- a/docs/en/engines/database-engines/sqlite.md
+++ b/docs/en/engines/database-engines/sqlite.md
@ -3,21 +3,21 @@ sidebar_position: 55
 sidebar_label: SQLite
 ---

-# SQLite {#sqlite}
+# SQLite

-Allows to connect to [SQLite](https://www.sqlite.org/index.html) database and perform `INSERT` and `SELECT` queries to exchange data between ClickHouse and SQLite. 
+Allows to connect to [SQLite](https://www.sqlite.org/index.html) database and perform `INSERT` and `SELECT` queries to exchange data between ClickHouse and SQLite.

 ## Creating a Database {#creating-a-database}

 ``` sql
-    CREATE DATABASE sqlite_database 
+    CREATE DATABASE sqlite_database
    ENGINE = SQLite('db_path')
 ```

 **Engine Parameters**

 -   `db_path` — Path to a file with SQLite database.
-    
+
 ## Data Types Support {#data_types-support}

 |  SQLite   | ClickHouse                                              |
@ -44,7 +44,7 @@ SHOW TABLES FROM sqlite_db;
 ``` text
 ┌──name───┐
 │ table1  │
-│ table2  │  
+│ table2  │
 └─────────┘
 ```

--- a/docs/en/engines/table-engines/index.md
+++ b/docs/en/engines/table-engines/index.md
@ -4,7 +4,7 @@ toc_priority: 26
 toc_title: Introduction
 ---

-# Table Engines {#table_engines}
+# Table Engines

 The table engine (type of table) determines:

--- a/docs/en/engines/table-engines/integrations/ExternalDistributed.md
+++ b/docs/en/engines/table-engines/integrations/ExternalDistributed.md
@ -3,7 +3,7 @@ sidebar_position: 12
 sidebar_label: ExternalDistributed
 ---

-# ExternalDistributed {#externaldistributed}
+# ExternalDistributed

 The `ExternalDistributed` engine allows to perform `SELECT` queries on data that is stored on a remote servers MySQL or PostgreSQL. Accepts [MySQL](../../../engines/table-engines/integrations/mysql.md) or [PostgreSQL](../../../engines/table-engines/integrations/postgresql.md) engines as an argument so sharding is possible.

--- a/docs/en/engines/table-engines/integrations/embedded-rocksdb.md
+++ b/docs/en/engines/table-engines/integrations/embedded-rocksdb.md
@ -3,7 +3,7 @@ sidebar_position: 9
 sidebar_label: EmbeddedRocksDB
 ---

-# EmbeddedRocksDB Engine {#EmbeddedRocksDB-engine}
+# EmbeddedRocksDB Engine

 This engine allows integrating ClickHouse with [rocksdb](http://rocksdb.org/).

--- a/docs/en/engines/table-engines/integrations/hdfs.md
+++ b/docs/en/engines/table-engines/integrations/hdfs.md
@ -3,7 +3,7 @@ sidebar_position: 6
 sidebar_label: HDFS
 ---

-# HDFS {#table_engines-hdfs}
+# HDFS

 This engine provides integration with the [Apache Hadoop](https://en.wikipedia.org/wiki/Apache_Hadoop) ecosystem by allowing to manage data on [HDFS](https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html) via ClickHouse. This engine is similar to the [File](../../../engines/table-engines/special/file.md#table_engines-file) and [URL](../../../engines/table-engines/special/url.md#table_engines-url) engines, but provides Hadoop-specific features.

@ -51,7 +51,7 @@ SELECT * FROM hdfs_engine_table LIMIT 2
 ## Implementation Details {#implementation-details}

 -   Reads and writes can be parallel.
-   [Zero-copy](../../../operations/storing-data.md#zero-copy) replication is supported.  
+-   [Zero-copy](../../../operations/storing-data.md#zero-copy) replication is supported.
 -   Not supported:
    -   `ALTER` and `SELECT...SAMPLE` operations.
    -   Indexes.
@ -98,7 +98,7 @@ Table consists of all the files in both directories (all files should satisfy fo
 CREATE TABLE table_with_asterisk (name String, value UInt32) ENGINE = HDFS('hdfs://hdfs1:9000/{some,another}_dir/*', 'TSV')
 ```

-:::warning    
+:::warning
 If the listing of files contains number ranges with leading zeros, use the construction with braces for each digit separately or use `?`.
 :::

--- a/docs/en/engines/table-engines/integrations/hive.md
+++ b/docs/en/engines/table-engines/integrations/hive.md
@ -3,11 +3,11 @@ sidebar_position: 4
 sidebar_label: Hive
 ---

-# Hive {#hive}
+# Hive

 The Hive engine allows you to perform `SELECT` quries on HDFS Hive table. Currently it supports input formats as below:

- Text: only supports simple scalar column types except `binary` 
+- Text: only supports simple scalar column types except `binary`

 - ORC: support simple scalar columns types except `char`; only support complex types like `array`

@ -66,33 +66,33 @@ When ClickHouse is started up with local cache for remote filesystem enabled, us
 #### Create Table in Hive
 ``` text
 hive > CREATE TABLE `test`.`test_orc`(
-  `f_tinyint` tinyint, 
-  `f_smallint` smallint, 
-  `f_int` int, 
-  `f_integer` int, 
-  `f_bigint` bigint, 
-  `f_float` float, 
-  `f_double` double, 
-  `f_decimal` decimal(10,0), 
-  `f_timestamp` timestamp, 
-  `f_date` date, 
-  `f_string` string, 
-  `f_varchar` varchar(100), 
-  `f_bool` boolean, 
-  `f_binary` binary, 
-  `f_array_int` array<int>, 
-  `f_array_string` array<string>, 
-  `f_array_float` array<float>, 
-  `f_array_array_int` array<array<int>>, 
-  `f_array_array_string` array<array<string>>, 
+  `f_tinyint` tinyint,
+  `f_smallint` smallint,
+  `f_int` int,
+  `f_integer` int,
+  `f_bigint` bigint,
+  `f_float` float,
+  `f_double` double,
+  `f_decimal` decimal(10,0),
+  `f_timestamp` timestamp,
+  `f_date` date,
+  `f_string` string,
+  `f_varchar` varchar(100),
+  `f_bool` boolean,
+  `f_binary` binary,
+  `f_array_int` array<int>,
+  `f_array_string` array<string>,
+  `f_array_float` array<float>,
+  `f_array_array_int` array<array<int>>,
+  `f_array_array_string` array<array<string>>,
  `f_array_array_float` array<array<float>>)
-PARTITIONED BY ( 
+PARTITIONED BY (
  `day` string)
-ROW FORMAT SERDE 
-  'org.apache.hadoop.hive.ql.io.orc.OrcSerde' 
-STORED AS INPUTFORMAT 
-  'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat' 
-OUTPUTFORMAT 
+ROW FORMAT SERDE
+  'org.apache.hadoop.hive.ql.io.orc.OrcSerde'
+STORED AS INPUTFORMAT
+  'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat'
+OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat'
 LOCATION
  'hdfs://testcluster/data/hive/test.db/test_orc'
@ -178,7 +178,7 @@ f_array_array_float:  [[1.11,2.22],[3.33,4.44]]
 day:                  2021-09-18


-1 rows in set. Elapsed: 0.078 sec. 
+1 rows in set. Elapsed: 0.078 sec.
 ```

 ### Query Hive Table with Parquet Input Format
@ -187,34 +187,34 @@ day:                  2021-09-18
 ``` text
 hive >
 CREATE TABLE `test`.`test_parquet`(
-  `f_tinyint` tinyint, 
-  `f_smallint` smallint, 
-  `f_int` int, 
-  `f_integer` int, 
-  `f_bigint` bigint, 
-  `f_float` float, 
-  `f_double` double, 
-  `f_decimal` decimal(10,0), 
-  `f_timestamp` timestamp, 
-  `f_date` date, 
-  `f_string` string, 
-  `f_varchar` varchar(100), 
-  `f_char` char(100), 
-  `f_bool` boolean, 
-  `f_binary` binary, 
-  `f_array_int` array<int>, 
-  `f_array_string` array<string>, 
-  `f_array_float` array<float>, 
-  `f_array_array_int` array<array<int>>, 
-  `f_array_array_string` array<array<string>>, 
+  `f_tinyint` tinyint,
+  `f_smallint` smallint,
+  `f_int` int,
+  `f_integer` int,
+  `f_bigint` bigint,
+  `f_float` float,
+  `f_double` double,
+  `f_decimal` decimal(10,0),
+  `f_timestamp` timestamp,
+  `f_date` date,
+  `f_string` string,
+  `f_varchar` varchar(100),
+  `f_char` char(100),
+  `f_bool` boolean,
+  `f_binary` binary,
+  `f_array_int` array<int>,
+  `f_array_string` array<string>,
+  `f_array_float` array<float>,
+  `f_array_array_int` array<array<int>>,
+  `f_array_array_string` array<array<string>>,
  `f_array_array_float` array<array<float>>)
-PARTITIONED BY ( 
+PARTITIONED BY (
  `day` string)
-ROW FORMAT SERDE 
-  'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe' 
-STORED AS INPUTFORMAT 
-  'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat' 
-OUTPUTFORMAT 
+ROW FORMAT SERDE
+  'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
+STORED AS INPUTFORMAT
+  'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
+OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
 LOCATION
  'hdfs://testcluster/data/hive/test.db/test_parquet'
@ -299,7 +299,7 @@ f_array_array_string: [['a','b'],['c','d']]
 f_array_array_float:  [[1.11,2.22],[3.33,4.44]]
 day:                  2021-09-18

-1 rows in set. Elapsed: 0.357 sec. 
+1 rows in set. Elapsed: 0.357 sec.
 ```

 ### Query Hive Table with Text Input Format
@ -307,34 +307,34 @@ day:                  2021-09-18
 ``` text
 hive >
 CREATE TABLE `test`.`test_text`(
-  `f_tinyint` tinyint, 
-  `f_smallint` smallint, 
-  `f_int` int, 
-  `f_integer` int, 
-  `f_bigint` bigint, 
-  `f_float` float, 
-  `f_double` double, 
-  `f_decimal` decimal(10,0), 
-  `f_timestamp` timestamp, 
-  `f_date` date, 
-  `f_string` string, 
-  `f_varchar` varchar(100), 
-  `f_char` char(100), 
-  `f_bool` boolean, 
-  `f_binary` binary, 
-  `f_array_int` array<int>, 
-  `f_array_string` array<string>, 
-  `f_array_float` array<float>, 
-  `f_array_array_int` array<array<int>>, 
-  `f_array_array_string` array<array<string>>, 
+  `f_tinyint` tinyint,
+  `f_smallint` smallint,
+  `f_int` int,
+  `f_integer` int,
+  `f_bigint` bigint,
+  `f_float` float,
+  `f_double` double,
+  `f_decimal` decimal(10,0),
+  `f_timestamp` timestamp,
+  `f_date` date,
+  `f_string` string,
+  `f_varchar` varchar(100),
+  `f_char` char(100),
+  `f_bool` boolean,
+  `f_binary` binary,
+  `f_array_int` array<int>,
+  `f_array_string` array<string>,
+  `f_array_float` array<float>,
+  `f_array_array_int` array<array<int>>,
+  `f_array_array_string` array<array<string>>,
  `f_array_array_float` array<array<float>>)
-PARTITIONED BY ( 
+PARTITIONED BY (
  `day` string)
-ROW FORMAT SERDE 
-  'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' 
-STORED AS INPUTFORMAT 
-  'org.apache.hadoop.mapred.TextInputFormat' 
-OUTPUTFORMAT 
+ROW FORMAT SERDE
+  'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
+STORED AS INPUTFORMAT
+  'org.apache.hadoop.mapred.TextInputFormat'
+OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
 LOCATION
  'hdfs://testcluster/data/hive/test.db/test_text'
@ -374,7 +374,7 @@ CREATE TABLE test.test_text
    `day` String
 )
 ENGINE = Hive('thrift://localhost:9083', 'test', 'test_text')
-PARTITION BY day 
+PARTITION BY day
 ```

 ``` sql
--- a/docs/en/engines/table-engines/integrations/index.md
+++ b/docs/en/engines/table-engines/integrations/index.md
@ -3,7 +3,7 @@ sidebar_position: 40
 sidebar_label:  Integrations
 ---

-# Table Engines for Integrations {#table-engines-for-integrations}
+# Table Engines for Integrations

 ClickHouse provides various means for integrating with external systems, including table engines. Like with all other table engines, the configuration is done using `CREATE TABLE` or `ALTER TABLE` queries. Then from a user perspective, the configured integration looks like a normal table, but queries to it are proxied to the external system. This transparent querying is one of the key advantages of this approach over alternative integration methods, like external dictionaries or table functions, which require to use custom query methods on each use.

--- a/docs/en/engines/table-engines/integrations/jdbc.md
+++ b/docs/en/engines/table-engines/integrations/jdbc.md
@ -3,7 +3,7 @@ sidebar_position: 3
 sidebar_label: JDBC
 ---

-# JDBC {#table-engine-jdbc}
+# JDBC

 Allows ClickHouse to connect to external databases via [JDBC](https://en.wikipedia.org/wiki/Java_Database_Connectivity).

--- a/docs/en/engines/table-engines/integrations/kafka.md
+++ b/docs/en/engines/table-engines/integrations/kafka.md
@ -3,7 +3,7 @@ sidebar_position: 8
 sidebar_label: Kafka
 ---

-# Kafka {#kafka}
+# Kafka

 This engine works with [Apache Kafka](http://kafka.apache.org/).

@ -87,7 +87,7 @@ Examples:

 <summary>Deprecated Method for Creating a Table</summary>

-:::warning    
+:::warning
 Do not use this method in new projects. If possible, switch old projects to the method described above.
 :::

--- a/docs/en/engines/table-engines/integrations/materialized-postgresql.md
+++ b/docs/en/engines/table-engines/integrations/materialized-postgresql.md
@ -3,7 +3,7 @@ sidebar_position: 12
 sidebar_label: MaterializedPostgreSQL
 ---

-# MaterializedPostgreSQL {#materialize-postgresql}
+# MaterializedPostgreSQL

 Creates ClickHouse table with an initial data dump of PostgreSQL table and starts replication process, i.e. executes background job to apply new changes as they happen on PostgreSQL table in the remote PostgreSQL database.

@ -52,7 +52,7 @@ PRIMARY KEY key;
 SELECT key, value, _version FROM postgresql_db.postgresql_replica;
 ```

-:::warning    
+:::warning
 Replication of [**TOAST**](https://www.postgresql.org/docs/9.5/storage-toast.html) values is not supported. The default value for the data type will be used.
 :::

--- a/docs/en/engines/table-engines/integrations/mongodb.md
+++ b/docs/en/engines/table-engines/integrations/mongodb.md
@ -3,7 +3,7 @@ sidebar_position: 5
 sidebar_label: MongoDB
 ---

-# MongoDB {#mongodb}
+# MongoDB

 MongoDB engine is read-only table engine which allows to read data (`SELECT` queries) from remote MongoDB collection. Engine supports only non-nested data types. `INSERT` queries are not supported.

--- a/docs/en/engines/table-engines/integrations/mysql.md
+++ b/docs/en/engines/table-engines/integrations/mysql.md
@ -3,7 +3,7 @@ sidebar_position: 4
 sidebar_label: MySQL
 ---

-# MySQL {#mysql}
+# MySQL

 The MySQL engine allows you to perform `SELECT` and `INSERT` queries on data that is stored on a remote MySQL server.

--- a/docs/en/engines/table-engines/integrations/odbc.md
+++ b/docs/en/engines/table-engines/integrations/odbc.md
@ -3,7 +3,7 @@ sidebar_position: 2
 sidebar_label: ODBC
 ---

-# ODBC {#table-engine-odbc}
+# ODBC

 Allows ClickHouse to connect to external databases via [ODBC](https://en.wikipedia.org/wiki/Open_Database_Connectivity).

--- a/docs/en/engines/table-engines/integrations/postgresql.md
+++ b/docs/en/engines/table-engines/integrations/postgresql.md
@ -3,7 +3,7 @@ sidebar_position: 11
 sidebar_label: PostgreSQL
 ---

-# PostgreSQL {#postgresql}
+# PostgreSQL

 The PostgreSQL engine allows to perform `SELECT` and `INSERT` queries on data that is stored on a remote PostgreSQL server.

--- a/docs/en/engines/table-engines/integrations/rabbitmq.md
+++ b/docs/en/engines/table-engines/integrations/rabbitmq.md
@ -3,7 +3,7 @@ sidebar_position: 10
 sidebar_label: RabbitMQ
 ---

-# RabbitMQ Engine {#rabbitmq-engine}
+# RabbitMQ Engine

 This engine allows integrating ClickHouse with [RabbitMQ](https://www.rabbitmq.com).

--- a/docs/en/engines/table-engines/integrations/s3.md
+++ b/docs/en/engines/table-engines/integrations/s3.md
@ -3,7 +3,7 @@ sidebar_position: 7
 sidebar_label: S3
 ---

-# S3 Table Engine {#table-engine-s3}
+# S3 Table Engine

 This engine provides integration with [Amazon S3](https://aws.amazon.com/s3/) ecosystem. This engine is similar to the [HDFS](../../../engines/table-engines/special/file.md#table_engines-hdfs) engine, but provides S3-specific features.

@ -25,7 +25,7 @@ CREATE TABLE s3_engine_table (name String, value UInt32)
 **Example**

 ``` sql
-CREATE TABLE s3_engine_table (name String, value UInt32) 
+CREATE TABLE s3_engine_table (name String, value UInt32)
    ENGINE=S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/test-data.csv.gz', 'CSV', 'gzip')
    SETTINGS input_format_with_names_use_header = 0;

@ -50,7 +50,7 @@ For more information about virtual columns see [here](../../../engines/table-eng
 ## Implementation Details {#implementation-details}

 -   Reads and writes can be parallel
-   [Zero-copy](../../../operations/storing-data.md#zero-copy) replication is supported.  
+-   [Zero-copy](../../../operations/storing-data.md#zero-copy) replication is supported.
 -   Not supported:
    -   `ALTER` and `SELECT...SAMPLE` operations.
    -   Indexes.
@ -66,7 +66,7 @@ For more information about virtual columns see [here](../../../engines/table-eng

 Constructions with `{}` are similar to the [remote](../../../sql-reference/table-functions/remote.md) table function.

-:::warning    
+:::warning
 If the listing of files contains number ranges with leading zeros, use the construction with braces for each digit separately or use `?`.
 :::

--- a/docs/en/engines/table-engines/integrations/sqlite.md
+++ b/docs/en/engines/table-engines/integrations/sqlite.md
@ -3,16 +3,16 @@ sidebar_position: 7
 sidebar_label: SQLite
 ---

-# SQLite {#sqlite}
+# SQLite

 The engine allows to import and export data to SQLite and supports queries to SQLite tables directly from ClickHouse.

 ## Creating a Table {#creating-a-table}

 ``` sql
-    CREATE TABLE [IF NOT EXISTS] [db.]table_name 
+    CREATE TABLE [IF NOT EXISTS] [db.]table_name
    (
-        name1 [type1], 
+        name1 [type1],
        name2 [type2], ...
    ) ENGINE = SQLite('db_path', 'table')
 ```
@ -32,10 +32,10 @@ SHOW CREATE TABLE sqlite_db.table2;

 ``` text
 CREATE TABLE SQLite.table2
-( 
-    `col1` Nullable(Int32), 
+(
+    `col1` Nullable(Int32),
    `col2` Nullable(String)
-) 
+)
 ENGINE = SQLite('sqlite.db','table2');
 ```

--- a/docs/en/engines/table-engines/log-family/index.md
+++ b/docs/en/engines/table-engines/log-family/index.md
@ -3,7 +3,7 @@ sidebar_position: 20
 sidebar_label:  Log Family
 ---

-# Log Engine Family {#log-engine-family}
+# Log Engine Family

 These engines were developed for scenarios when you need to quickly write many small tables (up to about 1 million rows) and read them later as a whole.

--- a/docs/en/engines/table-engines/log-family/log.md
+++ b/docs/en/engines/table-engines/log-family/log.md
@ -3,7 +3,7 @@ toc_priority: 33
 toc_title: Log
 ---

-# Log {#log}
+# Log

 The engine belongs to the family of `Log` engines. See the common properties of `Log` engines and their differences in the [Log Engine Family](../../../engines/table-engines/log-family/index.md) article.

--- a/docs/en/engines/table-engines/log-family/stripelog.md
+++ b/docs/en/engines/table-engines/log-family/stripelog.md
@ -3,7 +3,7 @@ toc_priority: 32
 toc_title: StripeLog
 ---

-# Stripelog {#stripelog}
+# Stripelog

 This engine belongs to the family of log engines. See the common properties of log engines and their differences in the [Log Engine Family](../../../engines/table-engines/log-family/index.md) article.

--- a/docs/en/engines/table-engines/log-family/tinylog.md
+++ b/docs/en/engines/table-engines/log-family/tinylog.md
@ -3,7 +3,7 @@ toc_priority: 34
 toc_title: TinyLog
 ---

-# TinyLog {#tinylog}
+# TinyLog

 The engine belongs to the log engine family. See [Log Engine Family](../../../engines/table-engines/log-family/index.md) for common properties of log engines and their differences.

--- a/docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md
@ -3,7 +3,7 @@ sidebar_position: 60
 sidebar_label:  AggregatingMergeTree
 ---

-# AggregatingMergeTree {#aggregatingmergetree}
+# AggregatingMergeTree

 The engine inherits from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree), altering the logic for data parts merging. ClickHouse replaces all rows with the same primary key (or more accurately, with the same [sorting key](../../../engines/table-engines/mergetree-family/mergetree.md)) with a single row (within a one data part) that stores a combination of states of aggregate functions.

--- a/docs/en/engines/table-engines/mergetree-family/collapsingmergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/collapsingmergetree.md
@ -3,7 +3,7 @@ sidebar_position: 70
 sidebar_label: CollapsingMergeTree
 ---

-# CollapsingMergeTree {#table_engine-collapsingmergetree}
+# CollapsingMergeTree

 The engine inherits from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md) and adds the logic of rows collapsing to data parts merge algorithm.

@ -42,7 +42,7 @@ When creating a `CollapsingMergeTree` table, the same [query clauses](../../../e

 <summary>Deprecated Method for Creating a Table</summary>

-:::warning    
+:::warning
 Do not use this method in new projects and, if possible, switch old projects to the method described above.
 :::

--- a/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md
+++ b/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md
@ -3,10 +3,10 @@ sidebar_position: 30
 sidebar_label: Custom Partitioning Key
 ---

-# Custom Partitioning Key {#custom-partitioning-key}
+# Custom Partitioning Key

-:::warning   
-In most cases you do not need a partition key, and in most other cases you do not need a partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression). 
+:::warning
+In most cases you do not need a partition key, and in most other cases you do not need a partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression).

 You should never use too granular of partitioning. Don't partition your data by client identifiers or names. Instead, make a client identifier or name the first column in the ORDER BY expression.
 :::
@ -43,7 +43,7 @@ By default, the floating-point partition key is not supported. To use it enable

 When inserting new data to a table, this data is stored as a separate part (chunk) sorted by the primary key. In 10-15 minutes after inserting, the parts of the same partition are merged into the entire part.

-:::info    
+:::info
 A merge only works for data parts that have the same value for the partitioning expression. This means **you shouldn’t make overly granular partitions** (more than about a thousand partitions). Otherwise, the `SELECT` query performs poorly because of an unreasonably large number of files in the file system and open file descriptors.
 :::

--- a/docs/en/engines/table-engines/mergetree-family/graphitemergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/graphitemergetree.md
@ -3,7 +3,7 @@ sidebar_position: 90
 sidebar_label:  GraphiteMergeTree
 ---

-# GraphiteMergeTree {#graphitemergetree}
+# GraphiteMergeTree

 This engine is designed for thinning and aggregating/averaging (rollup) [Graphite](http://graphite.readthedocs.io/en/latest/index.html) data. It may be helpful to developers who want to use ClickHouse as a data store for Graphite.

@ -54,7 +54,7 @@ When creating a `GraphiteMergeTree` table, the same [clauses](../../../engines/t

 <summary>Deprecated Method for Creating a Table</summary>

-:::warning    
+:::warning
 Do not use this method in new projects and, if possible, switch old projects to the method described above.
 :::

@ -120,7 +120,7 @@ default
    ...
 ```

-:::warning    
+:::warning
 Patterns must be strictly ordered:

 1. Patterns without `function` or `retention`.
@ -132,9 +132,9 @@ When processing a row, ClickHouse checks the rules in the `pattern` sections. Ea

 Fields for `pattern` and `default` sections:

-   `rule_type` - a rule's type. It's applied only to a particular metrics. The engine use it to separate plain and tagged metrics. Optional parameter. Default value: `all`.  
-It's unnecessary when performance is not critical, or only one metrics type is used, e.g. plain metrics. By default only one type of rules set is created. Otherwise, if any of special types is defined, two different sets are created. One for plain metrics (root.branch.leaf) and one for tagged metrics (root.branch.leaf;tag1=value1).  
-The default rules are ended up in both sets.  
+-   `rule_type` - a rule's type. It's applied only to a particular metrics. The engine use it to separate plain and tagged metrics. Optional parameter. Default value: `all`.
+It's unnecessary when performance is not critical, or only one metrics type is used, e.g. plain metrics. By default only one type of rules set is created. Otherwise, if any of special types is defined, two different sets are created. One for plain metrics (root.branch.leaf) and one for tagged metrics (root.branch.leaf;tag1=value1).
+The default rules are ended up in both sets.
 Valid values:
    -   `all` (default) - a universal rule, used when `rule_type` is omitted.
    -   `plain` - a rule for plain metrics. The field `regexp` is processed as regular expression.
@ -143,7 +143,7 @@ Valid values:
 -   `regexp` – A pattern for the metric name (a regular or DSL).
 -   `age` – The minimum age of the data in seconds.
 -   `precision`– How precisely to define the age of the data in seconds. Should be a divisor for 86400 (seconds in a day).
-   `function` – The name of the aggregating function to apply to data whose age falls within the range `[age, age + precision]`. Accepted functions: min / max / any / avg. The average is calculated imprecisely, like the average of the averages. 
+-   `function` – The name of the aggregating function to apply to data whose age falls within the range `[age, age + precision]`. Accepted functions: min / max / any / avg. The average is calculated imprecisely, like the average of the averages.

 ### Configuration Example without rules types {#configuration-example}

--- a/docs/en/engines/table-engines/mergetree-family/index.md
+++ b/docs/en/engines/table-engines/mergetree-family/index.md
@ -3,7 +3,7 @@ sidebar_position: 10
 sidebar_label: MergeTree Family
 ---

-# MergeTree Engine Family {#mergetree-engine-family}
+# MergeTree Engine Family

 Table engines from the MergeTree family are the core of ClickHouse data storage capabilities. They provide most features for resilience and high-performance data retrieval: columnar storage, custom partitioning, sparse primary index, secondary data-skipping indexes, etc.

--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@ -3,7 +3,7 @@ sidebar_position: 11
 sidebar_label:  MergeTree
 ---

-# MergeTree {#table_engines-mergetree}
+# MergeTree

 The `MergeTree` engine and other engines of this family (`*MergeTree`) are the most robust ClickHouse table engines.

@ -694,7 +694,7 @@ Tags:
 -   `volume_name_N` — Volume name. Volume names must be unique.
 -   `disk` — a disk within a volume.
 -   `max_data_part_size_bytes` — the maximum size of a part that can be stored on any of the volume’s disks. If the a size of a merged part estimated to be bigger than `max_data_part_size_bytes` then this part will be written to a next volume. Basically this feature allows to keep new/small parts on a hot (SSD) volume and move them to a cold (HDD) volume when they reach large size. Do not use this setting if your policy has only one volume.
-   `move_factor` — when the amount of available space gets lower than this factor, data automatically starts to move on the next volume if any (by default, 0.1). ClickHouse sorts existing parts by size from largest to smallest (in descending order) and selects parts with the total size that is sufficient to meet the `move_factor` condition. If the total size of all parts is insufficient, all parts will be moved. 
+-   `move_factor` — when the amount of available space gets lower than this factor, data automatically starts to move on the next volume if any (by default, 0.1). ClickHouse sorts existing parts by size from largest to smallest (in descending order) and selects parts with the total size that is sufficient to meet the `move_factor` condition. If the total size of all parts is insufficient, all parts will be moved.
 -   `prefer_not_to_merge` — Disables merging of data parts on this volume. When this setting is enabled, merging data on this volume is not allowed. This allows controlling how ClickHouse works with slow disks.
 -   `perform_ttl_move_on_insert` — Disables TTL move on data part INSERT. By default if we insert a data part that already expired by the TTL move rule it immediately goes to a volume/disk declared in move rule. This can significantly slowdown insert in case if destination volume/disk is slow (e.g. S3).
 -   `load_balancing` - Policy for disk balancing, `round_robin` or `least_used`.
--- a/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md
@ -3,7 +3,7 @@ sidebar_position: 40
 sidebar_label:  ReplacingMergeTree
 ---

-# ReplacingMergeTree {#replacingmergetree}
+# ReplacingMergeTree

 The engine differs from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree) in that it removes duplicate entries with the same [sorting key](../../../engines/table-engines/mergetree-family/mergetree.md) value (`ORDER BY` table section, not `PRIMARY KEY`).

--- a/docs/en/engines/table-engines/mergetree-family/replication.md
+++ b/docs/en/engines/table-engines/mergetree-family/replication.md
@ -3,7 +3,7 @@ sidebar_position: 20
 sidebar_label: Data Replication
 ---

-# Data Replication {#table_engines-replication}
+# Data Replication

 Replication is only supported for tables in the MergeTree family:

@ -112,7 +112,7 @@ Data blocks are deduplicated. For multiple writes of the same data block (data b

 During replication, only the source data to insert is transferred over the network. Further data transformation (merging) is coordinated and performed on all the replicas in the same way. This minimizes network usage, which means that replication works well when replicas reside in different datacenters. (Note that duplicating data in different datacenters is the main goal of replication.)

-You can have any number of replicas of the same data. Based on our experiences, a relatively reliable and convenient solution could use double replication in production, with each server using RAID-5 or RAID-6 (and RAID-10 in some cases). 
+You can have any number of replicas of the same data. Based on our experiences, a relatively reliable and convenient solution could use double replication in production, with each server using RAID-5 or RAID-6 (and RAID-10 in some cases).

 The system monitors data synchronicity on replicas and is able to recover after a failure. Failover is automatic (for small differences in data) or semi-automatic (when data differs too much, which may indicate a configuration error).

--- a/docs/en/engines/table-engines/mergetree-family/summingmergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/summingmergetree.md
@ -3,7 +3,7 @@ sidebar_position: 50
 sidebar_label:  SummingMergeTree
 ---

-# SummingMergeTree {#summingmergetree}
+# SummingMergeTree

 The engine inherits from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree). The difference is that when merging data parts for `SummingMergeTree` tables ClickHouse replaces all the rows with the same primary key (or more accurately, with the same [sorting key](../../../engines/table-engines/mergetree-family/mergetree.md)) with one row which contains summarized values for the columns with the numeric data type. If the sorting key is composed in a way that a single key value corresponds to large number of rows, this significantly reduces storage volume and speeds up data selection.

--- a/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md
@ -3,7 +3,7 @@ sidebar_position: 80
 sidebar_label:  VersionedCollapsingMergeTree
 ---

-# VersionedCollapsingMergeTree {#versionedcollapsingmergetree}
+# VersionedCollapsingMergeTree

 This engine:

@ -53,7 +53,7 @@ When creating a `VersionedCollapsingMergeTree` table, the same [clauses](../../.

 <summary>Deprecated Method for Creating a Table</summary>

-:::warning    
+:::warning
 Do not use this method in new projects. If possible, switch old projects to the method described above.
 :::

--- a/docs/en/engines/table-engines/special/buffer.md
+++ b/docs/en/engines/table-engines/special/buffer.md
@ -3,7 +3,7 @@ sidebar_position: 120
 sidebar_label:  Buffer
 ---

-# Buffer Table Engine {#buffer}
+# Buffer Table Engine

 Buffers the data to write in RAM, periodically flushing it to another table. During the read operation, data is read from the buffer and the other table simultaneously.

@ -54,7 +54,7 @@ If the set of columns in the Buffer table does not match the set of columns in a
 If the types do not match for one of the columns in the Buffer table and a subordinate table, an error message is entered in the server log, and the buffer is cleared.
 The same thing happens if the subordinate table does not exist when the buffer is flushed.

-:::warning    
+:::warning
 Running ALTER on the Buffer table in releases made before 26 Oct 2021 will cause a `Block structure mismatch` error (see [#15117](https://github.com/ClickHouse/ClickHouse/issues/15117) and [#30565](https://github.com/ClickHouse/ClickHouse/pull/30565)), so deleting the Buffer table and then recreating is the only option. It is advisable to check that this error is fixed in your release before trying to run ALTER on the Buffer table.
 :::

--- a/docs/en/engines/table-engines/special/dictionary.md
+++ b/docs/en/engines/table-engines/special/dictionary.md
@ -3,7 +3,7 @@ sidebar_position: 20
 sidebar_label: Dictionary
 ---

-# Dictionary Table Engine {#dictionary}
+# Dictionary Table Engine

 The `Dictionary` engine displays the [dictionary](../../../sql-reference/dictionaries/external-dictionaries/external-dicts.md) data as a ClickHouse table.

--- a/Show More
+++ b/Show More