Merge branch 'master' into ADQM-970

.github/workflows/master.yml

@@ -850,6 +850,48 @@ 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"
+  BuilderBinRISCV64:
+    needs: [DockerHubPush]
+    runs-on: [self-hosted, builder]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/build_check
+          IMAGES_PATH=${{runner.temp}}/images_path
+          REPO_COPY=${{runner.temp}}/build_check/ClickHouse
+          CACHES_PATH=${{runner.temp}}/../ccaches
+          BUILD_NAME=binary_riscv64
+          EOF
+      - name: Download changed images
+        uses: actions/download-artifact@v3
+        with:
+          name: changed_images
+          path: ${{ env.IMAGES_PATH }}
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+          submodules: true
+          fetch-depth: 0 # otherwise we will have no info about contributors
+      - name: Build
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
+      - name: Upload build URLs to artifacts
+        if: ${{ success() || failure() }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: ${{ env.BUILD_URLS }}
+          path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
+      - 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 "$TEMP_PATH" "$CACHES_PATH"
 ############################################################################################
 ##################################### Docker images  #######################################
 ############################################################################################
@@ -932,6 +974,7 @@ jobs:
       - BuilderBinDarwinAarch64
       - BuilderBinFreeBSD
       - BuilderBinPPC64
+      - BuilderBinRISCV64
       - BuilderBinAmd64Compat
       - BuilderBinAarch64V80Compat
       - BuilderBinClangTidy

.github/workflows/nightly.yml

@@ -75,51 +75,6 @@ jobs:
   Codebrowser:
     needs: [DockerHubPush]
     uses: ./.github/workflows/woboq.yml
-  BuilderCoverity:
-    needs: DockerHubPush
-    runs-on: [self-hosted, builder]
-    steps:
-      - name: Set envs
-        run: |
-          cat >> "$GITHUB_ENV" << 'EOF'
-          BUILD_NAME=coverity
-          CACHES_PATH=${{runner.temp}}/../ccaches
-          IMAGES_PATH=${{runner.temp}}/images_path
-          REPO_COPY=${{runner.temp}}/build_check/ClickHouse
-          TEMP_PATH=${{runner.temp}}/build_check
-          EOF
-          echo "COVERITY_TOKEN=${{ secrets.COVERITY_TOKEN }}" >> "$GITHUB_ENV"
-      - name: Download changed images
-        uses: actions/download-artifact@v3
-        with:
-          name: changed_images
-          path: ${{ env.IMAGES_PATH }}
-      - name: Check out repository code
-        uses: ClickHouse/checkout@v1
-        with:
-          clear-repository: true
-          submodules: true
-      - name: Build
-        run: |
-          sudo rm -fr "$TEMP_PATH"
-          mkdir -p "$TEMP_PATH"
-          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
-          cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
-      - name: Upload Coverity Analysis
-        if: ${{ success() || failure() }}
-        run: |
-          curl --form token="${COVERITY_TOKEN}" \
-            --form email='security+coverity@clickhouse.com' \
-            --form file="@$TEMP_PATH/$BUILD_NAME/coverity-scan.tar.gz" \
-            --form version="${GITHUB_REF#refs/heads/}-${GITHUB_SHA::6}" \
-            --form description="Nighly Scan: $(date +'%Y-%m-%dT%H:%M:%S')" \
-            https://scan.coverity.com/builds?project=ClickHouse%2FClickHouse
-      - name: Cleanup
-        if: always()
-        run: |
-          docker ps --quiet | xargs --no-run-if-empty docker kill ||:
-          docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
-          sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
   SonarCloud:
     runs-on: [self-hosted, builder]
     env:

.github/workflows/pull_request.yml

@@ -911,6 +911,47 @@ 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"
+  BuilderBinRISCV64:
+    needs: [DockerHubPush, FastTest, StyleCheck]
+    runs-on: [self-hosted, builder]
+    steps:
+      - name: Set envs
+        run: |
+          cat >> "$GITHUB_ENV" << 'EOF'
+          TEMP_PATH=${{runner.temp}}/build_check
+          IMAGES_PATH=${{runner.temp}}/images_path
+          REPO_COPY=${{runner.temp}}/build_check/ClickHouse
+          CACHES_PATH=${{runner.temp}}/../ccaches
+          BUILD_NAME=binary_riscv64
+          EOF
+      - name: Download changed images
+        uses: actions/download-artifact@v3
+        with:
+          name: changed_images
+          path: ${{ env.IMAGES_PATH }}
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          clear-repository: true
+          submodules: true
+      - name: Build
+        run: |
+          sudo rm -fr "$TEMP_PATH"
+          mkdir -p "$TEMP_PATH"
+          cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
+          cd "$REPO_COPY/tests/ci" && python3 build_check.py "$BUILD_NAME"
+      - name: Upload build URLs to artifacts
+        if: ${{ success() || failure() }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: ${{ env.BUILD_URLS }}
+          path: ${{ env.TEMP_PATH }}/${{ env.BUILD_URLS }}.json
+      - 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 "$TEMP_PATH" "$CACHES_PATH"
 ############################################################################################
 ##################################### Docker images  #######################################
 ############################################################################################
@@ -992,6 +1033,7 @@ jobs:
       - BuilderBinDarwinAarch64
       - BuilderBinFreeBSD
       - BuilderBinPPC64
+      - BuilderBinRISCV64
       - BuilderBinAmd64Compat
       - BuilderBinAarch64V80Compat
       - BuilderBinClangTidy

CMakeLists.txt

@@ -87,7 +87,6 @@ if (ENABLE_FUZZING)
     set (ENABLE_CLICKHOUSE_ODBC_BRIDGE OFF)
     set (ENABLE_LIBRARIES 0)
     set (ENABLE_SSL 1)
-    set (USE_UNWIND ON)
     set (ENABLE_EMBEDDED_COMPILER 0)
     set (ENABLE_EXAMPLES 0)
     set (ENABLE_UTILS 0)
@@ -344,9 +343,9 @@ if (COMPILER_CLANG)
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-absolute-paths")
     set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-absolute-paths")
 
-    if (NOT ENABLE_TESTS AND NOT SANITIZE)
+    if (NOT ENABLE_TESTS AND NOT SANITIZE AND OS_LINUX)
         # https://clang.llvm.org/docs/ThinLTO.html
-        # Applies to clang only.
+        # Applies to clang and linux only.
         # Disabled when building with tests or sanitizers.
         option(ENABLE_THINLTO "Clang-specific link time optimization" ON)
     endif()

base/base/getThreadId.cpp

@@ -15,25 +15,34 @@
 
 
 static thread_local uint64_t current_tid = 0;
+
+static void setCurrentThreadId()
+{
+#if defined(OS_ANDROID)
+    current_tid = gettid();
+#elif defined(OS_LINUX)
+    current_tid = static_cast<uint64_t>(syscall(SYS_gettid)); /// This call is always successful. - man gettid
+#elif defined(OS_FREEBSD)
+    current_tid = pthread_getthreadid_np();
+#elif defined(OS_SUNOS)
+    // On Solaris-derived systems, this returns the ID of the LWP, analogous
+    // to a thread.
+    current_tid = static_cast<uint64_t>(pthread_self());
+#else
+    if (0 != pthread_threadid_np(nullptr, &current_tid))
+        throw std::logic_error("pthread_threadid_np returned error");
+#endif
+}
+
 uint64_t getThreadId()
 {
     if (!current_tid)
-    {
+        setCurrentThreadId();
-#if defined(OS_ANDROID)
-        current_tid = gettid();
-#elif defined(OS_LINUX)
-        current_tid = static_cast<uint64_t>(syscall(SYS_gettid)); /// This call is always successful. - man gettid
-#elif defined(OS_FREEBSD)
-        current_tid = pthread_getthreadid_np();
-#elif defined(OS_SUNOS)
-        // On Solaris-derived systems, this returns the ID of the LWP, analogous
-        // to a thread.
-        current_tid = static_cast<uint64_t>(pthread_self());
-#else
-        if (0 != pthread_threadid_np(nullptr, &current_tid))
-            throw std::logic_error("pthread_threadid_np returned error");
-#endif
-    }
 
     return current_tid;
 }
+
+void updateCurrentThreadIdAfterFork()
+{
+    setCurrentThreadId();
+}

base/base/getThreadId.h

@@ -3,3 +3,5 @@
 
 /// Obtain thread id from OS. The value is cached in thread local variable.
 uint64_t getThreadId();
+
+void updateCurrentThreadIdAfterFork();

cmake/darwin/default_libs.cmake

@@ -15,6 +15,7 @@ set(CMAKE_OSX_DEPLOYMENT_TARGET 10.15)
 set(THREADS_PREFER_PTHREAD_FLAG ON)
 find_package(Threads REQUIRED)
 
+include (cmake/unwind.cmake)
 include (cmake/cxx.cmake)
 link_libraries(global-group)
 

cmake/limit_jobs.cmake

@@ -18,6 +18,9 @@ if (NOT PARALLEL_COMPILE_JOBS AND TOTAL_PHYSICAL_MEMORY AND MAX_COMPILER_MEMORY)
     if (NOT PARALLEL_COMPILE_JOBS)
         set (PARALLEL_COMPILE_JOBS 1)
     endif ()
+    if (NOT NUMBER_OF_LOGICAL_CORES OR PARALLEL_COMPILE_JOBS LESS NUMBER_OF_LOGICAL_CORES)
+        set (PARALLEL_COMPILE_JOBS_LESS TRUE)
+    endif()
 endif ()
 
 if (PARALLEL_COMPILE_JOBS AND (NOT NUMBER_OF_LOGICAL_CORES OR PARALLEL_COMPILE_JOBS LESS NUMBER_OF_LOGICAL_CORES))
@@ -33,6 +36,9 @@ if (NOT PARALLEL_LINK_JOBS AND TOTAL_PHYSICAL_MEMORY AND MAX_LINKER_MEMORY)
     if (NOT PARALLEL_LINK_JOBS)
         set (PARALLEL_LINK_JOBS 1)
     endif ()
+    if (NOT NUMBER_OF_LOGICAL_CORES OR PARALLEL_LINK_JOBS LESS NUMBER_OF_LOGICAL_CORES)
+        set (PARALLEL_LINK_JOBS_LESS TRUE)
+    endif()
 endif ()
 
 # ThinLTO provides its own parallel linking
@@ -56,4 +62,10 @@ if (PARALLEL_COMPILE_JOBS OR PARALLEL_LINK_JOBS)
     message(STATUS
         "${CMAKE_CURRENT_SOURCE_DIR}: Have ${TOTAL_PHYSICAL_MEMORY} megabytes of memory.
         Limiting concurrent linkers jobs to ${PARALLEL_LINK_JOBS} and compiler jobs to ${PARALLEL_COMPILE_JOBS} (system has ${NUMBER_OF_LOGICAL_CORES} logical cores)")
+    if (PARALLEL_COMPILE_JOBS_LESS)
+        message(WARNING "The autocalculated compile jobs limit (${PARALLEL_COMPILE_JOBS}) underutilizes CPU cores (${NUMBER_OF_LOGICAL_CORES}). Set PARALLEL_COMPILE_JOBS to override.")
+    endif()
+    if (PARALLEL_LINK_JOBS_LESS)
+        message(WARNING "The autocalculated link jobs limit (${PARALLEL_LINK_JOBS}) underutilizes CPU cores (${NUMBER_OF_LOGICAL_CORES}). Set PARALLEL_LINK_JOBS to override.")
+    endif()
 endif ()

cmake/target.cmake

@@ -33,6 +33,18 @@ if (CMAKE_CROSSCOMPILING)
         elseif (ARCH_PPC64LE)
             set (ENABLE_GRPC OFF CACHE INTERNAL "")
             set (ENABLE_SENTRY OFF CACHE INTERNAL "")
+        elseif (ARCH_RISCV64)
+            # RISC-V support is preliminary
+            set (GLIBC_COMPATIBILITY OFF CACHE INTERNAL "")
+            set (ENABLE_LDAP OFF CACHE INTERNAL "")
+            set (OPENSSL_NO_ASM ON CACHE INTERNAL "")
+            set (ENABLE_JEMALLOC ON CACHE INTERNAL "")
+            set (ENABLE_PARQUET OFF CACHE INTERNAL "")
+            set (ENABLE_GRPC OFF CACHE INTERNAL "")
+            set (ENABLE_HDFS OFF CACHE INTERNAL "")
+            set (ENABLE_MYSQL OFF CACHE INTERNAL "")
+            # It might be ok, but we need to update 'sysroot'
+            set (ENABLE_RUST OFF CACHE INTERNAL "")
         elseif (ARCH_S390X)
             set (ENABLE_GRPC OFF CACHE INTERNAL "")
             set (ENABLE_SENTRY OFF CACHE INTERNAL "")

cmake/unwind.cmake

@@ -1,13 +1 @@
-option (USE_UNWIND "Enable libunwind (better stacktraces)" ${ENABLE_LIBRARIES})
+add_subdirectory(contrib/libunwind-cmake)
-
-if (USE_UNWIND)
-    add_subdirectory(contrib/libunwind-cmake)
-    set (UNWIND_LIBRARIES unwind)
-    set (EXCEPTION_HANDLING_LIBRARY ${UNWIND_LIBRARIES})
-
-    message (STATUS "Using libunwind: ${UNWIND_LIBRARIES}")
-else ()
-    set (EXCEPTION_HANDLING_LIBRARY gcc_eh)
-endif ()
-
-message (STATUS "Using exception handler: ${EXCEPTION_HANDLING_LIBRARY}")

contrib/jemalloc-cmake/CMakeLists.txt

@@ -170,16 +170,13 @@ endif ()
 
 target_compile_definitions(_jemalloc PRIVATE -DJEMALLOC_PROF=1)
 
-if (USE_UNWIND)
+# jemalloc provides support for two different libunwind flavors: the original HP libunwind and the one coming with gcc / g++ / libstdc++.
-    # jemalloc provides support for two different libunwind flavors: the original HP libunwind and the one coming with gcc / g++ / libstdc++.
+# The latter is identified by `JEMALLOC_PROF_LIBGCC` and uses `_Unwind_Backtrace` method instead of `unw_backtrace`.
-    # The latter is identified by `JEMALLOC_PROF_LIBGCC` and uses `_Unwind_Backtrace` method instead of `unw_backtrace`.
+# At the time ClickHouse uses LLVM libunwind which follows libgcc's way of backtracing.
-    # At the time ClickHouse uses LLVM libunwind which follows libgcc's way of backtracing.
+#
-
+# ClickHouse has to provide `unw_backtrace` method by the means of [commit 8e2b31e](https://github.com/ClickHouse/libunwind/commit/8e2b31e766dd502f6df74909e04a7dbdf5182eb1).
-    # ClickHouse has to provide `unw_backtrace` method by the means of [commit 8e2b31e](https://github.com/ClickHouse/libunwind/commit/8e2b31e766dd502f6df74909e04a7dbdf5182eb1).
+target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBGCC=1)
-
+target_link_libraries (_jemalloc PRIVATE unwind)
-    target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBGCC=1)
-    target_link_libraries (_jemalloc PRIVATE unwind)
-endif ()
 
 # for RTLD_NEXT
 target_compile_options(_jemalloc PRIVATE -D_GNU_SOURCE)

contrib/libcxx-cmake/CMakeLists.txt

@@ -61,9 +61,7 @@ target_include_directories(cxx SYSTEM BEFORE PUBLIC  $<$<COMPILE_LANGUAGE:CXX>:$
 target_compile_definitions(cxx PRIVATE -D_LIBCPP_BUILDING_LIBRARY -DLIBCXX_BUILDING_LIBCXXABI)
 
 # Enable capturing stack traces for all exceptions.
-if (USE_UNWIND)
+target_compile_definitions(cxx PUBLIC -DSTD_EXCEPTION_HAS_STACK_TRACE=1)
-    target_compile_definitions(cxx PUBLIC -DSTD_EXCEPTION_HAS_STACK_TRACE=1)
-endif ()
 
 if (USE_MUSL)
     target_compile_definitions(cxx PUBLIC -D_LIBCPP_HAS_MUSL_LIBC=1)

contrib/libcxxabi-cmake/CMakeLists.txt

@@ -35,12 +35,10 @@ target_include_directories(cxxabi SYSTEM BEFORE
 )
 target_compile_definitions(cxxabi PRIVATE -D_LIBCPP_BUILDING_LIBRARY)
 target_compile_options(cxxabi PRIVATE -nostdinc++ -fno-sanitize=undefined -Wno-macro-redefined) # If we don't disable UBSan, infinite recursion happens in dynamic_cast.
-target_link_libraries(cxxabi PUBLIC ${EXCEPTION_HANDLING_LIBRARY})
+target_link_libraries(cxxabi PUBLIC unwind)
 
 # Enable capturing stack traces for all exceptions.
-if (USE_UNWIND)
+target_compile_definitions(cxxabi PUBLIC -DSTD_EXCEPTION_HAS_STACK_TRACE=1)
-    target_compile_definitions(cxxabi PUBLIC -DSTD_EXCEPTION_HAS_STACK_TRACE=1)
-endif ()
 
 install(
     TARGETS cxxabi

docker/keeper/Dockerfile

@@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
     esac
 
 ARG REPOSITORY="https://s3.amazonaws.com/clickhouse-builds/22.4/31c367d3cd3aefd316778601ff6565119fe36682/package_release"
-ARG VERSION="23.6.1.1524"
+ARG VERSION="23.6.2.18"
 ARG PACKAGES="clickhouse-keeper"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.

docker/packager/binary/Dockerfile

@@ -49,8 +49,8 @@ ENV CARGO_HOME=/rust/cargo
 ENV PATH="/rust/cargo/bin:${PATH}"
 RUN curl https://sh.rustup.rs -sSf | bash -s -- -y && \
     chmod 777 -R /rust && \
-    rustup toolchain install nightly && \
+    rustup toolchain install nightly-2023-07-04 && \
-    rustup default nightly && \
+    rustup default nightly-2023-07-04 && \
     rustup component add rust-src && \
     rustup target add aarch64-unknown-linux-gnu && \
     rustup target add x86_64-apple-darwin && \

docker/packager/packager

@@ -138,6 +138,7 @@ def parse_env_variables(
     ARM_V80COMPAT_SUFFIX = "-aarch64-v80compat"
     FREEBSD_SUFFIX = "-freebsd"
     PPC_SUFFIX = "-ppc64le"
+    RISCV_SUFFIX = "-riscv64"
     AMD64_COMPAT_SUFFIX = "-amd64-compat"
 
     result = []
@@ -150,6 +151,7 @@ def parse_env_variables(
     is_cross_arm = compiler.endswith(ARM_SUFFIX)
     is_cross_arm_v80compat = compiler.endswith(ARM_V80COMPAT_SUFFIX)
     is_cross_ppc = compiler.endswith(PPC_SUFFIX)
+    is_cross_riscv = compiler.endswith(RISCV_SUFFIX)
     is_cross_freebsd = compiler.endswith(FREEBSD_SUFFIX)
     is_amd64_compat = compiler.endswith(AMD64_COMPAT_SUFFIX)
 
@@ -206,6 +208,11 @@ def parse_env_variables(
         cmake_flags.append(
             "-DCMAKE_TOOLCHAIN_FILE=/build/cmake/linux/toolchain-ppc64le.cmake"
         )
+    elif is_cross_riscv:
+        cc = compiler[: -len(RISCV_SUFFIX)]
+        cmake_flags.append(
+            "-DCMAKE_TOOLCHAIN_FILE=/build/cmake/linux/toolchain-riscv64.cmake"
+        )
     elif is_amd64_compat:
         cc = compiler[: -len(AMD64_COMPAT_SUFFIX)]
         result.append("DEB_ARCH=amd64")
@@ -370,6 +377,7 @@ def parse_args() -> argparse.Namespace:
             "clang-16-aarch64",
             "clang-16-aarch64-v80compat",
             "clang-16-ppc64le",
+            "clang-16-riscv64",
             "clang-16-amd64-compat",
             "clang-16-freebsd",
         ),

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="23.6.1.1524"
+ARG VERSION="23.6.2.18"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.

docker/server/Dockerfile.ubuntu

@@ -23,7 +23,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
 
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
-ARG VERSION="23.6.1.1524"
+ARG VERSION="23.6.2.18"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # set non-empty deb_location_url url to create a docker image

docker/test/fasttest/run.sh

@@ -166,7 +166,6 @@ function run_cmake
         "-DENABLE_UTILS=0"
         "-DENABLE_EMBEDDED_COMPILER=0"
         "-DENABLE_THINLTO=0"
-        "-DUSE_UNWIND=1"
         "-DENABLE_NURAFT=1"
         "-DENABLE_SIMDJSON=1"
         "-DENABLE_JEMALLOC=1"

docker/test/fuzzer/run-fuzzer.sh

@@ -291,7 +291,7 @@ quit
     if [ "$server_died" == 1 ]
     then
         # The server has died.
-        if ! rg --text -o 'Received signal.*|Logical error.*|Assertion.*failed|Failed assertion.*|.*runtime error: .*|.*is located.*|(SUMMARY|ERROR): [a-zA-Z]+Sanitizer:.*|.*_LIBCPP_ASSERT.*' server.log > description.txt
+        if ! rg --text -o 'Received signal.*|Logical error.*|Assertion.*failed|Failed assertion.*|.*runtime error: .*|.*is located.*|(SUMMARY|ERROR): [a-zA-Z]+Sanitizer:.*|.*_LIBCPP_ASSERT.*|.*Child process was terminated by signal 9.*' server.log > description.txt
         then
             echo "Lost connection to server. See the logs." > description.txt
         fi

docker/test/integration/runner/Dockerfile

@@ -47,11 +47,13 @@ ENV TZ=Etc/UTC
 RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
 
 ENV DOCKER_CHANNEL stable
+# Unpin the docker version after the release 24.0.3 is released
+# https://github.com/moby/moby/issues/45770#issuecomment-1618255130
 RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
     && add-apt-repository "deb https://download.docker.com/linux/ubuntu $(lsb_release -c -s) ${DOCKER_CHANNEL}" \
     && apt-get update \
     && env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
-        docker-ce \
+        docker-ce='5:23.*' \
     && rm -rf \
         /var/lib/apt/lists/* \
         /var/cache/debconf \

docker/test/sqllogic/run.sh

@@ -92,8 +92,8 @@ sudo clickhouse stop ||:
 
 for _ in $(seq 1 60); do if [[ $(wget --timeout=1 -q 'localhost:8123' -O-) == 'Ok.' ]]; then sleep 1 ; else break; fi ; done
 
-grep -Fa "Fatal" /var/log/clickhouse-server/clickhouse-server.log ||:
+rg -Fa "Fatal" /var/log/clickhouse-server/clickhouse-server.log ||:
-pigz < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.gz &
+zstd < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst &
 
 # Compressed (FIXME: remove once only github actions will be left)
 rm /var/log/clickhouse-server/clickhouse-server.log

docker/test/stateless/Dockerfile

@@ -33,7 +33,6 @@ RUN apt-get update -y \
             qemu-user-static \
             sqlite3 \
             sudo \
-            telnet \
             tree \
             unixodbc \
             wget \

docker/test/stress/Dockerfile

@@ -8,8 +8,6 @@ RUN apt-get update -y \
         apt-get install --yes --no-install-recommends \
             bash \
             tzdata \
-            fakeroot \
-            debhelper \
             parallel \
             expect \
             python3 \
@@ -20,7 +18,6 @@ RUN apt-get update -y \
             sudo \
             openssl \
             netcat-openbsd \
-            telnet \
             brotli \
     && apt-get clean
 

docker/test/upgrade/Dockerfile

@@ -8,8 +8,6 @@ RUN apt-get update -y \
         apt-get install --yes --no-install-recommends \
             bash \
             tzdata \
-            fakeroot \
-            debhelper \
             parallel \
             expect \
             python3 \
@@ -20,7 +18,6 @@ RUN apt-get update -y \
             sudo \
             openssl \
             netcat-openbsd \
-            telnet \
             brotli \
     && apt-get clean
 

docker/test/upgrade/run.sh

@@ -67,6 +67,13 @@ start
 stop
 mv /var/log/clickhouse-server/clickhouse-server.log /var/log/clickhouse-server/clickhouse-server.initial.log
 
+# 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
+
 # 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>|" \
@@ -76,17 +83,11 @@ sudo mv /etc/clickhouse-server/config.d/keeper_port.xml.tmp /etc/clickhouse-serv
 # 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>|" \
-  > /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml.tmp    mv /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml.tmp /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml
+  > /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml.tmp
+mv /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml.tmp /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
-
 # it contains some new settings, but we can safely remove it
 rm /etc/clickhouse-server/config.d/merge_tree.xml
 rm /etc/clickhouse-server/users.d/nonconst_timezone.xml

docker/test/util/Dockerfile

@@ -44,7 +44,6 @@ RUN apt-get update \
         clang-${LLVM_VERSION} \
         clang-tidy-${LLVM_VERSION} \
         cmake \
-        fakeroot \
         gdb \
         git \
         gperf \
@@ -94,7 +93,10 @@ RUN mkdir /tmp/ccache \
     && rm -rf /tmp/ccache
 
 ARG TARGETARCH
-ARG SCCACHE_VERSION=v0.4.1
+ARG SCCACHE_VERSION=v0.5.4
+ENV SCCACHE_IGNORE_SERVER_IO_ERROR=1
+# sccache requires a value for the region. So by default we use The Default Region
+ENV SCCACHE_REGION=us-east-1
 RUN arch=${TARGETARCH:-amd64} \
   && case $arch in \
     amd64) rarch=x86_64 ;; \

docs/_includes/install/universal.sh

@@ -33,6 +33,9 @@ then
     elif [ "${ARCH}" = "powerpc64le" -o "${ARCH}" = "ppc64le" ]
     then
         DIR="powerpc64le"
+    elif [ "${ARCH}" = "riscv64" ]
+    then
+        DIR="riscv64"
     fi
 elif [ "${OS}" = "FreeBSD" ]
 then

docs/changelogs/v22.8.20.11-lts.md

@@ -0,0 +1,20 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v22.8.20.11-lts (c9ca79e24e8) FIXME as compared to v22.8.19.10-lts (989bc2fe8b0)
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Fix broken index analysis when binary operator contains a null constant argument [#50177](https://github.com/ClickHouse/ClickHouse/pull/50177) ([Amos Bird](https://github.com/amosbird)).
+* Fix incorrect constant folding [#50536](https://github.com/ClickHouse/ClickHouse/pull/50536) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix fuzzer failure in ActionsDAG [#51301](https://github.com/ClickHouse/ClickHouse/pull/51301) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix segfault in MathUnary [#51499](https://github.com/ClickHouse/ClickHouse/pull/51499) ([Ilya Yatsishin](https://github.com/qoega)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Decoupled commits from [#51180](https://github.com/ClickHouse/ClickHouse/issues/51180) for backports [#51561](https://github.com/ClickHouse/ClickHouse/pull/51561) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

docs/changelogs/v23.6.2.18-stable.md

@@ -0,0 +1,25 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.6.2.18-stable (89f39a7ccfe) FIXME as compared to v23.6.1.1524-stable (d1c7e13d088)
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#51888](https://github.com/ClickHouse/ClickHouse/issues/51888): Update cargo dependencies. [#51721](https://github.com/ClickHouse/ClickHouse/pull/51721) ([Raúl Marín](https://github.com/Algunenano)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Fix reading from empty column in `parseSipHashKey` [#51804](https://github.com/ClickHouse/ClickHouse/pull/51804) ([Nikita Taranov](https://github.com/nickitat)).
+* Allow parametric UDFs [#51964](https://github.com/ClickHouse/ClickHouse/pull/51964) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Remove the usage of Analyzer setting in the client [#51578](https://github.com/ClickHouse/ClickHouse/pull/51578) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix 02116_tuple_element with Analyzer [#51669](https://github.com/ClickHouse/ClickHouse/pull/51669) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix SQLLogic docker images [#51719](https://github.com/ClickHouse/ClickHouse/pull/51719) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix source image for sqllogic [#51728](https://github.com/ClickHouse/ClickHouse/pull/51728) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Pin for docker-ce [#51743](https://github.com/ClickHouse/ClickHouse/pull/51743) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+

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-16 CXX=clang++-16 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 -DUSE_UNWIND=OFF -DENABLE_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
+CC=clang-16 CXX=clang++-16 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_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
 ninja -C build-riscv64
 ```
 

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

@@ -33,6 +33,15 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name
 
 - `options` — MongoDB connection string options (optional parameter).
 
+:::tip
+If you are using the MongoDB Atlas cloud offering please add these options:
+
+```
+'connectTimeoutMS=10000&ssl=true&authSource=admin'
+```
+
+:::
+
 ## Usage Example {#usage-example}
 
 Create a table in ClickHouse which allows to read data from MongoDB collection:

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

@@ -54,7 +54,7 @@ $ sudo mysql
 
 ``` sql
 mysql> CREATE USER 'clickhouse'@'localhost' IDENTIFIED BY 'clickhouse';
-mysql> GRANT ALL PRIVILEGES ON *.* TO 'clickhouse'@'clickhouse' WITH GRANT OPTION;
+mysql> GRANT ALL PRIVILEGES ON *.* TO 'clickhouse'@'localhost' WITH GRANT OPTION;
 ```
 
 Then configure the connection in `/etc/odbc.ini`.
@@ -66,7 +66,7 @@ DRIVER = /usr/local/lib/libmyodbc5w.so
 SERVER = 127.0.0.1
 PORT = 3306
 DATABASE = test
-USERNAME = clickhouse
+USER = clickhouse
 PASSWORD = clickhouse
 ```
 
@@ -83,6 +83,9 @@ $ isql -v mysqlconn
 Table in MySQL:
 
 ``` text
+mysql> CREATE DATABASE test;
+Query OK, 1 row affected (0,01 sec)
+
 mysql> CREATE TABLE `test`.`test` (
     ->   `int_id` INT NOT NULL AUTO_INCREMENT,
     ->   `int_nullable` INT NULL DEFAULT NULL,
@@ -91,10 +94,10 @@ mysql> CREATE TABLE `test`.`test` (
     ->   PRIMARY KEY (`int_id`));
 Query OK, 0 rows affected (0,09 sec)
 
-mysql> insert into test (`int_id`, `float`) VALUES (1,2);
+mysql> insert into test.test (`int_id`, `float`) VALUES (1,2);
 Query OK, 1 row affected (0,00 sec)
 
-mysql> select * from test;
+mysql> select * from test.test;
 +------+----------+-----+----------+
 | int_id | int_nullable | float | float_nullable |
 +------+----------+-----+----------+

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

@@ -37,8 +37,8 @@ The [Merge](/docs/en/engines/table-engines/special/merge.md/#merge) engine does
 ``` sql
 CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
 (
-    name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1] [TTL expr1],
+    name1 [type1] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr1] [TTL expr1] [CODEC(codec1)] [[NOT] NULL|PRIMARY KEY],
-    name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2] [TTL expr2],
+    name2 [type2] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr2] [TTL expr2] [CODEC(codec2)] [[NOT] NULL|PRIMARY KEY],
     ...
     INDEX index_name1 expr1 TYPE type1(...) [GRANULARITY value1],
     INDEX index_name2 expr2 TYPE type2(...) [GRANULARITY value2],

docs/en/operations/settings/settings.md

@@ -17,7 +17,8 @@ Default value: 0.
 **Example**
 
 ``` sql
-insert into table_1 values (1, 'a'), (2, 'bb'), (3, 'ccc'), (4, 'dddd');
+INSERT INTO table_1 VALUES (1, 'a'), (2, 'bb'), (3, 'ccc'), (4, 'dddd');
+SELECT * FROM table_1;
 ```
 ```response
 ┌─x─┬─y────┐
@@ -30,7 +31,7 @@ insert into table_1 values (1, 'a'), (2, 'bb'), (3, 'ccc'), (4, 'dddd');
 ```sql
 SELECT *
 FROM table_1
-SETTINGS additional_table_filters = (('table_1', 'x != 2'))
+SETTINGS additional_table_filters = {'table_1': 'x != 2'}
 ```
 ```response
 ┌─x─┬─y────┐
@@ -50,7 +51,8 @@ Default value: `''`.
 **Example**
 
 ``` sql
-insert into table_1 values (1, 'a'), (2, 'bb'), (3, 'ccc'), (4, 'dddd');
+INSERT INTO table_1 VALUES (1, 'a'), (2, 'bb'), (3, 'ccc'), (4, 'dddd');
+SElECT * FROM table_1;
 ```
 ```response
 ┌─x─┬─y────┐
@@ -3201,6 +3203,40 @@ ENGINE = Log
 └──────────────────────────────────────────────────────────────────────────┘
 ```
 
+## default_temporary_table_engine {#default_temporary_table_engine}
+
+Same as [default_table_engine](#default_table_engine) but for temporary tables.
+
+Default value: `Memory`.
+
+In this example, any new temporary table that does not specify an `Engine` will use the `Log` table engine:
+
+Query:
+
+```sql
+SET default_temporary_table_engine = 'Log';
+
+CREATE TEMPORARY TABLE my_table (
+    x UInt32,
+    y UInt32
+);
+
+SHOW CREATE TEMPORARY TABLE my_table;
+```
+
+Result:
+
+```response
+┌─statement────────────────────────────────────────────────────────────────┐
+│ CREATE TEMPORARY TABLE default.my_table
+(
+    `x` UInt32,
+    `y` UInt32
+)
+ENGINE = Log
+└──────────────────────────────────────────────────────────────────────────┘
+```
+
 ## data_type_default_nullable {#data_type_default_nullable}
 
 Allows data types without explicit modifiers [NULL or NOT NULL](../../sql-reference/statements/create/table.md/#null-modifiers) in column definition will be [Nullable](../../sql-reference/data-types/nullable.md/#data_type-nullable).
@@ -3501,7 +3537,7 @@ Possible values:
 - Any positive integer.
 - 0 - Disabled (infinite timeout).
 
-Default value: 180.
+Default value: 30.
 
 ## http_receive_timeout {#http_receive_timeout}
 
@@ -3512,7 +3548,7 @@ Possible values:
 - Any positive integer.
 - 0 - Disabled (infinite timeout).
 
-Default value: 180.
+Default value: 30.
 
 ## check_query_single_value_result {#check_query_single_value_result}
 

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

@@ -9,7 +9,6 @@ Columns:
 
 - `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date.
 - `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time.
-- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Event time with microseconds resolution.
 - `name` ([String](../../sql-reference/data-types/string.md)) — Metric name.
 - `value` ([Float64](../../sql-reference/data-types/float.md)) — Metric value.
 
@@ -20,18 +19,18 @@ SELECT * FROM system.asynchronous_metric_log LIMIT 10
 ```
 
 ``` text
-┌─event_date─┬──────────event_time─┬────event_time_microseconds─┬─name─────────────────────────────────────┬─────value─┐
+┌─event_date─┬──────────event_time─┬─name─────────────────────────────────────┬─────value─┐
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ CPUFrequencyMHz_0                        │    2120.9 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ CPUFrequencyMHz_0                        │    2120.9 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.arenas.all.pmuzzy               │       743 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pmuzzy               │       743 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.arenas.all.pdirty               │     26288 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pdirty               │     26288 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.background_thread.run_intervals │         0 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.run_intervals │         0 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.background_thread.num_runs      │         0 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.num_runs      │         0 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.retained                        │  60694528 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.retained                        │  60694528 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.mapped                          │ 303161344 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.mapped                          │ 303161344 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.resident                        │ 260931584 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.resident                        │ 260931584 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.metadata                        │  12079488 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.metadata                        │  12079488 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.allocated                       │ 133756128 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.allocated                       │ 133756128 │
-└────────────┴─────────────────────┴────────────────────────────┴──────────────────────────────────────────┴───────────┘
+└────────────┴─────────────────────┴──────────────────────────────────────────┴───────────┘
 ```
 
 **See Also**

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

@@ -13,6 +13,7 @@ System tables provide information about:
 
 - Server states, processes, and environment.
 - Server’s internal processes.
+- Options used when the ClickHouse binary was built.
 
 System tables:
 

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

@@ -0,0 +1,45 @@
+---
+slug: /en/operations/system-tables/jemalloc_bins
+---
+# jemalloc_bins
+
+Contains information about memory allocations done via jemalloc allocator in different size classes (bins) aggregated from all arenas.
+These statistics might not be absolutely accurate because of thread local caching in jemalloc.
+
+Columns:
+
+- `index` (UInt64) — Index of the bin ordered by size
+- `large` (Bool) — True for large allocations and False for small
+- `size` (UInt64) — Size of allocations in this bin
+- `allocations` (UInt64) — Number of allocations
+- `deallocations` (UInt64) — Number of deallocations
+
+**Example**
+
+Find the sizes of allocations that contributed the most to the current overall memory usage.
+
+``` sql
+SELECT
+    *,
+    allocations - deallocations AS active_allocations,
+    size * active_allocations AS allocated_bytes
+FROM system.jemalloc_bins
+WHERE allocated_bytes > 0
+ORDER BY allocated_bytes DESC
+LIMIT 10
+```
+
+``` text
+┌─index─┬─large─┬─────size─┬─allocactions─┬─deallocations─┬─active_allocations─┬─allocated_bytes─┐
+│    82 │     1 │ 50331648 │            1 │             0 │                  1 │        50331648 │
+│    10 │     0 │      192 │       512336 │        370710 │             141626 │        27192192 │
+│    69 │     1 │  5242880 │            6 │             2 │                  4 │        20971520 │
+│     3 │     0 │       48 │     16938224 │      16559484 │             378740 │        18179520 │
+│    28 │     0 │     4096 │       122924 │        119142 │               3782 │        15491072 │
+│    61 │     1 │  1310720 │        44569 │         44558 │                 11 │        14417920 │
+│    39 │     1 │    28672 │         1285 │           913 │                372 │        10665984 │
+│     4 │     0 │       64 │      2837225 │       2680568 │             156657 │        10026048 │
+│     6 │     0 │       96 │      2617803 │       2531435 │              86368 │         8291328 │
+│    36 │     1 │    16384 │        22431 │         21970 │                461 │         7553024 │
+└───────┴───────┴──────────┴──────────────┴───────────────┴────────────────────┴─────────────────┘
+```

docs/en/sql-reference/functions/udf.md

@@ -171,12 +171,13 @@ Result:
 └──────────────────────────────┘
 ```
 
-Executable user defined functions can take constant parameters configured in `command` setting (works only for user defined functions with `executable` type).
+Executable user defined functions can take constant parameters configured in `command` setting (works only for user defined functions with `executable` type). It also requires the `execute_direct` option (to ensure no shell argument expansion vulnerability).
 File `test_function_parameter_python.xml` (`/etc/clickhouse-server/test_function_parameter_python.xml` with default path settings).
 ```xml
 <functions>
     <function>
         <type>executable</type>
+        <execute_direct>true</execute_direct>
         <name>test_function_parameter_python</name>
         <return_type>String</return_type>
         <argument>

docs/en/sql-reference/statements/alter/sample-by.md

@@ -5,15 +5,28 @@ sidebar_label: SAMPLE BY
 title: "Manipulating Sampling-Key Expressions"
 ---
 
-Syntax:
+# Manipulating SAMPLE BY expression
+
+The following operations are available:
+
+## MODIFY
 
 ``` sql
 ALTER TABLE [db].name [ON CLUSTER cluster] MODIFY SAMPLE BY new_expression
 ```
 
-The command changes the [sampling key](../../../engines/table-engines/mergetree-family/mergetree.md) of the table to `new_expression` (an expression or a tuple of expressions).
+The command changes the [sampling key](../../../engines/table-engines/mergetree-family/mergetree.md) of the table to `new_expression` (an expression or a tuple of expressions). The primary key must contain the new sample key.
 
-The command is lightweight in the sense that it only changes metadata. The primary key must contain the new sample key.
+## REMOVE
+
+``` sql
+ALTER TABLE [db].name [ON CLUSTER cluster] REMOVE SAMPLE BY
+```
+
+The command removes the [sampling key](../../../engines/table-engines/mergetree-family/mergetree.md) of the table.
+
+
+The commands `MODIFY` and `REMOVE` are lightweight in the sense that they only change metadata or remove files.
 
 :::note    
 It only works for tables in the [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md) family (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) tables).

docs/en/sql-reference/table-functions/mongodb.md

@@ -30,6 +30,14 @@ mongodb(host:port, database, collection, user, password, structure [, options])
 
 - `options` - MongoDB connection string options (optional parameter).
 
+:::tip
+If you are using the MongoDB Atlas cloud offering please add these options:
+
+```
+'connectTimeoutMS=10000&ssl=true&authSource=admin'
+```
+
+:::
 
 **Returned Value**
 

docs/ru/operations/system-tables/asynchronous_metric_log.md

@@ -8,7 +8,6 @@ slug: /ru/operations/system-tables/asynchronous_metric_log
 Столбцы:
 -   `event_date` ([Date](../../sql-reference/data-types/date.md)) — дата события.
 -   `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — время события.
--   `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — время события в микросекундах.
 -   `name` ([String](../../sql-reference/data-types/string.md)) — название метрики.
 -   `value` ([Float64](../../sql-reference/data-types/float.md)) — значение метрики.
 

docs/zh/development/build.md

@@ -3,13 +3,6 @@ slug: /zh/development/build
 ---
 # 如何构建 ClickHouse 发布包 {#ru-he-gou-jian-clickhouse-fa-bu-bao}
 
-## 安装 Git 和 Pbuilder {#an-zhuang-git-he-pbuilder}
-
-``` bash
-sudo apt-get update
-sudo apt-get install git pbuilder debhelper lsb-release fakeroot sudo debian-archive-keyring debian-keyring
-```
-
 ## 拉取 ClickHouse 源码 {#la-qu-clickhouse-yuan-ma}
 
 ``` bash

docs/zh/operations/system-tables/asynchronous_metric_log.md

@@ -8,7 +8,6 @@ slug: /zh/operations/system-tables/asynchronous_metric_log
 列：
 -   `event_date` ([Date](../../sql-reference/data-types/date.md)) — 事件日期。
 -   `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — 事件时间。
--   `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — 事件时间(微秒)。
 -   `name` ([String](../../sql-reference/data-types/string.md)) — 指标名。
 -   `value` ([Float64](../../sql-reference/data-types/float.md)) — 指标值。
 
@@ -17,18 +16,18 @@ slug: /zh/operations/system-tables/asynchronous_metric_log
 SELECT * FROM system.asynchronous_metric_log LIMIT 10
 ```
 ``` text
-┌─event_date─┬──────────event_time─┬────event_time_microseconds─┬─name─────────────────────────────────────┬─────value─┐
+┌─event_date─┬──────────event_time─┬─name─────────────────────────────────────┬─────value─┐
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ CPUFrequencyMHz_0                        │    2120.9 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ CPUFrequencyMHz_0                        │    2120.9 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.arenas.all.pmuzzy               │       743 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pmuzzy               │       743 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.arenas.all.pdirty               │     26288 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.arenas.all.pdirty               │     26288 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.background_thread.run_intervals │         0 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.run_intervals │         0 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.background_thread.num_runs      │         0 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.background_thread.num_runs      │         0 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.retained                        │  60694528 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.retained                        │  60694528 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.mapped                          │ 303161344 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.mapped                          │ 303161344 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.resident                        │ 260931584 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.resident                        │ 260931584 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.metadata                        │  12079488 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.metadata                        │  12079488 │
-│ 2020-09-05 │ 2020-09-05 15:56:30 │ 2020-09-05 15:56:30.025227 │ jemalloc.allocated                       │ 133756128 │
+│ 2020-09-05 │ 2020-09-05 15:56:30 │ jemalloc.allocated                       │ 133756128 │
-└────────────┴─────────────────────┴────────────────────────────┴──────────────────────────────────────────┴───────────┘
+└────────────┴─────────────────────┴──────────────────────────────────────────┴───────────┘
 ```
 
 **另请参阅**

docs/zh/sql-reference/functions/functions-for-nulls.md

@@ -192,7 +192,7 @@ SELECT coalesce(mail, phone, CAST(icq,'Nullable(String)')) FROM aBook
 **返回值**
 
 -   如果`x`不为`NULL`，返回非`Nullable`类型的原始值。
--   如果`x`为`NULL`，返回对应非`Nullable`类型的默认值。
+-   如果`x`为`NULL`，则返回任意值。
 
 **示例**
 

programs/diagnostics/internal/platform/data/file_test.go

@@ -135,7 +135,7 @@ func TestConfigFileFrameCopy(t *testing.T) {
 		sizes := map[string]int64{
 			"users.xml":            int64(2017),
 			"default-password.xml": int64(188),
-			"config.xml":           int64(61662),
+			"config.xml":           int64(59506),
 			"server-include.xml":   int64(168),
 			"user-include.xml":     int64(559),
 		}
@@ -189,7 +189,7 @@ func TestConfigFileFrameCopy(t *testing.T) {
 		sizes := map[string]int64{
 			"users.yaml":            int64(1023),
 			"default-password.yaml": int64(132),
-			"config.yaml":           int64(42512),
+			"config.yaml":           int64(41633),
 			"server-include.yaml":   int64(21),
 			"user-include.yaml":     int64(120),
 		}

programs/diagnostics/testdata/configs/xml/config.xml

@@ -649,73 +649,6 @@
                 </replica>
             </shard>
         </test_shard_localhost>
-        <test_cluster_two_shards_localhost>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards_localhost>
-        <test_cluster_two_shards>
-            <shard>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards>
-        <test_cluster_two_shards_internal_replication>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards_internal_replication>
-        <test_shard_localhost_secure>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9440</port>
-                    <secure>1</secure>
-                </replica>
-            </shard>
-        </test_shard_localhost_secure>
-        <test_unavailable_shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>1</port>
-                </replica>
-            </shard>
-        </test_unavailable_shard>
     </remote_servers>
 
     <!-- The list of hosts allowed to use in URL-related storage engines and table functions.

programs/diagnostics/testdata/configs/yaml/config.yaml

@@ -547,46 +547,6 @@ remote_servers:
         port: 9000
         # Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority).
         # priority: 1
-  test_cluster_two_shards_localhost:
-    shard:
-      - replica:
-          host: localhost
-          port: 9000
-      - replica:
-          host: localhost
-          port: 9000
-  test_cluster_two_shards:
-    shard:
-      - replica:
-          host: 127.0.0.1
-          port: 9000
-      - replica:
-          host: 127.0.0.2
-          port: 9000
-  test_cluster_two_shards_internal_replication:
-    shard:
-      - internal_replication: true
-        replica:
-          host: 127.0.0.1
-          port: 9000
-      - internal_replication: true
-        replica:
-          host: 127.0.0.2
-          port: 9000
-  test_shard_localhost_secure:
-    shard:
-      replica:
-        host: localhost
-        port: 9440
-        secure: 1
-  test_unavailable_shard:
-    shard:
-      - replica:
-          host: localhost
-          port: 9000
-      - replica:
-          host: localhost
-          port: 1
 
 # The list of hosts allowed to use in URL-related storage engines and table functions.
 # If this section is not present in configuration, all hosts are allowed.

programs/diagnostics/testdata/configs/yandex_xml/config.xml

@@ -649,73 +649,6 @@
                 </replica>
             </shard>
         </test_shard_localhost>
-        <test_cluster_two_shards_localhost>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards_localhost>
-        <test_cluster_two_shards>
-            <shard>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards>
-        <test_cluster_two_shards_internal_replication>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards_internal_replication>
-        <test_shard_localhost_secure>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9440</port>
-                    <secure>1</secure>
-                </replica>
-            </shard>
-        </test_shard_localhost_secure>
-        <test_unavailable_shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>1</port>
-                </replica>
-            </shard>
-        </test_unavailable_shard>
     </remote_servers>
 
     <!-- The list of hosts allowed to use in URL-related storage engines and table functions.

programs/disks/CommandCopy.cpp

@@ -59,7 +59,7 @@ public:
         String relative_path_from = validatePathAndGetAsRelative(path_from);
         String relative_path_to = validatePathAndGetAsRelative(path_to);
 
-        disk_from->copy(relative_path_from, disk_to, relative_path_to);
+        disk_from->copyDirectoryContent(relative_path_from, disk_to, relative_path_to);
     }
 };
 }

programs/keeper-converter/KeeperConverter.cpp

@@ -42,7 +42,7 @@ int mainEntryClickHouseKeeperConverter(int argc, char ** argv)
     {
         auto keeper_context = std::make_shared<KeeperContext>(true);
         keeper_context->setDigestEnabled(true);
-        keeper_context->setSnapshotDisk(std::make_shared<DiskLocal>("Keeper-snapshots", options["output-dir"].as<std::string>(), 0));
+        keeper_context->setSnapshotDisk(std::make_shared<DiskLocal>("Keeper-snapshots", options["output-dir"].as<std::string>()));
 
         DB::KeeperStorage storage(/* tick_time_ms */ 500, /* superdigest */ "", keeper_context, /* initialize_system_nodes */ false);
 

programs/keeper/Keeper.cpp

@@ -485,7 +485,7 @@ try
             LOG_INFO(log, "Closed all listening sockets.");
 
         if (current_connections > 0)
-            current_connections = waitServersToFinish(*servers, config().getInt("shutdown_wait_unfinished", 5));
+            current_connections = waitServersToFinish(*servers, servers_lock, config().getInt("shutdown_wait_unfinished", 5));
 
         if (current_connections)
             LOG_INFO(log, "Closed connections to Keeper. But {} remain. Probably some users cannot finish their connections after context shutdown.", current_connections);

programs/local/LocalServer.cpp

@@ -8,7 +8,9 @@
 #include <Poco/Logger.h>
 #include <Poco/NullChannel.h>
 #include <Poco/SimpleFileChannel.h>
+#include <Databases/DatabaseFilesystem.h>
 #include <Databases/DatabaseMemory.h>
+#include <Databases/DatabasesOverlay.h>
 #include <Storages/System/attachSystemTables.h>
 #include <Storages/System/attachInformationSchemaTables.h>
 #include <Interpreters/DatabaseCatalog.h>
@@ -50,6 +52,8 @@
 #include <base/argsToConfig.h>
 #include <filesystem>
 
+#include "config.h"
+
 #if defined(FUZZING_MODE)
     #include <Functions/getFuzzerData.h>
 #endif
@@ -71,6 +75,15 @@ namespace ErrorCodes
     extern const int FILE_ALREADY_EXISTS;
 }
 
+void applySettingsOverridesForLocal(ContextMutablePtr context)
+{
+    Settings settings = context->getSettings();
+
+    settings.allow_introspection_functions = true;
+    settings.storage_file_read_method = LocalFSReadMethod::mmap;
+
+    context->setSettings(settings);
+}
 
 void LocalServer::processError(const String &) const
 {
@@ -170,6 +183,13 @@ static DatabasePtr createMemoryDatabaseIfNotExists(ContextPtr context, const Str
     return system_database;
 }
 
+static DatabasePtr createClickHouseLocalDatabaseOverlay(const String & name_, ContextPtr context_)
+{
+    auto databaseCombiner = std::make_shared<DatabasesOverlay>(name_, context_);
+    databaseCombiner->registerNextDatabase(std::make_shared<DatabaseFilesystem>(name_, "", context_));
+    databaseCombiner->registerNextDatabase(std::make_shared<DatabaseMemory>(name_, context_));
+    return databaseCombiner;
+}
 
 /// If path is specified and not empty, will try to setup server environment and load existing metadata
 void LocalServer::tryInitPath()
@@ -657,6 +677,12 @@ void LocalServer::processConfig()
     CompiledExpressionCacheFactory::instance().init(compiled_expression_cache_size, compiled_expression_cache_elements_size);
 #endif
 
+    /// NOTE: it is important to apply any overrides before
+    /// setDefaultProfiles() calls since it will copy current context (i.e.
+    /// there is separate context for Buffer tables).
+    applySettingsOverridesForLocal(global_context);
+    applyCmdOptions(global_context);
+
     /// Load global settings from default_profile and system_profile.
     global_context->setDefaultProfiles(config());
 
@@ -669,9 +695,8 @@ void LocalServer::processConfig()
       *  if such tables will not be dropped, clickhouse-server will not be able to load them due to security reasons.
       */
     std::string default_database = config().getString("default_database", "_local");
-    DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared<DatabaseMemory>(default_database, global_context));
+    DatabaseCatalog::instance().attachDatabase(default_database, createClickHouseLocalDatabaseOverlay(default_database, global_context));
     global_context->setCurrentDatabase(default_database);
-    applyCmdOptions(global_context);
 
     if (config().has("path"))
     {

programs/server/Server.cpp

@@ -1146,7 +1146,16 @@ try
             size_t merges_mutations_memory_usage_soft_limit = server_settings_.merges_mutations_memory_usage_soft_limit;
 
             size_t default_merges_mutations_server_memory_usage = static_cast<size_t>(memory_amount * server_settings_.merges_mutations_memory_usage_to_ram_ratio);
-            if (merges_mutations_memory_usage_soft_limit == 0 || merges_mutations_memory_usage_soft_limit > default_merges_mutations_server_memory_usage)
+            if (merges_mutations_memory_usage_soft_limit == 0)
+            {
+                merges_mutations_memory_usage_soft_limit = default_merges_mutations_server_memory_usage;
+                LOG_INFO(log, "Setting merges_mutations_memory_usage_soft_limit was set to {}"
+                    " ({} available * {:.2f} merges_mutations_memory_usage_to_ram_ratio)",
+                    formatReadableSizeWithBinarySuffix(merges_mutations_memory_usage_soft_limit),
+                    formatReadableSizeWithBinarySuffix(memory_amount),
+                    server_settings_.merges_mutations_memory_usage_to_ram_ratio);
+            }
+            else if (merges_mutations_memory_usage_soft_limit > default_merges_mutations_server_memory_usage)
             {
                 merges_mutations_memory_usage_soft_limit = default_merges_mutations_server_memory_usage;
                 LOG_WARNING(log, "Setting merges_mutations_memory_usage_soft_limit was set to {}"
@@ -1523,7 +1532,7 @@ try
                 LOG_INFO(log, "Closed all listening sockets.");
 
             if (current_connections > 0)
-                current_connections = waitServersToFinish(servers_to_start_before_tables, config().getInt("shutdown_wait_unfinished", 5));
+                current_connections = waitServersToFinish(servers_to_start_before_tables, servers_lock, config().getInt("shutdown_wait_unfinished", 5));
 
             if (current_connections)
                 LOG_INFO(log, "Closed connections to servers for tables. But {} remain. Probably some tables of other users cannot finish their connections after context shutdown.", current_connections);
@@ -1581,6 +1590,15 @@ try
         /// After attaching system databases we can initialize system log.
         global_context->initializeSystemLogs();
         global_context->setSystemZooKeeperLogAfterInitializationIfNeeded();
+        /// Build loggers before tables startup to make log messages from tables
+        /// attach available in system.text_log
+        {
+            String level_str = config().getString("text_log.level", "");
+            int level = level_str.empty() ? INT_MAX : Poco::Logger::parseLevel(level_str);
+            setTextLog(global_context->getTextLog(), level);
+
+            buildLoggers(config(), logger());
+        }
         /// After the system database is created, attach virtual system tables (in addition to query_log and part_log)
         attachSystemTablesServer(global_context, *database_catalog.getSystemDatabase(), has_zookeeper);
         attachInformationSchema(global_context, *database_catalog.getDatabase(DatabaseCatalog::INFORMATION_SCHEMA));
@@ -1609,7 +1627,7 @@ try
 
     /// Init trace collector only after trace_log system table was created
     /// Disable it if we collect test coverage information, because it will work extremely slow.
-#if USE_UNWIND && !WITH_COVERAGE
+#if !WITH_COVERAGE
     /// Profilers cannot work reliably with any other libunwind or without PHDR cache.
     if (hasPHDRCache())
     {
@@ -1632,10 +1650,6 @@ try
 
     /// Describe multiple reasons when query profiler cannot work.
 
-#if !USE_UNWIND
-    LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they cannot work without bundled unwind (stack unwinding) library.");
-#endif
-
 #if WITH_COVERAGE
     LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they work extremely slow with test coverage.");
 #endif
@@ -1707,14 +1721,6 @@ try
         /// Must be done after initialization of `servers`, because async_metrics will access `servers` variable from its thread.
         async_metrics.start();
 
-        {
-            String level_str = config().getString("text_log.level", "");
-            int level = level_str.empty() ? INT_MAX : Poco::Logger::parseLevel(level_str);
-            setTextLog(global_context->getTextLog(), level);
-        }
-
-        buildLoggers(config(), logger());
-
         main_config_reloader->start();
         access_control.startPeriodicReloading();
 
@@ -1827,7 +1833,7 @@ try
                 global_context->getProcessList().killAllQueries();
 
             if (current_connections)
-                current_connections = waitServersToFinish(servers, config().getInt("shutdown_wait_unfinished", 5));
+                current_connections = waitServersToFinish(servers, servers_lock, config().getInt("shutdown_wait_unfinished", 5));
 
             if (current_connections)
                 LOG_WARNING(log, "Closed connections. But {} remain."

programs/server/config.d/more_clusters.xml

@@ -1,49 +0,0 @@
-<clickhouse>
-    <remote_servers>
-
-        <![CDATA[
-            You can run additional servers simply as
-             ./clickhouse-server -- --path=9001 --tcp_port=9001
-        ]]>
-
-        <single_remote_shard_at_port_9001>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9001</port>
-                </replica>
-            </shard>
-        </single_remote_shard_at_port_9001>
-
-        <two_remote_shards_at_port_9001_9002>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9001</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9002</port>
-                </replica>
-            </shard>
-        </two_remote_shards_at_port_9001_9002>
-
-        <two_shards_one_local_one_remote_at_port_9001>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9001</port>
-                </replica>
-            </shard>
-        </two_shards_one_local_one_remote_at_port_9001>
-
-    </remote_servers>
-</clickhouse>

programs/server/config.xml

@@ -805,7 +805,7 @@
       -->
     <remote_servers>
         <!-- Test only shard config for testing distributed storage -->
-        <test_shard_localhost>
+        <default>
             <!-- Inter-server per-cluster secret for Distributed queries
                  default: no secret (no authentication will be performed)
 
@@ -838,158 +838,11 @@
                     <port>9000</port>
                     <!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
                     <!-- <priority>1</priority> -->
+                    <!-- Use SSL? Default: no -->
+                    <!-- <secure>0</secure> -->
                 </replica>
             </shard>
-        </test_shard_localhost>
+        </default>
-        <test_cluster_one_shard_three_replicas_localhost>
-            <shard>
-                <internal_replication>false</internal_replication>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>127.0.0.3</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <!--shard>
-                <internal_replication>false</internal_replication>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>127.0.0.3</host>
-                    <port>9000</port>
-                </replica>
-            </shard-->
-        </test_cluster_one_shard_three_replicas_localhost>
-	<parallel_replicas>
-		<shard>
-            <internal_replication>false</internal_replication>
-            <replica>
-                <host>127.0.0.1</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.2</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.3</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.4</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.5</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.6</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.7</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.8</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.9</host>
-                <port>9000</port>
-            </replica>
-            <replica>
-                <host>127.0.0.10</host>
-                <port>9000</port>
-            </replica>
-            <!-- Unavailable replica -->
-            <replica>
-                <host>127.0.0.11</host>
-                <port>1234</port>
-            </replica>
-        </shard>
-	</parallel_replicas>
-        <test_cluster_two_shards_localhost>
-             <shard>
-                 <replica>
-                     <host>localhost</host>
-                     <port>9000</port>
-                 </replica>
-             </shard>
-             <shard>
-                 <replica>
-                     <host>localhost</host>
-                     <port>9000</port>
-                 </replica>
-             </shard>
-        </test_cluster_two_shards_localhost>
-        <test_cluster_two_shards>
-            <shard>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards>
-        <test_cluster_two_shards_internal_replication>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <internal_replication>true</internal_replication>
-                <replica>
-                    <host>127.0.0.2</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </test_cluster_two_shards_internal_replication>
-        <test_shard_localhost_secure>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9440</port>
-                    <secure>1</secure>
-                </replica>
-            </shard>
-        </test_shard_localhost_secure>
-        <test_unavailable_shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-            <shard>
-                <replica>
-                    <host>localhost</host>
-                    <port>1</port>
-                </replica>
-            </shard>
-        </test_unavailable_shard>
     </remote_servers>
 
     <!-- The list of hosts allowed to use in URL-related storage engines and table functions.

programs/server/config.yaml.example

@@ -515,7 +515,7 @@ remap_executable: false
 # https://clickhouse.com/docs/en/operations/table_engines/distributed/
 remote_servers:
     # Test only shard config for testing distributed storage
-    test_shard_localhost:
+    default:
         # Inter-server per-cluster secret for Distributed queries
         # default: no secret (no authentication will be performed)
 
@@ -546,46 +546,8 @@ remote_servers:
                 port: 9000
                 # Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority).
                 # priority: 1
-    test_cluster_two_shards_localhost:
+                # Use SSL? Default: no
-        shard:
+                # secure: 0
-            - replica:
-                  host: localhost
-                  port: 9000
-            - replica:
-                  host: localhost
-                  port: 9000
-    test_cluster_two_shards:
-        shard:
-            - replica:
-                  host: 127.0.0.1
-                  port: 9000
-            - replica:
-                  host: 127.0.0.2
-                  port: 9000
-    test_cluster_two_shards_internal_replication:
-        shard:
-            - internal_replication: true
-              replica:
-                  host: 127.0.0.1
-                  port: 9000
-            - internal_replication: true
-              replica:
-                  host: 127.0.0.2
-                  port: 9000
-    test_shard_localhost_secure:
-        shard:
-            replica:
-                host: localhost
-                port: 9440
-                secure: 1
-    test_unavailable_shard:
-        shard:
-            - replica:
-                  host: localhost
-                  port: 9000
-            - replica:
-                  host: localhost
-                  port: 1
 
 # The list of hosts allowed to use in URL-related storage engines and table functions.
 # If this section is not present in configuration, all hosts are allowed.

programs/server/dashboard.html

@@ -12,7 +12,8 @@
             --chart-background: white;
             --shadow-color: rgba(0, 0, 0, 0.25);
             --input-shadow-color: rgba(0, 255, 0, 1);
-            --error-color: white;
+            --error-color: red;
+            --auth-error-color: white;
             --legend-background: rgba(255, 255, 255, 0.75);
             --title-color: #666;
             --text-color: black;
@@ -258,7 +259,7 @@
             width: 60%;
             padding: .5rem;
 
-            color: var(--error-color);
+            color: var(--auth-error-color);
 
             display: flex;
             flex-flow: row nowrap;
@@ -906,9 +907,9 @@ async function draw(idx, chart, url_params, query) {
 
     if (error) {
         const errorMatch = errorMessages.find(({ regex }) => error.match(regex))
-        if (errorMatch) {
+        const match = error.match(errorMatch.regex)
-            const match = error.match(errorMatch.regex)
+        const message = errorMatch.messageFunc(match)
-            const message = errorMatch.messageFunc(match)
+        if (message) {
             const authError = new Error(message)
             throw authError
         }
@@ -1019,13 +1020,15 @@ async function drawAll() {
             firstLoad = false;
         } else {
             enableReloadButton();
+            enableRunButton();
         }
-        if (!results.includes(false)) {
+        if (results.includes(true)) {
             const element = document.querySelector('.inputs');
             element.classList.remove('unconnected');
             const add = document.querySelector('#add');
             add.style.display = 'block';
-        } else {
+        } 
+        else {
             const charts = document.querySelector('#charts')
             charts.style.height = '0px';
         }
@@ -1050,6 +1053,13 @@ function disableReloadButton() {
     reloadButton.classList.add('disabled')
 }
 
+function disableRunButton() {
+    const runButton = document.getElementById('run')
+    runButton.value = 'Reloading...'
+    runButton.disabled = true
+    runButton.classList.add('disabled')
+}
+
 function enableReloadButton() {
     const reloadButton = document.getElementById('reload')
     reloadButton.value = 'Reload'
@@ -1057,11 +1067,19 @@ function enableReloadButton() {
     reloadButton.classList.remove('disabled')
 }
 
+function enableRunButton() {
+    const runButton = document.getElementById('run')
+    runButton.value = 'Ok'
+    runButton.disabled = false
+    runButton.classList.remove('disabled')
+}
+
 function reloadAll() {
     updateParams();
     drawAll();
     saveState();
-    disableReloadButton()
+    disableReloadButton();
+    disableRunButton();
 }
 
 document.getElementById('params').onsubmit = function(event) {

src/Access/Common/AccessRightsElement.cpp

@@ -155,7 +155,7 @@ namespace
 
 
 AccessRightsElement::AccessRightsElement(AccessFlags access_flags_, std::string_view database_)
-    : access_flags(access_flags_), database(database_), any_database(false)
+    : access_flags(access_flags_), database(database_), parameter(database_), any_database(false), any_parameter(false)
 {
 }
 

src/Access/Common/AccessType.h

@@ -70,7 +70,7 @@ enum class AccessType
     M(ALTER_FREEZE_PARTITION, "FREEZE PARTITION, UNFREEZE", TABLE, ALTER_TABLE) \
     \
     M(ALTER_DATABASE_SETTINGS, "ALTER DATABASE SETTING, ALTER MODIFY DATABASE SETTING, MODIFY DATABASE SETTING", DATABASE, ALTER_DATABASE) /* allows to execute ALTER MODIFY SETTING */\
-    M(ALTER_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_CONTROL) /* allows to execute ALTER NAMED COLLECTION */\
+    M(ALTER_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) /* allows to execute ALTER NAMED COLLECTION */\
     \
     M(ALTER_TABLE, "", GROUP, ALTER) \
     M(ALTER_DATABASE, "", GROUP, ALTER) \
@@ -92,7 +92,7 @@ enum class AccessType
     M(CREATE_ARBITRARY_TEMPORARY_TABLE, "", GLOBAL, CREATE)  /* allows to create  and manipulate temporary tables
                                                                 with arbitrary table engine */\
     M(CREATE_FUNCTION, "", GLOBAL, CREATE) /* allows to execute CREATE FUNCTION */ \
-    M(CREATE_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_CONTROL) /* allows to execute CREATE NAMED COLLECTION */ \
+    M(CREATE_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) /* allows to execute CREATE NAMED COLLECTION */ \
     M(CREATE, "", GROUP, ALL) /* allows to execute {CREATE|ATTACH} */ \
     \
     M(DROP_DATABASE, "", DATABASE, DROP) /* allows to execute {DROP|DETACH} DATABASE */\
@@ -101,7 +101,7 @@ enum class AccessType
                                     implicitly enabled by the grant DROP_TABLE */\
     M(DROP_DICTIONARY, "", DICTIONARY, DROP) /* allows to execute {DROP|DETACH} DICTIONARY */\
     M(DROP_FUNCTION, "", GLOBAL, DROP) /* allows to execute DROP FUNCTION */\
-    M(DROP_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_CONTROL) /* allows to execute DROP NAMED COLLECTION */\
+    M(DROP_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) /* allows to execute DROP NAMED COLLECTION */\
     M(DROP, "", GROUP, ALL) /* allows to execute {DROP|DETACH} */\
     \
     M(UNDROP_TABLE, "", TABLE, ALL) /* allows to execute {UNDROP} TABLE */\
@@ -140,9 +140,10 @@ enum class AccessType
     M(SHOW_SETTINGS_PROFILES, "SHOW PROFILES, SHOW CREATE SETTINGS PROFILE, SHOW CREATE PROFILE", GLOBAL, SHOW_ACCESS) \
     M(SHOW_ACCESS, "", GROUP, ACCESS_MANAGEMENT) \
     M(ACCESS_MANAGEMENT, "", GROUP, ALL) \
-    M(SHOW_NAMED_COLLECTIONS, "SHOW NAMED COLLECTIONS", NAMED_COLLECTION, NAMED_COLLECTION_CONTROL) \
+    M(SHOW_NAMED_COLLECTIONS, "SHOW NAMED COLLECTIONS", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) \
-    M(SHOW_NAMED_COLLECTIONS_SECRETS, "SHOW NAMED COLLECTIONS SECRETS", NAMED_COLLECTION, NAMED_COLLECTION_CONTROL) \
+    M(SHOW_NAMED_COLLECTIONS_SECRETS, "SHOW NAMED COLLECTIONS SECRETS", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) \
-    M(NAMED_COLLECTION_CONTROL, "", NAMED_COLLECTION, ALL) \
+    M(NAMED_COLLECTION, "NAMED COLLECTION USAGE, USE NAMED COLLECTION", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) \
+    M(NAMED_COLLECTION_ADMIN, "NAMED COLLECTION CONTROL", NAMED_COLLECTION, ALL) \
     \
     M(SYSTEM_SHUTDOWN, "SYSTEM KILL, SHUTDOWN", GLOBAL, SYSTEM) \
     M(SYSTEM_DROP_DNS_CACHE, "SYSTEM DROP DNS, DROP DNS CACHE, DROP DNS", GLOBAL, SYSTEM_DROP_CACHE) \
@@ -157,7 +158,6 @@ enum class AccessType
     M(SYSTEM_DROP_CACHE, "DROP CACHE", GROUP, SYSTEM) \
     M(SYSTEM_RELOAD_CONFIG, "RELOAD CONFIG", GLOBAL, SYSTEM_RELOAD) \
     M(SYSTEM_RELOAD_USERS, "RELOAD USERS", GLOBAL, SYSTEM_RELOAD) \
-    M(SYSTEM_RELOAD_SYMBOLS, "RELOAD SYMBOLS", GLOBAL, SYSTEM_RELOAD) \
     M(SYSTEM_RELOAD_DICTIONARY, "SYSTEM RELOAD DICTIONARIES, RELOAD DICTIONARY, RELOAD DICTIONARIES", GLOBAL, SYSTEM_RELOAD) \
     M(SYSTEM_RELOAD_MODEL, "SYSTEM RELOAD MODELS, RELOAD MODEL, RELOAD MODELS", GLOBAL, SYSTEM_RELOAD) \
     M(SYSTEM_RELOAD_FUNCTION, "SYSTEM RELOAD FUNCTIONS, RELOAD FUNCTION, RELOAD FUNCTIONS", GLOBAL, SYSTEM_RELOAD) \

src/Access/UsersConfigAccessStorage.cpp

@@ -328,7 +328,7 @@ namespace
 
             if (!named_collection_control)
             {
-                user->access.revoke(AccessType::NAMED_COLLECTION_CONTROL);
+                user->access.revoke(AccessType::NAMED_COLLECTION_ADMIN);
             }
 
             if (!show_named_collections_secrets)

src/Access/tests/gtest_access_rights_ops.cpp

@@ -53,7 +53,7 @@ TEST(AccessRights, Union)
               "SHOW ROW POLICIES, SYSTEM MERGES, SYSTEM TTL MERGES, SYSTEM FETCHES, "
               "SYSTEM MOVES, SYSTEM SENDS, SYSTEM REPLICATION QUEUES, "
               "SYSTEM DROP REPLICA, SYSTEM SYNC REPLICA, SYSTEM RESTART REPLICA, "
-              "SYSTEM RESTORE REPLICA, SYSTEM WAIT LOADING PARTS, SYSTEM SYNC DATABASE REPLICA, SYSTEM FLUSH DISTRIBUTED, dictGet ON db1.*, GRANT NAMED COLLECTION CONTROL ON db1");
+              "SYSTEM RESTORE REPLICA, SYSTEM WAIT LOADING PARTS, SYSTEM SYNC DATABASE REPLICA, SYSTEM FLUSH DISTRIBUTED, dictGet ON db1.*, GRANT NAMED COLLECTION ADMIN ON db1");
 }
 
 

src/AggregateFunctions/AggregateFunctionMinMaxAny.h

@@ -51,7 +51,8 @@ private:
     T value = T{};
 
 public:
-    static constexpr bool is_nullable = false;
+    static constexpr bool result_is_nullable = false;
+    static constexpr bool should_skip_null_arguments = true;
     static constexpr bool is_any = false;
 
     bool has() const
@@ -501,7 +502,8 @@ private:
     char small_data[MAX_SMALL_STRING_SIZE]; /// Including the terminating zero.
 
 public:
-    static constexpr bool is_nullable = false;
+    static constexpr bool result_is_nullable = false;
+    static constexpr bool should_skip_null_arguments = true;
     static constexpr bool is_any = false;
 
     bool has() const
@@ -769,7 +771,7 @@ static_assert(
 
 
 /// For any other value types.
-template <bool IS_NULLABLE = false>
+template <bool RESULT_IS_NULLABLE = false>
 struct SingleValueDataGeneric
 {
 private:
@@ -779,12 +781,13 @@ private:
     bool has_value = false;
 
 public:
-    static constexpr bool is_nullable = IS_NULLABLE;
+    static constexpr bool result_is_nullable = RESULT_IS_NULLABLE;
+    static constexpr bool should_skip_null_arguments = !RESULT_IS_NULLABLE;
     static constexpr bool is_any = false;
 
     bool has() const
     {
-        if constexpr (is_nullable)
+        if constexpr (result_is_nullable)
             return has_value;
         return !value.isNull();
     }
@@ -820,14 +823,14 @@ public:
     void change(const IColumn & column, size_t row_num, Arena *)
     {
         column.get(row_num, value);
-        if constexpr (is_nullable)
+        if constexpr (result_is_nullable)
             has_value = true;
     }
 
     void change(const Self & to, Arena *)
     {
         value = to.value;
-        if constexpr (is_nullable)
+        if constexpr (result_is_nullable)
             has_value = true;
     }
 
@@ -844,7 +847,7 @@ public:
 
     bool changeFirstTime(const Self & to, Arena * arena)
     {
-        if (!has() && (is_nullable || to.has()))
+        if (!has() && (result_is_nullable || to.has()))
         {
             change(to, arena);
             return true;
@@ -879,7 +882,7 @@ public:
         }
         else
         {
-            if constexpr (is_nullable)
+            if constexpr (result_is_nullable)
             {
                 Field new_value;
                 column.get(row_num, new_value);
@@ -910,7 +913,7 @@ public:
     {
         if (!to.has())
             return false;
-        if constexpr (is_nullable)
+        if constexpr (result_is_nullable)
         {
             if (!has())
             {
@@ -945,7 +948,7 @@ public:
         }
         else
         {
-            if constexpr (is_nullable)
+            if constexpr (result_is_nullable)
             {
                 Field new_value;
                 column.get(row_num, new_value);
@@ -975,7 +978,7 @@ public:
     {
         if (!to.has())
             return false;
-        if constexpr (is_nullable)
+        if constexpr (result_is_nullable)
         {
             if (!value.isNull() && (to.value.isNull() || value < to.value))
             {
@@ -1138,13 +1141,20 @@ struct AggregateFunctionAnyLastData : Data
 #endif
 };
 
+
+/** The aggregate function 'singleValueOrNull' is used to implement subquery operators,
+  * such as x = ALL (SELECT ...)
+  * It checks if there is only one unique non-NULL value in the data.
+  * If there is only one unique value - returns it.
+  * If there are zero or at least two distinct values - returns NULL.
+  */
 template <typename Data>
 struct AggregateFunctionSingleValueOrNullData : Data
 {
-    static constexpr bool is_nullable = true;
-
     using Self = AggregateFunctionSingleValueOrNullData;
 
+    static constexpr bool result_is_nullable = true;
+
     bool first_value = true;
     bool is_null = false;
 
@@ -1166,7 +1176,7 @@ struct AggregateFunctionSingleValueOrNullData : Data
         if (!to.has())
             return;
 
-        if (first_value)
+        if (first_value && !to.first_value)
         {
             first_value = false;
             this->change(to, arena);
@@ -1311,7 +1321,7 @@ public:
 
     static DataTypePtr createResultType(const DataTypePtr & type_)
     {
-        if constexpr (Data::is_nullable)
+        if constexpr (Data::result_is_nullable)
             return makeNullable(type_);
         return type_;
     }
@@ -1431,13 +1441,13 @@ public:
     }
 
     AggregateFunctionPtr getOwnNullAdapter(
-        const AggregateFunctionPtr & nested_function,
+        const AggregateFunctionPtr & original_function,
         const DataTypes & /*arguments*/,
         const Array & /*params*/,
         const AggregateFunctionProperties & /*properties*/) const override
     {
-        if (Data::is_nullable)
+        if (Data::result_is_nullable && !Data::should_skip_null_arguments)
-            return nested_function;
+            return original_function;
         return nullptr;
     }
 

src/Analyzer/Passes/QueryAnalysisPass.cpp

@@ -116,7 +116,6 @@ namespace ErrorCodes
     extern const int UNKNOWN_TABLE;
     extern const int ILLEGAL_COLUMN;
     extern const int NUMBER_OF_COLUMNS_DOESNT_MATCH;
-    extern const int FUNCTION_CANNOT_HAVE_PARAMETERS;
 }
 
 /** Query analyzer implementation overview. Please check documentation in QueryAnalysisPass.h first.
@@ -4897,11 +4896,6 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
                     lambda_expression_untyped->formatASTForErrorMessage(),
                     scope.scope_node->formatASTForErrorMessage());
 
-            if (!parameters.empty())
-            {
-                throw Exception(ErrorCodes::FUNCTION_CANNOT_HAVE_PARAMETERS, "Function {} is not parametric", function_node.formatASTForErrorMessage());
-            }
-
             auto lambda_expression_clone = lambda_expression_untyped->clone();
 
             IdentifierResolveScope lambda_scope(lambda_expression_clone, &scope /*parent_scope*/);
@@ -5018,12 +5012,9 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
     }
 
     FunctionOverloadResolverPtr function = UserDefinedExecutableFunctionFactory::instance().tryGet(function_name, scope.context, parameters);
-    bool is_executable_udf = false;
 
     if (!function)
         function = FunctionFactory::instance().tryGet(function_name, scope.context);
-    else
-        is_executable_udf = true;
 
     if (!function)
     {
@@ -5074,12 +5065,6 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
         return result_projection_names;
     }
 
-    /// Executable UDFs may have parameters. They are checked in UserDefinedExecutableFunctionFactory.
-    if (!parameters.empty() && !is_executable_udf)
-    {
-        throw Exception(ErrorCodes::FUNCTION_CANNOT_HAVE_PARAMETERS, "Function {} is not parametric", function_name);
-    }
-
     /** For lambda arguments we need to initialize lambda argument types DataTypeFunction using `getLambdaArgumentTypes` function.
       * Then each lambda arguments are initialized with columns, where column source is lambda.
       * This information is important for later steps of query processing.

src/Backups/BackupIO_S3.cpp

@@ -253,6 +253,7 @@ std::unique_ptr<WriteBuffer> BackupWriterS3::writeFile(const String & file_name)
 {
     return std::make_unique<WriteBufferFromS3>(
         client,
+        client, // already has long timeout
         s3_uri.bucket,
         fs::path(s3_uri.key) / file_name,
         DBMS_DEFAULT_BUFFER_SIZE,

src/Backups/tests/gtest_backup_entries.cpp

@@ -24,7 +24,7 @@ protected:
         /// Make local disk.
         temp_dir = std::make_unique<Poco::TemporaryFile>();
         temp_dir->createDirectories();
-        local_disk = std::make_shared<DiskLocal>("local_disk", temp_dir->path() + "/", 0);
+        local_disk = std::make_shared<DiskLocal>("local_disk", temp_dir->path() + "/");
 
         /// Make encrypted disk.
         auto settings = std::make_unique<DiskEncryptedSettings>();
@@ -38,7 +38,7 @@ protected:
         settings->current_key = key;
         settings->current_key_fingerprint = fingerprint;
 
-        encrypted_disk = std::make_shared<DiskEncrypted>("encrypted_disk", std::move(settings), true);
+        encrypted_disk = std::make_shared<DiskEncrypted>("encrypted_disk", std::move(settings));
     }
 
     void TearDown() override

src/CMakeLists.txt

@@ -206,11 +206,10 @@ add_library (clickhouse_new_delete STATIC Common/new_delete.cpp)
 target_link_libraries (clickhouse_new_delete PRIVATE clickhouse_common_io)
 if (TARGET ch_contrib::jemalloc)
     target_link_libraries (clickhouse_new_delete PRIVATE ch_contrib::jemalloc)
+    target_link_libraries (clickhouse_common_io PRIVATE ch_contrib::jemalloc)
+    target_link_libraries (clickhouse_storages_system PRIVATE ch_contrib::jemalloc)
 endif()
 
-if (TARGET ch_contrib::jemalloc)
-    target_link_libraries (clickhouse_common_io PRIVATE ch_contrib::jemalloc)
-endif()
 target_link_libraries (clickhouse_common_io PUBLIC ch_contrib::sparsehash)
 
 add_subdirectory(Access/Common)

src/Client/ClientBase.cpp

@@ -575,9 +575,11 @@ try
                 }
 
                 auto flags = O_WRONLY | O_EXCL;
-                if (query_with_output->is_outfile_append)
+
+                auto file_exists = fs::exists(out_file);
+                if (file_exists && query_with_output->is_outfile_append)
                     flags |= O_APPEND;
-                else if (query_with_output->is_outfile_truncate)
+                else if (file_exists && query_with_output->is_outfile_truncate)
                     flags |= O_TRUNC;
                 else
                     flags |= O_CREAT;
@@ -2297,7 +2299,9 @@ void ClientBase::runInteractive()
         catch (const ErrnoException & e)
         {
             if (e.getErrno() != EEXIST)
-                throw;
+            {
+                std::cerr << getCurrentExceptionMessage(false) << '\n';
+            }
         }
     }
 

src/Client/ConnectionParameters.cpp

@@ -60,7 +60,15 @@ ConnectionParameters::ConnectionParameters(const Poco::Util::AbstractConfigurati
     quota_key = config.getString("quota_key", "");
 
     /// By default compression is disabled if address looks like localhost.
-    compression = config.getBool("compression", !isLocalAddress(DNSResolver::instance().resolveHost(host)))
+
+    /// Avoid DNS request if the host is "localhost".
+    /// If ClickHouse is run under QEMU-user with a binary for a different architecture,
+    /// and there are all listed startup dependency shared libraries available, but not the runtime dependencies of glibc,
+    /// the glibc cannot open "plugins" for DNS resolving, and the DNS resolution does not work.
+    /// At the same time, I want clickhouse-local to always work, regardless.
+    /// TODO: get rid of glibc, or replace getaddrinfo to c-ares.
+
+    compression = config.getBool("compression", host != "localhost" && !isLocalAddress(DNSResolver::instance().resolveHost(host)))
                   ? Protocol::Compression::Enable : Protocol::Compression::Disable;
 
     timeouts = ConnectionTimeouts(

src/Client/Suggest.cpp

@@ -101,9 +101,8 @@ static String getLoadSuggestionQuery(Int32 suggestion_limit, bool basic_suggesti
         add_column("name", "columns", true, suggestion_limit);
     }
 
-    /// FIXME: Forbid this query using new analyzer because of bug https://github.com/ClickHouse/ClickHouse/issues/50669
+    /// FIXME: This query does not work with the new analyzer because of bug https://github.com/ClickHouse/ClickHouse/issues/50669
-    /// We should remove this restriction after resolving this bug.
+    query = "SELECT DISTINCT arrayJoin(extractAll(name, '[\\\\w_]{2,}')) AS res FROM (" + query + ") WHERE notEmpty(res)";
-    query = "SELECT DISTINCT arrayJoin(extractAll(name, '[\\\\w_]{2,}')) AS res FROM (" + query + ") WHERE notEmpty(res) SETTINGS allow_experimental_analyzer=0";
     return query;
 }
 

src/Columns/ColumnVector.h

@@ -107,8 +107,8 @@ struct FloatCompareHelper
     }
 };
 
-template <class U> struct CompareHelper<Float32, U> : public FloatCompareHelper<Float32> {};
+template <typename U> struct CompareHelper<Float32, U> : public FloatCompareHelper<Float32> {};
-template <class U> struct CompareHelper<Float64, U> : public FloatCompareHelper<Float64> {};
+template <typename U> struct CompareHelper<Float64, U> : public FloatCompareHelper<Float64> {};
 
 
 /** A template for columns that use a simple array to store.

src/Common/Allocator.cpp

@@ -8,7 +8,7 @@
   * See also: https://gcc.gnu.org/legacy-ml/gcc-help/2017-12/msg00021.html
   */
 #ifdef NDEBUG
-    __attribute__((__weak__)) extern const size_t MMAP_THRESHOLD = 64 * (1ULL << 20);
+    __attribute__((__weak__)) extern const size_t MMAP_THRESHOLD = 128 * (1ULL << 20);
 #else
     /**
       * In debug build, use small mmap threshold to reproduce more memory

src/Common/CurrentMetrics.cpp

@@ -2,7 +2,7 @@
 
 
 /// Available metrics. Add something here as you wish.
-#define APPLY_FOR_METRICS(M) \
+#define APPLY_FOR_BUILTIN_METRICS(M) \
     M(Query, "Number of executing queries") \
     M(Merge, "Number of executing background merges") \
     M(Move, "Number of currently executing moves") \
@@ -93,8 +93,8 @@
     M(ThreadPoolFSReaderThreadsActive, "Number of threads in the thread pool for local_filesystem_read_method=threadpool running a task.") \
     M(BackupsIOThreads, "Number of threads in the BackupsIO thread pool.") \
     M(BackupsIOThreadsActive, "Number of threads in the BackupsIO thread pool running a task.") \
-    M(DiskObjectStorageAsyncThreads, "Number of threads in the async thread pool for DiskObjectStorage.") \
+    M(DiskObjectStorageAsyncThreads, "Obsolete metric, shows nothing.") \
-    M(DiskObjectStorageAsyncThreadsActive, "Number of threads in the async thread pool for DiskObjectStorage running a task.") \
+    M(DiskObjectStorageAsyncThreadsActive, "Obsolete metric, shows nothing.") \
     M(StorageHiveThreads, "Number of threads in the StorageHive thread pool.") \
     M(StorageHiveThreadsActive, "Number of threads in the StorageHive thread pool running a task.") \
     M(TablesLoaderThreads, "Number of threads in the tables loader thread pool.") \
@@ -141,6 +141,8 @@
     M(MergeTreeOutdatedPartsLoaderThreadsActive, "Number of active threads in the threadpool for loading Outdated data parts.") \
     M(MergeTreePartsCleanerThreads, "Number of threads in the MergeTree parts cleaner thread pool.") \
     M(MergeTreePartsCleanerThreadsActive, "Number of threads in the MergeTree parts cleaner thread pool running a task.") \
+    M(IDiskCopierThreads, "Number of threads for copying data between disks of different types.") \
+    M(IDiskCopierThreadsActive, "Number of threads for copying data between disks of different types running a task.") \
     M(SystemReplicasThreads, "Number of threads in the system.replicas thread pool.") \
     M(SystemReplicasThreadsActive, "Number of threads in the system.replicas thread pool running a task.") \
     M(RestartReplicaThreads, "Number of threads in the RESTART REPLICA thread pool.") \
@@ -200,7 +202,13 @@
     M(MergeTreeReadTaskRequestsSent, "The current number of callback requests in flight from the remote server back to the initiator server to choose the read task (for MergeTree tables). Measured on the remote server side.") \
     M(MergeTreeAllRangesAnnouncementsSent, "The current number of announcement being sent in flight from the remote server to the initiator server about the set of data parts (for MergeTree tables). Measured on the remote server side.") \
     M(CreatedTimersInQueryProfiler, "Number of Created thread local timers in QueryProfiler") \
-    M(ActiveTimersInQueryProfiler, "Number of Active thread local timers in QueryProfiler")
+    M(ActiveTimersInQueryProfiler, "Number of Active thread local timers in QueryProfiler") \
+
+#ifdef APPLY_FOR_EXTERNAL_METRICS
+    #define APPLY_FOR_METRICS(M) APPLY_FOR_BUILTIN_METRICS(M) APPLY_FOR_EXTERNAL_METRICS(M)
+#else
+    #define APPLY_FOR_METRICS(M) APPLY_FOR_BUILTIN_METRICS(M)
+#endif
 
 namespace CurrentMetrics
 {

src/Common/ErrorCodes.cpp

@@ -13,7 +13,7 @@
   * - system.errors table
   */
 
-#define APPLY_FOR_ERROR_CODES(M) \
+#define APPLY_FOR_BUILTIN_ERROR_CODES(M) \
     M(0, OK) \
     M(1, UNSUPPORTED_METHOD) \
     M(2, UNSUPPORTED_PARAMETER) \
@@ -589,6 +589,12 @@
     M(1002, UNKNOWN_EXCEPTION) \
 /* See END */
 
+#ifdef APPLY_FOR_EXTERNAL_ERROR_CODES
+    #define APPLY_FOR_ERROR_CODES(M) APPLY_FOR_BUILTIN_ERROR_CODES(M) APPLY_FOR_EXTERNAL_ERROR_CODES(M)
+#else
+    #define APPLY_FOR_ERROR_CODES(M) APPLY_FOR_BUILTIN_ERROR_CODES(M)
+#endif
+
 namespace DB
 {
 namespace ErrorCodes

src/Common/Exception.cpp

@@ -418,6 +418,18 @@ PreformattedMessage getCurrentExceptionMessageAndPattern(bool with_stacktrace, b
                 << " (version " << VERSION_STRING << VERSION_OFFICIAL << ")";
         }
         catch (...) {}
+
+// #ifdef ABORT_ON_LOGICAL_ERROR
+//         try
+//         {
+//             throw;
+//         }
+//         catch (const std::logic_error &)
+//         {
+//             abortOnFailedAssertion(stream.str());
+//         }
+//         catch (...) {}
+// #endif
     }
     catch (...)
     {

src/Common/MemoryTrackerSwitcher.h

@@ -0,0 +1,42 @@
+#pragma once
+
+#include <Common/CurrentThread.h>
+#include <Common/MemoryTracker.h>
+
+namespace DB
+{
+
+namespace ErrorCodes
+{
+    extern const int LOGICAL_ERROR;
+}
+
+struct MemoryTrackerSwitcher
+{
+    explicit MemoryTrackerSwitcher(MemoryTracker * new_tracker)
+    {
+        if (!current_thread)
+            throw Exception(ErrorCodes::LOGICAL_ERROR, "current_thread is not initialized");
+
+        auto * thread_tracker = CurrentThread::getMemoryTracker();
+        prev_untracked_memory = current_thread->untracked_memory;
+        prev_memory_tracker_parent = thread_tracker->getParent();
+
+        current_thread->untracked_memory = 0;
+        thread_tracker->setParent(new_tracker);
+    }
+
+    ~MemoryTrackerSwitcher()
+    {
+        CurrentThread::flushUntrackedMemory();
+        auto * thread_tracker = CurrentThread::getMemoryTracker();
+
+        current_thread->untracked_memory = prev_untracked_memory;
+        thread_tracker->setParent(prev_memory_tracker_parent);
+    }
+
+    MemoryTracker * prev_memory_tracker_parent = nullptr;
+    Int64 prev_untracked_memory = 0;
+};
+
+}

src/Common/OptimizedRegularExpression.cpp

@@ -540,7 +540,7 @@ bool OptimizedRegularExpressionImpl<thread_safe>::match(const char * subject, si
             }
         }
 
-        return re2->Match(StringPieceType(subject, subject_size), 0, subject_size, RegexType::UNANCHORED, nullptr, 0);
+        return re2->Match({subject, subject_size}, 0, subject_size, RegexType::UNANCHORED, nullptr, 0);
     }
 }
 
@@ -585,9 +585,9 @@ bool OptimizedRegularExpressionImpl<thread_safe>::match(const char * subject, si
                 return false;
         }
 
-        StringPieceType piece;
+        std::string_view piece;
 
-        if (!RegexType::PartialMatch(StringPieceType(subject, subject_size), *re2, &piece))
+        if (!RegexType::PartialMatch({subject, subject_size}, *re2, &piece))
             return false;
         else
         {
@@ -652,10 +652,10 @@ unsigned OptimizedRegularExpressionImpl<thread_safe>::match(const char * subject
                 return 0;
         }
 
-        DB::PODArrayWithStackMemory<StringPieceType, 128> pieces(limit);
+        DB::PODArrayWithStackMemory<std::string_view, 128> pieces(limit);
 
         if (!re2->Match(
-            StringPieceType(subject, subject_size),
+            {subject, subject_size},
             0,
             subject_size,
             RegexType::UNANCHORED,

src/Common/OptimizedRegularExpression.h

@@ -52,7 +52,6 @@ public:
     using MatchVec = std::vector<Match>;
 
     using RegexType = std::conditional_t<thread_safe, re2::RE2, re2_st::RE2>;
-    using StringPieceType = std::conditional_t<thread_safe, re2::StringPiece, re2_st::StringPiece>;
 
     OptimizedRegularExpressionImpl(const std::string & regexp_, int options = 0); /// NOLINT
     /// StringSearcher store pointers to required_substring, it must be updated on move.

src/Common/PoolBase.h

@@ -1,9 +1,11 @@
 #pragma once
 
-#include <mutex>
 #include <condition_variable>
-#include <Poco/Timespan.h>
+#include <mutex>
+#include <type_traits>
+#include <variant>
 #include <boost/noncopyable.hpp>
+#include <Poco/Timespan.h>
 
 #include <Common/logger_useful.h>
 #include <Common/Exception.h>
@@ -15,14 +17,6 @@ namespace ProfileEvents
     extern const Event ConnectionPoolIsFullMicroseconds;
 }
 
-namespace DB
-{
-    namespace ErrorCodes
-    {
-        extern const int LOGICAL_ERROR;
-    }
-}
-
 /** A class from which you can inherit and get a pool of something. Used for database connection pools.
   * Descendant class must provide a method for creating a new object to place in the pool.
   */
@@ -35,6 +29,22 @@ public:
     using ObjectPtr = std::shared_ptr<Object>;
     using Ptr = std::shared_ptr<PoolBase<TObject>>;
 
+    enum class BehaviourOnLimit
+    {
+        /**
+         * Default behaviour - when limit on pool size is reached, callers will wait until object will be returned back in pool.
+         */
+        Wait,
+
+        /**
+         * If no free objects in pool - allocate a new object, but not store it in pool.
+         * This behaviour is needed when we simply don't want to waste time waiting or if we cannot guarantee that query could be processed using fixed amount of connections.
+         * For example, when we read from table on s3, one GetObject request corresponds to the whole FileSystemCache segment. This segments are shared between different
+         * reading tasks, so in general case connection could be taken from pool by one task and returned back by another one. And these tasks are processed completely independently.
+         */
+        AllocateNewBypassingPool,
+    };
+
 private:
 
     /** The object with the flag, whether it is currently used. */
@@ -89,37 +99,53 @@ public:
         Object & operator*() && = delete;
         const Object & operator*() const && = delete;
 
-        Object * operator->() &             { return &*data->data.object; }
+        Object * operator->() &             { return castToObjectPtr(); }
-        const Object * operator->() const & { return &*data->data.object; }
+        const Object * operator->() const & { return castToObjectPtr(); }
-        Object & operator*() &              { return *data->data.object; }
+        Object & operator*() &              { return *castToObjectPtr(); }
-        const Object & operator*() const &  { return *data->data.object; }
+        const Object & operator*() const &  { return *castToObjectPtr(); }
 
         /**
          * Expire an object to make it reallocated later.
          */
         void expire()
         {
-            data->data.is_expired = true;
+            if (data.index() == 1)
+                std::get<1>(data)->data.is_expired = true;
         }
 
-        bool isNull() const { return data == nullptr; }
+        bool isNull() const { return data.index() == 0 ? !std::get<0>(data) : !std::get<1>(data); }
-
-        PoolBase * getPool() const
-        {
-            if (!data)
-                throw DB::Exception(DB::ErrorCodes::LOGICAL_ERROR, "Attempt to get pool from uninitialized entry");
-            return &data->data.pool;
-        }
 
     private:
-        std::shared_ptr<PoolEntryHelper> data;
+        /**
+         * Plain object will be stored instead of PoolEntryHelper if fallback was made in get() (see BehaviourOnLimit::AllocateNewBypassingPool).
+         */
+        std::variant<ObjectPtr, std::shared_ptr<PoolEntryHelper>> data;
 
-        explicit Entry(PooledObject & object) : data(std::make_shared<PoolEntryHelper>(object)) {}
+        explicit Entry(ObjectPtr && object) : data(std::move(object)) { }
+
+        explicit Entry(PooledObject & object) : data(std::make_shared<PoolEntryHelper>(object)) { }
+
+        auto castToObjectPtr() const
+        {
+            return std::visit(
+                [](const auto & ptr)
+                {
+                    using T = std::decay_t<decltype(ptr)>;
+                    if constexpr (std::is_same_v<ObjectPtr, T>)
+                        return ptr.get();
+                    else
+                        return ptr->data.object.get();
+                },
+                data);
+        }
     };
 
     virtual ~PoolBase() = default;
 
-    /** Allocates the object. Wait for free object in pool for 'timeout'. With 'timeout' < 0, the timeout is infinite. */
+    /** Allocates the object.
+     *  If 'behaviour_on_limit' is Wait - wait for free object in pool for 'timeout'. With 'timeout' < 0, the timeout is infinite.
+     *  If 'behaviour_on_limit' is AllocateNewBypassingPool and there is no free object - a new object will be created but not stored in the pool.
+     */
     Entry get(Poco::Timespan::TimeDiff timeout)
     {
         std::unique_lock lock(mutex);
@@ -150,6 +176,9 @@ public:
                 return Entry(*items.back());
             }
 
+            if (behaviour_on_limit == BehaviourOnLimit::AllocateNewBypassingPool)
+                return Entry(allocObject());
+
             Stopwatch blocked;
             if (timeout < 0)
             {
@@ -184,6 +213,8 @@ private:
     /** The maximum size of the pool. */
     unsigned max_items;
 
+    BehaviourOnLimit behaviour_on_limit;
+
     /** Pool. */
     Objects items;
 
@@ -192,11 +223,10 @@ private:
     std::condition_variable available;
 
 protected:
-
     Poco::Logger * log;
 
-    PoolBase(unsigned max_items_, Poco::Logger * log_)
+    PoolBase(unsigned max_items_, Poco::Logger * log_, BehaviourOnLimit behaviour_on_limit_ = BehaviourOnLimit::Wait)
-       : max_items(max_items_), log(log_)
+        : max_items(max_items_), behaviour_on_limit(behaviour_on_limit_), log(log_)
     {
         items.reserve(max_items);
     }

src/Common/ProfileEvents.cpp

@@ -4,7 +4,7 @@
 
 
 /// Available events. Add something here as you wish.
-#define APPLY_FOR_EVENTS(M) \
+#define APPLY_FOR_BUILTIN_EVENTS(M) \
     M(Query, "Number of queries to be interpreted and potentially executed. Does not include queries that failed to parse or were rejected due to AST size limits, quota limits or limits on the number of simultaneously running queries. May include internal queries initiated by ClickHouse itself. Does not count subqueries.") \
     M(SelectQuery, "Same as Query, but only for SELECT queries.") \
     M(InsertQuery, "Same as Query, but only for INSERT queries.") \
@@ -368,6 +368,10 @@ The server successfully detected this situation and will download merged part fr
     M(ReadBufferFromS3InitMicroseconds, "Time spent initializing connection to S3.") \
     M(ReadBufferFromS3Bytes, "Bytes read from S3.") \
     M(ReadBufferFromS3RequestsErrors, "Number of exceptions while reading from S3.") \
+    M(ReadBufferFromS3ResetSessions, "Number of HTTP sessions that were reset in ReadBufferFromS3.") \
+    M(ReadBufferFromS3PreservedSessions, "Number of HTTP sessions that were preserved in ReadBufferFromS3.") \
+    \
+    M(ReadWriteBufferFromHTTPPreservedSessions, "Number of HTTP sessions that were preserved in ReadWriteBufferFromHTTP.") \
     \
     M(WriteBufferFromS3Microseconds, "Time spent on writing to S3.") \
     M(WriteBufferFromS3Bytes, "Bytes written to S3.") \
@@ -536,6 +540,11 @@ The server successfully detected this situation and will download merged part fr
     M(LogError, "Number of log messages with level Error") \
     M(LogFatal, "Number of log messages with level Fatal") \
 
+#ifdef APPLY_FOR_EXTERNAL_EVENTS
+    #define APPLY_FOR_EVENTS(M) APPLY_FOR_BUILTIN_EVENTS(M) APPLY_FOR_EXTERNAL_EVENTS(M)
+#else
+    #define APPLY_FOR_EVENTS(M) APPLY_FOR_BUILTIN_EVENTS(M)
+#endif
 
 namespace ProfileEvents
 {

src/Common/QueryProfiler.cpp

@@ -91,7 +91,7 @@ namespace ErrorCodes
     extern const int NOT_IMPLEMENTED;
 }
 
-#if USE_UNWIND
+#ifndef __APPLE__
 Timer::Timer()
     : log(&Poco::Logger::get("Timer"))
 {}
@@ -120,6 +120,15 @@ void Timer::createIfNecessary(UInt64 thread_id, int clock_type, int pause_signal
                 throw Exception(ErrorCodes::CANNOT_CREATE_TIMER, "Failed to create thread timer. The function "
                                 "'timer_create' returned non-zero but didn't set errno. This is bug in your OS.");
 
+            /// For example, it cannot be created if the server is run under QEMU:
+            /// "Failed to create thread timer, errno: 11, strerror: Resource temporarily unavailable."
+
+            /// You could accidentally run the server under QEMU without being aware,
+            /// if you use Docker image for a different architecture,
+            /// and you have the "binfmt-misc" kernel module, and "qemu-user" tools.
+
+            /// Also, it cannot be created if the server has too many threads.
+
             throwFromErrno("Failed to create thread timer", ErrorCodes::CANNOT_CREATE_TIMER);
         }
         timer_id.emplace(local_timer_id);
@@ -200,13 +209,13 @@ QueryProfilerBase<ProfilerImpl>::QueryProfilerBase(UInt64 thread_id, int clock_t
     UNUSED(pause_signal);
 
     throw Exception(ErrorCodes::NOT_IMPLEMENTED, "QueryProfiler disabled because they cannot work under sanitizers");
-#elif !USE_UNWIND
+#elif defined(__APPLE__)
     UNUSED(thread_id);
     UNUSED(clock_type);
     UNUSED(period);
     UNUSED(pause_signal);
 
-    throw Exception(ErrorCodes::NOT_IMPLEMENTED, "QueryProfiler cannot work with stock libunwind");
+    throw Exception(ErrorCodes::NOT_IMPLEMENTED, "QueryProfiler cannot work on OSX");
 #else
     /// Sanity check.
     if (!hasPHDRCache())
@@ -255,7 +264,7 @@ QueryProfilerBase<ProfilerImpl>::~QueryProfilerBase()
 template <typename ProfilerImpl>
 void QueryProfilerBase<ProfilerImpl>::cleanup()
 {
-#if USE_UNWIND
+#ifndef __APPLE__
     timer.stop();
     signal_handler_disarmed = true;
 #endif

src/Common/QueryProfiler.h

@@ -28,7 +28,7 @@ namespace DB
   * Note that signal handler implementation is defined by template parameter. See QueryProfilerReal and QueryProfilerCPU.
   */
 
-#if USE_UNWIND
+#ifndef __APPLE__
 class Timer
 {
 public:
@@ -60,7 +60,7 @@ private:
 
     Poco::Logger * log;
 
-#if USE_UNWIND
+#ifndef __APPLE__
     inline static thread_local Timer timer = Timer();
 #endif
 

src/Common/SensitiveDataMasker.cpp

@@ -5,7 +5,6 @@
 #include <atomic>
 
 #include <re2/re2.h>
-#include <re2/stringpiece.h>
 
 #include <Poco/Util/AbstractConfiguration.h>
 
@@ -44,7 +43,7 @@ private:
     const std::string regexp_string;
 
     const RE2 regexp;
-    const re2::StringPiece replacement;
+    const std::string_view replacement;
 
 #ifndef NDEBUG
     mutable std::atomic<std::uint64_t> matches_count = 0;

src/Common/StackTrace.cpp

@@ -20,13 +20,10 @@
 #include <sstream>
 #include <unordered_map>
 #include <fmt/format.h>
+#include <libunwind.h>
 
 #include "config.h"
 
-#if USE_UNWIND
-#    include <libunwind.h>
-#endif
-
 namespace
 {
 /// Currently this variable is set up once on server startup.
@@ -211,8 +208,7 @@ void StackTrace::symbolize(
     const StackTrace::FramePointers & frame_pointers, [[maybe_unused]] size_t offset, size_t size, StackTrace::Frames & frames)
 {
 #if defined(__ELF__) && !defined(OS_FREEBSD)
-    auto symbol_index_ptr = DB::SymbolIndex::instance();
+    const DB::SymbolIndex & symbol_index = DB::SymbolIndex::instance();
-    const DB::SymbolIndex & symbol_index = *symbol_index_ptr;
     std::unordered_map<std::string, DB::Dwarf> dwarfs;
 
     for (size_t i = 0; i < offset; ++i)
@@ -287,12 +283,8 @@ StackTrace::StackTrace(const ucontext_t & signal_context)
 
 void StackTrace::tryCapture()
 {
-#if USE_UNWIND
     size = unw_backtrace(frame_pointers.data(), capacity);
     __msan_unpoison(frame_pointers.data(), size * sizeof(frame_pointers[0]));
-#else
-    size = 0;
-#endif
 }
 
 /// ClickHouse uses bundled libc++ so type names will be the same on every system thus it's safe to hardcode them
@@ -348,8 +340,7 @@ toStringEveryLineImpl([[maybe_unused]] bool fatal, const StackTraceRefTriple & s
     using enum DB::Dwarf::LocationInfoMode;
     const auto mode = fatal ? FULL_WITH_INLINE : FAST;
 
-    auto symbol_index_ptr = DB::SymbolIndex::instance();
+    const DB::SymbolIndex & symbol_index = DB::SymbolIndex::instance();
-    const DB::SymbolIndex & symbol_index = *symbol_index_ptr;
     std::unordered_map<String, DB::Dwarf> dwarfs;
 
     for (size_t i = stack_trace.offset; i < stack_trace.size; ++i)

src/Common/StringSearcher.h

@@ -793,88 +793,6 @@ public:
     }
 };
 
-
-// Searches for needle surrounded by token-separators.
-// Separators are anything inside ASCII (0-128) and not alphanum.
-// Any value outside of basic ASCII (>=128) is considered a non-separator symbol, hence UTF-8 strings
-// should work just fine. But any Unicode whitespace is not considered a token separtor.
-template <typename StringSearcher>
-class TokenSearcher : public StringSearcherBase
-{
-    StringSearcher searcher;
-    size_t needle_size;
-
-public:
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    static bool isValidNeedle(const CharT * needle_, size_t needle_size_)
-    {
-        return std::none_of(needle_, needle_ + needle_size_, isTokenSeparator);
-    }
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    TokenSearcher(const CharT * needle_, size_t needle_size_)
-        : searcher(needle_, needle_size_)
-        , needle_size(needle_size_)
-    {
-        /// The caller is responsible for calling isValidNeedle()
-        chassert(isValidNeedle(needle_, needle_size_));
-    }
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    ALWAYS_INLINE bool compare(const CharT * haystack, const CharT * haystack_end, const CharT * pos) const
-    {
-        // use searcher only if pos is in the beginning of token and pos + searcher.needle_size is end of token.
-        if (isToken(haystack, haystack_end, pos))
-            return searcher.compare(haystack, haystack_end, pos);
-
-        return false;
-    }
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    const CharT * search(const CharT * haystack, const CharT * const haystack_end) const
-    {
-        // use searcher.search(), then verify that returned value is a token
-        // if it is not, skip it and re-run
-
-        const auto * pos = haystack;
-        while (pos < haystack_end)
-        {
-            pos = searcher.search(pos, haystack_end);
-            if (pos == haystack_end || isToken(haystack, haystack_end, pos))
-                return pos;
-
-            // assuming that heendle does not contain any token separators.
-            pos += needle_size;
-        }
-        return haystack_end;
-    }
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    const CharT * search(const CharT * haystack, size_t haystack_size) const
-    {
-        return search(haystack, haystack + haystack_size);
-    }
-
-    template <typename CharT>
-    requires (sizeof(CharT) == 1)
-    ALWAYS_INLINE bool isToken(const CharT * haystack, const CharT * const haystack_end, const CharT* p) const
-    {
-        return (p == haystack || isTokenSeparator(*(p - 1)))
-             && (p + needle_size >= haystack_end || isTokenSeparator(*(p + needle_size)));
-    }
-
-    ALWAYS_INLINE static bool isTokenSeparator(const uint8_t c)
-    {
-        return !(isAlphaNumericASCII(c) || !isASCII(c));
-    }
-};
-
 }
 
 using ASCIICaseSensitiveStringSearcher =   impl::StringSearcher<true, true>;
@@ -882,9 +800,6 @@ using ASCIICaseInsensitiveStringSearcher = impl::StringSearcher<false, true>;
 using UTF8CaseSensitiveStringSearcher =    impl::StringSearcher<true, false>;
 using UTF8CaseInsensitiveStringSearcher =  impl::StringSearcher<false, false>;
 
-using ASCIICaseSensitiveTokenSearcher =    impl::TokenSearcher<ASCIICaseSensitiveStringSearcher>;
-using ASCIICaseInsensitiveTokenSearcher =  impl::TokenSearcher<ASCIICaseInsensitiveStringSearcher>;
-
 /// Use only with short haystacks where cheap initialization is required.
 template <bool CaseInsensitive>
 struct StdLibASCIIStringSearcher
@@ -906,11 +821,11 @@ struct StdLibASCIIStringSearcher
         if constexpr (CaseInsensitive)
             return std::search(
                 haystack_start, haystack_end, needle_start, needle_end,
-                [](char c1, char c2) {return std::toupper(c1) == std::toupper(c2);});
+                [](char c1, char c2) { return std::toupper(c1) == std::toupper(c2); });
         else
             return std::search(
                 haystack_start, haystack_end, needle_start, needle_end,
-                [](char c1, char c2) {return c1 == c2;});
+                [](char c1, char c2) { return c1 == c2; });
     }
 
     template <typename CharT>

src/Common/SymbolIndex.cpp

@@ -9,7 +9,6 @@
 
 #include <link.h>
 
-//#include <iostream>
 #include <filesystem>
 
 #include <base/sort.h>
@@ -510,7 +509,7 @@ const T * find(const void * address, const std::vector<T> & vec)
 }
 
 
-void SymbolIndex::update()
+void SymbolIndex::load()
 {
     dl_iterate_phdr(collectSymbols, &data);
 
@@ -550,24 +549,12 @@ String SymbolIndex::getBuildIDHex() const
     return build_id_hex;
 }
 
-MultiVersion<SymbolIndex> & SymbolIndex::instanceImpl()
+const SymbolIndex & SymbolIndex::instance()
 {
-    static MultiVersion<SymbolIndex> instance(std::unique_ptr<SymbolIndex>(new SymbolIndex));
+    static SymbolIndex instance;
     return instance;
 }
 
-MultiVersion<SymbolIndex>::Version SymbolIndex::instance()
-{
-    return instanceImpl().get();
-}
-
-void SymbolIndex::reload()
-{
-    instanceImpl().set(std::unique_ptr<SymbolIndex>(new SymbolIndex));
-    /// Also drop stacktrace cache.
-    StackTrace::dropCache();
-}
-
 }
 
 #endif

src/Common/SymbolIndex.h

@@ -8,8 +8,6 @@
 #include <Common/Elf.h>
 #include <boost/noncopyable.hpp>
 
-#include <Common/MultiVersion.h>
-
 namespace DB
 {
 
@@ -20,11 +18,10 @@ namespace DB
 class SymbolIndex : private boost::noncopyable
 {
 protected:
-    SymbolIndex() { update(); }
+    SymbolIndex() { load(); }
 
 public:
-    static MultiVersion<SymbolIndex>::Version instance();
+    static const SymbolIndex & instance();
-    static void reload();
 
     struct Symbol
     {
@@ -90,8 +87,7 @@ public:
 private:
     Data data;
 
-    void update();
+    void load();
-    static MultiVersion<SymbolIndex> & instanceImpl();
 };
 
 }

src/Common/ThreadStatus.cpp

@@ -67,8 +67,8 @@ ThreadGroup::ThreadGroup()
     : master_thread_id(CurrentThread::get().thread_id)
 {}
 
-ThreadStatus::ThreadStatus()
+ThreadStatus::ThreadStatus(bool check_current_thread_on_destruction_)
-    : thread_id{getThreadId()}
+    : thread_id{getThreadId()}, check_current_thread_on_destruction(check_current_thread_on_destruction_)
 {
     last_rusage = std::make_unique<RUsageCounters>();
 
@@ -199,10 +199,14 @@ ThreadStatus::~ThreadStatus()
     if (deleter)
         deleter();
 
+    chassert(!check_current_thread_on_destruction || current_thread == this);
+
     /// Only change current_thread if it's currently being used by this ThreadStatus
     /// For example, PushingToViews chain creates and deletes ThreadStatus instances while running in the main query thread
     if (current_thread == this)
         current_thread = nullptr;
+    else if (check_current_thread_on_destruction)
+        LOG_ERROR(log, "current_thread contains invalid address");
 }
 
 void ThreadStatus::updatePerformanceCounters()

src/Common/ThreadStatus.h

@@ -224,8 +224,10 @@ private:
 
     Poco::Logger * log = nullptr;
 
+    bool check_current_thread_on_destruction;
+
 public:
-    ThreadStatus();
+    explicit ThreadStatus(bool check_current_thread_on_destruction_ = true);
     ~ThreadStatus();
 
     ThreadGroupPtr getThreadGroup() const;

src/Common/Volnitsky.h

@@ -730,9 +730,6 @@ using VolnitskyUTF8 = VolnitskyBase<true, false, UTF8CaseSensitiveStringSearcher
 using VolnitskyCaseInsensitive = VolnitskyBase<false, true, ASCIICaseInsensitiveStringSearcher>; /// ignores non-ASCII bytes
 using VolnitskyCaseInsensitiveUTF8 = VolnitskyBase<false, false, UTF8CaseInsensitiveStringSearcher>;
 
-using VolnitskyCaseSensitiveToken = VolnitskyBase<true, true, ASCIICaseSensitiveTokenSearcher>;
-using VolnitskyCaseInsensitiveToken = VolnitskyBase<false, true, ASCIICaseInsensitiveTokenSearcher>;
-
 using MultiVolnitsky = MultiVolnitskyBase<true, true, ASCIICaseSensitiveStringSearcher>;
 using MultiVolnitskyUTF8 = MultiVolnitskyBase<true, false, UTF8CaseSensitiveStringSearcher>;
 using MultiVolnitskyCaseInsensitive = MultiVolnitskyBase<false, true, ASCIICaseInsensitiveStringSearcher>;

src/Common/checkStackSize.cpp

@@ -27,7 +27,7 @@ static thread_local size_t max_stack_size = 0;
  * @param out_address - if not nullptr, here the address of the stack will be written.
  * @return stack size
  */
-size_t getStackSize(void ** out_address)
+static size_t getStackSize(void ** out_address)
 {
     using namespace DB;
 
@@ -54,7 +54,15 @@ size_t getStackSize(void ** out_address)
         throwFromErrno("Cannot pthread_attr_get_np", ErrorCodes::CANNOT_PTHREAD_ATTR);
 #   else
     if (0 != pthread_getattr_np(pthread_self(), &attr))
-        throwFromErrno("Cannot pthread_getattr_np", ErrorCodes::CANNOT_PTHREAD_ATTR);
+    {
+        if (errno == ENOENT)
+        {
+            /// Most likely procfs is not mounted.
+            return 0;
+        }
+        else
+            throwFromErrno("Cannot pthread_getattr_np", ErrorCodes::CANNOT_PTHREAD_ATTR);
+    }
 #   endif
 
     SCOPE_EXIT({ pthread_attr_destroy(&attr); });
@@ -83,6 +91,10 @@ __attribute__((__weak__)) void checkStackSize()
     if (!stack_address)
         max_stack_size = getStackSize(&stack_address);
 
+    /// The check is impossible.
+    if (!max_stack_size)
+        return;
+
     const void * frame_address = __builtin_frame_address(0);
     uintptr_t int_frame_address = reinterpret_cast<uintptr_t>(frame_address);
     uintptr_t int_stack_address = reinterpret_cast<uintptr_t>(stack_address);

src/Common/config.h.in

@@ -9,7 +9,6 @@
 #cmakedefine01 USE_AWS_S3
 #cmakedefine01 USE_AZURE_BLOB_STORAGE
 #cmakedefine01 USE_BROTLI
-#cmakedefine01 USE_UNWIND
 #cmakedefine01 USE_CASSANDRA
 #cmakedefine01 USE_SENTRY
 #cmakedefine01 USE_GRPC

src/Common/examples/symbol_index.cpp

@@ -22,8 +22,7 @@ int main(int argc, char ** argv)
         return 1;
     }
 
-    auto symbol_index_ptr = SymbolIndex::instance();
+    const SymbolIndex & symbol_index = SymbolIndex::instance();
-    const SymbolIndex & symbol_index = *symbol_index_ptr;
 
     for (const auto & elem : symbol_index.symbols())
         std::cout << elem.name << ": " << elem.address_begin << " ... " << elem.address_end << "\n";

src/Common/getResource.cpp

@@ -16,7 +16,7 @@ std::string_view getResource(std::string_view name)
 
 #if defined USE_MUSL
     /// If static linking is used, we cannot use dlsym and have to parse ELF symbol table by ourself.
-    return DB::SymbolIndex::instance()->getResource(name_replaced);
+    return DB::SymbolIndex::instance().getResource(name_replaced);
 
 #else
     // In most `dlsym(3)` APIs, one passes the symbol name as it appears via

src/Common/parseGlobs.cpp

@@ -3,7 +3,6 @@
 #include <IO/ReadBufferFromString.h>
 #include <IO/Operators.h>
 #include <re2/re2.h>
-#include <re2/stringpiece.h>
 #include <algorithm>
 #include <sstream>
 #include <iomanip>
@@ -33,14 +32,14 @@ std::string makeRegexpPatternFromGlobs(const std::string & initial_str_with_glob
     std::string escaped_with_globs = buf_for_escaping.str();
 
     static const re2::RE2 enum_or_range(R"({([\d]+\.\.[\d]+|[^{}*,]+,[^{}*]*[^{}*,])})");    /// regexp for {expr1,expr2,expr3} or {M..N}, where M and N - non-negative integers, expr's should be without "{", "}", "*" and ","
-    re2::StringPiece input(escaped_with_globs);
+    std::string_view input(escaped_with_globs);
-    re2::StringPiece matched;
+    std::string_view matched;
     std::ostringstream oss_for_replacing;       // STYLE_CHECK_ALLOW_STD_STRING_STREAM
     oss_for_replacing.exceptions(std::ios::failbit);
     size_t current_index = 0;
     while (RE2::FindAndConsume(&input, enum_or_range, &matched))
     {
-        std::string buffer{matched};
+        std::string buffer(matched);
         oss_for_replacing << escaped_with_globs.substr(current_index, matched.data() - escaped_with_globs.data() - current_index - 1) << '(';
 
         if (buffer.find(',') == std::string::npos)

src/Compression/CompressionCodecLZ4.cpp

@@ -42,7 +42,6 @@ private:
     UInt32 getMaxCompressedDataSize(UInt32 uncompressed_size) const override;
 
     mutable LZ4::PerformanceStatistics lz4_stat;
-    ASTPtr codec_desc;
 };
 
 

src/Coordination/KeeperContext.cpp

@@ -220,7 +220,7 @@ KeeperContext::Storage KeeperContext::getLogsPathFromConfig(const Poco::Util::Ab
         if (!fs::exists(path))
             fs::create_directories(path);
 
-        return std::make_shared<DiskLocal>("LocalLogDisk", path, 0);
+        return std::make_shared<DiskLocal>("LocalLogDisk", path);
     };
 
     /// the most specialized path
@@ -246,7 +246,7 @@ KeeperContext::Storage KeeperContext::getSnapshotsPathFromConfig(const Poco::Uti
         if (!fs::exists(path))
             fs::create_directories(path);
 
-        return std::make_shared<DiskLocal>("LocalSnapshotDisk", path, 0);
+        return std::make_shared<DiskLocal>("LocalSnapshotDisk", path);
     };
 
     /// the most specialized path
@@ -272,7 +272,7 @@ KeeperContext::Storage KeeperContext::getStatePathFromConfig(const Poco::Util::A
         if (!fs::exists(path))
             fs::create_directories(path);
 
-        return std::make_shared<DiskLocal>("LocalStateFileDisk", path, 0);
+        return std::make_shared<DiskLocal>("LocalStateFileDisk", path);
     };
 
     if (config.has("keeper_server.state_storage_disk"))

src/Coordination/KeeperSnapshotManagerS3.cpp

@@ -145,14 +145,14 @@ void KeeperSnapshotManagerS3::uploadSnapshotImpl(const SnapshotFileInfo & snapsh
 
         const auto create_writer = [&](const auto & key)
         {
-            return WriteBufferFromS3
+            return WriteBufferFromS3(
-            {
+                s3_client->client,
                 s3_client->client,
                 s3_client->uri.bucket,
                 key,
                 DBMS_DEFAULT_BUFFER_SIZE,
                 request_settings_1
-            };
+            );
         };
 
         LOG_INFO(log, "Will try to upload snapshot on {} to S3", snapshot_file_info.path);

src/Coordination/tests/gtest_coordination.cpp

@@ -71,16 +71,16 @@ protected:
     DB::KeeperContextPtr keeper_context = std::make_shared<DB::KeeperContext>(true);
     Poco::Logger * log{&Poco::Logger::get("CoordinationTest")};
 
-    void setLogDirectory(const std::string & path) { keeper_context->setLogDisk(std::make_shared<DB::DiskLocal>("LogDisk", path, 0)); }
+    void setLogDirectory(const std::string & path) { keeper_context->setLogDisk(std::make_shared<DB::DiskLocal>("LogDisk", path)); }
 
     void setSnapshotDirectory(const std::string & path)
     {
-        keeper_context->setSnapshotDisk(std::make_shared<DB::DiskLocal>("SnapshotDisk", path, 0));
+        keeper_context->setSnapshotDisk(std::make_shared<DB::DiskLocal>("SnapshotDisk", path));
     }
 
     void setStateFileDirectory(const std::string & path)
     {
-        keeper_context->setStateFileDisk(std::make_shared<DB::DiskLocal>("StateFile", path, 0));
+        keeper_context->setStateFileDisk(std::make_shared<DB::DiskLocal>("StateFile", path));
     }
 };
 
@@ -1503,9 +1503,9 @@ void testLogAndStateMachine(
     using namespace DB;
 
     ChangelogDirTest snapshots("./snapshots");
-    keeper_context->setSnapshotDisk(std::make_shared<DiskLocal>("SnapshotDisk", "./snapshots", 0));
+    keeper_context->setSnapshotDisk(std::make_shared<DiskLocal>("SnapshotDisk", "./snapshots"));
     ChangelogDirTest logs("./logs");
-    keeper_context->setLogDisk(std::make_shared<DiskLocal>("LogDisk", "./logs", 0));
+    keeper_context->setLogDisk(std::make_shared<DiskLocal>("LogDisk", "./logs"));
 
     ResponsesQueue queue(std::numeric_limits<size_t>::max());
     SnapshotsQueue snapshots_queue{1};

src/Core/Defines.h

@@ -41,7 +41,7 @@
 /// The boundary on which the blocks for asynchronous file operations should be aligned.
 #define DEFAULT_AIO_FILE_BLOCK_SIZE 4096
 
-#define DEFAULT_HTTP_READ_BUFFER_TIMEOUT 180
+#define DEFAULT_HTTP_READ_BUFFER_TIMEOUT 30
 #define DEFAULT_HTTP_READ_BUFFER_CONNECTION_TIMEOUT 1
 /// Maximum number of http-connections between two endpoints
 /// the number is unmotivated