thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-19 16:20:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into variant_inference

Browse Source
This commit is contained in:
Kruglov Pavel 2024-08-15 14:23:20 +02:00 committed by GitHub
commit f539507592
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
805 changed files with 20131 additions and 10018 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -59,6 +59,9 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] <!---ci_exclude_tsan|msan|ubsan|coverage--> Exclude: All with TSAN, MSAN, UBSAN, Coverage
- [ ] <!---ci_exclude_aarch64|release|debug--> Exclude: All with aarch64, release, debug
---
- [ ] <!---ci_include_fuzzer--> Run only fuzzers related jobs (libFuzzer fuzzers, AST fuzzers, etc.)
- [ ] <!---ci_exclude_ast--> Exclude: AST fuzzers
---
- [ ] <!---do_not_test--> Do not test
- [ ] <!---woolen_wolfdog--> Woolen Wolfdog
- [ ] <!---upload_all--> Upload binaries for special builds

3
.github/workflows/create_release.yml vendored
View File

@ -101,6 +101,7 @@ jobs:
--volume=".:/wd" --workdir="/wd" \
clickhouse/style-test \
./tests/ci/changelog.py -v --debug-helpers \
--gh-user-or-token ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }} \
--jobs=5 \
--output="./docs/changelogs/${{ env.RELEASE_TAG }}.md" ${{ env.RELEASE_TAG }}
git add ./docs/changelogs/${{ env.RELEASE_TAG }}.md
@ -129,9 +130,9 @@ jobs:
if: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
shell: bash
run: |
python3 ./tests/ci/create_release.py --set-progress-completed
git reset --hard HEAD
git checkout "$GITHUB_REF_NAME"
python3 ./tests/ci/create_release.py --set-progress-completed
- name: Create GH Release
if: ${{ inputs.type == 'patch' && ! inputs.only-repo }}
shell: bash

6
.gitmodules vendored
View File

@ -230,9 +230,6 @@
[submodule "contrib/minizip-ng"]
path = contrib/minizip-ng
url = https://github.com/zlib-ng/minizip-ng
[submodule "contrib/annoy"]
path = contrib/annoy
url = https://github.com/ClickHouse/annoy
[submodule "contrib/qpl"]
path = contrib/qpl
url = https://github.com/intel/qpl
@ -348,9 +345,6 @@
[submodule "contrib/FP16"]
path = contrib/FP16
url = https://github.com/Maratyszcza/FP16.git
[submodule "contrib/robin-map"]
path = contrib/robin-map
url = https://github.com/Tessil/robin-map.git
[submodule "contrib/aklomp-base64"]
path = contrib/aklomp-base64
url = https://github.com/aklomp/base64.git

20
CMakeLists.txt
View File

@ -187,14 +187,6 @@ else ()
set(NO_WHOLE_ARCHIVE --no-whole-archive)
endif ()
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# Can be lld or ld-lld or lld-13 or /path/to/lld.
if (LINKER_NAME MATCHES "lld")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
message (STATUS "Adding .gdb-index via --gdb-index linker option.")
endif ()
endif()
if (NOT (SANITIZE_COVERAGE OR WITH_COVERAGE)
AND (CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE"
OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO"
@ -330,17 +322,21 @@ if (DISABLE_OMIT_FRAME_POINTER)
set (CMAKE_ASM_FLAGS_ADD "${CMAKE_ASM_FLAGS_ADD} -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer")
endif()
# Before you start hating your debugger because it refuses to show variables ('<optimized out>'), try building with -DDEBUG_O_LEVEL="0"
# https://stackoverflow.com/questions/63386189/whats-the-difference-between-a-compilers-o0-option-and-og-option/63386263#63386263
set(DEBUG_O_LEVEL "g" CACHE STRING "The -Ox level used for debug builds")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${COMPILER_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${DEBUG_INFO_FLAGS} ${CMAKE_CXX_FLAGS_ADD}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${COMPILER_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${DEBUG_INFO_FLAGS} ${CMAKE_C_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_RELWITHDEBINFO "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -Og ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O${DEBUG_O_LEVEL} ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
if (OS_DARWIN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
@ -402,7 +398,7 @@ if ((NOT OS_LINUX AND NOT OS_ANDROID) OR (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
set(ENABLE_GWP_ASAN OFF)
endif ()
option (ENABLE_FIU "Enable Fiu" ON)
option (ENABLE_LIBFIU "Enable libfiu" ON)
option(WERROR "Enable -Werror compiler option" ON)

2
base/base/CMakeLists.txt
View File

@ -1,4 +1,4 @@
add_compile_options($<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>)
add_compile_options("$<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>")
if (USE_CLANG_TIDY)
set (CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_PATH}")

46
base/base/cgroupsv2.cpp
View File

@ -27,27 +27,6 @@ bool cgroupsV2Enabled()
#endif
}
bool cgroupsV2MemoryControllerEnabled()
{
#if defined(OS_LINUX)
chassert(cgroupsV2Enabled());
/// According to https://docs.kernel.org/admin-guide/cgroup-v2.html, file "cgroup.controllers" defines which controllers are available
/// for the current + child cgroups. The set of available controllers can be restricted from level to level using file
/// "cgroups.subtree_control". It is therefore sufficient to check the bottom-most nested "cgroup.controllers" file.
fs::path cgroup_dir = cgroupV2PathOfProcess();
if (cgroup_dir.empty())
return false;
std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
if (!controllers_file.is_open())
return false;
std::string controllers;
std::getline(controllers_file, controllers);
return controllers.find("memory") != std::string::npos;
#else
return false;
#endif
}
fs::path cgroupV2PathOfProcess()
{
#if defined(OS_LINUX)
@ -71,3 +50,28 @@ fs::path cgroupV2PathOfProcess()
return {};
#endif
}
std::optional<std::string> getCgroupsV2PathContainingFile([[maybe_unused]] std::string_view file_name)
{
#if defined(OS_LINUX)
if (!cgroupsV2Enabled())
return {};
fs::path current_cgroup = cgroupV2PathOfProcess();
if (current_cgroup.empty())
return {};
/// Return the bottom-most nested file. If there is no such file at the current
/// level, try again at the parent level as settings are inherited.
while (current_cgroup != default_cgroups_mount.parent_path())
{
const auto path = current_cgroup / file_name;
if (fs::exists(path))
return {current_cgroup};
current_cgroup = current_cgroup.parent_path();
}
return {};
#else
return {};
#endif
}

9
base/base/cgroupsv2.h
View File

@ -1,6 +1,7 @@
#pragma once
#include <filesystem>
#include <string_view>
#if defined(OS_LINUX)
/// I think it is possible to mount the cgroups hierarchy somewhere else (e.g. when in containers).
@ -11,11 +12,11 @@ static inline const std::filesystem::path default_cgroups_mount = "/sys/fs/cgrou
/// Is cgroups v2 enabled on the system?
bool cgroupsV2Enabled();
/// Is the memory controller of cgroups v2 enabled on the system?
/// Assumes that cgroupsV2Enabled() is enabled.
bool cgroupsV2MemoryControllerEnabled();
/// Detects which cgroup v2 the process belongs to and returns the filesystem path to the cgroup.
/// Returns an empty path the cgroup cannot be determined.
/// Assumes that cgroupsV2Enabled() is enabled.
std::filesystem::path cgroupV2PathOfProcess();
/// Returns the most nested cgroup dir containing the specified file.
/// If cgroups v2 is not enabled - returns an empty optional.
std::optional<std::string> getCgroupsV2PathContainingFile([[maybe_unused]] std::string_view file_name);

3
base/base/getMemoryAmount.cpp
View File

@ -19,9 +19,6 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
if (!cgroupsV2Enabled())
return {};
if (!cgroupsV2MemoryControllerEnabled())
return {};
std::filesystem::path current_cgroup = cgroupV2PathOfProcess();
if (current_cgroup.empty())
return {};

4
base/poco/Net/include/Poco/Net/HTTPServerSession.h
View File

@ -58,6 +58,10 @@ namespace Net
void setKeepAliveTimeout(Poco::Timespan keepAliveTimeout);
size_t getKeepAliveTimeout() const { return _keepAliveTimeout.totalSeconds(); }
size_t getMaxKeepAliveRequests() const { return _maxKeepAliveRequests; }
private:
bool _firstRequest;
Poco::Timespan _keepAliveTimeout;

21
base/poco/Net/src/HTTPServerSession.cpp
View File

@ -19,11 +19,11 @@ namespace Poco {
namespace Net {
HTTPServerSession::HTTPServerSession(const StreamSocket& socket, HTTPServerParams::Ptr pParams):
HTTPSession(socket, pParams->getKeepAlive()),
_firstRequest(true),
_keepAliveTimeout(pParams->getKeepAliveTimeout()),
_maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
HTTPServerSession::HTTPServerSession(const StreamSocket & socket, HTTPServerParams::Ptr pParams)
: HTTPSession(socket, pParams->getKeepAlive())
, _firstRequest(true)
, _keepAliveTimeout(pParams->getKeepAliveTimeout())
, _maxKeepAliveRequests(pParams->getMaxKeepAliveRequests())
{
setTimeout(pParams->getTimeout());
}
@ -52,11 +52,12 @@ bool HTTPServerSession::hasMoreRequests()
}
else if (_maxKeepAliveRequests != 0 && getKeepAlive())
{
if (_maxKeepAliveRequests > 0)
--_maxKeepAliveRequests;
return buffered() > 0 || socket().poll(_keepAliveTimeout, Socket::SELECT_READ);
}
else return false;
if (_maxKeepAliveRequests > 0)
--_maxKeepAliveRequests;
return buffered() > 0 || socket().poll(_keepAliveTimeout, Socket::SELECT_READ);
}
else
return false;
}

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: VERSION_REVISION has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54489)
SET(VERSION_REVISION 54490)
SET(VERSION_MAJOR 24)
SET(VERSION_MINOR 8)
SET(VERSION_MINOR 9)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 3f8b27d7accd2b5ec4afe7d0dd459115323304af)
SET(VERSION_DESCRIBE v24.8.1.1-testing)
SET(VERSION_STRING 24.8.1.1)
SET(VERSION_GITHASH e02b434d2fc0c4fbee29ca675deab7474d274608)
SET(VERSION_DESCRIBE v24.9.1.1-testing)
SET(VERSION_STRING 24.9.1.1)
# end of autochange

4
cmake/sanitize.cmake
View File

@ -57,8 +57,8 @@ option(WITH_COVERAGE "Instrumentation for code coverage with default implementat
if (WITH_COVERAGE)
message (STATUS "Enabled instrumentation for code coverage")
set(COVERAGE_FLAGS "SHELL:-fprofile-instr-generate -fcoverage-mapping")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
set (COVERAGE_FLAGS -fprofile-instr-generate -fcoverage-mapping)
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
endif()
option (SANITIZE_COVERAGE "Instrumentation for code coverage with custom callbacks" OFF)

8
contrib/CMakeLists.txt vendored
View File

@ -179,7 +179,7 @@ else()
message(STATUS "Not using QPL")
endif ()
if (OS_LINUX AND ARCH_AMD64)
if (OS_LINUX AND ARCH_AMD64 AND NOT NO_SSE3_OR_HIGHER)
option (ENABLE_QATLIB "Enable Intel® QuickAssist Technology Library (QATlib)" ${ENABLE_LIBRARIES})
elseif(ENABLE_QATLIB)
message (${RECONFIGURE_MESSAGE_LEVEL} "QATLib is only supported on x86_64")
@ -205,14 +205,12 @@ add_contrib (morton-nd-cmake morton-nd)
if (ARCH_S390X)
add_contrib(crc32-s390x-cmake crc32-s390x)
endif()
add_contrib (annoy-cmake annoy)
option(ENABLE_USEARCH "Enable USearch (Approximate Neighborhood Search, HNSW) support" ${ENABLE_LIBRARIES})
option(ENABLE_USEARCH "Enable USearch" ${ENABLE_LIBRARIES})
if (ENABLE_USEARCH)
add_contrib (FP16-cmake FP16)
add_contrib (robin-map-cmake robin-map)
add_contrib (SimSIMD-cmake SimSIMD)
add_contrib (usearch-cmake usearch) # requires: FP16, robin-map, SimdSIMD
add_contrib (usearch-cmake usearch) # requires: FP16, SimdSIMD
else ()
message(STATUS "Not using USearch")
endif ()

4
contrib/QAT-ZSTD-Plugin-cmake/CMakeLists.txt
View File

@ -27,7 +27,7 @@ if (ENABLE_QAT_OUT_OF_TREE_BUILD)
${QAT_AL_INCLUDE_DIR}
${QAT_USDM_INCLUDE_DIR}
${ZSTD_LIBRARY_DIR})
target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DENABLE_ZSTD_QAT_CODEC)
target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0)
add_library (ch_contrib::qatzstd_plugin ALIAS _qatzstd_plugin)
else () # In-tree build
message(STATUS "Intel QATZSTD in-tree build")
@ -78,7 +78,7 @@ else () # In-tree build
${QAT_USDM_INCLUDE_DIR}
${ZSTD_LIBRARY_DIR}
${LIBQAT_HEADER_DIR})
target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DENABLE_ZSTD_QAT_CODEC -DINTREE)
target_compile_definitions(_qatzstd_plugin PRIVATE -DDEBUGLEVEL=0 PUBLIC -DINTREE)
target_include_directories(_qatzstd_plugin SYSTEM PUBLIC $<BUILD_INTERFACE:${QATZSTD_SRC_DIR}> $<INSTALL_INTERFACE:include>)
add_library (ch_contrib::qatzstd_plugin ALIAS _qatzstd_plugin)
endif ()

2
contrib/SimSIMD vendored

@ -1 +1 @@
Subproject commit de2cb75b9e9e3389d5e1e51fd9f8ed151f3c17cf
Subproject commit 91a76d1ac519b3b9dc8957734a3dabd985f00c26

1
contrib/annoy vendored

@ -1 +0,0 @@
Subproject commit f2ac8e7b48f9a9cf676d3b58286e5455aba8e956

24
contrib/annoy-cmake/CMakeLists.txt
View File

@ -1,24 +0,0 @@
option(ENABLE_ANNOY "Enable Annoy index support" ${ENABLE_LIBRARIES})
# Annoy index should be disabled with undefined sanitizer. Because of memory storage optimizations
# (https://github.com/ClickHouse/annoy/blob/9d8a603a4cd252448589e84c9846f94368d5a289/src/annoylib.h#L442-L463)
# UBSan fails and leads to crash. Simmilar issue is already opened in Annoy repo
# https://github.com/spotify/annoy/issues/456
# Problem with aligment can lead to errors like
# (https://stackoverflow.com/questions/46790550/c-undefined-behavior-strict-aliasing-rule-or-incorrect-alignment)
# or will lead to crash on arm https://developer.arm.com/documentation/ka003038/latest
# This issues should be resolved before annoy became non-experimental (--> setting "allow_experimental_annoy_index")
if ((NOT ENABLE_ANNOY) OR (SANITIZE STREQUAL "undefined") OR (ARCH_AARCH64))
message (STATUS "Not using annoy")
return()
endif()
set(ANNOY_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/annoy")
set(ANNOY_SOURCE_DIR "${ANNOY_PROJECT_DIR}/src")
add_library(_annoy INTERFACE)
target_include_directories(_annoy SYSTEM INTERFACE ${ANNOY_SOURCE_DIR})
add_library(ch_contrib::annoy ALIAS _annoy)
target_compile_definitions(_annoy INTERFACE ENABLE_ANNOY)
target_compile_definitions(_annoy INTERFACE ANNOYLIB_MULTITHREADED_BUILD)

27
contrib/libfiu-cmake/CMakeLists.txt
View File

@ -1,20 +1,21 @@
if (NOT ENABLE_FIU)
message (STATUS "Not using fiu")
if (NOT ENABLE_LIBFIU)
message (STATUS "Not using libfiu")
return ()
endif ()
set(FIU_DIR "${ClickHouse_SOURCE_DIR}/contrib/libfiu/")
set(LIBFIU_DIR "${ClickHouse_SOURCE_DIR}/contrib/libfiu/")
set(FIU_SOURCES
${FIU_DIR}/libfiu/fiu.c
${FIU_DIR}/libfiu/fiu-rc.c
${FIU_DIR}/libfiu/backtrace.c
${FIU_DIR}/libfiu/wtable.c
set(LIBFIU_SOURCES
${LIBFIU_DIR}/libfiu/fiu.c
${LIBFIU_DIR}/libfiu/fiu-rc.c
${LIBFIU_DIR}/libfiu/backtrace.c
${LIBFIU_DIR}/libfiu/wtable.c
)
set(FIU_HEADERS "${FIU_DIR}/libfiu")
set(LIBFIU_HEADERS "${LIBFIU_DIR}/libfiu")
add_library(_fiu ${FIU_SOURCES})
target_compile_definitions(_fiu PUBLIC DUMMY_BACKTRACE)
target_include_directories(_fiu PUBLIC ${FIU_HEADERS})
add_library(ch_contrib::fiu ALIAS _fiu)
add_library(_libfiu ${LIBFIU_SOURCES})
target_compile_definitions(_libfiu PUBLIC DUMMY_BACKTRACE)
target_compile_definitions(_libfiu PUBLIC FIU_ENABLE)
target_include_directories(_libfiu PUBLIC ${LIBFIU_HEADERS})
add_library(ch_contrib::libfiu ALIAS _libfiu)

2
contrib/libprotobuf-mutator vendored

@ -1 +1 @@
Subproject commit 1f95f8083066f5b38fd2db172e7e7f9aa7c49d2d
Subproject commit b922c8ab9004ef9944982e4f165e2747b13223fa

2
contrib/libunwind vendored

@ -1 +1 @@
Subproject commit a89d904befea07814628c6ce0b44083c4e149c62
Subproject commit 601db0b0e03018c01710470a37703b618f9cf08b

4
contrib/qpl-cmake/CMakeLists.txt
View File

@ -728,10 +728,6 @@ add_library(_qpl STATIC ${LIB_DEPS})
target_include_directories(_qpl
PUBLIC $<BUILD_INTERFACE:${QPL_PROJECT_DIR}/include/> $<INSTALL_INTERFACE:include>)
target_compile_definitions(_qpl
PUBLIC -DENABLE_QPL_COMPRESSION)
target_link_libraries(_qpl
PRIVATE ch_contrib::accel-config)

1
contrib/robin-map vendored

@ -1 +0,0 @@
Subproject commit 851a59e0e3063ee0e23089062090a73fd3de482d

1
contrib/robin-map-cmake/CMakeLists.txt
View File

@ -1 +0,0 @@
# See contrib/usearch-cmake/CMakeLists.txt

2
contrib/usearch vendored

@ -1 +1 @@
Subproject commit 30810452bec5d3d3aa0931bb5d761e2f09aa6356
Subproject commit e21a5778a0d4469ddaf38c94b7be0196bb701ee4

11
contrib/usearch-cmake/CMakeLists.txt
View File

@ -1,17 +1,12 @@
set(USEARCH_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/usearch")
set(USEARCH_SOURCE_DIR "${USEARCH_PROJECT_DIR}/include")
set(FP16_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/FP16")
set(ROBIN_MAP_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/robin-map")
set(SIMSIMD_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/SimSIMD-map")
set(SIMSIMD_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/SimSIMD")
set(USEARCH_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/usearch")
add_library(_usearch INTERFACE)
target_include_directories(_usearch SYSTEM INTERFACE
${FP16_PROJECT_DIR}/include
${ROBIN_MAP_PROJECT_DIR}/include
${SIMSIMD_PROJECT_DIR}/include
${USEARCH_SOURCE_DIR})
${USEARCH_PROJECT_DIR}/include)
add_library(ch_contrib::usearch ALIAS _usearch)
target_compile_definitions(_usearch INTERFACE ENABLE_USEARCH)

3
docker/packager/binary-builder/build.sh
View File

@ -108,7 +108,8 @@ if [ -n "$MAKE_DEB" ]; then
bash -x /build/packages/build
fi
mv ./programs/clickhouse* /output || mv ./programs/*_fuzzer /output
mv ./programs/clickhouse* /output ||:
mv ./programs/*_fuzzer /output ||:
[ -x ./programs/self-extracting/clickhouse ] && mv ./programs/self-extracting/clickhouse /output
[ -x ./programs/self-extracting/clickhouse-stripped ] && mv ./programs/self-extracting/clickhouse-stripped /output
[ -x ./programs/self-extracting/clickhouse-keeper ] && mv ./programs/self-extracting/clickhouse-keeper /output

26
docker/packager/cctools/Dockerfile
View File

@ -1,3 +1,5 @@
# docker build -t clickhouse/cctools .
# This is a hack to significantly reduce the build time of the clickhouse/binary-builder
# It's based on the assumption that we don't care of the cctools version so much
# It event does not depend on the clickhouse/fasttest in the `docker/images.json`
@ -30,5 +32,29 @@ RUN git clone https://github.com/tpoechtrager/cctools-port.git \
&& cd ../.. \
&& rm -rf cctools-port
#
# GDB
#
# ld from binutils is 2.38, which has the following error:
#
# DWARF error: invalid or unhandled FORM value: 0x23
#
ENV LD=ld.lld-${LLVM_VERSION}
ARG GDB_VERSION=15.1
RUN apt-get update \
&& apt-get install --yes \
libgmp-dev \
libmpfr-dev \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
RUN wget https://sourceware.org/pub/gdb/releases/gdb-$GDB_VERSION.tar.gz \
&& tar -xvf gdb-$GDB_VERSION.tar.gz \
&& cd gdb-$GDB_VERSION \
&& ./configure --prefix=/opt/gdb \
&& make -j $(nproc) \
&& make install \
&& rm -fr gdb-$GDB_VERSION gdb-$GDB_VERSION.tar.gz
FROM scratch
COPY --from=builder /cctools /cctools
COPY --from=builder /opt/gdb /opt/gdb

2
docker/test/fasttest/Dockerfile
View File

@ -83,7 +83,7 @@ RUN arch=${TARGETARCH:-amd64} \
# Give suid to gdb to grant it attach permissions
# chmod 777 to make the container user independent
RUN chmod u+s /usr/bin/gdb \
RUN chmod u+s /opt/gdb/bin/gdb \
&& mkdir -p /var/lib/clickhouse \
&& chmod 777 /var/lib/clickhouse

4
docker/test/integration/base/Dockerfile
View File

@ -11,7 +11,6 @@ RUN apt-get update \
curl \
default-jre \
g++ \
gdb \
iproute2 \
krb5-user \
libicu-dev \
@ -73,3 +72,6 @@ maxClientCnxns=80' > /opt/zookeeper/conf/zoo.cfg && \
ENV TZ=Etc/UTC
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
COPY --from=clickhouse/cctools:0d6b90a7a490 /opt/gdb /opt/gdb
ENV PATH="/opt/gdb/bin:${PATH}"

3
docker/test/integration/runner/Dockerfile
View File

@ -30,7 +30,6 @@ RUN apt-get update \
luajit \
libssl-dev \
libcurl4-openssl-dev \
gdb \
default-jdk \
software-properties-common \
libkrb5-dev \
@ -87,6 +86,8 @@ COPY modprobe.sh /usr/local/bin/modprobe
COPY dockerd-entrypoint.sh /usr/local/bin/
COPY misc/ /misc/
COPY --from=clickhouse/cctools:0d6b90a7a490 /opt/gdb /opt/gdb
ENV PATH="/opt/gdb/bin:${PATH}"
# Same options as in test/base/Dockerfile
# (in case you need to override them in tests)

4
docker/test/performance-comparison/Dockerfile
View File

@ -9,7 +9,6 @@ RUN apt-get update \
curl \
dmidecode \
g++ \
gdb \
git \
gnuplot \
imagemagick \
@ -42,6 +41,9 @@ RUN pip3 --no-cache-dir install -r requirements.txt
COPY run.sh /
COPY --from=clickhouse/cctools:0d6b90a7a490 /opt/gdb /opt/gdb
ENV PATH="/opt/gdb/bin:${PATH}"
CMD ["bash", "/run.sh"]
# docker run --network=host --volume <workspace>:/workspace --volume=<output>:/output -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/performance-comparison

4
docker/test/stateless/Dockerfile
View File

@ -69,8 +69,8 @@ ENV MAX_RUN_TIME=0
# Unrelated to vars in setup_minio.sh, but should be the same there
# to have the same binaries for local running scenario
ARG MINIO_SERVER_VERSION=2022-01-03T18-22-58Z
ARG MINIO_CLIENT_VERSION=2022-01-05T23-52-51Z
ARG MINIO_SERVER_VERSION=2024-08-03T04-33-23Z
ARG MINIO_CLIENT_VERSION=2024-07-31T15-58-33Z
ARG TARGETARCH
# Download Minio-related binaries

59
docker/test/stateless/run.sh
View File

@ -54,8 +54,6 @@ source /utils.lib
/usr/share/clickhouse-test/config/install.sh
./setup_minio.sh stateless
./mc admin trace clickminio > /test_output/minio.log &
MC_ADMIN_PID=$!
./setup_hdfs_minicluster.sh
@ -176,6 +174,55 @@ done
setup_logs_replication
attach_gdb_to_clickhouse
# create tables for minio log webhooks
clickhouse-client --query "CREATE TABLE minio_audit_logs
(
log String,
event_time DateTime64(9) MATERIALIZED parseDateTime64BestEffortOrZero(trim(BOTH '\"' FROM JSONExtractRaw(log, 'time')), 9, 'UTC')
)
ENGINE = MergeTree
ORDER BY tuple()"
clickhouse-client --query "CREATE TABLE minio_server_logs
(
log String,
event_time DateTime64(9) MATERIALIZED parseDateTime64BestEffortOrZero(trim(BOTH '\"' FROM JSONExtractRaw(log, 'time')), 9, 'UTC')
)
ENGINE = MergeTree
ORDER BY tuple()"
# create minio log webhooks for both audit and server logs
# use async inserts to avoid creating too many parts
./mc admin config set clickminio logger_webhook:ch_server_webhook endpoint="http://localhost:8123/?async_insert=1&wait_for_async_insert=0&async_insert_busy_timeout_min_ms=5000&async_insert_busy_timeout_max_ms=5000&async_insert_max_query_number=1000&async_insert_max_data_size=10485760&query=INSERT%20INTO%20minio_server_logs%20FORMAT%20LineAsString" queue_size=1000000 batch_size=500
./mc admin config set clickminio audit_webhook:ch_audit_webhook endpoint="http://localhost:8123/?async_insert=1&wait_for_async_insert=0&async_insert_busy_timeout_min_ms=5000&async_insert_busy_timeout_max_ms=5000&async_insert_max_query_number=1000&async_insert_max_data_size=10485760&query=INSERT%20INTO%20minio_audit_logs%20FORMAT%20LineAsString" queue_size=1000000 batch_size=500
max_retries=100
retry=1
while [ $retry -le $max_retries ]; do
echo "clickminio restart attempt $retry:"
output=$(./mc admin service restart clickminio --wait --json 2>&1 | jq -r .status)
echo "Output of restart status: $output"
expected_output="success
success"
if [ "$output" = "$expected_output" ]; then
echo "Restarted clickminio successfully."
break
fi
sleep 1
retry=$((retry + 1))
done
if [ $retry -gt $max_retries ]; then
echo "Failed to restart clickminio after $max_retries attempts."
fi
./mc admin trace clickminio > /test_output/minio.log &
MC_ADMIN_PID=$!
function fn_exists() {
declare -F "$1" > /dev/null;
}
@ -339,6 +386,14 @@ do
fi
done
# collect minio audit and server logs
# wait for minio to flush its batch if it has any
sleep 1
clickhouse-client -q "SYSTEM FLUSH ASYNC INSERT QUEUE"
clickhouse-client -q "SELECT log FROM minio_audit_logs ORDER BY event_time INTO OUTFILE '/test_output/minio_audit_logs.jsonl.zst' FORMAT JSONEachRow"
clickhouse-client -q "SELECT log FROM minio_server_logs ORDER BY event_time INTO OUTFILE '/test_output/minio_server_logs.jsonl.zst' FORMAT JSONEachRow"
# Stop server so we can safely read data with clickhouse-local.
# Why do we read data with clickhouse-local?
# Because it's the simplest way to read it when server has crashed.

17
docker/test/stateless/setup_minio.sh
View File

@ -59,8 +59,8 @@ find_os() {
download_minio() {
local os
local arch
local minio_server_version=${MINIO_SERVER_VERSION:-2022-09-07T22-25-02Z}
local minio_client_version=${MINIO_CLIENT_VERSION:-2022-08-28T20-08-11Z}
local minio_server_version=${MINIO_SERVER_VERSION:-2024-08-03T04-33-23Z}
local minio_client_version=${MINIO_CLIENT_VERSION:-2024-07-31T15-58-33Z}
os=$(find_os)
arch=$(find_arch)
@ -82,10 +82,10 @@ setup_minio() {
local test_type=$1
./mc alias set clickminio http://localhost:11111 clickhouse clickhouse
./mc admin user add clickminio test testtest
./mc admin policy set clickminio readwrite user=test
./mc admin policy attach clickminio readwrite --user=test
./mc mb --ignore-existing clickminio/test
if [ "$test_type" = "stateless" ]; then
./mc policy set public clickminio/test
./mc anonymous set public clickminio/test
fi
}
@ -99,10 +99,9 @@ upload_data() {
# iterating over globs will cause redundant file variable to be
# a path to a file, not a filename
# shellcheck disable=SC2045
for file in $(ls "${data_path}"); do
echo "${file}";
./mc cp "${data_path}"/"${file}" clickminio/test/"${file}";
done
if [ -d "${data_path}" ]; then
./mc cp --recursive "${data_path}"/ clickminio/test/
fi
}
setup_aws_credentials() {
@ -148,4 +147,4 @@ main() {
setup_aws_credentials
}
main "$@"
main "$@"

4
docker/test/util/Dockerfile
View File

@ -44,7 +44,6 @@ RUN apt-get update \
bash \
bsdmainutils \
build-essential \
gdb \
git \
gperf \
moreutils \
@ -58,3 +57,6 @@ RUN apt-get update \
&& rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
COPY process_functional_tests_result.py /
COPY --from=clickhouse/cctools:0d6b90a7a490 /opt/gdb /opt/gdb
ENV PATH="/opt/gdb/bin:${PATH}"

29
docs/changelogs/v24.3.7.30-lts.md Normal file
View File

@ -0,0 +1,29 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.3.7.30-lts (c8a28cf4331) FIXME as compared to v24.3.6.48-lts (b2d33c3c45d)
#### Improvement
* Backported in [#68103](https://github.com/ClickHouse/ClickHouse/issues/68103): Distinguish booleans and integers while parsing values for custom settings: ``` SET custom_a = true; SET custom_b = 1; ```. [#62206](https://github.com/ClickHouse/ClickHouse/pull/62206) ([Vitaly Baranov](https://github.com/vitlibar)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#67931](https://github.com/ClickHouse/ClickHouse/issues/67931): Fixing the `Not-ready Set` error after the `PREWHERE` optimization for StorageMerge. [#65057](https://github.com/ClickHouse/ClickHouse/pull/65057) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Backported in [#68062](https://github.com/ClickHouse/ClickHouse/issues/68062): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
* Backported in [#67812](https://github.com/ClickHouse/ClickHouse/issues/67812): Only relevant to the experimental Variant data type. Fix crash with Variant + AggregateFunction type. [#67122](https://github.com/ClickHouse/ClickHouse/pull/67122) ([Kruglov Pavel](https://github.com/Avogar)).
* Backported in [#67848](https://github.com/ClickHouse/ClickHouse/issues/67848): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
* Backported in [#68271](https://github.com/ClickHouse/ClickHouse/issues/68271): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Backported in [#67806](https://github.com/ClickHouse/ClickHouse/issues/67806): Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
* Backported in [#67834](https://github.com/ClickHouse/ClickHouse/issues/67834): Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Backported in [#68206](https://github.com/ClickHouse/ClickHouse/issues/68206): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Backported in [#68089](https://github.com/ClickHouse/ClickHouse/issues/68089): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
* Backported in [#68120](https://github.com/ClickHouse/ClickHouse/issues/68120): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Update version after release. [#67676](https://github.com/ClickHouse/ClickHouse/pull/67676) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Backported in [#68074](https://github.com/ClickHouse/ClickHouse/issues/68074): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).

4
docs/en/development/tests.md
View File

@ -14,7 +14,7 @@ Each functional test sends one or multiple queries to the running ClickHouse ser
Tests are located in `queries` directory. There are two subdirectories: `stateless` and `stateful`. Stateless tests run queries without any preloaded test data - they often create small synthetic datasets on the fly, within the test itself. Stateful tests require preloaded test data from ClickHouse and it is available to general public.
Each test can be one of two types: `.sql` and `.sh`. `.sql` test is the simple SQL script that is piped to `clickhouse-client --multiquery`. `.sh` test is a script that is run by itself. SQL tests are generally preferable to `.sh` tests. You should use `.sh` tests only when you have to test some feature that cannot be exercised from pure SQL, such as piping some input data into `clickhouse-client` or testing `clickhouse-local`.
Each test can be one of two types: `.sql` and `.sh`. `.sql` test is the simple SQL script that is piped to `clickhouse-client`. `.sh` test is a script that is run by itself. SQL tests are generally preferable to `.sh` tests. You should use `.sh` tests only when you have to test some feature that cannot be exercised from pure SQL, such as piping some input data into `clickhouse-client` or testing `clickhouse-local`.
:::note
A common mistake when testing data types `DateTime` and `DateTime64` is assuming that the server uses a specific time zone (e.g. "UTC"). This is not the case, time zones in CI test runs
@ -38,7 +38,7 @@ For more options, see `tests/clickhouse-test --help`. You can simply run all tes
### Adding a New Test
To add new test, create a `.sql` or `.sh` file in `queries/0_stateless` directory, check it manually and then generate `.reference` file in the following way: `clickhouse-client --multiquery < 00000_test.sql > 00000_test.reference` or `./00000_test.sh > ./00000_test.reference`.
To add new test, create a `.sql` or `.sh` file in `queries/0_stateless` directory, check it manually and then generate `.reference` file in the following way: `clickhouse-client < 00000_test.sql > 00000_test.reference` or `./00000_test.sh > ./00000_test.reference`.
Tests should use (create, drop, etc) only tables in `test` database that is assumed to be created beforehand; also tests can use temporary tables.

235
docs/en/engines/table-engines/mergetree-family/annindexes.md
View File

@ -17,7 +17,7 @@ In terms of SQL, the nearest neighborhood problem can be expressed as follows:
``` sql
SELECT *
FROM table_with_ann_index
FROM table
ORDER BY Distance(vectors, Point)
LIMIT N
```
@ -27,75 +27,111 @@ Function `Distance` computes the distance between two vectors. Often, the Euclid
distance functions](/docs/en/sql-reference/functions/distance-functions.md) are also possible. `Point` is the reference point, e.g. `(0.17,
0.33, ...)`, and `N` limits the number of search results.
An alternative formulation of the nearest neighborhood search problem looks as follows:
This query returns the top-`N` closest points to the reference point. Parameter `N` limits the number of returned values which is useful for
situations where `MaxDistance` is difficult to determine in advance.
``` sql
SELECT *
FROM table_with_ann_index
WHERE Distance(vectors, Point) < MaxDistance
LIMIT N
```
While the first query returns the top-`N` closest points to the reference point, the second query returns all points closer to the reference
point than a maximally allowed radius `MaxDistance`. Parameter `N` limits the number of returned values which is useful for situations where
`MaxDistance` is difficult to determine in advance.
With brute force search, both queries are expensive (linear in the number of points) because the distance between all points in `vectors` and
With brute force search, the query is expensive (linear in the number of points) because the distance between all points in `vectors` and
`Point` must be computed. To speed this process up, Approximate Nearest Neighbor Search Indexes (ANN indexes) store a compact representation
of the search space (using clustering, search trees, etc.) which allows to compute an approximate answer much quicker (in sub-linear time).
# Creating and Using ANN Indexes {#creating_using_ann_indexes}
# Creating and Using Vector Similarity Indexes
Syntax to create an ANN index over an [Array(Float32)](../../../sql-reference/data-types/array.md) column:
Syntax to create a vector similarity index over an [Array(Float32)](../../../sql-reference/data-types/array.md) column:
```sql
CREATE TABLE table_with_ann_index
CREATE TABLE table
(
`id` Int64,
`vectors` Array(Float32),
INDEX [ann_index_name vectors TYPE [ann_index_type]([ann_index_parameters]) [GRANULARITY [N]]
id Int64,
vectors Array(Float32),
INDEX index_name vectors TYPE vector_similarity(method, distance_function[, quantization, connectivity, expansion_add, expansion_search]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
```
Parameters:
- `method`: Supports currently only `hnsw`.
- `distance_function`: either `L2Distance` (the [Euclidean distance](https://en.wikipedia.org/wiki/Euclidean_distance) - the length of a
line between two points in Euclidean space), or `cosineDistance` (the [cosine
distance](https://en.wikipedia.org/wiki/Cosine_similarity#Cosine_distance)- the angle between two non-zero vectors).
- `quantization`: either `f32`, `f16`, or `i8` for storing the vector with reduced precision (optional, default: `f32`)
- `m`: the number of neighbors per graph node (optional, default: 16)
- `ef_construction`: (optional, default: 128)
- `ef_search`: (optional, default: 64)
Value 0 for parameters `m`, `ef_construction`, and `ef_search` refers to the default value.
Example:
```sql
CREATE TABLE table
(
id Int64,
vectors Array(Float32),
INDEX idx vectors TYPE vector_similarity('hnsw', 'L2Distance') -- Alternative syntax: TYPE vector_similarity(hnsw, L2Distance)
)
ENGINE = MergeTree
ORDER BY id;
```
Vector similarity indexes are based on the [USearch library](https://github.com/unum-cloud/usearch), which implements the [HNSW
algorithm](https://arxiv.org/abs/1603.09320), i.e., a hierarchical graph where each point represents a vector and the edges represent
similarity. Such hierarchical structures can be very efficient on large collections. They may often fetch 0.05% or less data from the
overall dataset, while still providing 99% recall. This is especially useful when working with high-dimensional vectors, that are expensive
to load and compare. The library also has several hardware-specific SIMD optimizations to accelerate further distance computations on modern
Arm (NEON and SVE) and x86 (AVX2 and AVX-512) CPUs and OS-specific optimizations to allow efficient navigation around immutable persistent
files, without loading them into RAM.
USearch indexes are currently experimental, to use them you first need to `SET allow_experimental_vector_similarity_index = 1`.
Vector similarity indexes currently support two distance functions:
- `L2Distance`, also called Euclidean distance, is the length of a line segment between two points in Euclidean space
([Wikipedia](https://en.wikipedia.org/wiki/Euclidean_distance)).
- `cosineDistance`, also called cosine similarity, is the cosine of the angle between two (non-zero) vectors
([Wikipedia](https://en.wikipedia.org/wiki/Cosine_similarity)).
Vector similarity indexes allows storing the vectors in reduced precision formats. Supported scalar kinds are `f64`, `f32`, `f16` or `i8`.
If no scalar kind was specified during index creation, `f16` is used as default.
For normalized data, `L2Distance` is usually a better choice, otherwise `cosineDistance` is recommended to compensate for scale. If no
distance function was specified during index creation, `L2Distance` is used as default.
:::note
All arrays must have same length. To avoid errors, you can use a
[CONSTRAINT](/docs/en/sql-reference/statements/create/table.md#constraints), for example, `CONSTRAINT constraint_name_1 CHECK
length(vectors) = 256`. Also, empty `Arrays` and unspecified `Array` values in INSERT statements (i.e. default values) are not supported.
:::
:::note
The vector similarity index currently does not work with per-table, non-default `index_granularity` settings (see
[here](https://github.com/ClickHouse/ClickHouse/pull/51325#issuecomment-1605920475)). If necessary, the value must be changed in config.xml.
:::
ANN indexes are built during column insertion and merge. As a result, `INSERT` and `OPTIMIZE` statements will be slower than for ordinary
tables. ANNIndexes are ideally used only with immutable or rarely changed data, respectively when are far more read requests than write
requests.
ANN indexes support two types of queries:
- ORDER BY queries:
ANN indexes support these queries:
``` sql
SELECT *
FROM table_with_ann_index
FROM table
[WHERE ...]
ORDER BY Distance(vectors, Point)
LIMIT N
```
- WHERE queries:
``` sql
SELECT *
FROM table_with_ann_index
WHERE Distance(vectors, Point) < MaxDistance
LIMIT N
```
:::tip
To avoid writing out large vectors, you can use [query
parameters](/docs/en/interfaces/cli.md#queries-with-parameters-cli-queries-with-parameters), e.g.
```bash
clickhouse-client --param_vec='hello' --query="SELECT * FROM table_with_ann_index WHERE L2Distance(vectors, {vec: Array(Float32)}) < 1.0"
clickhouse-client --param_vec='hello' --query="SELECT * FROM table WHERE L2Distance(vectors, {vec: Array(Float32)}) < 1.0"
```
:::
**Restrictions**: Queries that contain both a `WHERE Distance(vectors, Point) < MaxDistance` and an `ORDER BY Distance(vectors, Point)`
clause cannot use ANN indexes. Also, the approximate algorithms used to determine the nearest neighbors require a limit, hence queries
without `LIMIT` clause cannot utilize ANN indexes. Also, ANN indexes are only used if the query has a `LIMIT` value smaller than setting
**Restrictions**: Approximate algorithms used to determine the nearest neighbors require a limit, hence queries without `LIMIT` clause
cannot utilize ANN indexes. Also, ANN indexes are only used if the query has a `LIMIT` value smaller than setting
`max_limit_for_ann_queries` (default: 1 million rows). This is a safeguard to prevent large memory allocations by external libraries for
approximate neighbor search.
@ -122,128 +158,3 @@ brute-force distance calculation over all rows of the granules. With a small `GR
equally good, only the processing performance differs. It is generally recommended to use a large `GRANULARITY` for ANN indexes and fall
back to a smaller `GRANULARITY` values only in case of problems like excessive memory consumption of the ANN structures. If no `GRANULARITY`
was specified for ANN indexes, the default value is 100 million.
# Available ANN Indexes {#available_ann_indexes}
- [Annoy](/docs/en/engines/table-engines/mergetree-family/annindexes.md#annoy-annoy)
- [USearch](/docs/en/engines/table-engines/mergetree-family/annindexes.md#usearch-usearch)
## Annoy {#annoy}
Annoy indexes are currently experimental, to use them you first need to `SET allow_experimental_annoy_index = 1`. They are also currently
disabled on ARM due to memory safety problems with the algorithm.
This type of ANN index is based on the [Annoy library](https://github.com/spotify/annoy) which recursively divides the space into random
linear surfaces (lines in 2D, planes in 3D etc.).
<div class='vimeo-container'>
<iframe src="//www.youtube.com/embed/QkCCyLW0ehU"
width="640"
height="360"
frameborder="0"
allow="autoplay;
fullscreen;
picture-in-picture"
allowfullscreen>
</iframe>
</div>
Syntax to create an Annoy index over an [Array(Float32)](../../../sql-reference/data-types/array.md) column:
```sql
CREATE TABLE table_with_annoy_index
(
id Int64,
vectors Array(Float32),
INDEX [ann_index_name] vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
```
Annoy currently supports two distance functions:
- `L2Distance`, also called Euclidean distance, is the length of a line segment between two points in Euclidean space
([Wikipedia](https://en.wikipedia.org/wiki/Euclidean_distance)).
- `cosineDistance`, also called cosine similarity, is the cosine of the angle between two (non-zero) vectors
([Wikipedia](https://en.wikipedia.org/wiki/Cosine_similarity)).
For normalized data, `L2Distance` is usually a better choice, otherwise `cosineDistance` is recommended to compensate for scale. If no
distance function was specified during index creation, `L2Distance` is used as default.
Parameter `NumTrees` is the number of trees which the algorithm creates (default if not specified: 100). Higher values of `NumTree` mean
more accurate search results but slower index creation / query times (approximately linearly) as well as larger index sizes.
:::note
All arrays must have same length. To avoid errors, you can use a
[CONSTRAINT](/docs/en/sql-reference/statements/create/table.md#constraints), for example, `CONSTRAINT constraint_name_1 CHECK
length(vectors) = 256`. Also, empty `Arrays` and unspecified `Array` values in INSERT statements (i.e. default values) are not supported.
:::
The creation of Annoy indexes (whenever a new part is build, e.g. at the end of a merge) is a relatively slow process. You can increase
setting `max_threads_for_annoy_index_creation` (default: 4) which controls how many threads are used to create an Annoy index. Please be
careful with this setting, it is possible that multiple indexes are created in parallel in which case there can be overparallelization.
Setting `annoy_index_search_k_nodes` (default: `NumTrees * LIMIT`) determines how many tree nodes are inspected during SELECTs. Larger
values mean more accurate results at the cost of longer query runtime:
```sql
SELECT *
FROM table_name
ORDER BY L2Distance(vectors, Point)
LIMIT N
SETTINGS annoy_index_search_k_nodes=100;
```
:::note
The Annoy index currently does not work with per-table, non-default `index_granularity` settings (see
[here](https://github.com/ClickHouse/ClickHouse/pull/51325#issuecomment-1605920475)). If necessary, the value must be changed in config.xml.
:::
## USearch {#usearch}
This type of ANN index is based on the [USearch library](https://github.com/unum-cloud/usearch), which implements the [HNSW
algorithm](https://arxiv.org/abs/1603.09320), i.e., builds a hierarchical graph where each point represents a vector and the edges represent
similarity. Such hierarchical structures can be very efficient on large collections. They may often fetch 0.05% or less data from the
overall dataset, while still providing 99% recall. This is especially useful when working with high-dimensional vectors,
that are expensive to load and compare. The library also has several hardware-specific SIMD optimizations to accelerate further
distance computations on modern Arm (NEON and SVE) and x86 (AVX2 and AVX-512) CPUs and OS-specific optimizations to allow efficient
navigation around immutable persistent files, without loading them into RAM.
<div class='vimeo-container'>
<iframe src="//www.youtube.com/embed/UMrhB3icP9w"
width="640"
height="360"
frameborder="0"
allow="autoplay;
fullscreen;
picture-in-picture"
allowfullscreen>
</iframe>
</div>
Syntax to create an USearch index over an [Array](../../../sql-reference/data-types/array.md) column:
```sql
CREATE TABLE table_with_usearch_index
(
id Int64,
vectors Array(Float32),
INDEX [ann_index_name] vectors TYPE usearch([Distance[, ScalarKind]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
```
USearch currently supports two distance functions:
- `L2Distance`, also called Euclidean distance, is the length of a line segment between two points in Euclidean space
([Wikipedia](https://en.wikipedia.org/wiki/Euclidean_distance)).
- `cosineDistance`, also called cosine similarity, is the cosine of the angle between two (non-zero) vectors
([Wikipedia](https://en.wikipedia.org/wiki/Cosine_similarity)).
USearch allows storing the vectors in reduced precision formats. Supported scalar kinds are `f64`, `f32`, `f16` or `i8`. If no scalar kind
was specified during index creation, `f16` is used as default.
For normalized data, `L2Distance` is usually a better choice, otherwise `cosineDistance` is recommended to compensate for scale. If no
distance function was specified during index creation, `L2Distance` is used as default.

8
docs/en/interfaces/prometheus.md
View File

@ -75,7 +75,7 @@ Data are received by this protocol and written to a [TimeSeries](/en/engines/tab
<my_rule_1>
<url>/write</url>
<handler>
<type>remote_write</type
<type>remote_write</type>
<database>db_name</database>
<table>time_series_table</table>
</handler>
@ -105,7 +105,7 @@ Data are read from a [TimeSeries](/en/engines/table-engines/special/time_series)
<my_rule_1>
<url>/read</url>
<handler>
<type>remote_read</type
<type>remote_read</type>
<database>db_name</database>
<table>time_series_table</table>
</handler>
@ -144,14 +144,14 @@ Multiple protocols can be specified together in one place:
<my_rule_2>
<url>/write</url>
<handler>
<type>remote_write</type
<type>remote_write</type>
<table>db_name.time_series_table</table>
</handler>
</my_rule_2>
<my_rule_3>
<url>/read</url>
<handler>
<type>remote_read</type
<type>remote_read</type>
<table>db_name.time_series_table</table>
</handler>
</my_rule_3>

12
docs/en/operations/query-cache.md
View File

@ -143,6 +143,18 @@ value can be specified at session, profile or query level using setting [query_c
Entries in the query cache are compressed by default. This reduces the overall memory consumption at the cost of slower writes into / reads
from the query cache. To disable compression, use setting [query_cache_compress_entries](settings/settings.md#query-cache-compress-entries).
Sometimes it is useful to keep multiple results for the same query cached. This can be achieved using setting
[query_cache_tag](settings/settings.md#query-cache-tag) that acts as as a label (or namespace) for a query cache entries. The query cache
considers results of the same query with different tags different.
Example for creating three different query cache entries for the same query:
```sql
SELECT 1 SETTINGS use_query_cache = true; -- query_cache_tag is implicitly '' (empty string)
SELECT 1 SETTINGS use_query_cache = true, query_cache_tag = 'tag 1';
SELECT 1 SETTINGS use_query_cache = true, query_cache_tag = 'tag 2';
```
ClickHouse reads table data in blocks of [max_block_size](settings/settings.md#setting-max_block_size) rows. Due to filtering, aggregation,
etc., result blocks are typically much smaller than 'max_block_size' but there are also cases where they are much bigger. Setting
[query_cache_squash_partial_results](settings/settings.md#query-cache-squash-partial-results) (enabled by default) controls if result blocks

10
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -1400,6 +1400,16 @@ The number of seconds that ClickHouse waits for incoming requests before closing
<keep_alive_timeout>10</keep_alive_timeout>
```
## max_keep_alive_requests {#max-keep-alive-requests}
Maximal number of requests through a single keep-alive connection until it will be closed by ClickHouse server. Default to 10000.
**Example**
``` xml
<max_keep_alive_requests>10</max_keep_alive_requests>
```
## listen_host {#listen_host}
Restriction on hosts that requests can come from. If you want the server to answer all of them, specify `::`.

11
docs/en/operations/settings/merge-tree-settings.md
View File

@ -1041,3 +1041,14 @@ Compression rates of LZ4 or ZSTD improve on average by 20-40%.
This setting works best for tables with no primary key or a low-cardinality primary key, i.e. a table with only few distinct primary key values.
High-cardinality primary keys, e.g. involving timestamp columns of type `DateTime64`, are not expected to benefit from this setting.
### deduplicate_merge_projection_mode
Whether to allow create projection for the table with non-classic MergeTree, that is not (Replicated, Shared) MergeTree. If allowed, what is the action when merge projections, either drop or rebuild. So classic MergeTree would ignore this setting.
It also controls `OPTIMIZE DEDUPLICATE` as well, but has effect on all MergeTree family members.
Possible values:
- throw, drop, rebuild
Default value: throw

17
docs/en/operations/settings/settings.md
View File

@ -1800,6 +1800,17 @@ Possible values:
Default value: `0`.
## query_cache_tag {#query-cache-tag}
A string which acts as a label for [query cache](../query-cache.md) entries.
The same queries with different tags are considered different by the query cache.
Possible values:
- Any string
Default value: `''`
## query_cache_max_size_in_bytes {#query-cache-max-size-in-bytes}
The maximum amount of memory (in bytes) the current user may allocate in the [query cache](../query-cache.md). 0 means unlimited.
@ -5627,6 +5638,12 @@ Disable all insert and mutations (alter table update / alter table delete / alte
Default value: `false`.
## use_hive_partitioning
When enabled, ClickHouse will detect Hive-style partitioning in path (`/name=value/`) in file-like table engines [File](../../engines/table-engines/special/file.md#hive-style-partitioning)/[S3](../../engines/table-engines/integrations/s3.md#hive-style-partitioning)/[URL](../../engines/table-engines/special/url.md#hive-style-partitioning)/[HDFS](../../engines/table-engines/integrations/hdfs.md#hive-style-partitioning)/[AzureBlobStorage](../../engines/table-engines/integrations/azureBlobStorage.md#hive-style-partitioning) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
Default value: `false`.
## allow_experimental_time_series_table {#allow-experimental-time-series-table}
Allows creation of tables with the [TimeSeries](../../engines/table-engines/integrations/time-series.md) table engine.

1
docs/en/operations/system-tables/kafka_consumers.md
View File

@ -24,6 +24,7 @@ Columns:
- `num_rebalance_revocations`, (UInt64) - number of times the consumer was revoked its partitions
- `num_rebalance_assignments`, (UInt64) - number of times the consumer was assigned to Kafka cluster
- `is_currently_used`, (UInt8) - consumer is in use
- `last_used`, (UInt64) - last time this consumer was in use, unix time in microseconds
- `rdkafka_stat` (String) - library internal statistic. See https://github.com/ClickHouse/librdkafka/blob/master/STATISTICS.md . Set `statistics_interval_ms` to 0 disable, default is 3000 (once in three seconds).
Example:

2
docs/en/operations/system-tables/query_cache.md
View File

@ -9,6 +9,7 @@ Columns:
- `query` ([String](../../sql-reference/data-types/string.md)) — Query string.
- `result_size` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Size of the query cache entry.
- `tag` ([LowCardinality(String)](../../sql-reference/data-types/lowcardinality.md)) — Tag of the query cache entry.
- `stale` ([UInt8](../../sql-reference/data-types/int-uint.md)) — If the query cache entry is stale.
- `shared` ([UInt8](../../sql-reference/data-types/int-uint.md)) — If the query cache entry is shared between multiple users.
- `compressed` ([UInt8](../../sql-reference/data-types/int-uint.md)) — If the query cache entry is compressed.
@ -26,6 +27,7 @@ Row 1:
──────
query: SELECT 1 SETTINGS use_query_cache = 1
result_size: 128
tag:
stale: 0
shared: 0
compressed: 1

123
docs/en/sql-reference/data-types/dynamic.md
View File

@ -14,7 +14,7 @@ To declare a column of `Dynamic` type, use the following syntax:
<column_name> Dynamic(max_types=N)
```
Where `N` is an optional parameter between `1` and `255` indicating how many different data types can be stored inside a column with type `Dynamic` across single block of data that is stored separately (for example across single data part for MergeTree table). If this limit is exceeded, all new types will be converted to type `String`. Default value of `max_types` is `32`.
Where `N` is an optional parameter between `0` and `254` indicating how many different data types can be stored as separate subcolumns inside a column with type `Dynamic` across single block of data that is stored separately (for example across single data part for MergeTree table). If this limit is exceeded, all values with new types will be stored together in a special shared data structure in binary form. Default value of `max_types` is `32`.
:::note
The Dynamic data type is an experimental feature. To use it, set `allow_experimental_dynamic_type = 1`.
@ -224,41 +224,43 @@ SELECT d::Dynamic(max_types=5) as d2, dynamicType(d2) FROM test;
└───────┴────────────────┘
```
If `K < N`, then the values with the rarest types are converted to `String`:
If `K < N`, then the values with the rarest types will be inserted into a single special subcolumn, but still will be accessible:
```text
CREATE TABLE test (d Dynamic(max_types=4)) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), (43), ('42.42'), (true), ([1, 2, 3]);
SELECT d, dynamicType(d), d::Dynamic(max_types=2) as d2, dynamicType(d2) FROM test;
SELECT d, dynamicType(d), d::Dynamic(max_types=2) as d2, dynamicType(d2), isDynamicElementInSharedData(d2) FROM test;
```
```text
┌─d───────┬─dynamicType(d)─┬─d2──────┬─dynamicType(d2)─┐
│ ᴺᵁᴸᴸ │ None │ ᴺᵁᴸᴸ │ None │
│ 42 │ Int64 │ 42 │ Int64 │
│ 43 │ Int64 │ 43 │ Int64 │
│ 42.42 │ String │ 42.42 │ String │
│ true │ Bool │ true │ String │
│ [1,2,3] │ Array(Int64) │ [1,2,3] │ String │
└─────────┴────────────────┴─────────┴─────────────────┘
┌─d───────┬─dynamicType(d)─┬─d2──────┬─dynamicType(d2)─┬─isDynamicElementInSharedData(d2)─┐
│ ᴺᵁᴸᴸ │ None │ ᴺᵁᴸᴸ │ None │ false │
│ 42 │ Int64 │ 42 │ Int64 │ false │
│ 43 │ Int64 │ 43 │ Int64 │ false │
│ 42.42 │ String │ 42.42 │ String │ false │
│ true │ Bool │ true │ Bool │ true │
│ [1,2,3] │ Array(Int64) │ [1,2,3] │ Array(Int64) │ true │
└─────────┴────────────────┴─────────┴─────────────────┴──────────────────────────────────┘
```
If `K=1`, all types are converted to `String`:
Functions `isDynamicElementInSharedData` returns `true` for rows that are stored in a special shared data structure inside `Dynamic` and as we can see, resulting column contains only 2 types that are not stored in shared data structure.
If `K=0`, all types will be inserted into single special subcolumn:
```text
CREATE TABLE test (d Dynamic(max_types=4)) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), (43), ('42.42'), (true), ([1, 2, 3]);
SELECT d, dynamicType(d), d::Dynamic(max_types=1) as d2, dynamicType(d2) FROM test;
SELECT d, dynamicType(d), d::Dynamic(max_types=0) as d2, dynamicType(d2), isDynamicElementInSharedData(d2) FROM test;
```
```text
┌─d───────┬─dynamicType(d)─┬─d2──────┬─dynamicType(d2)─┐
│ ᴺᵁᴸᴸ │ None │ ᴺᵁᴸᴸ │ None │
│ 42 │ Int64 │ 42 │ String │
│ 43 │ Int64 │ 43 │ String │
│ 42.42 │ String │ 42.42 │ String │
│ true │ Bool │ true │ String │
│ [1,2,3] │ Array(Int64) │ [1,2,3] │ String │
└─────────┴────────────────┴─────────┴─────────────────┘
┌─d───────┬─dynamicType(d)─┬─d2──────┬─dynamicType(d2)─┬─isDynamicElementInSharedData(d2)─┐
│ ᴺᵁᴸᴸ │ None │ ᴺᵁᴸᴸ │ None │ false │
│ 42 │ Int64 │ 42 │ Int64 │ true │
│ 43 │ Int64 │ 43 │ Int64 │ true │
│ 42.42 │ String │ 42.42 │ String │ true │
│ true │ Bool │ true │ Bool │ true │
│ [1,2,3] │ Array(Int64) │ [1,2,3] │ Array(Int64) │ true │
└─────────┴────────────────┴─────────┴─────────────────┴──────────────────────────────────┘
```
## Reading Dynamic type from the data
@ -411,17 +413,17 @@ SELECT d, dynamicType(d) FROM test ORDER by d;
## Reaching the limit in number of different data types stored inside Dynamic
`Dynamic` data type can store only limited number of different data types inside. By default, this limit is 32, but you can change it in type declaration using syntax `Dynamic(max_types=N)` where N is between 1 and 255 (due to implementation details, it's impossible to have more than 255 different data types inside Dynamic).
When the limit is reached, all new data types inserted to `Dynamic` column will be casted to `String` and stored as `String` values.
`Dynamic` data type can store only limited number of different data types as separate subcolumns. By default, this limit is 32, but you can change it in type declaration using syntax `Dynamic(max_types=N)` where N is between 0 and 254 (due to implementation details, it's impossible to have more than 254 different data types that can be stored as separate subcolumns inside Dynamic).
When the limit is reached, all new data types inserted to `Dynamic` column will be inserted into a single shared data structure that stores values with different data types in binary form.
Let's see what happens when the limit is reached in different scenarios.
### Reaching the limit during data parsing
During parsing of `Dynamic` values from the data, when the limit is reached for current block of data, all new values will be inserted as `String` values:
During parsing of `Dynamic` values from the data, when the limit is reached for current block of data, all new values will be inserted into shared data structure:
```sql
SELECT d, dynamicType(d) FROM format(JSONEachRow, 'd Dynamic(max_types=3)', '
SELECT d, dynamicType(d), isDynamicElementInSharedData(d) FROM format(JSONEachRow, 'd Dynamic(max_types=3)', '
{"d" : 42}
{"d" : [1, 2, 3]}
{"d" : "Hello, World!"}
@ -432,22 +434,22 @@ SELECT d, dynamicType(d) FROM format(JSONEachRow, 'd Dynamic(max_types=3)', '
```
```text
┌─d──────────────────────────┬─dynamicType(d)─┐
│ 42 │ Int64 │
│ [1,2,3] │ Array(Int64) │
│ Hello, World! │ String │
│ 2020-01-01 │ String │
│ ["str1", "str2", "str3"] │ String │
│ {"a" : 1, "b" : [1, 2, 3]} │ String │
└────────────────────────────┴────────────────┘
┌─d──────────────────────┬─dynamicType(d)─────────────────┬─isDynamicElementInSharedData(d)─┐
│ 42 │ Int64 │ false │
│ [1,2,3] │ Array(Int64) │ false │
│ Hello, World! │ String │ false │
│ 2020-01-01 │ Date │ true │
│ ['str1','str2','str3'] │ Array(String) │ true │
│ (1,[1,2,3]) │ Tuple(a Int64, b Array(Int64)) │ true │
└────────────────────────┴────────────────────────────────┴─────────────────────────────────┘
```
As we can see, after inserting 3 different data types `Int64`, `Array(Int64)` and `String` all new types were converted to `String`.
As we can see, after inserting 3 different data types `Int64`, `Array(Int64)` and `String` all new types were inserted into special shared data structure.
### During merges of data parts in MergeTree table engines
During merge of several data parts in MergeTree table the `Dynamic` column in the resulting data part can reach the limit of different data types inside and won't be able to store all types from source parts.
In this case ClickHouse chooses what types will remain after merge and what types will be casted to `String`. In most cases ClickHouse tries to keep the most frequent types and cast the rarest types to `String`, but it depends on the implementation.
During merge of several data parts in MergeTree table the `Dynamic` column in the resulting data part can reach the limit of different data types that can be stored in separate subcolumns inside and won't be able to store all types as subcolumns from source parts.
In this case ClickHouse chooses what types will remain as separate subcolumns after merge and what types will be inserted into shared data structure. In most cases ClickHouse tries to keep the most frequent types and store the rarest types in shared data structure, but it depends on the implementation.
Let's see an example of such merge. First, let's create a table with `Dynamic` column, set the limit of different data types to `3` and insert values with `5` different types:
@ -463,17 +465,17 @@ INSERT INTO test SELECT number, 'str_' || toString(number) FROM numbers(1);
Each insert will create a separate data pert with `Dynamic` column containing single type:
```sql
SELECT count(), dynamicType(d), _part FROM test GROUP BY _part, dynamicType(d) ORDER BY _part;
SELECT count(), dynamicType(d), isDynamicElementInSharedData(d), _part FROM test GROUP BY _part, dynamicType(d), isDynamicElementInSharedData(d) ORDER BY _part, count();
```
```text
┌─count()─┬─dynamicType(d)──────┬─_part─────┐
│ 5 │ UInt64 │ all_1_1_0 │
│ 4 │ Array(UInt64) │ all_2_2_0 │
│ 3 │ Date │ all_3_3_0 │
│ 2 │ Map(UInt64, UInt64) │ all_4_4_0 │
│ 1 │ String │ all_5_5_0 │
└─────────┴─────────────────────┴───────────┘
┌─count()─┬─dynamicType(d)──────┬─isDynamicElementInSharedData(d)─┬─_part─────┐
│ 5 │ UInt64 │ false │ all_1_1_0 │
│ 4 │ Array(UInt64) │ false │ all_2_2_0 │
│ 3 │ Date │ false │ all_3_3_0 │
│ 2 │ Map(UInt64, UInt64) │ false │ all_4_4_0 │
│ 1 │ String │ false │ all_5_5_0 │
└─────────┴─────────────────────┴─────────────────────────────────┴───────────┘
```
Now, let's merge all parts into one and see what will happen:
@ -481,18 +483,20 @@ Now, let's merge all parts into one and see what will happen:
```sql
SYSTEM START MERGES test;
OPTIMIZE TABLE test FINAL;
SELECT count(), dynamicType(d), _part FROM test GROUP BY _part, dynamicType(d) ORDER BY _part;
SELECT count(), dynamicType(d), isDynamicElementInSharedData(d), _part FROM test GROUP BY _part, dynamicType(d), isDynamicElementInSharedData(d) ORDER BY _part, count() desc;
```
```text
┌─count()─┬─dynamicType(d)─┬─_part─────┐
│ 5 │ UInt64 │ all_1_5_2 │
│ 6 │ String │ all_1_5_2 │
│ 4 │ Array(UInt64) │ all_1_5_2 │
└─────────┴────────────────┴───────────┘
┌─count()─┬─dynamicType(d)──────┬─isDynamicElementInSharedData(d)─┬─_part─────┐
│ 5 │ UInt64 │ false │ all_1_5_2 │
│ 4 │ Array(UInt64) │ false │ all_1_5_2 │
│ 3 │ Date │ false │ all_1_5_2 │
│ 2 │ Map(UInt64, UInt64) │ true │ all_1_5_2 │
│ 1 │ String │ true │ all_1_5_2 │
└─────────┴─────────────────────┴─────────────────────────────────┴───────────┘
```
As we can see, ClickHouse kept the most frequent types `UInt64` and `Array(UInt64)` and casted all other types to `String`.
As we can see, ClickHouse kept the most frequent types `UInt64` and `Array(UInt64)` as subcolumns and inserted all other types into shared data.
## JSONExtract functions with Dynamic
@ -509,22 +513,23 @@ SELECT JSONExtract('{"a" : [1, 2, 3]}', 'a', 'Dynamic') AS dynamic, dynamicType(
```
```sql
SELECT JSONExtract('{"obj" : {"a" : 42, "b" : "Hello", "c" : [1,2,3]}}', 'obj', 'Map(String, Variant(UInt32, String, Array(UInt32)))') AS map_of_dynamics, mapApply((k, v) -> (k, variantType(v)), map_of_dynamics) AS map_of_dynamic_types```
SELECT JSONExtract('{"obj" : {"a" : 42, "b" : "Hello", "c" : [1,2,3]}}', 'obj', 'Map(String, Dynamic)') AS map_of_dynamics, mapApply((k, v) -> (k, dynamicType(v)), map_of_dynamics) AS map_of_dynamic_types
```
```text
┌─map_of_dynamics──────────────────┬─map_of_dynamic_types────────────────────────────┐
│ {'a':42,'b':'Hello','c':[1,2,3]} │ {'a':'UInt32','b':'String','c':'Array(UInt32)'} │
└──────────────────────────────────┴─────────────────────────────────────────────────┘
┌─map_of_dynamics──────────────────┬─map_of_dynamic_types────────────────────────────────────┐
│ {'a':42,'b':'Hello','c':[1,2,3]} │ {'a':'Int64','b':'String','c':'Array(Nullable(Int64))'} │
└──────────────────────────────────┴─────────────────────────────────────────────────────────┘
```
```sql
SELECT JSONExtractKeysAndValues('{"a" : 42, "b" : "Hello", "c" : [1,2,3]}', 'Variant(UInt32, String, Array(UInt32))') AS dynamics, arrayMap(x -> (x.1, variantType(x.2)), dynamics) AS dynamic_types```
SELECT JSONExtractKeysAndValues('{"a" : 42, "b" : "Hello", "c" : [1,2,3]}', 'Dynamic') AS dynamics, arrayMap(x -> (x.1, dynamicType(x.2)), dynamics) AS dynamic_types```
```
```text
┌─dynamics───────────────────────────────┬─dynamic_types─────────────────────────────────────────┐
│ [('a',42),('b','Hello'),('c',[1,2,3])] │ [('a','UInt32'),('b','String'),('c','Array(UInt32)')] │
└────────────────────────────────────────┴───────────────────────────────────────────────────────┘
┌─dynamics───────────────────────────────┬─dynamic_types─────────────────────────────────────────────────┐
│ [('a',42),('b','Hello'),('c',[1,2,3])] │ [('a','Int64'),('b','String'),('c','Array(Nullable(Int64))')] │
└────────────────────────────────────────┴───────────────────────────────────────────────────────────────┘
```
### Binary output format

42
docs/en/sql-reference/data-types/geo.md
View File

@ -52,6 +52,48 @@ Result:
└───────────────────────────────┴───────────────┘
```
## LineString
`LineString` is a line stored as an array of points: [Array](array.md)([Point](#point)).
**Example**
Query:
```sql
CREATE TABLE geo_linestring (l LineString) ENGINE = Memory();
INSERT INTO geo_linestring VALUES([(0, 0), (10, 0), (10, 10), (0, 10)]);
SELECT l, toTypeName(l) FROM geo_linestring;
```
Result:
``` text
┌─r─────────────────────────────┬─toTypeName(r)─┐
│ [(0,0),(10,0),(10,10),(0,10)] │ LineString │
└───────────────────────────────┴───────────────┘
```
## MultiLineString
`MultiLineString` is multiple lines stored as an array of `LineString`: [Array](array.md)([LineString](#linestring)).
**Example**
Query:
```sql
CREATE TABLE geo_multilinestring (l MultiLineString) ENGINE = Memory();
INSERT INTO geo_multilinestring VALUES([[(0, 0), (10, 0), (10, 10), (0, 10)], [(1, 1), (2, 2), (3, 3)]]);
SELECT l, toTypeName(l) FROM geo_multilinestring;
```
Result:
``` text
┌─l───────────────────────────────────────────────────┬─toTypeName(l)───┐
│ [[(0,0),(10,0),(10,10),(0,10)],[(1,1),(2,2),(3,3)]] │ MultiLineString │
└─────────────────────────────────────────────────────┴─────────────────┘
```
## Polygon
`Polygon` is a polygon with holes stored as an array of rings: [Array](array.md)([Ring](#ring)). First element of outer array is the outer shape of polygon and all the following elements are holes.

42
docs/en/sql-reference/functions/geo/polygon.md
View File

@ -6,11 +6,13 @@ title: "Functions for Working with Polygons"
## WKT
Returns a WKT (Well Known Text) geometric object from various [Geo Data Types](../../data-types/geo.md). Supported WKT objects are:
Returns a WKT (Well Known Text) geometric object from various [Geo Data Types](../../data-types/geo.md). Supported WKT objects are:
- POINT
- POLYGON
- MULTIPOLYGON
- LINESTRING
- MULTILINESTRING
**Syntax**
@ -26,12 +28,16 @@ WKT(geo_data)
- [Ring](../../data-types/geo.md#ring)
- [Polygon](../../data-types/geo.md#polygon)
- [MultiPolygon](../../data-types/geo.md#multipolygon)
- [LineString](../../data-types/geo.md#linestring)
- [MultiLineString](../../data-types/geo.md#multilinestring)
**Returned value**
- WKT geometric object `POINT` is returned for a Point.
- WKT geometric object `POLYGON` is returned for a Polygon
- WKT geometric object `MULTIPOLYGON` is returned for a MultiPolygon.
- WKT geometric object `MULTIPOLYGON` is returned for a MultiPolygon.
- WKT geometric object `LINESTRING` is returned for a LineString.
- WKT geometric object `MULTILINESTRING` is returned for a MultiLineString.
**Examples**
@ -84,7 +90,7 @@ SELECT
### Input parameters
String starting with `MULTIPOLYGON`
String starting with `MULTIPOLYGON`
### Returned value
@ -170,6 +176,34 @@ SELECT readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)');
[(1,1),(2,2),(3,3),(1,1)]
```
## readWKTMultiLineString
Parses a Well-Known Text (WKT) representation of a MultiLineString geometry and returns it in the internal ClickHouse format.
### Syntax
```sql
readWKTMultiLineString(wkt_string)
```
### Arguments
- `wkt_string`: The input WKT string representing a MultiLineString geometry.
### Returned value
The function returns a ClickHouse internal representation of the multilinestring geometry.
### Example
```sql
SELECT readWKTMultiLineString('MULTILINESTRING ((1 1, 2 2, 3 3), (4 4, 5 5, 6 6))');
```
```response
[[(1,1),(2,2),(3,3)],[(4,4),(5,5),(6,6)]]
```
## readWKTRing
Parses a Well-Known Text (WKT) representation of a Polygon geometry and returns a ring (closed linestring) in the internal ClickHouse format.
@ -219,7 +253,7 @@ UInt8, 0 for false, 1 for true
## polygonsDistanceSpherical
Calculates the minimal distance between two points where one point belongs to the first polygon and the second to another polygon. Spherical means that coordinates are interpreted as coordinates on a pure and ideal sphere, which is not true for the Earth. Using this type of coordinate system speeds up execution, but of course is not precise.
Calculates the minimal distance between two points where one point belongs to the first polygon and the second to another polygon. Spherical means that coordinates are interpreted as coordinates on a pure and ideal sphere, which is not true for the Earth. Using this type of coordinate system speeds up execution, but of course is not precise.
### Example

91
docs/en/sql-reference/functions/other-functions.md
View File

@ -4189,3 +4189,94 @@ Result:
│ 32 │
└─────────────────────────────┘
```
## getSubcolumn
Takes a table expression or identifier and constant string with the name of the sub-column, and returns the requested sub-column extracted from the expression.
**Syntax**
```sql
getSubcolumn(col_name, subcol_name)
```
**Arguments**
- `col_name` — Table expression or identifier. [Expression](../syntax.md/#expressions), [Identifier](../syntax.md/#identifiers).
- `subcol_name` — The name of the sub-column. [String](../data-types/string.md).
**Returned value**
- Returns the extracted sub-column.
**Example**
Query:
```sql
CREATE TABLE t_arr (arr Array(Tuple(subcolumn1 UInt32, subcolumn2 String))) ENGINE = MergeTree ORDER BY tuple();
INSERT INTO t_arr VALUES ([(1, 'Hello'), (2, 'World')]), ([(3, 'This'), (4, 'is'), (5, 'subcolumn')]);
SELECT getSubcolumn(arr, 'subcolumn1'), getSubcolumn(arr, 'subcolumn2') FROM t_arr;
```
Result:
```response
┌─getSubcolumn(arr, 'subcolumn1')─┬─getSubcolumn(arr, 'subcolumn2')─┐
1. │ [1,2] │ ['Hello','World'] │
2. │ [3,4,5] │ ['This','is','subcolumn'] │
└─────────────────────────────────┴─────────────────────────────────┘
```
## getTypeSerializationStreams
Enumerates stream paths of a data type.
:::note
This function is intended for use by developers.
:::
**Syntax**
```sql
getTypeSerializationStreams(col)
```
**Arguments**
- `col` — Column or string representation of a data-type from which the data type will be detected.
**Returned value**
- Returns an array with all the serialization sub-stream paths.[Array](../data-types/array.md)([String](../data-types/string.md)).
**Examples**
Query:
```sql
SELECT getTypeSerializationStreams(tuple('a', 1, 'b', 2));
```
Result:
```response
┌─getTypeSerializationStreams(('a', 1, 'b', 2))─────────────────────────────────────────────────────────────────────────┐
1. │ ['{TupleElement(1), Regular}','{TupleElement(2), Regular}','{TupleElement(3), Regular}','{TupleElement(4), Regular}'] │
└───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
Query:
```sql
SELECT getTypeSerializationStreams('Map(String, Int64)');
```
Result:
```response
┌─getTypeSerializationStreams('Map(String, Int64)')────────────────────────────────────────────────────────────────┐
1. │ ['{ArraySizes}','{ArrayElements, TupleElement(keys), Regular}','{ArrayElements, TupleElement(values), Regular}'] │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```

1249
docs/en/sql-reference/functions/type-conversion-functions.md
View File

File diff suppressed because it is too large Load Diff

16
docs/en/sql-reference/statements/alter/statistics.md
View File

@ -8,26 +8,28 @@ sidebar_label: STATISTICS
The following operations are available:
- `ALTER TABLE [db].table ADD STATISTICS (columns list) TYPE (type list)` - Adds statistic description to tables metadata.
- `ALTER TABLE [db].table ADD STATISTICS [IF NOT EXISTS] (column list) TYPE (type list)` - Adds statistic description to tables metadata.
- `ALTER TABLE [db].table MODIFY STATISTICS (columns list) TYPE (type list)` - Modifies statistic description to tables metadata.
- `ALTER TABLE [db].table MODIFY STATISTICS (column list) TYPE (type list)` - Modifies statistic description to tables metadata.
- `ALTER TABLE [db].table DROP STATISTICS (columns list)` - Removes statistics from the metadata of the specified columns and deletes all statistics objects in all parts for the specified columns.
- `ALTER TABLE [db].table DROP STATISTICS [IF EXISTS] (column list)` - Removes statistics from the metadata of the specified columns and deletes all statistics objects in all parts for the specified columns.
- `ALTER TABLE [db].table CLEAR STATISTICS (columns list)` - Deletes all statistics objects in all parts for the specified columns. Statistics objects can be rebuild using `ALTER TABLE MATERIALIZE STATISTICS`.
- `ALTER TABLE [db].table CLEAR STATISTICS [IF EXISTS] (column list)` - Deletes all statistics objects in all parts for the specified columns. Statistics objects can be rebuild using `ALTER TABLE MATERIALIZE STATISTICS`.
- `ALTER TABLE [db.]table MATERIALIZE STATISTICS (columns list)` - Rebuilds the statistic for columns. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
- `ALTER TABLE [db.]table MATERIALIZE STATISTICS [IF EXISTS] (column list)` - Rebuilds the statistic for columns. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
The first two commands are lightweight in a sense that they only change metadata or remove files.
Also, they are replicated, syncing statistics metadata via ZooKeeper.
There is an example adding two statistics types to two columns:
## Example:
Adding two statistics types to two columns:
```
ALTER TABLE t1 MODIFY STATISTICS c, d TYPE TDigest, Uniq;
```
:::note
Statistic manipulation is supported only for tables with [`*MergeTree`](../../../engines/table-engines/mergetree-family/mergetree.md) engine (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) variants).
Statistic are supported only for [`*MergeTree`](../../../engines/table-engines/mergetree-family/mergetree.md) engine tables (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) variants).
:::

2
docs/en/sql-reference/statements/select/join.md
View File

@ -186,7 +186,7 @@ Otherwise, you'll get `INVALID_JOIN_ON_EXPRESSION`.
:::
Clickhouse currently supports `ALL INNER/LEFT/RIGHT/FULL JOIN` with inequality conditions in addition to equality conditions. The inequality conditions are supported only for `hash` and `grace_hash` join algorithms. The inequality conditions are not supported with `join_use_nulls`.
Clickhouse currently supports `ALL/ANY/SEMI/ANTI INNER/LEFT/RIGHT/FULL JOIN` with inequality conditions in addition to equality conditions. The inequality conditions are supported only for `hash` and `grace_hash` join algorithms. The inequality conditions are not supported with `join_use_nulls`.
**Example**

13
docs/en/sql-reference/table-functions/azureBlobStorage.md
View File

@ -77,3 +77,16 @@ SELECT count(*) FROM azureBlobStorage('DefaultEndpointsProtocol=https;AccountNam
**See Also**
- [AzureBlobStorage Table Engine](/docs/en/engines/table-engines/integrations/azureBlobStorage.md)
## Hive-style partitioning {#hive-style-partitioning}
When setting `use_hive_partitioning` is set to 1, ClickHouse will detect Hive-style partitioning in the path (`/name=value/`) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
**Example**
Use virtual column, created with Hive-style partitioning
``` sql
SET use_hive_partitioning = 1;
SELECT * from azureBlobStorage(config, storage_account_url='...', container='...', blob_path='http://data/path/date=*/country=*/code=*/*.parquet') where _date > '2020-01-01' and _country = 'Netherlands' and _code = 42;
```

15
docs/en/sql-reference/table-functions/file.md
View File

@ -103,7 +103,7 @@ LIMIT 2;
└─────────┴─────────┴─────────┘
```
### Inserting data from a file into a table:
### Inserting data from a file into a table
``` sql
INSERT INTO FUNCTION
@ -206,6 +206,19 @@ SELECT count(*) FROM file('big_dir/**/file002', 'CSV', 'name String, value UInt3
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the file size is unknown, the value is `NULL`.
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Hive-style partitioning {#hive-style-partitioning}
When setting `use_hive_partitioning` is set to 1, ClickHouse will detect Hive-style partitioning in the path (`/name=value/`) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
**Example**
Use virtual column, created with Hive-style partitioning
``` sql
SET use_hive_partitioning = 1;
SELECT * from file('data/path/date=*/country=*/code=*/*.parquet') where _date > '2020-01-01' and _country = 'Netherlands' and _code = 42;
```
## Settings {#settings}
- [engine_file_empty_if_not_exists](/docs/en/operations/settings/settings.md#engine-file-empty_if-not-exists) - allows to select empty data from a file that doesn't exist. Disabled by default.

13
docs/en/sql-reference/table-functions/hdfs.md
View File

@ -100,6 +100,19 @@ FROM hdfs('hdfs://hdfs1:9000/big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name Strin
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Hive-style partitioning {#hive-style-partitioning}
When setting `use_hive_partitioning` is set to 1, ClickHouse will detect Hive-style partitioning in the path (`/name=value/`) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
**Example**
Use virtual column, created with Hive-style partitioning
``` sql
SET use_hive_partitioning = 1;
SELECT * from HDFS('hdfs://hdfs1:9000/data/path/date=*/country=*/code=*/*.parquet') where _date > '2020-01-01' and _country = 'Netherlands' and _code = 42;
```
## Storage Settings {#storage-settings}
- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.

13
docs/en/sql-reference/table-functions/s3.md
View File

@ -274,6 +274,19 @@ FROM s3(
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the file size is unknown, the value is `NULL`. In case of archive shows uncompressed file size of the file inside the archive.
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Hive-style partitioning {#hive-style-partitioning}
When setting `use_hive_partitioning` is set to 1, ClickHouse will detect Hive-style partitioning in the path (`/name=value/`) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
**Example**
Use virtual column, created with Hive-style partitioning
``` sql
SET use_hive_partitioning = 1;
SELECT * from s3('s3://data/path/date=*/country=*/code=*/*.parquet') where _date > '2020-01-01' and _country = 'Netherlands' and _code = 42;
```
## Storage Settings {#storage-settings}
- [s3_truncate_on_insert](/docs/en/operations/settings/settings.md#s3_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.

13
docs/en/sql-reference/table-functions/url.md
View File

@ -55,6 +55,19 @@ Character `|` inside patterns is used to specify failover addresses. They are it
- `_size` — Size of the resource in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Hive-style partitioning {#hive-style-partitioning}
When setting `use_hive_partitioning` is set to 1, ClickHouse will detect Hive-style partitioning in the path (`/name=value/`) and will allow to use partition columns as virtual columns in the query. These virtual columns will have the same names as in the partitioned path, but starting with `_`.
**Example**
Use virtual column, created with Hive-style partitioning
``` sql
SET use_hive_partitioning = 1;
SELECT * from url('http://data/path/date=*/country=*/code=*/*.parquet') where _date > '2020-01-01' and _country = 'Netherlands' and _code = 42;
```
## Storage Settings {#storage-settings}
- [engine_url_skip_empty_files](/docs/en/operations/settings/settings.md#engine_url_skip_empty_files) - allows to skip empty files while reading. Disabled by default.

16
docs/zh/operations/external-authenticators/kerberos.md
View File

@ -23,30 +23,30 @@ slug: /zh/operations/external-authenticators/kerberos
示例 (进入 `config.xml`):
```xml
<yandex>
<clickhouse>
<!- ... -->
<kerberos />
</yandex>
</clickhouse>
```
主体规范:
```xml
<yandex>
<clickhouse>
<!- ... -->
<kerberos>
<principal>HTTP/clickhouse.example.com@EXAMPLE.COM</principal>
</kerberos>
</yandex>
</clickhouse>
```
按领域过滤:
```xml
<yandex>
<clickhouse>
<!- ... -->
<kerberos>
<realm>EXAMPLE.COM</realm>
</kerberos>
</yandex>
</clickhouse>
```
!!! warning "注意"
@ -74,7 +74,7 @@ Kerberos主体名称格式通常遵循以下模式:
示例 (进入 `users.xml`):
```
<yandex>
<clickhouse>
<!- ... -->
<users>
<!- ... -->
@ -85,7 +85,7 @@ Kerberos主体名称格式通常遵循以下模式:
</kerberos>
</my_user>
</users>
</yandex>
</clickhouse>
```
!!! warning "警告"

2
programs/CMakeLists.txt
View File

@ -1,4 +1,4 @@
add_compile_options($<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>)
add_compile_options("$<$<OR:$<COMPILE_LANGUAGE:C>,$<COMPILE_LANGUAGE:CXX>>:${COVERAGE_FLAGS}>")
if (USE_CLANG_TIDY)
set (CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_PATH}")

52
programs/benchmark/Benchmark.cpp
View File

@ -75,6 +75,8 @@ public:
const String & default_database_,
const String & user_,
const String & password_,
const String & proto_send_chunked_,
const String & proto_recv_chunked_,
const String & quota_key_,
const String & stage,
bool randomize_,
@ -128,7 +130,9 @@ public:
connections.emplace_back(std::make_unique<ConnectionPool>(
concurrency,
cur_host, cur_port,
default_database_, user_, password_, quota_key_,
default_database_, user_, password_,
proto_send_chunked_, proto_recv_chunked_,
quota_key_,
/* cluster_= */ "",
/* cluster_secret_= */ "",
/* client_name_= */ std::string(DEFAULT_CLIENT_NAME),
@ -662,6 +666,50 @@ int mainEntryClickHouseBenchmark(int argc, char ** argv)
Strings hosts = options.count("host") ? options["host"].as<Strings>() : Strings({"localhost"});
String proto_send_chunked {"notchunked"};
String proto_recv_chunked {"notchunked"};
if (options.count("proto_caps"))
{
std::string proto_caps_str = options["proto_caps"].as<std::string>();
std::vector<std::string_view> proto_caps;
splitInto<','>(proto_caps, proto_caps_str);
for (auto cap_str : proto_caps)
{
std::string direction;
if (cap_str.starts_with("send_"))
{
direction = "send";
cap_str = cap_str.substr(std::string_view("send_").size());
}
else if (cap_str.starts_with("recv_"))
{
direction = "recv";
cap_str = cap_str.substr(std::string_view("recv_").size());
}
if (cap_str != "chunked" && cap_str != "notchunked" && cap_str != "chunked_optional" && cap_str != "notchunked_optional")
throw Exception(ErrorCodes::BAD_ARGUMENTS, "proto_caps option is incorrect ({})", proto_caps_str);
if (direction.empty())
{
proto_send_chunked = cap_str;
proto_recv_chunked = cap_str;
}
else
{
if (direction == "send")
proto_send_chunked = cap_str;
else
proto_recv_chunked = cap_str;
}
}
}
Benchmark benchmark(
options["concurrency"].as<unsigned>(),
options["delay"].as<double>(),
@ -673,6 +721,8 @@ int mainEntryClickHouseBenchmark(int argc, char ** argv)
options["database"].as<std::string>(),
options["user"].as<std::string>(),
options["password"].as<std::string>(),
proto_send_chunked,
proto_recv_chunked,
options["quota_key"].as<std::string>(),
options["stage"].as<std::string>(),
options.count("randomize"),

2
programs/client/Client.cpp
View File

@ -223,7 +223,7 @@ std::vector<String> Client::loadWarningMessages()
size_t rows = packet.block.rows();
for (size_t i = 0; i < rows; ++i)
messages.emplace_back(column[i].get<String>());
messages.emplace_back(column[i].safeGet<String>());
}
continue;

15
programs/client/clickhouse-client.xml
View File

@ -38,6 +38,21 @@
<production>{display_name} \e[1;31m:)\e[0m </production> <!-- if it matched to the substring "production" in the server display name -->
</prompt_by_server_display_name>
<!-- Chunked capabilities for native protocol by client.
Can be enabled separately for send and receive channels.
Supported modes:
- chunked - client will only work with server supporting chunked protocol;
- chunked_optional - client prefer server to enable chunked protocol, but can switch to notchunked if server does not support this;
- notchunked - client will only work with server supporting notchunked protocol (current default);
- notchunked_optional - client prefer server notchunked protocol, but can switch to chunked if server does not support this.
-->
<!--
<proto_caps>
<send>chunked_optional</send>
<recv>chunked_optional</recv>
</proto_caps>
-->
<!--
Settings adjustable via command-line parameters
can take their defaults from that config file, see examples:

6
programs/keeper-client/Commands.cpp
View File

@ -95,7 +95,7 @@ void SetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
client->zookeeper->set(
client->getAbsolutePath(query->args[0].safeGet<String>()),
query->args[1].safeGet<String>(),
static_cast<Int32>(query->args[2].get<Int32>()));
static_cast<Int32>(query->args[2].safeGet<Int32>()));
}
bool CreateCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
@ -494,7 +494,7 @@ void RMCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
{
Int32 version{-1};
if (query->args.size() == 2)
version = static_cast<Int32>(query->args[1].get<Int32>());
version = static_cast<Int32>(query->args[1].safeGet<Int32>());
client->zookeeper->remove(client->getAbsolutePath(query->args[0].safeGet<String>()), version);
}
@ -549,7 +549,7 @@ void ReconfigCommand::execute(const DB::ASTKeeperQuery * query, DB::KeeperClient
String leaving;
String new_members;
auto operation = query->args[0].get<ReconfigCommand::Operation>();
auto operation = query->args[0].safeGet<ReconfigCommand::Operation>();
switch (operation)
{
case static_cast<UInt8>(ReconfigCommand::Operation::ADD):

2
programs/library-bridge/LibraryBridge.cpp
View File

@ -27,7 +27,7 @@ std::string LibraryBridge::bridgeName() const
LibraryBridge::HandlerFactoryPtr LibraryBridge::getHandlerFactoryPtr(ContextPtr context) const
{
return std::make_shared<LibraryBridgeHandlerFactory>("LibraryRequestHandlerFactory", keep_alive_timeout, context);
return std::make_shared<LibraryBridgeHandlerFactory>("LibraryRequestHandlerFactory", context);
}
}

10
programs/library-bridge/LibraryBridgeHandlerFactory.cpp
View File

@ -9,12 +9,10 @@ namespace DB
{
LibraryBridgeHandlerFactory::LibraryBridgeHandlerFactory(
const std::string & name_,
size_t keep_alive_timeout_,
ContextPtr context_)
: WithContext(context_)
, log(getLogger(name_))
, name(name_)
, keep_alive_timeout(keep_alive_timeout_)
{
}
@ -26,17 +24,17 @@ std::unique_ptr<HTTPRequestHandler> LibraryBridgeHandlerFactory::createRequestHa
if (request.getMethod() == Poco::Net::HTTPRequest::HTTP_GET)
{
if (uri.getPath() == "/extdict_ping")
return std::make_unique<ExternalDictionaryLibraryBridgeExistsHandler>(keep_alive_timeout, getContext());
return std::make_unique<ExternalDictionaryLibraryBridgeExistsHandler>(getContext());
else if (uri.getPath() == "/catboost_ping")
return std::make_unique<CatBoostLibraryBridgeExistsHandler>(keep_alive_timeout, getContext());
return std::make_unique<CatBoostLibraryBridgeExistsHandler>(getContext());
}
if (request.getMethod() == Poco::Net::HTTPRequest::HTTP_POST)
{
if (uri.getPath() == "/extdict_request")
return std::make_unique<ExternalDictionaryLibraryBridgeRequestHandler>(keep_alive_timeout, getContext());
return std::make_unique<ExternalDictionaryLibraryBridgeRequestHandler>(getContext());
else if (uri.getPath() == "/catboost_request")
return std::make_unique<CatBoostLibraryBridgeRequestHandler>(keep_alive_timeout, getContext());
return std::make_unique<CatBoostLibraryBridgeRequestHandler>(getContext());
}
return nullptr;

2
programs/library-bridge/LibraryBridgeHandlerFactory.h
View File

@ -13,7 +13,6 @@ class LibraryBridgeHandlerFactory : public HTTPRequestHandlerFactory, WithContex
public:
LibraryBridgeHandlerFactory(
const std::string & name_,
size_t keep_alive_timeout_,
ContextPtr context_);
std::unique_ptr<HTTPRequestHandler> createRequestHandler(const HTTPServerRequest & request) override;
@ -21,7 +20,6 @@ public:
private:
LoggerPtr log;
const std::string name;
const size_t keep_alive_timeout;
};
}

33
programs/library-bridge/LibraryBridgeHandlers.cpp
View File

@ -87,10 +87,8 @@ static void writeData(Block data, OutputFormatPtr format)
}
ExternalDictionaryLibraryBridgeRequestHandler::ExternalDictionaryLibraryBridgeRequestHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, keep_alive_timeout(keep_alive_timeout_)
, log(getLogger("ExternalDictionaryLibraryBridgeRequestHandler"))
ExternalDictionaryLibraryBridgeRequestHandler::ExternalDictionaryLibraryBridgeRequestHandler(ContextPtr context_)
: WithContext(context_), log(getLogger("ExternalDictionaryLibraryBridgeRequestHandler"))
{
}
@ -137,7 +135,7 @@ void ExternalDictionaryLibraryBridgeRequestHandler::handleRequest(HTTPServerRequ
const String & dictionary_id = params.get("dictionary_id");
LOG_TRACE(log, "Library method: '{}', dictionary id: {}", method, dictionary_id);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{
@ -374,10 +372,8 @@ void ExternalDictionaryLibraryBridgeRequestHandler::handleRequest(HTTPServerRequ
}
ExternalDictionaryLibraryBridgeExistsHandler::ExternalDictionaryLibraryBridgeExistsHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, keep_alive_timeout(keep_alive_timeout_)
, log(getLogger("ExternalDictionaryLibraryBridgeExistsHandler"))
ExternalDictionaryLibraryBridgeExistsHandler::ExternalDictionaryLibraryBridgeExistsHandler(ContextPtr context_)
: WithContext(context_), log(getLogger("ExternalDictionaryLibraryBridgeExistsHandler"))
{
}
@ -401,7 +397,7 @@ void ExternalDictionaryLibraryBridgeExistsHandler::handleRequest(HTTPServerReque
String res = library_handler ? "1" : "0";
setResponseDefaultHeaders(response, keep_alive_timeout);
setResponseDefaultHeaders(response);
LOG_TRACE(log, "Sending ping response: {} (dictionary id: {})", res, dictionary_id);
response.sendBuffer(res.data(), res.size());
}
@ -412,11 +408,8 @@ void ExternalDictionaryLibraryBridgeExistsHandler::handleRequest(HTTPServerReque
}
CatBoostLibraryBridgeRequestHandler::CatBoostLibraryBridgeRequestHandler(
size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, keep_alive_timeout(keep_alive_timeout_)
, log(getLogger("CatBoostLibraryBridgeRequestHandler"))
CatBoostLibraryBridgeRequestHandler::CatBoostLibraryBridgeRequestHandler(ContextPtr context_)
: WithContext(context_), log(getLogger("CatBoostLibraryBridgeRequestHandler"))
{
}
@ -455,7 +448,7 @@ void CatBoostLibraryBridgeRequestHandler::handleRequest(HTTPServerRequest & requ
const String & method = params.get("method");
LOG_TRACE(log, "Library method: '{}'", method);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{
@ -617,10 +610,8 @@ void CatBoostLibraryBridgeRequestHandler::handleRequest(HTTPServerRequest & requ
}
CatBoostLibraryBridgeExistsHandler::CatBoostLibraryBridgeExistsHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, keep_alive_timeout(keep_alive_timeout_)
, log(getLogger("CatBoostLibraryBridgeExistsHandler"))
CatBoostLibraryBridgeExistsHandler::CatBoostLibraryBridgeExistsHandler(ContextPtr context_)
: WithContext(context_), log(getLogger("CatBoostLibraryBridgeExistsHandler"))
{
}
@ -634,7 +625,7 @@ void CatBoostLibraryBridgeExistsHandler::handleRequest(HTTPServerRequest & reque
String res = "1";
setResponseDefaultHeaders(response, keep_alive_timeout);
setResponseDefaultHeaders(response);
LOG_TRACE(log, "Sending ping response: {}", res);
response.sendBuffer(res.data(), res.size());
}

12
programs/library-bridge/LibraryBridgeHandlers.h
View File

@ -18,14 +18,13 @@ namespace DB
class ExternalDictionaryLibraryBridgeRequestHandler : public HTTPRequestHandler, WithContext
{
public:
ExternalDictionaryLibraryBridgeRequestHandler(size_t keep_alive_timeout_, ContextPtr context_);
explicit ExternalDictionaryLibraryBridgeRequestHandler(ContextPtr context_);
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
static constexpr auto FORMAT = "RowBinary";
const size_t keep_alive_timeout;
LoggerPtr log;
};
@ -34,12 +33,11 @@ private:
class ExternalDictionaryLibraryBridgeExistsHandler : public HTTPRequestHandler, WithContext
{
public:
ExternalDictionaryLibraryBridgeExistsHandler(size_t keep_alive_timeout_, ContextPtr context_);
explicit ExternalDictionaryLibraryBridgeExistsHandler(ContextPtr context_);
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
const size_t keep_alive_timeout;
LoggerPtr log;
};
@ -63,12 +61,11 @@ private:
class CatBoostLibraryBridgeRequestHandler : public HTTPRequestHandler, WithContext
{
public:
CatBoostLibraryBridgeRequestHandler(size_t keep_alive_timeout_, ContextPtr context_);
explicit CatBoostLibraryBridgeRequestHandler(ContextPtr context_);
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
const size_t keep_alive_timeout;
LoggerPtr log;
};
@ -77,12 +74,11 @@ private:
class CatBoostLibraryBridgeExistsHandler : public HTTPRequestHandler, WithContext
{
public:
CatBoostLibraryBridgeExistsHandler(size_t keep_alive_timeout_, ContextPtr context_);
explicit CatBoostLibraryBridgeExistsHandler(ContextPtr context_);
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
const size_t keep_alive_timeout;
LoggerPtr log;
};

2
programs/local/LocalServer.cpp
View File

@ -143,7 +143,7 @@ void LocalServer::initialize(Poco::Util::Application & self)
if (fs::exists(config_path))
{
ConfigProcessor config_processor(config_path, false, true);
ConfigProcessor config_processor(config_path);
ConfigProcessor::setConfigPath(fs::path(config_path).parent_path());
auto loaded_config = config_processor.loadConfig();
getClientConfiguration().add(loaded_config.configuration.duplicate(), PRIO_DEFAULT, false);

1
programs/obfuscator/Obfuscator.cpp
View File

@ -1307,6 +1307,7 @@ try
throw ErrnoException(ErrorCodes::CANNOT_SEEK_THROUGH_FILE, "Input must be seekable file (it will be read twice)");
SingleReadBufferIterator read_buffer_iterator(std::move(file));
schema_columns = readSchemaFromFormat(input_format, {}, read_buffer_iterator, context_const);
}
else

5
programs/odbc-bridge/ColumnInfoHandler.cpp
View File

@ -202,10 +202,7 @@ void ODBCColumnsInfoHandler::handleRequest(HTTPServerRequest & request, HTTPServ
if (columns.empty())
throw Exception(ErrorCodes::UNKNOWN_TABLE, "Columns definition was not returned");
WriteBufferFromHTTPServerResponse out(
response,
request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD,
keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{
writeStringBinary(columns.toString(), out);

8
programs/odbc-bridge/ColumnInfoHandler.h
View File

@ -15,18 +15,12 @@ namespace DB
class ODBCColumnsInfoHandler : public HTTPRequestHandler, WithContext
{
public:
ODBCColumnsInfoHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, log(getLogger("ODBCColumnsInfoHandler"))
, keep_alive_timeout(keep_alive_timeout_)
{
}
explicit ODBCColumnsInfoHandler(ContextPtr context_) : WithContext(context_), log(getLogger("ODBCColumnsInfoHandler")) { }
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
LoggerPtr log;
size_t keep_alive_timeout;
};
}

2
programs/odbc-bridge/IdentifierQuoteHandler.cpp
View File

@ -74,7 +74,7 @@ void IdentifierQuoteHandler::handleRequest(HTTPServerRequest & request, HTTPServ
auto identifier = getIdentifierQuote(std::move(connection));
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{
writeStringBinary(identifier, out);

8
programs/odbc-bridge/IdentifierQuoteHandler.h
View File

@ -14,18 +14,12 @@ namespace DB
class IdentifierQuoteHandler : public HTTPRequestHandler, WithContext
{
public:
IdentifierQuoteHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, log(getLogger("IdentifierQuoteHandler"))
, keep_alive_timeout(keep_alive_timeout_)
{
}
explicit IdentifierQuoteHandler(ContextPtr context_) : WithContext(context_), log(getLogger("IdentifierQuoteHandler")) { }
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
LoggerPtr log;
size_t keep_alive_timeout;
};
}

2
programs/odbc-bridge/MainHandler.cpp
View File

@ -132,7 +132,7 @@ void ODBCHandler::handleRequest(HTTPServerRequest & request, HTTPServerResponse
return;
}
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{

3
programs/odbc-bridge/MainHandler.h
View File

@ -20,12 +20,10 @@ class ODBCHandler : public HTTPRequestHandler, WithContext
{
public:
ODBCHandler(
size_t keep_alive_timeout_,
ContextPtr context_,
const String & mode_)
: WithContext(context_)
, log(getLogger("ODBCHandler"))
, keep_alive_timeout(keep_alive_timeout_)
, mode(mode_)
{
}
@ -35,7 +33,6 @@ public:
private:
LoggerPtr log;
size_t keep_alive_timeout;
String mode;
static inline std::mutex mutex;

2
programs/odbc-bridge/ODBCBridge.cpp
View File

@ -27,7 +27,7 @@ std::string ODBCBridge::bridgeName() const
ODBCBridge::HandlerFactoryPtr ODBCBridge::getHandlerFactoryPtr(ContextPtr context) const
{
return std::make_shared<ODBCBridgeHandlerFactory>("ODBCRequestHandlerFactory-factory", keep_alive_timeout, context);
return std::make_shared<ODBCBridgeHandlerFactory>("ODBCRequestHandlerFactory-factory", context);
}
}

19
programs/odbc-bridge/ODBCHandlerFactory.cpp
View File

@ -9,11 +9,8 @@
namespace DB
{
ODBCBridgeHandlerFactory::ODBCBridgeHandlerFactory(const std::string & name_, size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, log(getLogger(name_))
, name(name_)
, keep_alive_timeout(keep_alive_timeout_)
ODBCBridgeHandlerFactory::ODBCBridgeHandlerFactory(const std::string & name_, ContextPtr context_)
: WithContext(context_), log(getLogger(name_)), name(name_)
{
}
@ -23,33 +20,33 @@ std::unique_ptr<HTTPRequestHandler> ODBCBridgeHandlerFactory::createRequestHandl
LOG_TRACE(log, "Request URI: {}", uri.toString());
if (uri.getPath() == "/ping" && request.getMethod() == Poco::Net::HTTPRequest::HTTP_GET)
return std::make_unique<PingHandler>(keep_alive_timeout);
return std::make_unique<PingHandler>();
if (request.getMethod() == Poco::Net::HTTPRequest::HTTP_POST)
{
if (uri.getPath() == "/columns_info")
#if USE_ODBC
return std::make_unique<ODBCColumnsInfoHandler>(keep_alive_timeout, getContext());
return std::make_unique<ODBCColumnsInfoHandler>(getContext());
#else
return nullptr;
#endif
else if (uri.getPath() == "/identifier_quote")
#if USE_ODBC
return std::make_unique<IdentifierQuoteHandler>(keep_alive_timeout, getContext());
return std::make_unique<IdentifierQuoteHandler>(getContext());
#else
return nullptr;
#endif
else if (uri.getPath() == "/schema_allowed")
#if USE_ODBC
return std::make_unique<SchemaAllowedHandler>(keep_alive_timeout, getContext());
return std::make_unique<SchemaAllowedHandler>(getContext());
#else
return nullptr;
#endif
else if (uri.getPath() == "/write")
return std::make_unique<ODBCHandler>(keep_alive_timeout, getContext(), "write");
return std::make_unique<ODBCHandler>(getContext(), "write");
else
return std::make_unique<ODBCHandler>(keep_alive_timeout, getContext(), "read");
return std::make_unique<ODBCHandler>(getContext(), "read");
}
return nullptr;
}

3
programs/odbc-bridge/ODBCHandlerFactory.h
View File

@ -17,14 +17,13 @@ namespace DB
class ODBCBridgeHandlerFactory : public HTTPRequestHandlerFactory, WithContext
{
public:
ODBCBridgeHandlerFactory(const std::string & name_, size_t keep_alive_timeout_, ContextPtr context_);
ODBCBridgeHandlerFactory(const std::string & name_, ContextPtr context_);
std::unique_ptr<HTTPRequestHandler> createRequestHandler(const HTTPServerRequest & request) override;
private:
LoggerPtr log;
std::string name;
size_t keep_alive_timeout;
};
}

2
programs/odbc-bridge/PingHandler.cpp
View File

@ -10,7 +10,7 @@ void PingHandler::handleRequest(HTTPServerRequest & /* request */, HTTPServerRes
{
try
{
setResponseDefaultHeaders(response, keep_alive_timeout);
setResponseDefaultHeaders(response);
const char * data = "Ok.\n";
response.sendBuffer(data, strlen(data));
}

4
programs/odbc-bridge/PingHandler.h
View File

@ -9,11 +9,7 @@ namespace DB
class PingHandler : public HTTPRequestHandler
{
public:
explicit PingHandler(size_t keep_alive_timeout_) : keep_alive_timeout(keep_alive_timeout_) {}
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
size_t keep_alive_timeout;
};
}

2
programs/odbc-bridge/SchemaAllowedHandler.cpp
View File

@ -88,7 +88,7 @@ void SchemaAllowedHandler::handleRequest(HTTPServerRequest & request, HTTPServer
bool result = isSchemaAllowed(std::move(connection));
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD);
try
{
writeBoolText(result, out);

8
programs/odbc-bridge/SchemaAllowedHandler.h
View File

@ -17,18 +17,12 @@ class Context;
class SchemaAllowedHandler : public HTTPRequestHandler, WithContext
{
public:
SchemaAllowedHandler(size_t keep_alive_timeout_, ContextPtr context_)
: WithContext(context_)
, log(getLogger("SchemaAllowedHandler"))
, keep_alive_timeout(keep_alive_timeout_)
{
}
explicit SchemaAllowedHandler(ContextPtr context_) : WithContext(context_), log(getLogger("SchemaAllowedHandler")) { }
void handleRequest(HTTPServerRequest & request, HTTPServerResponse & response, const ProfileEvents::Event & write_event) override;
private:
LoggerPtr log;
size_t keep_alive_timeout;
};
}

1
programs/server/Server.cpp
View File

@ -2428,6 +2428,7 @@ void Server::createServers(
Poco::Net::HTTPServerParams::Ptr http_params = new Poco::Net::HTTPServerParams;
http_params->setTimeout(settings.http_receive_timeout);
http_params->setKeepAliveTimeout(global_context->getServerSettings().keep_alive_timeout);
http_params->setMaxKeepAliveRequests(static_cast<int>(global_context->getServerSettings().max_keep_alive_requests));
Poco::Util::AbstractConfiguration::Keys protocols;
config.keys("protocols", protocols);

1
programs/server/config.d/transactions.xml Symbolic link
View File

@ -0,0 +1 @@
../../../tests/config/config.d/transactions.xml

15
programs/server/config.xml
View File

@ -150,6 +150,21 @@
-->
<tcp_port>9000</tcp_port>
<!-- Chunked capabilities for native protocol by server.
Can be enabled separately for send and receive channels.
Supported modes:
- chunked - server requires from client to have chunked enabled;
- chunked_optional - server supports both chunked and notchunked protocol;
- notchunked - server requires from client notchunked protocol (current default);
- notchunked_optional - server supports both chunked and notchunked protocol.
-->
<!--
<proto_caps>
<send>notchunked_optional</send>
<recv>notchunked_optional</recv>
</proto_caps>
-->
<!-- Compatibility with MySQL protocol.
ClickHouse will pretend to be MySQL for applications connecting to this port.
-->

9
programs/server/fuzzers/tcp_protocol_fuzzer.cpp
View File

@ -10,6 +10,7 @@
#include <Poco/Net/SocketAddress.h>
#include <Poco/Net/StreamSocket.h>
#include <Daemon/BaseDaemon.h>
#include <Interpreters/Context.h>
@ -25,6 +26,12 @@ static int64_t port = 9000;
using namespace std::chrono_literals;
void on_exit()
{
BaseDaemon::terminate();
main_app.wait();
}
extern "C"
int LLVMFuzzerInitialize(int * argc, char ***argv)
{
@ -60,6 +67,8 @@ int LLVMFuzzerInitialize(int * argc, char ***argv)
exit(-1);
}
atexit(on_exit);
return 0;
}

12
src/AggregateFunctions/AggregateFunctionGroupArray.cpp
View File

@ -780,12 +780,12 @@ AggregateFunctionPtr createAggregateFunctionGroupArray(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
if ((type == Field::Types::Int64 && parameters[0].get<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].get<UInt64>() == 0))
if ((type == Field::Types::Int64 && parameters[0].safeGet<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
has_limit = true;
max_elems = parameters[0].get<UInt64>();
max_elems = parameters[0].safeGet<UInt64>();
}
else
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
@ -816,11 +816,11 @@ AggregateFunctionPtr createAggregateFunctionGroupArraySample(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
if ((type == Field::Types::Int64 && parameters[i].get<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[i].get<UInt64>() == 0))
if ((type == Field::Types::Int64 && parameters[i].safeGet<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[i].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
return parameters[i].get<UInt64>();
return parameters[i].safeGet<UInt64>();
};
UInt64 max_elems = get_parameter(0);

6
src/AggregateFunctions/AggregateFunctionGroupArrayIntersect.cpp
View File

@ -83,16 +83,16 @@ public:
if (version == 1)
{
for (size_t i = 0; i < arr_size; ++i)
set.insert(static_cast<T>((*data_column)[offset + i].get<T>()));
set.insert(static_cast<T>((*data_column)[offset + i].safeGet<T>()));
}
else if (!set.empty())
{
typename State::Set new_set;
for (size_t i = 0; i < arr_size; ++i)
{
typename State::Set::LookupResult set_value = set.find(static_cast<T>((*data_column)[offset + i].get<T>()));
typename State::Set::LookupResult set_value = set.find(static_cast<T>((*data_column)[offset + i].safeGet<T>()));
if (set_value != nullptr)
new_set.insert(static_cast<T>((*data_column)[offset + i].get<T>()));
new_set.insert(static_cast<T>((*data_column)[offset + i].safeGet<T>()));
}
set = std::move(new_set);
}

6
src/AggregateFunctions/AggregateFunctionGroupArrayMoving.cpp
View File

@ -269,12 +269,12 @@ AggregateFunctionPtr createAggregateFunctionMoving(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive integer", name);
if ((type == Field::Types::Int64 && parameters[0].get<Int64>() <= 0) ||
(type == Field::Types::UInt64 && parameters[0].get<UInt64>() == 0))
if ((type == Field::Types::Int64 && parameters[0].safeGet<Int64>() <= 0) ||
(type == Field::Types::UInt64 && parameters[0].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive integer", name);
limit_size = true;
max_elems = parameters[0].get<UInt64>();
max_elems = parameters[0].safeGet<UInt64>();
}
else
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,

6
src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp
View File

@ -397,11 +397,11 @@ AggregateFunctionPtr createAggregateFunctionGroupArray(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
if ((type == Field::Types::Int64 && parameters[0].get<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].get<UInt64>() == 0))
if ((type == Field::Types::Int64 && parameters[0].safeGet<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
max_elems = parameters[0].get<UInt64>();
max_elems = parameters[0].safeGet<UInt64>();
}
else
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,

10
src/AggregateFunctions/AggregateFunctionGroupConcat.cpp
View File

@ -247,7 +247,7 @@ AggregateFunctionPtr createAggregateFunctionGroupConcat(
if (type != Field::Types::String)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "First parameter for aggregate function {} should be string", name);
delimiter = parameters[0].get<String>();
delimiter = parameters[0].safeGet<String>();
}
if (parameters.size() == 2)
{
@ -256,12 +256,12 @@ AggregateFunctionPtr createAggregateFunctionGroupConcat(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Second parameter for aggregate function {} should be a positive number", name);
if ((type == Field::Types::Int64 && parameters[1].get<Int64>() <= 0) ||
(type == Field::Types::UInt64 && parameters[1].get<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Second parameter for aggregate function {} should be a positive number, got: {}", name, parameters[1].get<Int64>());
if ((type == Field::Types::Int64 && parameters[1].safeGet<Int64>() <= 0) ||
(type == Field::Types::UInt64 && parameters[1].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Second parameter for aggregate function {} should be a positive number, got: {}", name, parameters[1].safeGet<Int64>());
has_limit = true;
limit = parameters[1].get<UInt64>();
limit = parameters[1].safeGet<UInt64>();
}
if (has_limit)

6
src/AggregateFunctions/AggregateFunctionGroupUniqArray.cpp
View File

@ -323,12 +323,12 @@ AggregateFunctionPtr createAggregateFunctionGroupUniqArray(
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
if ((type == Field::Types::Int64 && parameters[0].get<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].get<UInt64>() == 0))
if ((type == Field::Types::Int64 && parameters[0].safeGet<Int64>() < 0) ||
(type == Field::Types::UInt64 && parameters[0].safeGet<UInt64>() == 0))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter for aggregate function {} should be positive number", name);
limit_size = true;
max_elems = parameters[0].get<UInt64>();
max_elems = parameters[0].safeGet<UInt64>();
}
else
throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,

4
src/AggregateFunctions/AggregateFunctionKolmogorovSmirnovTest.cpp
View File

@ -238,7 +238,7 @@ public:
if (params[0].getType() != Field::Types::String)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} require first parameter to be a String", getName());
const auto & param = params[0].get<String>();
const auto & param = params[0].safeGet<String>();
if (param == "two-sided")
alternative = Alternative::TwoSided;
else if (param == "less")
@ -255,7 +255,7 @@ public:
if (params[1].getType() != Field::Types::String)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} require second parameter to be a String", getName());
method = params[1].get<String>();
method = params[1].safeGet<String>();
if (method != "auto" && method != "exact" && method != "asymp" && method != "asymptotic")
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unknown method in aggregate function {}. "
"It must be one of: 'auto', 'exact', 'asymp' (or 'asymptotic')", getName());

2
src/AggregateFunctions/AggregateFunctionLargestTriangleThreeBuckets.cpp
View File

@ -181,7 +181,7 @@ public:
throw Exception(
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} require first parameter to be a UInt64", getName());
total_buckets = params[0].get<UInt64>();
total_buckets = params[0].safeGet<UInt64>();
this->x_type = WhichDataType(arguments[0]).idx;
this->y_type = WhichDataType(arguments[1]).idx;

4
src/AggregateFunctions/AggregateFunctionMannWhitney.cpp
View File

@ -152,7 +152,7 @@ public:
if (params[0].getType() != Field::Types::String)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} require first parameter to be a String", getName());
const auto & param = params[0].get<String>();
const auto & param = params[0].safeGet<String>();
if (param == "two-sided")
alternative = Alternative::TwoSided;
else if (param == "less")
@ -169,7 +169,7 @@ public:
if (params[1].getType() != Field::Types::UInt64)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} require second parameter to be a UInt64", getName());
continuity_correction = static_cast<bool>(params[1].get<UInt64>());
continuity_correction = static_cast<bool>(params[1].safeGet<UInt64>());
}
String getName() const override

6
src/AggregateFunctions/AggregateFunctionQuantile.h
View File

@ -117,7 +117,7 @@ public:
throw Exception(
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} requires relative accuracy parameter with Float64 type", getName());
relative_accuracy = relative_accuracy_field.get<Float64>();
relative_accuracy = relative_accuracy_field.safeGet<Float64>();
if (relative_accuracy <= 0 || relative_accuracy >= 1 || isNaN(relative_accuracy))
throw Exception(
@ -147,9 +147,9 @@ public:
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Aggregate function {} requires accuracy parameter with integer type", getName());
if (accuracy_field.getType() == Field::Types::Int64)
accuracy = accuracy_field.get<Int64>();
accuracy = accuracy_field.safeGet<Int64>();
else
accuracy = accuracy_field.get<UInt64>();
accuracy = accuracy_field.safeGet<UInt64>();
if (accuracy <= 0)
throw Exception(

10
src/AggregateFunctions/AggregateFunctionSumMap.cpp
View File

@ -300,12 +300,12 @@ public:
/// Compatibility with previous versions.
if (value.getType() == Field::Types::Decimal32)
{
auto source = value.get<DecimalField<Decimal32>>();
auto source = value.safeGet<DecimalField<Decimal32>>();
value = DecimalField<Decimal128>(source.getValue(), source.getScale());
}
else if (value.getType() == Field::Types::Decimal64)
{
auto source = value.get<DecimalField<Decimal64>>();
auto source = value.safeGet<DecimalField<Decimal64>>();
value = DecimalField<Decimal128>(source.getValue(), source.getScale());
}
@ -355,7 +355,7 @@ public:
/// Compatibility with previous versions.
if (value.getType() == Field::Types::Decimal128)
{
auto source = value.get<DecimalField<Decimal128>>();
auto source = value.safeGet<DecimalField<Decimal128>>();
WhichDataType value_type(values_types[col_idx]);
if (value_type.isDecimal32())
{
@ -560,7 +560,7 @@ private:
template <typename FieldType>
bool compareImpl(FieldType & x) const
{
auto val = rhs.get<FieldType>();
auto val = rhs.safeGet<FieldType>();
if (val > x)
{
x = val;
@ -600,7 +600,7 @@ private:
template <typename FieldType>
bool compareImpl(FieldType & x) const
{
auto val = rhs.get<FieldType>();
auto val = rhs.safeGet<FieldType>();
if (val < x)
{
x = val;

2
src/AggregateFunctions/fuzzers/CMakeLists.txt
View File

@ -1,2 +1,2 @@
clickhouse_add_executable(aggregate_function_state_deserialization_fuzzer aggregate_function_state_deserialization_fuzzer.cpp ${SRCS})
target_link_libraries(aggregate_function_state_deserialization_fuzzer PRIVATE dbms clickhouse_aggregate_functions clickhouse_functions)
target_link_libraries(aggregate_function_state_deserialization_fuzzer PRIVATE clickhouse_functions clickhouse_aggregate_functions)

2
src/Analyzer/Passes/ComparisonTupleEliminationPass.cpp
View File

@ -137,7 +137,7 @@ private:
if (constant_node_value.getType() != Field::Types::Which::Tuple)
return {};
const auto & constant_tuple = constant_node_value.get<const Tuple &>();
const auto & constant_tuple = constant_node_value.safeGet<const Tuple &>();
const auto & function_arguments_nodes = function_node_typed.getArguments().getNodes();
size_t function_arguments_nodes_size = function_arguments_nodes.size();

Some files were not shown because too many files have changed in this diff Show More