thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 15:12:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into ip-dict-no-trie

Browse Source
This commit is contained in:
Nikolai Kochetov 2020-11-25 23:07:19 +03:00 committed by GitHub
commit 729272391f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
587 changed files with 12531 additions and 2750 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.github/ISSUE_TEMPLATE/documentation-issue.md vendored
View File

@ -2,8 +2,7 @@
name: Documentation issue
about: Report something incorrect or missing in documentation
title: ''
labels: documentation
assignees: BayoNet
labels: comp-documentation
---

6
.gitmodules vendored
View File

@ -44,6 +44,7 @@
[submodule "contrib/protobuf"]
path = contrib/protobuf
url = https://github.com/ClickHouse-Extras/protobuf.git
branch = v3.13.0.1
[submodule "contrib/boost"]
path = contrib/boost
url = https://github.com/ClickHouse-Extras/boost.git
@ -107,6 +108,7 @@
[submodule "contrib/grpc"]
path = contrib/grpc
url = https://github.com/ClickHouse-Extras/grpc.git
branch = v1.33.2
[submodule "contrib/aws"]
path = contrib/aws
url = https://github.com/ClickHouse-Extras/aws-sdk-cpp.git
@ -200,3 +202,7 @@
[submodule "contrib/xz"]
path = contrib/xz
url = https://github.com/xz-mirror/xz
[submodule "contrib/abseil-cpp"]
path = contrib/abseil-cpp
url = https://github.com/ClickHouse-Extras/abseil-cpp.git
branch = lts_2020_02_25

1
base/common/StringRef.h
View File

@ -1,6 +1,7 @@
#pragma once
#include <cassert>
#include <stdexcept> // for std::logic_error
#include <string>
#include <vector>
#include <functional>

1
base/common/logger_useful.h
View File

@ -3,7 +3,6 @@
/// Macros for convenient usage of Poco logger.
#include <fmt/format.h>
#include <fmt/ostream.h>
#include <Poco/Logger.h>
#include <Poco/Message.h>
#include <Common/CurrentThread.h>

19
base/glibc-compatibility/musl/accept4.c Normal file
View File

@ -0,0 +1,19 @@
#define _GNU_SOURCE
#include <sys/socket.h>
#include <errno.h>
#include <fcntl.h>
#include "syscall.h"
int accept4(int fd, struct sockaddr *restrict addr, socklen_t *restrict len, int flg)
{
if (!flg) return accept(fd, addr, len);
int ret = socketcall_cp(accept4, fd, addr, len, flg, 0, 0);
if (ret>=0 || (errno != ENOSYS && errno != EINVAL)) return ret;
ret = accept(fd, addr, len);
if (ret<0) return ret;
if (flg & SOCK_CLOEXEC)
__syscall(SYS_fcntl, ret, F_SETFD, FD_CLOEXEC);
if (flg & SOCK_NONBLOCK)
__syscall(SYS_fcntl, ret, F_SETFL, O_NONBLOCK);
return ret;
}

37
base/glibc-compatibility/musl/epoll.c Normal file
View File

@ -0,0 +1,37 @@
#include <sys/epoll.h>
#include <signal.h>
#include <errno.h>
#include "syscall.h"
int epoll_create(int size)
{
return epoll_create1(0);
}
int epoll_create1(int flags)
{
int r = __syscall(SYS_epoll_create1, flags);
#ifdef SYS_epoll_create
if (r==-ENOSYS && !flags) r = __syscall(SYS_epoll_create, 1);
#endif
return __syscall_ret(r);
}
int epoll_ctl(int fd, int op, int fd2, struct epoll_event *ev)
{
return syscall(SYS_epoll_ctl, fd, op, fd2, ev);
}
int epoll_pwait(int fd, struct epoll_event *ev, int cnt, int to, const sigset_t *sigs)
{
int r = __syscall(SYS_epoll_pwait, fd, ev, cnt, to, sigs, _NSIG/8);
#ifdef SYS_epoll_wait
if (r==-ENOSYS && !sigs) r = __syscall(SYS_epoll_wait, fd, ev, cnt, to);
#endif
return __syscall_ret(r);
}
int epoll_wait(int fd, struct epoll_event *ev, int cnt, int to)
{
return epoll_pwait(fd, ev, cnt, to, 0);
}

23
base/glibc-compatibility/musl/eventfd.c Normal file
View File

@ -0,0 +1,23 @@
#include <sys/eventfd.h>
#include <unistd.h>
#include <errno.h>
#include "syscall.h"
int eventfd(unsigned int count, int flags)
{
int r = __syscall(SYS_eventfd2, count, flags);
#ifdef SYS_eventfd
if (r==-ENOSYS && !flags) r = __syscall(SYS_eventfd, count);
#endif
return __syscall_ret(r);
}
int eventfd_read(int fd, eventfd_t *value)
{
return (sizeof(*value) == read(fd, value, sizeof(*value))) ? 0 : -1;
}
int eventfd_write(int fd, eventfd_t value)
{
return (sizeof(value) == write(fd, &value, sizeof(value))) ? 0 : -1;
}

45
base/glibc-compatibility/musl/getauxval.c Normal file
View File

@ -0,0 +1,45 @@
#include <sys/auxv.h>
#include <unistd.h> // __environ
#include <errno.h>
// We don't have libc struct available here. Compute aux vector manually.
static unsigned long * __auxv = NULL;
static unsigned long __auxv_secure = 0;
static size_t __find_auxv(unsigned long type)
{
size_t i;
for (i = 0; __auxv[i]; i += 2)
{
if (__auxv[i] == type)
return i + 1;
}
return (size_t) -1;
}
__attribute__((constructor)) static void __auxv_init()
{
size_t i;
for (i = 0; __environ[i]; i++);
__auxv = (unsigned long *) (__environ + i + 1);
size_t secure_idx = __find_auxv(AT_SECURE);
if (secure_idx != ((size_t) -1))
__auxv_secure = __auxv[secure_idx];
}
unsigned long getauxval(unsigned long type)
{
if (type == AT_SECURE)
return __auxv_secure;
if (__auxv)
{
size_t index = __find_auxv(type);
if (index != ((size_t) -1))
return __auxv[index];
}
errno = ENOENT;
return 0;
}

8
base/glibc-compatibility/musl/secure_getenv.c Normal file
View File

@ -0,0 +1,8 @@
#define _GNU_SOURCE
#include <stdlib.h>
#include <sys/auxv.h>
char * secure_getenv(const char * name)
{
return getauxval(AT_SECURE) ? NULL : getenv(name);
}

8
base/glibc-compatibility/musl/syscall.h
View File

@ -13,3 +13,11 @@ long __syscall(syscall_arg_t, ...);
__attribute__((visibility("hidden")))
void *__vdsosym(const char *, const char *);
#define syscall(...) __syscall_ret(__syscall(__VA_ARGS__))
#define socketcall(...) __syscall_ret(__socketcall(__VA_ARGS__))
#define __socketcall(nm,a,b,c,d,e,f) __syscall(SYS_##nm, a, b, c, d, e, f)
#define socketcall_cp socketcall

16
base/glibc-compatibility/musl/vdso.c
View File

@ -40,24 +40,10 @@ static int checkver(Verdef *def, int vsym, const char *vername, char *strings)
#define OK_TYPES (1<<STT_NOTYPE | 1<<STT_OBJECT | 1<<STT_FUNC | 1<<STT_COMMON)
#define OK_BINDS (1<<STB_GLOBAL | 1<<STB_WEAK | 1<<STB_GNU_UNIQUE)
extern char** environ;
static Ehdr *eh = NULL;
void *__vdsosym(const char *vername, const char *name);
// We don't have libc struct available here. Compute aux vector manually.
__attribute__((constructor)) static void auxv_init()
{
size_t i, *auxv;
for (i=0; environ[i]; i++);
auxv = (void *)(environ+i+1);
for (i=0; auxv[i] != AT_SYSINFO_EHDR; i+=2)
if (!auxv[i]) return;
if (!auxv[i+1]) return;
eh = (void *)auxv[i+1];
}
void *__vdsosym(const char *vername, const char *name)
{
size_t i;
Ehdr * eh = (void *) getauxval(AT_SYSINFO_EHDR);
if (!eh) return 0;
Phdr *ph = (void *)((char *)eh + eh->e_phoff);
size_t *dynv=0, base=-1;

27
cmake/Modules/FindgRPC.cmake
View File

@ -6,11 +6,9 @@ Defines the following variables:
The include directories of the gRPC framework, including the include directories of the C++ wrapper.
``gRPC_LIBRARIES``
The libraries of the gRPC framework.
``gRPC_UNSECURE_LIBRARIES``
The libraries of the gRPC framework without SSL.
``_gRPC_CPP_PLUGIN``
``gRPC_CPP_PLUGIN``
The plugin for generating gRPC client and server C++ stubs from `.proto` files
``_gRPC_PYTHON_PLUGIN``
``gRPC_PYTHON_PLUGIN``
The plugin for generating gRPC client and server Python stubs from `.proto` files
The following :prop_tgt:`IMPORTED` targets are also defined:
@ -19,6 +17,13 @@ The following :prop_tgt:`IMPORTED` targets are also defined:
``grpc_cpp_plugin``
``grpc_python_plugin``
Set the following variables to adjust the behaviour of this script:
``gRPC_USE_UNSECURE_LIBRARIES``
if set gRPC_LIBRARIES will be filled with the unsecure version of the libraries (i.e. without SSL)
instead of the secure ones.
``gRPC_DEBUG`
if set the debug message will be printed.
Add custom commands to process ``.proto`` files to C++::
protobuf_generate_grpc_cpp(<SRCS> <HDRS>
[DESCRIPTORS <DESC>] [EXPORT_MACRO <MACRO>] [<ARGN>...])
@ -242,6 +247,7 @@ find_library(gRPC_LIBRARY NAMES grpc)
find_library(gRPC_CPP_LIBRARY NAMES grpc++)
find_library(gRPC_UNSECURE_LIBRARY NAMES grpc_unsecure)
find_library(gRPC_CPP_UNSECURE_LIBRARY NAMES grpc++_unsecure)
find_library(gRPC_CARES_LIBRARY NAMES cares)
set(gRPC_LIBRARIES)
if(gRPC_USE_UNSECURE_LIBRARIES)
@ -259,6 +265,7 @@ else()
set(gRPC_LIBRARIES ${gRPC_LIBRARIES} ${gRPC_CPP_LIBRARY})
endif()
endif()
set(gRPC_LIBRARIES ${gRPC_LIBRARIES} ${gRPC_CARES_LIBRARY})
# Restore the original find library ordering.
if(gRPC_USE_STATIC_LIBS)
@ -278,11 +285,11 @@ else()
endif()
# Get full path to plugin.
find_program(_gRPC_CPP_PLUGIN
find_program(gRPC_CPP_PLUGIN
NAMES grpc_cpp_plugin
DOC "The plugin for generating gRPC client and server C++ stubs from `.proto` files")
find_program(_gRPC_PYTHON_PLUGIN
find_program(gRPC_PYTHON_PLUGIN
NAMES grpc_python_plugin
DOC "The plugin for generating gRPC client and server Python stubs from `.proto` files")
@ -317,14 +324,14 @@ endif()
#include(FindPackageHandleStandardArgs.cmake)
FIND_PACKAGE_HANDLE_STANDARD_ARGS(gRPC
REQUIRED_VARS gRPC_LIBRARY gRPC_CPP_LIBRARY gRPC_UNSECURE_LIBRARY gRPC_CPP_UNSECURE_LIBRARY
gRPC_INCLUDE_DIR gRPC_CPP_INCLUDE_DIR _gRPC_CPP_PLUGIN _gRPC_PYTHON_PLUGIN)
REQUIRED_VARS gRPC_LIBRARY gRPC_CPP_LIBRARY gRPC_UNSECURE_LIBRARY gRPC_CPP_UNSECURE_LIBRARY gRPC_CARES_LIBRARY
gRPC_INCLUDE_DIR gRPC_CPP_INCLUDE_DIR gRPC_CPP_PLUGIN gRPC_PYTHON_PLUGIN)
if(gRPC_FOUND)
if(gRPC_DEBUG)
message(STATUS "gRPC: INCLUDE_DIRS=${gRPC_INCLUDE_DIRS}")
message(STATUS "gRPC: LIBRARIES=${gRPC_LIBRARIES}")
message(STATUS "gRPC: CPP_PLUGIN=${_gRPC_CPP_PLUGIN}")
message(STATUS "gRPC: PYTHON_PLUGIN=${_gRPC_PYTHON_PLUGIN}")
message(STATUS "gRPC: CPP_PLUGIN=${gRPC_CPP_PLUGIN}")
message(STATUS "gRPC: PYTHON_PLUGIN=${gRPC_PYTHON_PLUGIN}")
endif()
endif()

10
cmake/autogenerated_versions.txt
View File

@ -1,9 +1,9 @@
# This strings autochanged from release_lib.sh:
SET(VERSION_REVISION 54443)
SET(VERSION_REVISION 54444)
SET(VERSION_MAJOR 20)
SET(VERSION_MINOR 12)
SET(VERSION_MINOR 13)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH c53725fb1f846fda074347607ab582fbb9c6f7a1)
SET(VERSION_DESCRIBE v20.12.1.1-prestable)
SET(VERSION_STRING 20.12.1.1)
SET(VERSION_GITHASH e581f9ccfc5c64867b0f488cce72412fd2966471)
SET(VERSION_DESCRIBE v20.13.1.1-prestable)
SET(VERSION_STRING 20.13.1.1)
# end of autochange

10
cmake/find/grpc.cmake
View File

@ -37,8 +37,8 @@ if(NOT USE_INTERNAL_GRPC_LIBRARY)
if(NOT gRPC_INCLUDE_DIRS OR NOT gRPC_LIBRARIES)
message(${RECONFIGURE_MESSAGE_LEVEL} "Can't find system gRPC library")
set(EXTERNAL_GRPC_LIBRARY_FOUND 0)
elseif(NOT _gRPC_CPP_PLUGIN)
message(${RECONFIGURE_MESSAGE_LEVEL} "Can't find system grcp_cpp_plugin")
elseif(NOT gRPC_CPP_PLUGIN)
message(${RECONFIGURE_MESSAGE_LEVEL} "Can't find system grpc_cpp_plugin")
set(EXTERNAL_GRPC_LIBRARY_FOUND 0)
else()
set(EXTERNAL_GRPC_LIBRARY_FOUND 1)
@ -53,8 +53,8 @@ if(NOT EXTERNAL_GRPC_LIBRARY_FOUND AND NOT MISSING_INTERNAL_GRPC_LIBRARY)
else()
set(gRPC_LIBRARIES grpc grpc++)
endif()
set(_gRPC_CPP_PLUGIN $<TARGET_FILE:grpc_cpp_plugin>)
set(_gRPC_PROTOC_EXECUTABLE $<TARGET_FILE:protobuf::protoc>)
set(gRPC_CPP_PLUGIN $<TARGET_FILE:grpc_cpp_plugin>)
set(gRPC_PYTHON_PLUGIN $<TARGET_FILE:grpc_python_plugin>)
include("${ClickHouse_SOURCE_DIR}/contrib/grpc-cmake/protobuf_generate_grpc.cmake")
@ -62,4 +62,4 @@ if(NOT EXTERNAL_GRPC_LIBRARY_FOUND AND NOT MISSING_INTERNAL_GRPC_LIBRARY)
set(USE_GRPC 1)
endif()
message(STATUS "Using gRPC=${USE_GRPC}: ${gRPC_INCLUDE_DIRS} : ${gRPC_LIBRARIES} : ${_gRPC_CPP_PLUGIN}")
message(STATUS "Using gRPC=${USE_GRPC}: ${gRPC_INCLUDE_DIRS} : ${gRPC_LIBRARIES} : ${gRPC_CPP_PLUGIN}")

1
contrib/abseil-cpp vendored Submodule

@ -0,0 +1 @@
Subproject commit 4f3b686f86c3ebaba7e4e926e62a79cb1c659a54

2
contrib/cctz vendored

@ -1 +1 @@
Subproject commit 7a2db4ece6e0f1b246173cbdb62711ae258ee841
Subproject commit 260ba195ef6c489968bae8c88c62a67cdac5ff9d

2
contrib/grpc vendored

@ -1 +1 @@
Subproject commit a6570b863cf76c9699580ba51c7827d5bffaac43
Subproject commit 7436366ceb341ba5c00ea29f1645e02a2b70bf93

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

@ -1,6 +1,7 @@
set(_gRPC_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/grpc")
set(_gRPC_BINARY_DIR "${ClickHouse_BINARY_DIR}/contrib/grpc")
# Use re2 from ClickHouse contrib, not from gRPC third_party.
if(NOT RE2_INCLUDE_DIR)
message(FATAL_ERROR " grpc: The location of the \"re2\" library is unknown")
endif()
@ -8,6 +9,7 @@ set(gRPC_RE2_PROVIDER "clickhouse" CACHE STRING "" FORCE)
set(_gRPC_RE2_INCLUDE_DIR "${RE2_INCLUDE_DIR}")
set(_gRPC_RE2_LIBRARIES "${RE2_LIBRARY}")
# Use zlib from ClickHouse contrib, not from gRPC third_party.
if(NOT ZLIB_INCLUDE_DIRS)
message(FATAL_ERROR " grpc: The location of the \"zlib\" library is unknown")
endif()
@ -15,6 +17,7 @@ set(gRPC_ZLIB_PROVIDER "clickhouse" CACHE STRING "" FORCE)
set(_gRPC_ZLIB_INCLUDE_DIR "${ZLIB_INCLUDE_DIRS}")
set(_gRPC_ZLIB_LIBRARIES "${ZLIB_LIBRARIES}")
# Use protobuf from ClickHouse contrib, not from gRPC third_party.
if(NOT Protobuf_INCLUDE_DIR OR NOT Protobuf_LIBRARY)
message(FATAL_ERROR " grpc: The location of the \"protobuf\" library is unknown")
elseif (NOT Protobuf_PROTOC_EXECUTABLE)
@ -29,21 +32,33 @@ set(_gRPC_PROTOBUF_PROTOC "protoc")
set(_gRPC_PROTOBUF_PROTOC_EXECUTABLE "${Protobuf_PROTOC_EXECUTABLE}")
set(_gRPC_PROTOBUF_PROTOC_LIBRARIES "${Protobuf_PROTOC_LIBRARY}")
# Use OpenSSL from ClickHouse contrib, not from gRPC third_party.
set(gRPC_SSL_PROVIDER "clickhouse" CACHE STRING "" FORCE)
set(_gRPC_SSL_INCLUDE_DIR ${OPENSSL_INCLUDE_DIR})
set(_gRPC_SSL_LIBRARIES ${OPENSSL_LIBRARIES})
# Use abseil-cpp from ClickHouse contrib, not from gRPC third_party.
set(gRPC_ABSL_PROVIDER "clickhouse" CACHE STRING "" FORCE)
set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
if(NOT EXISTS "${ABSL_ROOT_DIR}/CMakeLists.txt")
message(FATAL_ERROR " grpc: submodule third_party/abseil-cpp is missing. To fix try run: \n git submodule update --init --recursive")
endif()
add_subdirectory("${ABSL_ROOT_DIR}" "${ClickHouse_BINARY_DIR}/contrib/abseil-cpp")
# Choose to build static or shared library for c-ares.
if (MAKE_STATIC_LIBRARIES)
set(CARES_STATIC ON CACHE BOOL "" FORCE)
set(CARES_SHARED OFF CACHE BOOL "" FORCE)
else ()
set(CARES_STATIC OFF CACHE BOOL "" FORCE)
set(CARES_SHARED ON CACHE BOOL "" FORCE)
endif ()
# We don't want to build C# extensions.
set(gRPC_BUILD_CSHARP_EXT OFF)
# We don't want to build abseil tests, so we temporarily switch BUILD_TESTING off.
set(_gRPC_ORIG_BUILD_TESTING ${BUILD_TESTING})
set(BUILD_TESTING OFF)
add_subdirectory("${_gRPC_SOURCE_DIR}" "${_gRPC_BINARY_DIR}")
set(BUILD_TESTING ${_gRPC_ORIG_BUILD_TESTING})
# The contrib/grpc/CMakeLists.txt redefined the PROTOBUF_GENERATE_GRPC_CPP() function for its own purposes,
# so we need to redefine it back.
include("${ClickHouse_SOURCE_DIR}/contrib/grpc-cmake/protobuf_generate_grpc.cmake")

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

@ -22,7 +22,16 @@ set_source_files_properties(${LIBUNWIND_C_SOURCES} PROPERTIES COMPILE_FLAGS "-st
set(LIBUNWIND_ASM_SOURCES
${LIBUNWIND_SOURCE_DIR}/src/UnwindRegistersRestore.S
${LIBUNWIND_SOURCE_DIR}/src/UnwindRegistersSave.S)
set_source_files_properties(${LIBUNWIND_ASM_SOURCES} PROPERTIES LANGUAGE C)
# CMake doesn't pass the correct architecture for Apple prior to CMake 3.19 [1]
# Workaround these two issues by compiling as C.
#
# [1]: https://gitlab.kitware.com/cmake/cmake/-/issues/20771
if (APPLE AND CMAKE_VERSION VERSION_LESS 3.19)
set_source_files_properties(${LIBUNWIND_ASM_SOURCES} PROPERTIES LANGUAGE C)
else()
enable_language(ASM)
endif()
set(LIBUNWIND_SOURCES
${LIBUNWIND_CXX_SOURCES}

2
contrib/protobuf vendored

@ -1 +1 @@
Subproject commit 445d1ae73a450b1e94622e7040989aa2048402e3
Subproject commit 73b12814204ad9068ba352914d0dc244648b48ee

4
debian/changelog vendored
View File

@ -1,5 +1,5 @@
clickhouse (20.12.1.1) unstable; urgency=low
clickhouse (20.13.1.1) unstable; urgency=low
* Modified source code
-- clickhouse-release <clickhouse-release@yandex-team.ru> Thu, 05 Nov 2020 21:52:47 +0300
-- clickhouse-release <clickhouse-release@yandex-team.ru> Mon, 23 Nov 2020 10:29:24 +0300

2
docker/client/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.12.1.*
ARG version=20.13.1.*
RUN apt-get update \
&& apt-get install --yes --no-install-recommends \

1
docker/packager/unbundled/Dockerfile
View File

@ -56,6 +56,7 @@ RUN apt-get update \
libprotoc-dev \
libgrpc++-dev \
protobuf-compiler-grpc \
libc-ares-dev \
rapidjson-dev \
libsnappy-dev \
libparquet-dev \

2
docker/server/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:20.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.12.1.*
ARG version=20.13.1.*
ARG gosu_ver=1.10
RUN apt-get update \

2
docker/test/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=20.12.1.*
ARG version=20.13.1.*
RUN apt-get update && \
apt-get install -y apt-transport-https dirmngr && \

8
docker/test/coverage/Dockerfile
View File

@ -7,8 +7,10 @@ ENV SOURCE_DIR=/build
ENV OUTPUT_DIR=/output
ENV IGNORE='.*contrib.*'
CMD mkdir -p /build/obj-x86_64-linux-gnu && cd /build/obj-x86_64-linux-gnu && CC=clang-10 CXX=clang++-10 cmake .. && cd /; \
RUN apt-get update && apt-get install cmake --yes --no-install-recommends
CMD mkdir -p /build/obj-x86_64-linux-gnu && cd /build/obj-x86_64-linux-gnu && CC=clang-11 CXX=clang++-11 cmake .. && cd /; \
dpkg -i /package_folder/clickhouse-common-static_*.deb; \
llvm-profdata-10 merge -sparse ${COVERAGE_DIR}/* -o clickhouse.profdata && \
llvm-cov-10 export /usr/bin/clickhouse -instr-profile=clickhouse.profdata -j=16 -format=lcov -skip-functions -ignore-filename-regex $IGNORE > output.lcov && \
llvm-profdata-11 merge -sparse ${COVERAGE_DIR}/* -o clickhouse.profdata && \
llvm-cov-11 export /usr/bin/clickhouse -instr-profile=clickhouse.profdata -j=16 -format=lcov -skip-functions -ignore-filename-regex $IGNORE > output.lcov && \
genhtml output.lcov --ignore-errors source --output-directory ${OUTPUT_DIR}

5
docker/test/fasttest/run.sh
View File

@ -15,6 +15,9 @@ stage=${stage:-}
# empty parameter.
read -ra FASTTEST_CMAKE_FLAGS <<< "${FASTTEST_CMAKE_FLAGS:-}"
# Run only matching tests.
FASTTEST_FOCUS=${FASTTEST_FOCUS:-""}
FASTTEST_WORKSPACE=$(readlink -f "${FASTTEST_WORKSPACE:-.}")
FASTTEST_SOURCE=$(readlink -f "${FASTTEST_SOURCE:-$FASTTEST_WORKSPACE/ch}")
FASTTEST_BUILD=$(readlink -f "${FASTTEST_BUILD:-${BUILD:-$FASTTEST_WORKSPACE/build}}")
@ -291,7 +294,7 @@ TESTS_TO_SKIP=(
01563_distributed_query_finish
)
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
# substr is to remove semicolon after test name
readarray -t FAILED_TESTS < <(awk '/FAIL|TIMEOUT|ERROR/ { print substr($3, 1, length($3)-1) }' "$FASTTEST_OUTPUT/test_log.txt" | tee "$FASTTEST_OUTPUT/failed-parallel-tests.txt")

2
docker/test/performance-comparison/Dockerfile
View File

@ -30,7 +30,7 @@ RUN apt-get update \
tzdata \
vim \
wget \
&& pip3 --no-cache-dir install clickhouse_driver scipy \
&& pip3 --no-cache-dir install 'clickhouse-driver>=0.1.5' scipy \
&& apt-get purge --yes python3-dev g++ \
&& apt-get autoremove --yes \
&& apt-get clean \

104
docker/test/performance-comparison/perf.py
View File

@ -14,10 +14,12 @@ import string
import sys
import time
import traceback
import logging
import xml.etree.ElementTree as et
from threading import Thread
from scipy import stats
logging.basicConfig(format='%(asctime)s: %(levelname)s: %(module)s: %(message)s', level='WARNING')
total_start_seconds = time.perf_counter()
stage_start_seconds = total_start_seconds
@ -46,6 +48,8 @@ parser.add_argument('--profile-seconds', type=int, default=0, help='For how many
parser.add_argument('--long', action='store_true', help='Do not skip the tests tagged as long.')
parser.add_argument('--print-queries', action='store_true', help='Print test queries and exit.')
parser.add_argument('--print-settings', action='store_true', help='Print test settings and exit.')
parser.add_argument('--keep-created-tables', action='store_true', help="Don't drop the created tables after the test.")
parser.add_argument('--use-existing-tables', action='store_true', help="Don't create or drop the tables, use the existing ones instead.")
args = parser.parse_args()
reportStageEnd('start')
@ -146,20 +150,21 @@ for i, s in enumerate(servers):
reportStageEnd('connect')
# Run drop queries, ignoring errors. Do this before all other activity, because
# clickhouse_driver disconnects on error (this is not configurable), and the new
# connection loses the changes in settings.
drop_query_templates = [q.text for q in root.findall('drop_query')]
drop_queries = substitute_parameters(drop_query_templates)
for conn_index, c in enumerate(all_connections):
for q in drop_queries:
try:
c.execute(q)
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
except:
pass
if not args.use_existing_tables:
# Run drop queries, ignoring errors. Do this before all other activity,
# because clickhouse_driver disconnects on error (this is not configurable),
# and the new connection loses the changes in settings.
drop_query_templates = [q.text for q in root.findall('drop_query')]
drop_queries = substitute_parameters(drop_query_templates)
for conn_index, c in enumerate(all_connections):
for q in drop_queries:
try:
c.execute(q)
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
except:
pass
reportStageEnd('drop-1')
reportStageEnd('drop-1')
# Apply settings.
# If there are errors, report them and continue -- maybe a new test uses a setting
@ -171,12 +176,9 @@ reportStageEnd('drop-1')
settings = root.findall('settings/*')
for conn_index, c in enumerate(all_connections):
for s in settings:
try:
q = f"set {s.tag} = '{s.text}'"
c.execute(q)
print(f'set\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
except:
print(traceback.format_exc(), file=sys.stderr)
# requires clickhouse-driver >= 1.1.5 to accept arbitrary new settings
# (https://github.com/mymarilyn/clickhouse-driver/pull/142)
c.settings[s.tag] = s.text
reportStageEnd('settings')
@ -194,37 +196,40 @@ for t in tables:
reportStageEnd('preconditions')
# Run create and fill queries. We will run them simultaneously for both servers,
# to save time.
# The weird search is to keep the relative order of elements, which matters, and
# etree doesn't support the appropriate xpath query.
create_query_templates = [q.text for q in root.findall('./*') if q.tag in ('create_query', 'fill_query')]
create_queries = substitute_parameters(create_query_templates)
if not args.use_existing_tables:
# Run create and fill queries. We will run them simultaneously for both
# servers, to save time. The weird XML search + filter is because we want to
# keep the relative order of elements, and etree doesn't support the
# appropriate xpath query.
create_query_templates = [q.text for q in root.findall('./*')
if q.tag in ('create_query', 'fill_query')]
create_queries = substitute_parameters(create_query_templates)
# Disallow temporary tables, because the clickhouse_driver reconnects on errors,
# and temporary tables are destroyed. We want to be able to continue after some
# errors.
for q in create_queries:
if re.search('create temporary table', q, flags=re.IGNORECASE):
print(f"Temporary tables are not allowed in performance tests: '{q}'",
file = sys.stderr)
sys.exit(1)
# Disallow temporary tables, because the clickhouse_driver reconnects on
# errors, and temporary tables are destroyed. We want to be able to continue
# after some errors.
for q in create_queries:
if re.search('create temporary table', q, flags=re.IGNORECASE):
print(f"Temporary tables are not allowed in performance tests: '{q}'",
file = sys.stderr)
sys.exit(1)
def do_create(connection, index, queries):
for q in queries:
connection.execute(q)
print(f'create\t{index}\t{connection.last_query.elapsed}\t{tsv_escape(q)}')
def do_create(connection, index, queries):
for q in queries:
connection.execute(q)
print(f'create\t{index}\t{connection.last_query.elapsed}\t{tsv_escape(q)}')
threads = [Thread(target = do_create, args = (connection, index, create_queries))
for index, connection in enumerate(all_connections)]
threads = [
Thread(target = do_create, args = (connection, index, create_queries))
for index, connection in enumerate(all_connections)]
for t in threads:
t.start()
for t in threads:
t.start()
for t in threads:
t.join()
for t in threads:
t.join()
reportStageEnd('create')
reportStageEnd('create')
# By default, test all queries.
queries_to_run = range(0, len(test_queries))
@ -403,10 +408,11 @@ print(f'profile-total\t{profile_total_seconds}')
reportStageEnd('run')
# Run drop queries
drop_queries = substitute_parameters(drop_query_templates)
for conn_index, c in enumerate(all_connections):
for q in drop_queries:
c.execute(q)
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
if not args.keep_created_tables and not args.use_existing_tables:
drop_queries = substitute_parameters(drop_query_templates)
for conn_index, c in enumerate(all_connections):
for q in drop_queries:
c.execute(q)
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
reportStageEnd('drop-2')

8
docker/test/pvs/Dockerfile
View File

@ -10,6 +10,11 @@ RUN apt-get update --yes \
gpg-agent \
debsig-verify \
strace \
protobuf-compiler \
protobuf-compiler-grpc \
libprotoc-dev \
libgrpc++-dev \
libc-ares-dev \
--yes --no-install-recommends
#RUN wget -nv -O - http://files.viva64.com/etc/pubkey.txt | sudo apt-key add -
@ -33,7 +38,8 @@ RUN set -x \
&& dpkg -i "${PKG_VERSION}.deb"
CMD echo "Running PVS version $PKG_VERSION" && cd /repo_folder && pvs-studio-analyzer credentials $LICENCE_NAME $LICENCE_KEY -o ./licence.lic \
&& cmake . -D"ENABLE_EMBEDDED_COMPILER"=OFF && ninja re2_st \
&& cmake . -D"ENABLE_EMBEDDED_COMPILER"=OFF -D"USE_INTERNAL_PROTOBUF_LIBRARY"=OFF -D"USE_INTERNAL_GRPC_LIBRARY"=OFF \
&& ninja re2_st clickhouse_grpc_protos \
&& pvs-studio-analyzer analyze -o pvs-studio.log -e contrib -j 4 -l ./licence.lic; \
plog-converter -a GA:1,2 -t fullhtml -o /test_output/pvs-studio-html-report pvs-studio.log; \
plog-converter -a GA:1,2 -t tasklist -o /test_output/pvs-studio-task-report.txt pvs-studio.log

4
docker/test/stateful_with_coverage/Dockerfile
View File

@ -1,12 +1,12 @@
# docker build -t yandex/clickhouse-stateful-test-with-coverage .
FROM yandex/clickhouse-stateless-test
FROM yandex/clickhouse-stateless-test-with-coverage
RUN echo "deb [trusted=yes] http://apt.llvm.org/bionic/ llvm-toolchain-bionic-9 main" >> /etc/apt/sources.list
RUN apt-get update -y \
&& env DEBIAN_FRONTEND=noninteractive \
apt-get install --yes --no-install-recommends \
python3-requests
python3-requests procps psmisc
COPY s3downloader /s3downloader
COPY run.sh /run.sh

99
docker/test/stateful_with_coverage/run.sh
View File

@ -1,40 +1,44 @@
#!/bin/bash
kill_clickhouse () {
kill "$(pgrep -u clickhouse)" 2>/dev/null
echo "clickhouse pids $(pgrep -u clickhouse)" | ts '%Y-%m-%d %H:%M:%S'
pkill -f "clickhouse-server" 2>/dev/null
for _ in {1..10}
for _ in {1..120}
do
if ! kill -0 "$(pgrep -u clickhouse)"; then
echo "No clickhouse process"
break
else
echo "Process $(pgrep -u clickhouse) still alive"
sleep 10
fi
if ! pkill -0 -f "clickhouse-server" ; then break ; fi
echo "ClickHouse still alive" | ts '%Y-%m-%d %H:%M:%S'
sleep 1
done
if pkill -0 -f "clickhouse-server"
then
pstree -apgT
jobs
echo "Failed to kill the ClickHouse server" | ts '%Y-%m-%d %H:%M:%S'
return 1
fi
}
start_clickhouse () {
LLVM_PROFILE_FILE='server_%h_%p_%m.profraw' sudo -Eu clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml &
}
wait_llvm_profdata () {
while kill -0 "$(pgrep llvm-profdata-10)"
counter=0
until clickhouse-client --query "SELECT 1"
do
echo "Waiting for profdata $(pgrep llvm-profdata-10) still alive"
sleep 3
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
sleep 0.5
counter=$((counter + 1))
done
}
merge_client_files_in_background () {
client_files=$(ls /client_*profraw 2>/dev/null)
if [ -n "$client_files" ]
then
llvm-profdata-10 merge -sparse "$client_files" -o "merged_client_$(date +%s).profraw"
rm "$client_files"
fi
}
chmod 777 /
@ -51,26 +55,7 @@ chmod 777 -R /var/log/clickhouse-server/
# install test configs
/usr/share/clickhouse-test/config/install.sh
function start()
{
counter=0
until clickhouse-client --query "SELECT 1"
do
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
timeout 120 service clickhouse-server start
sleep 0.5
counter=$((counter + 1))
done
}
start
start_clickhouse
# shellcheck disable=SC2086 # No quotes because I want to split it into words.
if ! /s3downloader --dataset-names $DATASETS; then
@ -81,25 +66,20 @@ fi
chmod 777 -R /var/lib/clickhouse
while /bin/true; do
merge_client_files_in_background
sleep 2
done &
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "SHOW DATABASES"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "ATTACH DATABASE datasets ENGINE = Ordinary"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "CREATE DATABASE test"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "SHOW DATABASES"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "ATTACH DATABASE datasets ENGINE = Ordinary"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "CREATE DATABASE test"
kill_clickhouse
start_clickhouse
sleep 10
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "SHOW TABLES FROM datasets"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "SHOW TABLES FROM test"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "RENAME TABLE datasets.hits_v1 TO test.hits"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "RENAME TABLE datasets.visits_v1 TO test.visits"
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "SHOW TABLES FROM test"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "SHOW TABLES FROM datasets"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "SHOW TABLES FROM test"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "RENAME TABLE datasets.hits_v1 TO test.hits"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "RENAME TABLE datasets.visits_v1 TO test.visits"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-client --query "SHOW TABLES FROM test"
if grep -q -- "--use-skip-list" /usr/bin/clickhouse-test; then
SKIP_LIST_OPT="--use-skip-list"
@ -109,15 +89,10 @@ fi
# more idiologically correct.
read -ra ADDITIONAL_OPTIONS <<< "${ADDITIONAL_OPTIONS:-}"
LLVM_PROFILE_FILE='client_%h_%p_%m.profraw' clickhouse-test --testname --shard --zookeeper --no-stateless --hung-check --print-time "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" "$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt
LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-test --testname --shard --zookeeper --no-stateless --hung-check --print-time "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" "$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt
kill_clickhouse
wait_llvm_profdata
sleep 3
wait_llvm_profdata # 100% merged all parts
cp /*.profraw /profraw ||:

6
docker/test/stateless_with_coverage/Dockerfile
View File

@ -1,4 +1,4 @@
# docker build -t yandex/clickhouse-stateless-with-coverage-test .
# docker build -t yandex/clickhouse-stateless-test-with-coverage .
# TODO: that can be based on yandex/clickhouse-stateless-test (llvm version and CMD differs)
FROM yandex/clickhouse-test-base
@ -28,7 +28,9 @@ RUN apt-get update -y \
lsof \
unixodbc \
wget \
qemu-user-static
qemu-user-static \
procps \
psmisc
RUN mkdir -p /tmp/clickhouse-odbc-tmp \
&& wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \

43
docker/test/stateless_with_coverage/run.sh
View File

@ -2,27 +2,41 @@
kill_clickhouse () {
echo "clickhouse pids $(pgrep -u clickhouse)" | ts '%Y-%m-%d %H:%M:%S'
kill "$(pgrep -u clickhouse)" 2>/dev/null
pkill -f "clickhouse-server" 2>/dev/null
for _ in {1..10}
for _ in {1..120}
do
if ! kill -0 "$(pgrep -u clickhouse)"; then
echo "No clickhouse process" | ts '%Y-%m-%d %H:%M:%S'
break
else
echo "Process $(pgrep -u clickhouse) still alive" | ts '%Y-%m-%d %H:%M:%S'
sleep 10
fi
if ! pkill -0 -f "clickhouse-server" ; then break ; fi
echo "ClickHouse still alive" | ts '%Y-%m-%d %H:%M:%S'
sleep 1
done
echo "Will try to send second kill signal for sure"
kill "$(pgrep -u clickhouse)" 2>/dev/null
sleep 5
echo "clickhouse pids $(pgrep -u clickhouse)" | ts '%Y-%m-%d %H:%M:%S'
if pkill -0 -f "clickhouse-server"
then
pstree -apgT
jobs
echo "Failed to kill the ClickHouse server" | ts '%Y-%m-%d %H:%M:%S'
return 1
fi
}
start_clickhouse () {
LLVM_PROFILE_FILE='server_%h_%p_%m.profraw' sudo -Eu clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml &
counter=0
until clickhouse-client --query "SELECT 1"
do
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
sleep 0.5
counter=$((counter + 1))
done
}
chmod 777 /
@ -44,9 +58,6 @@ chmod 777 -R /var/log/clickhouse-server/
start_clickhouse
sleep 10
if grep -q -- "--use-skip-list" /usr/bin/clickhouse-test; then
SKIP_LIST_OPT="--use-skip-list"
fi

2
docs/en/engines/table-engines/mergetree-family/replication.md
View File

@ -152,7 +152,7 @@ You can specify default arguments for `Replicated` table engine in the server co
```xml
<default_replica_path>/clickhouse/tables/{shard}/{database}/{table}</default_replica_path>
<default_replica_name>{replica}</default_replica_path>
<default_replica_name>{replica}</default_replica_name>
```
In this case, you can omit arguments when creating tables:

35
docs/en/operations/opentelemetry.md
View File

@ -44,11 +44,10 @@ stages, such as query planning or distributed queries.
To be useful, the tracing information has to be exported to a monitoring system
that supports OpenTelemetry, such as Jaeger or Prometheus. ClickHouse avoids
a dependency on a particular monitoring system, instead only
providing the tracing data conforming to the standard. A natural way to do so
in an SQL RDBMS is a system table. OpenTelemetry trace span information
a dependency on a particular monitoring system, instead only providing the
tracing data through a system table. OpenTelemetry trace span information
[required by the standard](https://github.com/open-telemetry/opentelemetry-specification/blob/master/specification/overview.md#span)
is stored in the system table called `system.opentelemetry_span_log`.
is stored in the `system.opentelemetry_span_log` table.
The table must be enabled in the server configuration, see the `opentelemetry_span_log`
element in the default config file `config.xml`. It is enabled by default.
@ -67,3 +66,31 @@ The table has the following columns:
The tags or attributes are saved as two parallel arrays, containing the keys
and values. Use `ARRAY JOIN` to work with them.
## Integration with monitoring systems
At the moment, there is no ready tool that can export the tracing data from
ClickHouse to a monitoring system.
For testing, it is possible to setup the export using a materialized view with the URL engine over the `system.opentelemetry_span_log` table, which would push the arriving log data to an HTTP endpoint of a trace collector. For example, to push the minimal span data to a Zipkin instance running at `http://localhost:9411`, in Zipkin v2 JSON format:
```sql
CREATE MATERIALIZED VIEW default.zipkin_spans
ENGINE = URL('http://127.0.0.1:9411/api/v2/spans', 'JSONEachRow')
SETTINGS output_format_json_named_tuples_as_objects = 1,
output_format_json_array_of_rows = 1 AS
SELECT
lower(hex(reinterpretAsFixedString(trace_id))) AS traceId,
lower(hex(parent_span_id)) AS parentId,
lower(hex(span_id)) AS id,
operation_name AS name,
start_time_us AS timestamp,
finish_time_us - start_time_us AS duration,
cast(tuple('clickhouse'), 'Tuple(serviceName text)') AS localEndpoint,
cast(tuple(
attribute.values[indexOf(attribute.names, 'db.statement')]),
'Tuple("db.statement" text)') AS tags
FROM system.opentelemetry_span_log
```
In case of any errors, the part of the log data for which the error has occurred will be silently lost. Check the server log for error messages if the data does not arrive.

6
docs/en/operations/settings/settings.md
View File

@ -2317,4 +2317,10 @@ Possible values:
Default value: `1`.
## output_format_tsv_null_representation {#output_format_tsv_null_representation}
Allows configurable `NULL` representation for [TSV](../../interfaces/formats.md#tabseparated) output format. The setting only controls output format and `\N` is the only supported `NULL` representation for TSV input format.
Default value: `\N`.
[Original article](https://clickhouse.tech/docs/en/operations/settings/settings/) <!-- hide -->

70
docs/en/operations/system-tables/replicated_fetches.md Normal file
View File

@ -0,0 +1,70 @@
# system.replicated_fetches {#system_tables-replicated_fetches}
Contains information about currently running background fetches.
Columns:
- `database` ([String](../../sql-reference/data-types/string.md)) — Name of the database.
- `table` ([String](../../sql-reference/data-types/string.md)) — Name of the table.
- `elapsed` ([Float64](../../sql-reference/data-types/float.md)) — The time elapsed (in seconds) since showing currently running background fetches started.
- `progress` ([Float64](../../sql-reference/data-types/float.md)) — The percentage of completed work from 0 to 1.
- `result_part_name` ([String](../../sql-reference/data-types/string.md)) — The name of the part that will be formed as the result of showing currently running background fetches.
- `result_part_path` ([String](../../sql-reference/data-types/string.md)) — Absolute path to the part that will be formed as the result of showing currently running background fetches.
- `partition_id` ([String](../../sql-reference/data-types/string.md)) — ID of the partition.
- `total_size_bytes_compressed` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The total size (in bytes) of the compressed data in the result part.
- `bytes_read_compressed` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The number of compressed bytes read from the result part.
- `source_replica_path` ([String](../../sql-reference/data-types/string.md)) — Absolute path to the source replica.
- `source_replica_hostname` ([String](../../sql-reference/data-types/string.md)) — Hostname of the source replica.
- `source_replica_port` ([UInt16](../../sql-reference/data-types/int-uint.md)) — Port number of the source replica.
- `interserver_scheme` ([String](../../sql-reference/data-types/string.md)) — Name of the interserver scheme.
- `URI` ([String](../../sql-reference/data-types/string.md)) — Uniform resource identifier.
- `to_detached` ([UInt8](../../sql-reference/data-types/int-uint.md)) — The flag indicates whether the currently running background fetch is being performed using the `TO DETACHED` expression.
- `thread_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Thread identifier.
**Example**
``` sql
SELECT * FROM system.replicated_fetches LIMIT 1 FORMAT Vertical;
```
``` text
Row 1:
──────
database: default
table: t
elapsed: 7.243039876
progress: 0.41832135995612835
result_part_name: all_0_0_0
result_part_path: /var/lib/clickhouse/store/700/70080a04-b2de-4adf-9fa5-9ea210e81766/all_0_0_0/
partition_id: all
total_size_bytes_compressed: 1052783726
bytes_read_compressed: 440401920
source_replica_path: /clickhouse/test/t/replicas/1
source_replica_hostname: node1
source_replica_port: 9009
interserver_scheme: http
URI: http://node1:9009/?endpoint=DataPartsExchange%3A%2Fclickhouse%2Ftest%2Ft%2Freplicas%2F1&part=all_0_0_0&client_protocol_version=4&compress=false
to_detached: 0
thread_id: 54
```
**See Also**
- [Managing ReplicatedMergeTree Tables](../../sql-reference/statements/system/#query-language-system-replicated)
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/replicated_fetches) <!--hide-->

84
docs/en/operations/utilities/clickhouse-obfuscator.md
View File

@ -1,42 +1,42 @@
# ClickHouse obfuscator
Simple tool for table data obfuscation.
It reads input table and produces output table, that retain some properties of input, but contains different data.
It allows to publish almost real production data for usage in benchmarks.
It is designed to retain the following properties of data:
- cardinalities of values (number of distinct values) for every column and for every tuple of columns;
- conditional cardinalities: number of distinct values of one column under condition on value of another column;
- probability distributions of absolute value of integers; sign of signed integers; exponent and sign for floats;
- probability distributions of length of strings;
- probability of zero values of numbers; empty strings and arrays, NULLs;
- data compression ratio when compressed with LZ77 and entropy family of codecs;
- continuity (magnitude of difference) of time values across table; continuity of floating point values.
- date component of DateTime values;
- UTF-8 validity of string values;
- string values continue to look somewhat natural.
Most of the properties above are viable for performance testing:
reading data, filtering, aggregation and sorting will work at almost the same speed
as on original data due to saved cardinalities, magnitudes, compression ratios, etc.
It works in deterministic fashion: you define a seed value and transform is totally determined by input data and by seed.
Some transforms are one to one and could be reversed, so you need to have large enough seed and keep it in secret.
It use some cryptographic primitives to transform data, but from the cryptographic point of view,
It doesn't do anything properly and you should never consider the result as secure, unless you have other reasons for it.
It may retain some data you don't want to publish.
It always leave numbers 0, 1, -1 as is. Also it leaves dates, lengths of arrays and null flags exactly as in source data.
For example, you have a column IsMobile in your table with values 0 and 1. In transformed data, it will have the same value.
So, the user will be able to count exact ratio of mobile traffic.
Another example, suppose you have some private data in your table, like user email and you don't want to publish any single email address.
If your table is large enough and contain multiple different emails and there is no email that have very high frequency than all others,
It will perfectly anonymize all data. But if you have small amount of different values in a column, it can possibly reproduce some of them.
And you should take care and look at exact algorithm, how this tool works, and probably fine tune some of it command line parameters.
This tool works fine only with reasonable amount of data (at least 1000s of rows).
# ClickHouse obfuscator
A simple tool for table data obfuscation.
It reads an input table and produces an output table, that retains some properties of input, but contains different data.
It allows publishing almost real production data for usage in benchmarks.
It is designed to retain the following properties of data:
- cardinalities of values (number of distinct values) for every column and every tuple of columns;
- conditional cardinalities: number of distinct values of one column under the condition on the value of another column;
- probability distributions of the absolute value of integers; the sign of signed integers; exponent and sign for floats;
- probability distributions of the length of strings;
- probability of zero values of numbers; empty strings and arrays, `NULL`s;
- data compression ratio when compressed with LZ77 and entropy family of codecs;
- continuity (magnitude of difference) of time values across the table; continuity of floating-point values;
- date component of `DateTime` values;
- UTF-8 validity of string values;
- string values look natural.
Most of the properties above are viable for performance testing:
reading data, filtering, aggregatio, and sorting will work at almost the same speed
as on original data due to saved cardinalities, magnitudes, compression ratios, etc.
It works in a deterministic fashion: you define a seed value and the transformation is determined by input data and by seed.
Some transformations are one to one and could be reversed, so you need to have a large seed and keep it in secret.
It uses some cryptographic primitives to transform data but from the cryptographic point of view, it doesn't do it properly, that is why you should not consider the result as secure unless you have another reason. The result may retain some data you don't want to publish.
It always leaves 0, 1, -1 numbers, dates, lengths of arrays, and null flags exactly as in source data.
For example, you have a column `IsMobile` in your table with values 0 and 1. In transformed data, it will have the same value.
So, the user will be able to count the exact ratio of mobile traffic.
Let's give another example. When you have some private data in your table, like user email and you don't want to publish any single email address.
If your table is large enough and contains multiple different emails and no email has a very high frequency than all others, it will anonymize all data. But if you have a small number of different values in a column, it can reproduce some of them.
You should look at the working algorithm of this tool works, and fine-tune its command line parameters.
This tool works fine only with an average amount of data (at least 1000s of rows).

2
docs/en/sql-reference/aggregate-functions/index.md
View File

@ -44,8 +44,6 @@ SELECT sum(y) FROM t_null_big
└────────┘
```
The `sum` function interprets `NULL` as `0`. In particular, this means that if the function receives input of a selection where all the values are `NULL`, then the result will be `0`, not `NULL`.
Now you can use the `groupArray` function to create an array from the `y` column:
``` sql

37
docs/en/sql-reference/aggregate-functions/reference/initializeAggregation.md Normal file
View File

@ -0,0 +1,37 @@
---
toc_priority: 150
---
## initializeAggregation {#initializeaggregation}
Initializes aggregation for your input rows. It is intended for the functions with the suffix `State`.
Use it for tests or to process columns of types `AggregateFunction` and `AggregationgMergeTree`.
**Syntax**
``` sql
initializeAggregation (aggregate_function, column_1, column_2);
```
**Parameters**
- `aggregate_function` — Name of the aggregation function. The state of this function — the creating one. [String](../../../sql-reference/data-types/string.md#string).
- `column_n` — The column to translate it into the function as it's argument. [String](../../../sql-reference/data-types/string.md#string).
**Returned value(s)**
Returns the result of the aggregation for your input rows. The return type will be the same as the return type of function, that `initializeAgregation` takes as first argument.
For example for functions with the suffix `State` the return type will be `AggregateFunction`.
**Example**
Query:
```sql
SELECT uniqMerge(state) FROM (SELECT initializeAggregation('uniqState', number % 3) AS state FROM system.numbers LIMIT 10000);
```
Result:
┌─uniqMerge(state)─┐
│ 3 │
└──────────────────┘

13
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -535,18 +535,7 @@ dateDiff('unit', startdate, enddate, [timezone])
- `unit` — Time unit, in which the returned value is expressed. [String](../../sql-reference/syntax.md#syntax-string-literal).
Supported values:
| unit |
| ---- |
|second |
|minute |
|hour |
|day |
|week |
|month |
|quarter |
|year |
Supported values: second, minute, hour, day, week, month, quarter, year.
- `startdate` — The first time value to compare. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).

16
docs/en/sql-reference/functions/url-functions.md
View File

@ -115,7 +115,21 @@ Returns the “first significant subdomain”. This is a non-standard concept sp
Returns the part of the domain that includes top-level subdomains up to the “first significant subdomain” (see the explanation above).
For example, `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
For example:
- `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
- `cutToFirstSignificantSubdomain('www.tr') = 'tr'`.
- `cutToFirstSignificantSubdomain('tr') = ''`.
### cutToFirstSignificantSubdomainWithWWW {#cuttofirstsignificantsubdomainwithwww}
Returns the part of the domain that includes top-level subdomains up to the “first significant subdomain”, without stripping "www".
For example:
- `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
- `cutToFirstSignificantSubdomain('www.tr') = 'www.tr'`.
- `cutToFirstSignificantSubdomain('tr') = ''`.
### port(URL\[, default_port = 0\]) {#port}

4
docs/en/sql-reference/statements/select/from.md
View File

@ -27,9 +27,9 @@ It is applicable when selecting data from tables that use the [MergeTree](../../
### Drawbacks {#drawbacks}
Queries that use `FINAL` are executed not as fast as similar queries that don’t, because:
Queries that use `FINAL` are executed slightly slower than similar queries that don’t, because:
- Query is executed in a single thread and data is merged during query execution.
- Data is merged during query execution.
- Queries with `FINAL` read primary key columns in addition to the columns specified in the query.
**In most cases, avoid using `FINAL`.** The common approach is to use different queries that assume the background processes of the `MergeTree` engine have’t happened yet and deal with it by applying aggregation (for example, to discard duplicates). {## TODO: examples ##}

156
docs/en/sql-reference/statements/select/group-by.md
View File

@ -6,7 +6,7 @@ toc_title: GROUP BY
`GROUP BY` clause switches the `SELECT` query into an aggregation mode, which works as follows:
- `GROUP BY` clause contains a list of expressions (or a single expression, which is considered to be the list of length one). This list acts as a “grouping key”, while each individual expression will be referred to as a “key expressions”.
- `GROUP BY` clause contains a list of expressions (or a single expression, which is considered to be the list of length one). This list acts as a “grouping key”, while each individual expression will be referred to as a “key expression”.
- All the expressions in the [SELECT](../../../sql-reference/statements/select/index.md), [HAVING](../../../sql-reference/statements/select/having.md), and [ORDER BY](../../../sql-reference/statements/select/order-by.md) clauses **must** be calculated based on key expressions **or** on [aggregate functions](../../../sql-reference/aggregate-functions/index.md) over non-key expressions (including plain columns). In other words, each column selected from the table must be used either in a key expression or inside an aggregate function, but not both.
- Result of aggregating `SELECT` query will contain as many rows as there were unique values of “grouping key” in source table. Usually this signficantly reduces the row count, often by orders of magnitude, but not necessarily: row count stays the same if all “grouping key” values were distinct.
@ -45,6 +45,154 @@ You can see that `GROUP BY` for `y = NULL` summed up `x`, as if `NULL` is this v
If you pass several keys to `GROUP BY`, the result will give you all the combinations of the selection, as if `NULL` were a specific value.
## WITH ROLLUP Modifier {#with-rollup-modifier}
`WITH ROLLUP` modifier is used to calculate subtotals for the key expressions, based on their order in the `GROUP BY` list. The subtotals rows are added after the result table.
The subtotals are calculated in the reverse order: at first subtotals are calculated for the last key expression in the list, then for the previous one, and so on up to the first key expression.
In the subtotals rows the values of already "grouped" key expressions are set to `0` or empty line.
!!! note "Note"
Mind that [HAVING](../../../sql-reference/statements/select/having.md) clause can affect the subtotals results.
**Example**
Consider the table t:
```text
┌─year─┬─month─┬─day─┐
│ 2019 │ 1 │ 5 │
│ 2019 │ 1 │ 15 │
│ 2020 │ 1 │ 5 │
│ 2020 │ 1 │ 15 │
│ 2020 │ 10 │ 5 │
│ 2020 │ 10 │ 15 │
└──────┴───────┴─────┘
```
Query:
```sql
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH ROLLUP;
```
As `GROUP BY` section has three key expressions, the result contains four tables with subtotals "rolled up" from right to left:
- `GROUP BY year, month, day`;
- `GROUP BY year, month` (and `day` column is filled with zeros);
- `GROUP BY year` (now `month, day` columns are both filled with zeros);
- and totals (and all three key expression columns are zeros).
```text
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 10 │ 15 │ 1 │
│ 2020 │ 1 │ 5 │ 1 │
│ 2019 │ 1 │ 5 │ 1 │
│ 2020 │ 1 │ 15 │ 1 │
│ 2019 │ 1 │ 15 │ 1 │
│ 2020 │ 10 │ 5 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 1 │ 0 │ 2 │
│ 2020 │ 1 │ 0 │ 2 │
│ 2020 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 0 │ 0 │ 2 │
│ 2020 │ 0 │ 0 │ 4 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 0 │ 6 │
└──────┴───────┴─────┴─────────┘
```
## WITH CUBE Modifier {#with-cube-modifier}
`WITH CUBE` modifier is used to calculate subtotals for every combination of the key expressions in the `GROUP BY` list. The subtotals rows are added after the result table.
In the subtotals rows the values of all "grouped" key expressions are set to `0` or empty line.
!!! note "Note"
Mind that [HAVING](../../../sql-reference/statements/select/having.md) clause can affect the subtotals results.
**Example**
Consider the table t:
```text
┌─year─┬─month─┬─day─┐
│ 2019 │ 1 │ 5 │
│ 2019 │ 1 │ 15 │
│ 2020 │ 1 │ 5 │
│ 2020 │ 1 │ 15 │
│ 2020 │ 10 │ 5 │
│ 2020 │ 10 │ 15 │
└──────┴───────┴─────┘
```
Query:
```sql
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH CUBE;
```
As `GROUP BY` section has three key expressions, the result contains eight tables with subtotals for all key expression combinations:
- `GROUP BY year, month, day`
- `GROUP BY year, month`
- `GROUP BY year, day`
- `GROUP BY year`
- `GROUP BY month, day`
- `GROUP BY month`
- `GROUP BY day`
- and totals.
Columns, excluded from `GROUP BY`, are filled with zeros.
```text
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 10 │ 15 │ 1 │
│ 2020 │ 1 │ 5 │ 1 │
│ 2019 │ 1 │ 5 │ 1 │
│ 2020 │ 1 │ 15 │ 1 │
│ 2019 │ 1 │ 15 │ 1 │
│ 2020 │ 10 │ 5 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 1 │ 0 │ 2 │
│ 2020 │ 1 │ 0 │ 2 │
│ 2020 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 0 │ 5 │ 2 │
│ 2019 │ 0 │ 5 │ 1 │
│ 2020 │ 0 │ 15 │ 2 │
│ 2019 │ 0 │ 15 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 0 │ 0 │ 2 │
│ 2020 │ 0 │ 0 │ 4 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 1 │ 5 │ 2 │
│ 0 │ 10 │ 15 │ 1 │
│ 0 │ 10 │ 5 │ 1 │
│ 0 │ 1 │ 15 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 1 │ 0 │ 4 │
│ 0 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 5 │ 3 │
│ 0 │ 0 │ 15 │ 3 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 0 │ 6 │
└──────┴───────┴─────┴─────────┘
```
## WITH TOTALS Modifier {#with-totals-modifier}
If the `WITH TOTALS` modifier is specified, another row will be calculated. This row will have key columns containing default values (zeros or empty lines), and columns of aggregate functions with the values calculated across all the rows (the “total” values).
@ -88,8 +236,6 @@ SELECT
FROM hits
```
However, in contrast to standard SQL, if the table doesn’t have any rows (either there aren’t any at all, or there aren’t any after using WHERE to filter), an empty result is returned, and not the result from one of the rows containing the initial values of aggregate functions.
As opposed to MySQL (and conforming to standard SQL), you can’t get some value of some column that is not in a key or aggregate function (except constant expressions). To work around this, you can use the ‘any’ aggregate function (get the first encountered value) or ‘min/max’.
Example:
@ -105,10 +251,6 @@ GROUP BY domain
For every different key value encountered, `GROUP BY` calculates a set of aggregate function values.
`GROUP BY` is not supported for array columns.
A constant can’t be specified as arguments for aggregate functions. Example: `sum(1)`. Instead of this, you can get rid of the constant. Example: `count()`.
## Implementation Details {#implementation-details}
Aggregation is one of the most important features of a column-oriented DBMS, and thus it’s implementation is one of the most heavily optimized parts of ClickHouse. By default, aggregation is done in memory using a hash-table. It has 40+ specializations that are chosen automatically depending on “grouping key” data types.

115
docs/en/sql-reference/statements/select/index.md
View File

@ -20,12 +20,12 @@ SELECT [DISTINCT] expr_list
[GLOBAL] [ANY|ALL|ASOF] [INNER|LEFT|RIGHT|FULL|CROSS] [OUTER|SEMI|ANTI] JOIN (subquery)|table (ON <expr_list>)|(USING <column_list>)
[PREWHERE expr]
[WHERE expr]
[GROUP BY expr_list] [WITH TOTALS]
[GROUP BY expr_list] [WITH ROLLUP|WITH CUBE] [WITH TOTALS]
[HAVING expr]
[ORDER BY expr_list] [WITH FILL] [FROM expr] [TO expr] [STEP expr]
[LIMIT [offset_value, ]n BY columns]
[LIMIT [n, ]m] [WITH TIES]
[UNION ALL ...]
[UNION ...]
[INTO OUTFILE filename]
[FORMAT format]
```
@ -46,7 +46,7 @@ Specifics of each optional clause are covered in separate sections, which are li
- [SELECT clause](#select-clause)
- [DISTINCT clause](../../../sql-reference/statements/select/distinct.md)
- [LIMIT clause](../../../sql-reference/statements/select/limit.md)
- [UNION ALL clause](../../../sql-reference/statements/select/union-all.md)
- [UNION clause](../../../sql-reference/statements/select/union-all.md)
- [INTO OUTFILE clause](../../../sql-reference/statements/select/into-outfile.md)
- [FORMAT clause](../../../sql-reference/statements/select/format.md)
@ -159,4 +159,111 @@ If the query omits the `DISTINCT`, `GROUP BY` and `ORDER BY` clauses and the `IN
For more information, see the section “Settings”. It is possible to use external sorting (saving temporary tables to a disk) and external aggregation.
{## [Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/) ##}
## SELECT modifiers {#select-modifiers}
You can use the following modifiers in `SELECT` queries.
### APPLY {#apply-modifier}
Allows you to invoke some function for each row returned by an outer table expression of a query.
**Syntax:**
``` sql
SELECT <expr> APPLY( <func> ) FROM [db.]table_name
```
**Example:**
``` sql
CREATE TABLE columns_transformers (i Int64, j Int16, k Int64) ENGINE = MergeTree ORDER by (i);
INSERT INTO columns_transformers VALUES (100, 10, 324), (120, 8, 23);
SELECT * APPLY(sum) FROM columns_transformers;
```
```
┌─sum(i)─┬─sum(j)─┬─sum(k)─┐
│ 220 │ 18 │ 347 │
└────────┴────────┴────────┘
```
### EXCEPT {#except-modifier}
Specifies the names of one or more columns to exclude from the result. All matching column names are omitted from the output.
**Syntax:**
``` sql
SELECT <expr> EXCEPT ( col_name1 [, col_name2, col_name3, ...] ) FROM [db.]table_name
```
**Example:**
``` sql
SELECT * EXCEPT (i) from columns_transformers;
```
```
┌──j─┬───k─┐
│ 10 │ 324 │
│ 8 │ 23 │
└────┴─────┘
```
### REPLACE {#replace-modifier}
Specifies one or more [expression aliases](../../../sql-reference/syntax.md#syntax-expression_aliases). Each alias must match a column name from the `SELECT *` statement. In the output column list, the column that matches the alias is replaced by the expression in that `REPLACE`.
This modifier does not change the names or order of columns. However, it can change the value and the value type.
**Syntax:**
``` sql
SELECT <expr> REPLACE( <expr> AS col_name) from [db.]table_name
```
**Example:**
``` sql
SELECT * REPLACE(i + 1 AS i) from columns_transformers;
```
```
┌───i─┬──j─┬───k─┐
│ 101 │ 10 │ 324 │
│ 121 │ 8 │ 23 │
└─────┴────┴─────┘
```
### Modifier Combinations {#modifier-combinations}
You can use each modifier separately or combine them.
**Examples:**
Using the same modifier multiple times.
``` sql
SELECT COLUMNS('[jk]') APPLY(toString) APPLY(length) APPLY(max) from columns_transformers;
```
```
┌─max(length(toString(j)))─┬─max(length(toString(k)))─┐
│ 2 │ 3 │
└──────────────────────────┴──────────────────────────┘
```
Using multiple modifiers in a single query.
``` sql
SELECT * REPLACE(i + 1 AS i) EXCEPT (j) APPLY(sum) from columns_transformers;
```
```
┌─sum(plus(i, 1))─┬─sum(k)─┐
│ 222 │ 347 │
└─────────────────┴────────┘
```
[Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/)
<!--hide-->

11
docs/en/sql-reference/statements/select/union-all.md
View File

@ -1,5 +1,5 @@
---
toc_title: UNION ALL
toc_title: UNION
---
# UNION ALL Clause {#union-all-clause}
@ -25,10 +25,13 @@ Type casting is performed for unions. For example, if two queries being combined
Queries that are parts of `UNION ALL` can’t be enclosed in round brackets. [ORDER BY](../../../sql-reference/statements/select/order-by.md) and [LIMIT](../../../sql-reference/statements/select/limit.md) are applied to separate queries, not to the final result. If you need to apply a conversion to the final result, you can put all the queries with `UNION ALL` in a subquery in the [FROM](../../../sql-reference/statements/select/from.md) clause.
## Limitations {#limitations}
# UNION DISTINCT Clause {#union-distinct-clause}
The difference between `UNION ALL` and `UNION DISTINCT` is that `UNION DISTINCT` will do a distinct transform for union result, it is equivalent to `SELECT DISTINCT` from a subquery containing `UNION ALL`.
# UNION Clause {#union-clause}
By default, `UNION` has the same behavior as `UNION DISTINCT`, but you can specify union mode by setting `union_default_mode`, values can be 'ALL', 'DISTINCT' or empty string. However, if you use `UNION` with setting `union_default_mode` to empty string, it will throw an exception.
Only `UNION ALL` is supported. The regular `UNION` (`UNION DISTINCT`) is not supported. If you need `UNION DISTINCT`, you can write `SELECT DISTINCT` from a subquery containing `UNION ALL`.
## Implementation Details {#implementation-details}
Queries that are parts of `UNION ALL` can be run simultaneously, and their results can be mixed together.
Queries that are parts of `UNION/UNION ALL/UNION DISTINCT` can be run simultaneously, and their results can be mixed together.

6
docs/ru/operations/settings/settings.md
View File

@ -2187,4 +2187,10 @@ SELECT CAST(toNullable(toInt32(0)) AS Int32) as x, toTypeName(x);
Значение по умолчанию: `1`.
## output_format_tsv_null_representation {#output_format_tsv_null_representation}
Позволяет настраивать представление `NULL` для формата выходных данных [TSV](../../interfaces/formats.md#tabseparated). Настройка управляет форматом выходных данных, `\N` является единственным поддерживаемым представлением для формата входных данных TSV.
Значение по умолчанию: `\N`.
[Оригинальная статья](https://clickhouse.tech/docs/ru/operations/settings/settings/) <!--hide-->

70
docs/ru/operations/system-tables/replicated_fetches.md Normal file
View File

@ -0,0 +1,70 @@
# system.replicated_fetches {#system_tables-replicated_fetches}
Содержит информацию о выполняемых в данный момент фоновых операциях скачивания кусков данных с других реплик.
Столбцы:
- `database` ([String](../../sql-reference/data-types/string.md)) — имя базы данных.
- `table` ([String](../../sql-reference/data-types/string.md)) — имя таблицы.
- `elapsed` ([Float64](../../sql-reference/data-types/float.md)) — время, прошедшее от момента начала скачивания куска, в секундах.
- `progress` ([Float64](../../sql-reference/data-types/float.md)) — доля выполненной работы от 0 до 1.
- `result_part_name` ([String](../../sql-reference/data-types/string.md)) — имя скачиваемого куска.
- `result_part_path` ([String](../../sql-reference/data-types/string.md)) — абсолютный путь к скачиваемому куску.
- `partition_id` ([String](../../sql-reference/data-types/string.md)) — идентификатор партиции.
- `total_size_bytes_compressed` ([UInt64](../../sql-reference/data-types/int-uint.md)) — общий размер сжатой информации в скачиваемом куске в байтах.
- `bytes_read_compressed` ([UInt64](../../sql-reference/data-types/int-uint.md)) — размер сжатой информации, считанной из скачиваемого куска, в байтах.
- `source_replica_path` ([String](../../sql-reference/data-types/string.md)) — абсолютный путь к исходной реплике.
- `source_replica_hostname` ([String](../../sql-reference/data-types/string.md)) — имя хоста исходной реплики.
- `source_replica_port` ([UInt16](../../sql-reference/data-types/int-uint.md)) — номер порта исходной реплики.
- `interserver_scheme` ([String](../../sql-reference/data-types/string.md)) — имя межсерверной схемы.
- `URI` ([String](../../sql-reference/data-types/string.md)) — универсальный идентификатор ресурса.
- `to_detached` ([UInt8](../../sql-reference/data-types/int-uint.md)) — флаг, указывающий на использование выражения `TO DETACHED` в текущих фоновых операциях.
- `thread_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — идентификатор потока.
**Пример**
``` sql
SELECT * FROM system.replicated_fetches LIMIT 1 FORMAT Vertical;
```
``` text
Row 1:
──────
database: default
table: t
elapsed: 7.243039876
progress: 0.41832135995612835
result_part_name: all_0_0_0
result_part_path: /var/lib/clickhouse/store/700/70080a04-b2de-4adf-9fa5-9ea210e81766/all_0_0_0/
partition_id: all
total_size_bytes_compressed: 1052783726
bytes_read_compressed: 440401920
source_replica_path: /clickhouse/test/t/replicas/1
source_replica_hostname: node1
source_replica_port: 9009
interserver_scheme: http
URI: http://node1:9009/?endpoint=DataPartsExchange%3A%2Fclickhouse%2Ftest%2Ft%2Freplicas%2F1&part=all_0_0_0&client_protocol_version=4&compress=false
to_detached: 0
thread_id: 54
```
**Смотрите также**
- [Управление таблицами ReplicatedMergeTree](../../sql-reference/statements/system/#query-language-system-replicated)
[Оригинальная статья](https://clickhouse.tech/docs/en/operations/system_tables/replicated_fetches) <!--hide-->

43
docs/ru/operations/utilities/clickhouse-obfuscator.md Normal file
View File

@ -0,0 +1,43 @@
# Обфускатор ClickHouse
Простой инструмент для обфускации табличных данных.
Он считывает данные входной таблицы и создает выходную таблицу, которая сохраняет некоторые свойства входных данных, но при этом содержит другие данные.
Это позволяет публиковать практически реальные данные и использовать их в тестах на производительность.
Обфускатор предназначен для сохранения следующих свойств данных:
- кардинальность (количество уникальных данных) для каждого столбца и каждого кортежа столбцов;
- условная кардинальность: количество уникальных данных одного столбца в соответствии со значением другого столбца;
- вероятностные распределения абсолютного значения целых чисел; знак числа типа Int; показатель степени и знак для чисел с плавающей запятой;
- вероятностное распределение длины строк;
- вероятность нулевых значений чисел; пустые строки и массивы, `NULL`;
- степень сжатия данных алгоритмом LZ77 и семейством энтропийных кодеков;
- непрерывность (величина разницы) значений времени в таблице; непрерывность значений с плавающей запятой;
- дату из значений `DateTime`;
- кодировка UTF-8 значений строки;
- строковые значения выглядят естественным образом.
Большинство перечисленных выше свойств пригодны для тестирования производительности. Чтение данных, фильтрация, агрегирование и сортировка будут работать почти с той же скоростью, что и исходные данные, благодаря сохраненной кардинальности, величине, степени сжатия и т. д.
Он работает детерминированно. Вы задаёте значение инициализатора, а преобразование полностью определяется входными данными и инициализатором.
Некоторые преобразования выполняются один к одному, и их можно отменить. Поэтому нужно использовать большое значение инициализатора и хранить его в секрете.
Обфускатор использует некоторые криптографические примитивы для преобразования данных, но, с криптографической точки зрения, результат будет небезопасным. В нем могут сохраниться данные, которые не следует публиковать.
Он всегда оставляет без изменений числа 0, 1, -1, даты, длины массивов и нулевые флаги.
Например, если у вас есть столбец `IsMobile` в таблице со значениями 0 и 1, то в преобразованных данных он будет иметь то же значение.
Таким образом, пользователь сможет посчитать точное соотношение мобильного трафика.
Давайте рассмотрим случай, когда у вас есть какие-то личные данные в таблице (например, электронная почта пользователя), и вы не хотите их публиковать.
Если ваша таблица достаточно большая и содержит несколько разных электронных почтовых адресов, и ни один из них не встречается часто, то обфускатор полностью анонимизирует все данные. Но, если у вас есть небольшое количество разных значений в столбце, он может скопировать некоторые из них.
В этом случае вам следует посмотреть на алгоритм работы инструмента и настроить параметры командной строки.
Обфускатор полезен в работе со средним объемом данных (не менее 1000 строк).

2
docs/ru/sql-reference/aggregate-functions/index.md
View File

@ -44,8 +44,6 @@ SELECT sum(y) FROM t_null_big
└────────┘
```
Функция `sum` работает с `NULL` как с `0`. В частности, это означает, что если на вход в функцию подать выборку, где все значения `NULL`, то результат будет `0`, а не `NULL`.
Теперь с помощью функции `groupArray` сформируем массив из столбца `y`:
``` sql

40
docs/ru/sql-reference/aggregate-functions/reference/initializeAggregation.md Normal file
View File

@ -0,0 +1,40 @@
---
toc_priority: 150
---
## initializeAggregation {#initializeaggregation}
Инициализирует агрегацию для введеных строчек. Предназначена для функций с суффиксом `State`.
Поможет вам проводить тесты или работать со столбцами типов: `AggregateFunction` и `AggregationgMergeTree`.
**Синтаксис**
``` sql
initializeAggregation (aggregate_function, column_1, column_2);
```
**Параметры**
- `aggregate_function` — название функции агрегации, состояние которой нужно создать. [String](../../../sql-reference/data-types/string.md#string).
- `column_n` — столбец, который передается в функцию агрегации как аргумент. [String](../../../sql-reference/data-types/string.md#string).
**Возвращаемое значение**
Возвращает результат агрегации введенной информации. Тип возвращаемого значения такой же, как и для функции, которая становится первым аргументом для `initializeAgregation`.
Пример:
Возвращаемый тип функций с суффиксом `State` — `AggregateFunction`.
**Пример**
Запрос:
```sql
SELECT uniqMerge(state) FROM (SELECT initializeAggregation('uniqState', number % 3) AS state FROM system.numbers LIMIT 10000);
```
Результат:
┌─uniqMerge(state)─┐
│ 3 │
└──────────────────┘

4
docs/ru/sql-reference/statements/select/from.md
View File

@ -27,9 +27,9 @@ toc_title: FROM
### Недостатки {#drawbacks}
Запросы, которые используют `FINAL` выполняются не так быстро, как аналогичные запросы без него, потому что:
Запросы, которые используют `FINAL` выполняются немного медленее, чем аналогичные запросы без него, потому что:
- Запрос выполняется в одном потоке, и данные мёржатся во время выполнения запроса.
- Данные мёржатся во время выполнения запроса.
- Запросы с модификатором `FINAL` читают столбцы первичного ключа в дополнение к столбцам, используемым в запросе.
**В большинстве случаев избегайте использования `FINAL`.** Общий подход заключается в использовании агрегирующих запросов, которые предполагают, что фоновые процессы движков семейства `MergeTree` ещё не случились (например, сами отбрасывают дубликаты). {## TODO: examples ##}

153
docs/ru/sql-reference/statements/select/group-by.md
View File

@ -43,6 +43,153 @@ toc_title: GROUP BY
Если в `GROUP BY` передать несколько ключей, то в результате мы получим все комбинации выборки, как если бы `NULL` был конкретным значением.
## Модификатор WITH ROLLUP {#with-rollup-modifier}
Модификатор `WITH ROLLUP` применяется для подсчета подытогов для ключевых выражений. При этом учитывается порядок следования ключевых выражений в списке `GROUP BY`. Подытоги подсчитываются в обратном порядке: сначала для последнего ключевого выражения в списке, потом для предпоследнего и так далее вплоть до самого первого ключевого выражения.
Строки с подытогами добавляются в конец результирующей таблицы. В колонках, по которым строки уже сгруппированы, указывается значение `0` или пустая строка.
!!! note "Примечание"
Если в запросе есть секция [HAVING](../../../sql-reference/statements/select/having.md), она может повлиять на результаты расчета подытогов.
**Пример**
Рассмотрим таблицу t:
```text
┌─year─┬─month─┬─day─┐
│ 2019 │ 1 │ 5 │
│ 2019 │ 1 │ 15 │
│ 2020 │ 1 │ 5 │
│ 2020 │ 1 │ 15 │
│ 2020 │ 10 │ 5 │
│ 2020 │ 10 │ 15 │
└──────┴───────┴─────┘
```
Запрос:
```sql
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH ROLLUP;
```
Поскольку секция `GROUP BY` содержит три ключевых выражения, результат состоит из четырех таблиц с подытогами, которые как бы "сворачиваются" справа налево:
- `GROUP BY year, month, day`;
- `GROUP BY year, month` (а колонка `day` заполнена нулями);
- `GROUP BY year` (теперь обе колонки `month, day` заполнены нулями);
- и общий итог (все три колонки с ключевыми выражениями заполнены нулями).
```text
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 10 │ 15 │ 1 │
│ 2020 │ 1 │ 5 │ 1 │
│ 2019 │ 1 │ 5 │ 1 │
│ 2020 │ 1 │ 15 │ 1 │
│ 2019 │ 1 │ 15 │ 1 │
│ 2020 │ 10 │ 5 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 1 │ 0 │ 2 │
│ 2020 │ 1 │ 0 │ 2 │
│ 2020 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 0 │ 0 │ 2 │
│ 2020 │ 0 │ 0 │ 4 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 0 │ 6 │
└──────┴───────┴─────┴─────────┘
```
## Модификатор WITH CUBE {#with-cube-modifier}
Модификатор `WITH CUBE` применятеся для расчета подытогов по всем комбинациям группировки ключевых выражений в списке `GROUP BY`.
Строки с подытогами добавляются в конец результирующей таблицы. В колонках, по которым выполняется группировка, указывается значение `0` или пустая строка.
!!! note "Примечание"
Если в запросе есть секция [HAVING](../../../sql-reference/statements/select/having.md), она может повлиять на результаты расчета подытогов.
**Пример**
Рассмотрим таблицу t:
```text
┌─year─┬─month─┬─day─┐
│ 2019 │ 1 │ 5 │
│ 2019 │ 1 │ 15 │
│ 2020 │ 1 │ 5 │
│ 2020 │ 1 │ 15 │
│ 2020 │ 10 │ 5 │
│ 2020 │ 10 │ 15 │
└──────┴───────┴─────┘
```
Query:
```sql
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH CUBE;
```
Поскольку секция `GROUP BY` содержит три ключевых выражения, результат состоит из восьми таблиц с подытогами — по таблице для каждой комбинации ключевых выражений:
- `GROUP BY year, month, day`
- `GROUP BY year, month`
- `GROUP BY year, day`
- `GROUP BY year`
- `GROUP BY month, day`
- `GROUP BY month`
- `GROUP BY day`
- и общий итог.
Колонки, которые не участвуют в `GROUP BY`, заполнены нулями.
```text
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 10 │ 15 │ 1 │
│ 2020 │ 1 │ 5 │ 1 │
│ 2019 │ 1 │ 5 │ 1 │
│ 2020 │ 1 │ 15 │ 1 │
│ 2019 │ 1 │ 15 │ 1 │
│ 2020 │ 10 │ 5 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 1 │ 0 │ 2 │
│ 2020 │ 1 │ 0 │ 2 │
│ 2020 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2020 │ 0 │ 5 │ 2 │
│ 2019 │ 0 │ 5 │ 1 │
│ 2020 │ 0 │ 15 │ 2 │
│ 2019 │ 0 │ 15 │ 1 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 2019 │ 0 │ 0 │ 2 │
│ 2020 │ 0 │ 0 │ 4 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 1 │ 5 │ 2 │
│ 0 │ 10 │ 15 │ 1 │
│ 0 │ 10 │ 5 │ 1 │
│ 0 │ 1 │ 15 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 1 │ 0 │ 4 │
│ 0 │ 10 │ 0 │ 2 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 5 │ 3 │
│ 0 │ 0 │ 15 │ 3 │
└──────┴───────┴─────┴─────────┘
┌─year─┬─month─┬─day─┬─count()─┐
│ 0 │ 0 │ 0 │ 6 │
└──────┴───────┴─────┴─────────┘
```
## Модификатор WITH TOTALS {#with-totals-modifier}
Если указан модификатор `WITH TOTALS`, то будет посчитана ещё одна строчка, в которой в столбцах-ключах будут содержаться значения по умолчанию (нули, пустые строки), а в столбцах агрегатных функций - значения, посчитанные по всем строкам («тотальные» значения).
@ -86,8 +233,6 @@ SELECT
FROM hits
```
Но, в отличие от стандартного SQL, если в таблице нет строк (вообще нет или после фильтрации с помощью WHERE), в качестве результата возвращается пустой результат, а не результат из одной строки, содержащий «начальные» значения агрегатных функций.
В отличие от MySQL (и в соответствии со стандартом SQL), вы не можете получить какое-нибудь значение некоторого столбца, не входящего в ключ или агрегатную функцию (за исключением константных выражений). Для обхода этого вы можете воспользоваться агрегатной функцией any (получить первое попавшееся значение) или min/max.
Пример:
@ -103,10 +248,6 @@ GROUP BY domain
GROUP BY вычисляет для каждого встретившегося различного значения ключей, набор значений агрегатных функций.
Не поддерживается GROUP BY по столбцам-массивам.
Не поддерживается указание констант в качестве аргументов агрегатных функций. Пример: `sum(1)`. Вместо этого, вы можете избавиться от констант. Пример: `count()`.
## Детали реализации {#implementation-details}
Агрегация является одной из наиболее важных возможностей столбцовых СУБД, и поэтому её реализация является одной из наиболее сильно оптимизированных частей ClickHouse. По умолчанию агрегирование выполняется в памяти с помощью хэш-таблицы. Она имеет более 40 специализаций, которые выбираются автоматически в зависимости от типов данных ключа группировки.

2
docs/ru/sql-reference/statements/select/index.md
View File

@ -18,7 +18,7 @@ SELECT [DISTINCT] expr_list
[GLOBAL] [ANY|ALL|ASOF] [INNER|LEFT|RIGHT|FULL|CROSS] [OUTER|SEMI|ANTI] JOIN (subquery)|table (ON <expr_list>)|(USING <column_list>)
[PREWHERE expr]
[WHERE expr]
[GROUP BY expr_list] [WITH TOTALS]
[GROUP BY expr_list] [WITH ROLLUP|WITH CUBE] [WITH TOTALS]
[HAVING expr]
[ORDER BY expr_list] [WITH FILL] [FROM expr] [TO expr] [STEP expr]
[LIMIT [offset_value, ]n BY columns]

8
docs/zh/getting-started/playground.md
View File

@ -21,15 +21,15 @@ toc_title: "\u266A\u64CD\u573A\u266A"
ClickHouse体验还有如下：
[ClickHouse管理服务](https://cloud.yandex.com/services/managed-clickhouse)
实例托管 [Yandex云](https://cloud.yandex.com/).
更多信息 [云提供商](../commercial/cloud.md).
实例托管 [Yandex云](https://cloud.yandex.com/)。
更多信息 [云提供商](../commercial/cloud.md)。
ClickHouse体验平台界面实际上是通过ClickHouse [HTTP API](../interfaces/http.md)接口实现的.
体验平台后端只是一个ClickHouse集群，没有任何额外的服务器端应用程序。
体验平台也同样提供了ClickHouse HTTPS服务端口。
您可以使用任何HTTP客户端向体验平台进行查询，例如 [curl](https://curl.haxx.se) 或 [wget](https://www.gnu.org/software/wget/)，或使用以下方式建立连接 [JDBC](../interfaces/jdbc.md) 或 [ODBC](../interfaces/odbc.md) 司机
有关支持ClickHouse的软件产品的更多信息，请访问 [这里](../interfaces/index.md).
您可以使用任何HTTP客户端向体验平台进行查询，例如 [curl](https://curl.haxx.se) 或 [wget](https://www.gnu.org/software/wget/)，或使用以下方式建立连接 [JDBC](../interfaces/jdbc.md) 或 [ODBC](../interfaces/odbc.md) 驱动。
有关支持ClickHouse的软件产品的更多信息，请访问 [这里](../interfaces/index.md)。
| 参数 | 值 |
|:---------|:--------------------------------------|

8
docs/zh/operations/monitoring.md
View File

@ -33,10 +33,10 @@ ClickHouse 收集的指标项：
- 服务用于计算的资源占用的各种指标。
- 关于查询处理的常见统计信息。
可以在 [系统指标](system-tables/metrics.md#system_tables-metrics) ，[系统事件](system-tables/events.md#system_tables-events) 以及[系统异步指标](system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) 等系统表查看所有的指标项。
可以在[系统指标](system-tables/metrics.md#system_tables-metrics)，[系统事件](system-tables/events.md#system_tables-events)以及[系统异步指标](system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics)等系统表查看所有的指标项。
可以配置ClickHouse 往 [石墨](https://github.com/graphite-project)导入指标。 参考 [石墨部分](server-configuration-parameters/settings.md#server_configuration_parameters-graphite) 配置文件。在配置指标导出之前，需要参考Graphite[官方教程](https://graphite.readthedocs.io/en/latest/install.html)搭建服务。
可以配置ClickHouse向[Graphite](https://github.com/graphite-project)推送监控信息并导入指标。参考[Graphite监控](server-configuration-parameters/settings.md#server_configuration_parameters-graphite)配置文件。在配置指标导出之前，需要参考[Graphite官方教程](https://graphite.readthedocs.io/en/latest/install.html)搭建Graphite服务。
此外，您可以通过HTTP API监视服务器可用性。 将HTTP GET请求发送到 `/ping`。 如果服务器可用，它将以 `200 OK` 响应。
此外，您可以通过HTTP API监视服务器可用性。将HTTP GET请求发送到`/ping`。如果服务器可用，它将以 `200 OK` 响应。
要监视服务器集群的配置，应设置[max_replica_delay_for_distributed_queries](settings/settings.md#settings-max_replica_delay_for_distributed_queries)参数并使用HTTP资源`/replicas_status`。 如果副本可用，并且不延迟在其他副本之后，则对`/replicas_status`的请求将返回200 OK。 如果副本滞后，请求将返回 `503 HTTP_SERVICE_UNAVAILABLE`，包括有关待办事项大小的信息。
要监视服务器集群的配置，应设置[max_replica_delay_for_distributed_queries](settings/settings.md#settings-max_replica_delay_for_distributed_queries)参数并使用HTTP资源`/replicas_status`。 如果副本可用，并且不延迟在其他副本之后，则对`/replicas_status`的请求将返回`200 OK`。 如果副本滞后，请求将返回`503 HTTP_SERVICE_UNAVAILABLE`，包括有关待办事项大小的信息。

2
docs/zh/sql-reference/functions/bitmap-functions.md
View File

@ -6,7 +6,7 @@
我们使用RoaringBitmap实际存储位图对象，当基数小于或等于32时，它使用Set保存。当基数大于32时，它使用RoaringBitmap保存。这也是为什么低基数集的存储更快的原因。
有关RoaringBitmap的更多信息，请参阅：[呻吟声](https://github.com/RoaringBitmap/CRoaring)。
有关RoaringBitmap的更多信息，请参阅：[RoaringBitmap](https://github.com/RoaringBitmap/CRoaring)。
## bitmapBuild {#bitmapbuild}

2
programs/CMakeLists.txt
View File

@ -112,6 +112,8 @@ add_subdirectory (obfuscator)
add_subdirectory (install)
add_subdirectory (git-import)
#add_subdirectory (grpc-client)
if (ENABLE_CLICKHOUSE_ODBC_BRIDGE)
add_subdirectory (odbc-bridge)
endif ()

4
programs/client/Client.cpp
View File

@ -2515,7 +2515,7 @@ public:
{
std::string traceparent = options["opentelemetry-traceparent"].as<std::string>();
std::string error;
if (!context.getClientInfo().parseTraceparentHeader(
if (!context.getClientInfo().client_trace_context.parseTraceparentHeader(
traceparent, error))
{
throw Exception(ErrorCodes::BAD_ARGUMENTS,
@ -2526,7 +2526,7 @@ public:
if (options.count("opentelemetry-tracestate"))
{
context.getClientInfo().opentelemetry_tracestate =
context.getClientInfo().client_trace_context.tracestate =
options["opentelemetry-tracestate"].as<std::string>();
}

26
programs/copier/ClusterCopier.cpp
View File

@ -62,6 +62,9 @@ decltype(auto) ClusterCopier::retry(T && func, UInt64 max_tries)
{
std::exception_ptr exception;
if (max_tries == 0)
throw Exception("Cannot perform zero retries", ErrorCodes::LOGICAL_ERROR);
for (UInt64 try_number = 1; try_number <= max_tries; ++try_number)
{
try
@ -605,7 +608,7 @@ TaskStatus ClusterCopier::tryMoveAllPiecesToDestinationTable(const TaskTable & t
settings_push.replication_alter_partitions_sync = 2;
query_alter_ast_string += " ALTER TABLE " + getQuotedTable(original_table) +
" ATTACH PARTITION " + partition_name +
((partition_name == "'all'") ? " ATTACH PARTITION ID " : " ATTACH PARTITION ") + partition_name +
" FROM " + getQuotedTable(helping_table);
LOG_DEBUG(log, "Executing ALTER query: {}", query_alter_ast_string);
@ -636,7 +639,7 @@ TaskStatus ClusterCopier::tryMoveAllPiecesToDestinationTable(const TaskTable & t
if (!task_table.isReplicatedTable())
{
query_deduplicate_ast_string += " OPTIMIZE TABLE " + getQuotedTable(original_table) +
" PARTITION " + partition_name + " DEDUPLICATE;";
((partition_name == "'all'") ? " PARTITION ID " : " PARTITION ") + partition_name + " DEDUPLICATE;";
LOG_DEBUG(log, "Executing OPTIMIZE DEDUPLICATE query: {}", query_alter_ast_string);
@ -807,7 +810,7 @@ bool ClusterCopier::tryDropPartitionPiece(
DatabaseAndTableName helping_table = DatabaseAndTableName(original_table.first, original_table.second + "_piece_" + toString(current_piece_number));
String query = "ALTER TABLE " + getQuotedTable(helping_table);
query += " DROP PARTITION " + task_partition.name + "";
query += ((task_partition.name == "'all'") ? " DROP PARTITION ID " : " DROP PARTITION ") + task_partition.name + "";
/// TODO: use this statement after servers will be updated up to 1.1.54310
// query += " DROP PARTITION ID '" + task_partition.name + "'";
@ -1567,7 +1570,7 @@ void ClusterCopier::dropParticularPartitionPieceFromAllHelpingTables(const TaskT
DatabaseAndTableName original_table = task_table.table_push;
DatabaseAndTableName helping_table = DatabaseAndTableName(original_table.first, original_table.second + "_piece_" + toString(current_piece_number));
String query = "ALTER TABLE " + getQuotedTable(helping_table) + " DROP PARTITION " + partition_name;
String query = "ALTER TABLE " + getQuotedTable(helping_table) + ((partition_name == "'all'") ? " DROP PARTITION ID " : " DROP PARTITION ") + partition_name;
const ClusterPtr & cluster_push = task_table.cluster_push;
Settings settings_push = task_cluster->settings_push;
@ -1670,14 +1673,24 @@ void ClusterCopier::createShardInternalTables(const ConnectionTimeouts & timeout
std::set<String> ClusterCopier::getShardPartitions(const ConnectionTimeouts & timeouts, TaskShard & task_shard)
{
std::set<String> res;
createShardInternalTables(timeouts, task_shard, false);
TaskTable & task_table = task_shard.task_table;
const String & partition_name = queryToString(task_table.engine_push_partition_key_ast);
if (partition_name == "'all'")
{
res.emplace("'all'");
return res;
}
String query;
{
WriteBufferFromOwnString wb;
wb << "SELECT DISTINCT " << queryToString(task_table.engine_push_partition_key_ast) << " AS partition FROM"
wb << "SELECT DISTINCT " << partition_name << " AS partition FROM"
<< " " << getQuotedTable(task_shard.table_read_shard) << " ORDER BY partition DESC";
query = wb.str();
}
@ -1692,7 +1705,6 @@ std::set<String> ClusterCopier::getShardPartitions(const ConnectionTimeouts & ti
local_context.setSettings(task_cluster->settings_pull);
Block block = getBlockWithAllStreamData(InterpreterFactory::get(query_ast, local_context)->execute().getInputStream());
std::set<String> res;
if (block)
{
ColumnWithTypeAndName & column = block.getByPosition(0);
@ -1803,7 +1815,7 @@ UInt64 ClusterCopier::executeQueryOnCluster(
if (execution_mode == ClusterExecutionMode::ON_EACH_NODE)
max_successful_executions_per_shard = 0;
std::atomic<size_t> origin_replicas_number;
std::atomic<size_t> origin_replicas_number = 0;
/// We need to execute query on one replica at least
auto do_for_shard = [&] (UInt64 shard_index, Settings shard_settings)

7
programs/grpc-client/CMakeLists.txt Normal file
View File

@ -0,0 +1,7 @@
include_directories(${CMAKE_CURRENT_BINARY_DIR})
get_filename_component(rpc_proto "${CMAKE_CURRENT_SOURCE_DIR}/../server/grpc_protos/GrpcConnection.proto" ABSOLUTE)
protobuf_generate_cpp(PROTO_SRCS PROTO_HDRS ${rpc_proto})
PROTOBUF_GENERATE_GRPC_CPP(GRPC_SRCS GRPC_HDRS ${rpc_proto})
add_executable(grpc-client grpc_client.cpp ${PROTO_SRCS} ${PROTO_HDRS} ${GRPC_SRCS} ${GRPC_HDRS})
target_link_libraries(grpc-client PUBLIC grpc++ PUBLIC libprotobuf PUBLIC daemon)

173
programs/grpc-client/grpc_client.cpp Normal file
View File

@ -0,0 +1,173 @@
#include <iostream>
#include <memory>
#include <string>
#include <vector>
#include <thread>
#include <stdlib.h>
#include <grpc++/channel.h>
#include <grpc++/client_context.h>
#include <grpc++/create_channel.h>
#include <grpc++/security/credentials.h>
#include "GrpcConnection.grpc.pb.h"
class GRPCClient
{
public:
explicit GRPCClient(std::shared_ptr<grpc::Channel> channel)
: stub_(GRPCConnection::GRPC::NewStub(channel))
{}
std::string Query(const GRPCConnection::User& userInfo,
const std::string& query,
std::vector<std::string> insert_data = {})
{
GRPCConnection::QueryRequest request;
grpc::Status status;
GRPCConnection::QueryResponse reply;
grpc::ClientContext context;
auto deadline = std::chrono::system_clock::now() + std::chrono::milliseconds(10000);
context.set_deadline(deadline);
auto user = std::make_unique<GRPCConnection::User>(userInfo);
auto querySettigs = std::make_unique<GRPCConnection::QuerySettings>();
int id = rand();
request.set_allocated_user_info(user.release());
// interactive_delay in miliseconds
request.set_interactive_delay(1000);
querySettigs->set_query(query);
querySettigs->set_format("Values");
querySettigs->set_query_id(std::to_string(id));
querySettigs->set_data_stream((insert_data.size() != 0));
(*querySettigs->mutable_settings())["max_query_size"] ="100";
request.set_allocated_query_info(querySettigs.release());
void* got_tag = (void*)1;
bool ok = false;
std::unique_ptr<grpc::ClientReaderWriter<GRPCConnection::QueryRequest, GRPCConnection::QueryResponse> > reader(stub_->Query(&context));
reader->Write(request);
auto write = [&reply, &reader, &insert_data]()
{
GRPCConnection::QueryRequest request_insert;
for (const auto& data : insert_data)
{
request_insert.set_insert_data(data);
if (reply.exception_occured().empty())
{
reader->Write(request_insert);
}
else
{
break;
}
}
request_insert.set_insert_data("");
if (reply.exception_occured().empty())
{
reader->Write(request_insert);
}
// reader->WritesDone();
};
std::thread write_thread(write);
write_thread.detach();
while (reader->Read(&reply))
{
if (!reply.output().empty())
{
std::cout << "Query Part:\n " << id<< reply.output()<<'\n';
}
else if (reply.progress().read_rows()
|| reply.progress().read_bytes()
|| reply.progress().total_rows_to_read()
|| reply.progress().written_rows()
|| reply.progress().written_bytes())
{
std::cout << "Progress " << id<< ":{\n" << "read_rows: " << reply.progress().read_rows() << '\n'
<< "read_bytes: " << reply.progress().read_bytes() << '\n'
<< "total_rows_to_read: " << reply.progress().total_rows_to_read() << '\n'
<< "written_rows: " << reply.progress().written_rows() << '\n'
<< "written_bytes: " << reply.progress().written_bytes() << '\n';
}
else if (!reply.totals().empty())
{
std::cout << "Totals:\n " << id << " " << reply.totals() <<'\n';
}
else if (!reply.extremes().empty())
{
std::cout << "Extremes:\n " << id << " " << reply.extremes() <<'\n';
}
}
if (status.ok() && reply.exception_occured().empty())
{
return "";
}
else if (status.ok() && !reply.exception_occured().empty())
{
return reply.exception_occured();
}
else
{
return "RPC failed";
}
}
private:
std::unique_ptr<GRPCConnection::GRPC::Stub> stub_;
};
int main(int argc, char** argv)
{
GRPCConnection::User userInfo1;
userInfo1.set_user("default");
userInfo1.set_password("");
userInfo1.set_quota("default");
std::cout << "Try: " << argv[1] << std::endl;
grpc::ChannelArguments ch_args;
ch_args.SetMaxReceiveMessageSize(-1);
GRPCClient client(
grpc::CreateCustomChannel(argv[1], grpc::InsecureChannelCredentials(), ch_args));
{
std::cout << client.Query(userInfo1, "CREATE TABLE t (a UInt8) ENGINE = Memory") << std::endl;
std::cout << client.Query(userInfo1, "CREATE TABLE t (a UInt8) ENGINE = Memory") << std::endl;
std::cout << client.Query(userInfo1, "INSERT INTO t VALUES", {"(1),(2),(3)", "(4),(6),(5)"}) << std::endl;
std::cout << client.Query(userInfo1, "INSERT INTO t_not_defined VALUES", {"(1),(2),(3)", "(4),(6),(5)"}) << std::endl;
std::cout << client.Query(userInfo1, "SELECT a FROM t ORDER BY a") << std::endl;
std::cout << client.Query(userInfo1, "DROP TABLE t") << std::endl;
}
{
std::cout << client.Query(userInfo1, "SELECT count() FROM numbers(1)") << std::endl;
std::cout << client.Query(userInfo1, "SELECT 100") << std::endl;
std::cout << client.Query(userInfo1, "SELECT count() FROM numbers(10000000000)") << std::endl;
std::cout << client.Query(userInfo1, "SELECT count() FROM numbers(100)") << std::endl;
}
{
std::cout << client.Query(userInfo1, "CREATE TABLE arrays_test (s String, arr Array(UInt8)) ENGINE = Memory;") << std::endl;
std::cout << client.Query(userInfo1, "INSERT INTO arrays_test VALUES ('Hello', [1,2]), ('World', [3,4,5]), ('Goodbye', []);") << std::endl;
std::cout << client.Query(userInfo1, "SELECT s FROM arrays_test") << std::endl;
std::cout << client.Query(userInfo1, "DROP TABLE arrays_test") << std::endl;
std::cout << client.Query(userInfo1, "") << std::endl;
}
{//Check null return from pipe
std::cout << client.Query(userInfo1, "CREATE TABLE table2 (x UInt8, y UInt8) ENGINE = Memory;") << std::endl;
std::cout << client.Query(userInfo1, "SELECT x FROM table2") << std::endl;
std::cout << client.Query(userInfo1, "DROP TABLE table2") << std::endl;
}
{//Check Totals
std::cout << client.Query(userInfo1, "CREATE TABLE tabl (x UInt8, y UInt8) ENGINE = Memory;") << std::endl;
std::cout << client.Query(userInfo1, "INSERT INTO tabl VALUES (1, 2), (2, 4), (3, 2), (3, 3), (3, 4);") << std::endl;
std::cout << client.Query(userInfo1, "SELECT sum(x), y FROM tabl GROUP BY y WITH TOTALS") << std::endl;
std::cout << client.Query(userInfo1, "DROP TABLE tabl") << std::endl;
}
return 0;
}

29
programs/odbc-bridge/ODBCBridge.cpp
View File

@ -109,6 +109,14 @@ void ODBCBridge::defineOptions(Poco::Util::OptionSet & options)
.argument("err-log-path")
.binding("logger.errorlog"));
options.addOption(Poco::Util::Option("stdout-path", "", "stdout log path, default console")
.argument("stdout-path")
.binding("logger.stdout"));
options.addOption(Poco::Util::Option("stderr-path", "", "stderr log path, default console")
.argument("stderr-path")
.binding("logger.stderr"));
using Me = std::decay_t<decltype(*this)>;
options.addOption(Poco::Util::Option("help", "", "produce this help message")
.binding("help")
@ -127,6 +135,27 @@ void ODBCBridge::initialize(Application & self)
config().setString("logger", "ODBCBridge");
/// Redirect stdout, stderr to specified files.
/// Some libraries and sanitizers write to stderr in case of errors.
const auto stdout_path = config().getString("logger.stdout", "");
if (!stdout_path.empty())
{
if (!freopen(stdout_path.c_str(), "a+", stdout))
throw Poco::OpenFileException("Cannot attach stdout to " + stdout_path);
/// Disable buffering for stdout.
setbuf(stdout, nullptr);
}
const auto stderr_path = config().getString("logger.stderr", "");
if (!stderr_path.empty())
{
if (!freopen(stderr_path.c_str(), "a+", stderr))
throw Poco::OpenFileException("Cannot attach stderr to " + stderr_path);
/// Disable buffering for stderr.
setbuf(stderr, nullptr);
}
buildLoggers(config(), logger(), self.commandName());
BaseDaemon::logRevision();

25
programs/server/Server.cpp
View File

@ -64,6 +64,7 @@
#include <Common/ThreadFuzzer.h>
#include <Server/MySQLHandlerFactory.h>
#include <Server/PostgreSQLHandlerFactory.h>
#include <Server/ProtocolServerAdapter.h>
#if !defined(ARCADIA_BUILD)
@ -84,6 +85,11 @@
# include <Poco/Net/SecureServerSocket.h>
#endif
#if USE_GRPC
# include <Server/GRPCServer.h>
#endif
namespace CurrentMetrics
{
extern const Metric Revision;
@ -806,7 +812,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
http_params->setTimeout(settings.http_receive_timeout);
http_params->setKeepAliveTimeout(keep_alive_timeout);
std::vector<std::unique_ptr<Poco::Net::TCPServer>> servers;
std::vector<ProtocolServerAdapter> servers;
std::vector<std::string> listen_hosts = DB::getMultipleValuesFromConfig(config(), "", "listen_host");
@ -1035,6 +1041,15 @@ int Server::main(const std::vector<std::string> & /*args*/)
LOG_INFO(log, "Listening for PostgreSQL compatibility protocol: " + address.toString());
});
#if USE_GRPC
create_server("grpc_port", [&](UInt16 port)
{
Poco::Net::SocketAddress server_address(listen_host, port);
servers.emplace_back(std::make_unique<GRPCServer>(*this, make_socket_address(listen_host, port)));
LOG_INFO(log, "Listening for gRPC protocol: " + server_address.toString());
});
#endif
/// Prometheus (if defined and not setup yet with http_port)
create_server("prometheus.port", [&](UInt16 port)
{
@ -1056,7 +1071,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
global_context->enableNamedSessions();
for (auto & server : servers)
server->start();
server.start();
{
String level_str = config().getString("text_log.level", "");
@ -1088,8 +1103,8 @@ int Server::main(const std::vector<std::string> & /*args*/)
int current_connections = 0;
for (auto & server : servers)
{
server->stop();
current_connections += server->currentConnections();
server.stop();
current_connections += server.currentConnections();
}
if (current_connections)
@ -1109,7 +1124,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
{
current_connections = 0;
for (auto & server : servers)
current_connections += server->currentConnections();
current_connections += server.currentConnections();
if (!current_connections)
break;
sleep_current_ms += sleep_one_ms;

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

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

31
programs/server/config.xml
View File

@ -11,6 +11,9 @@
<level>trace</level>
<log>/var/log/clickhouse-server/clickhouse-server.log</log>
<errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
<!-- Rotation policy
See https://github.com/pocoproject/poco/blob/poco-1.9.4-release/Foundation/include/Poco/FileChannel.h#L54-L85
-->
<size>1000M</size>
<count>10</count>
<!-- <console>1</console> --> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
@ -131,6 +134,34 @@
<max_connections>4096</max_connections>
<keep_alive_timeout>3</keep_alive_timeout>
<!-- gRPC protocol (see src/Server/grpc_protos/clickhouse_grpc.proto for the API)
<grpc_port>9001</grpc_port>
<grpc>
<enable_ssl>true</enable_ssl> -->
<!-- The following two files are used only if enable_ssl=1
<ssl_cert_file>/path/to/ssl_cert_file</ssl_cert_file>
<ssl_key_file>/path/to/ssl_key_file</ssl_key_file> -->
<!-- Whether server will request client for a certificate
<ssl_require_client_auth>true</ssl_require_client_auth> -->
<!-- The following file is used only if ssl_require_client_auth=1
<ssl_ca_cert_file>/path/to/ssl_ca_cert_file</ssl_ca_cert_file> -->
<!-- Default compression algorithm (applied if client doesn't specify another algorithm).
Supported algorithms: none, deflate, gzip, stream_gzip
<compression>gzip</compression> -->
<!-- Default compression level (applied if client doesn't specify another level).
Supported levels: none, low, medium, high
<compression_level>high</compression_level> -->
<!-- Send/receive message size limits in bytes. -1 means unlimited
<max_send_message_size>-1</max_send_message_size>
<max_receive_message_size>4194304</max_receive_message_size>
</grpc> -->
<!-- Maximum number of concurrent queries. -->
<max_concurrent_queries>100</max_concurrent_queries>

146
programs/server/play.html
View File

@ -1,6 +1,7 @@
<html> <!-- TODO If I write DOCTYPE HTML something changes but I don't know what. -->
<head>
<meta charset="UTF-8">
<link rel="icon" href="data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSI1NCIgaGVpZ2h0PSI0OCIgdmlld0JveD0iMCAwIDkgOCI+PHN0eWxlPi5ve2ZpbGw6I2ZjMH0ucntmaWxsOnJlZH08L3N0eWxlPjxwYXRoIGQ9Ik0wLDcgaDEgdjEgaC0xIHoiIGNsYXNzPSJyIi8+PHBhdGggZD0iTTAsMCBoMSB2NyBoLTEgeiIgY2xhc3M9Im8iLz48cGF0aCBkPSJNMiwwIGgxIHY4IGgtMSB6IiBjbGFzcz0ibyIvPjxwYXRoIGQ9Ik00LDAgaDEgdjggaC0xIHoiIGNsYXNzPSJvIi8+PHBhdGggZD0iTTYsMCBoMSB2OCBoLTEgeiIgY2xhc3M9Im8iLz48cGF0aCBkPSJNOCwzLjI1IGgxIHYxLjUgaC0xIHoiIGNsYXNzPSJvIi8+PC9zdmc+">
<title>ClickHouse Query</title>
<!-- Code Style:
@ -21,26 +22,11 @@
<!-- Development Roadmap:
1. Add indication that the query was sent and when the query has been finished.
Do not use any animated spinners. Just a text or check mark.
Eliminate race conditions (results from the previous query should be ignored on arrival, the previous request should be cancelled).
2. Support readonly servers.
1. Support readonly servers.
Check if readonly = 1 (with SELECT FROM system.settings) to avoid sending settings. It can be done once on address/credentials change.
It can be done in background, e.g. wait 100 ms after address/credentials change and do the check.
Also it can provide visual indication that credentials are correct.
3. Add history in localstorage. Integrate with history API.
There can be a counter in localstorage, that will be appended to location #fragment.
The 'back', 'forward' buttons in browser should work.
Also there should be UI element to list all the queries from history and select from the list.
4. Trivial sharing capabilities.
Sharing is only possible when system.query_log is accessible. Read the X-ClickHouse-QueryId from the response.
Share button will: - emit SYSTEM FLUSH LOGS if not readonly; - find the query in the query_log;
- generate an URL with the query id and: server address if not equal to the URL's host; user name if not default;
indication that password should be entered in case of non-empty password.
-->
<style type="text/css">
@ -273,6 +259,22 @@
{
color: var(--null-color);
}
#hourglass
{
display: none;
padding-left: 1rem;
font-size: 110%;
color: #888;
}
#check-mark
{
display: none;
padding-left: 1rem;
font-size: 110%;
color: #080;
}
</style>
</head>
@ -286,6 +288,8 @@
<div id="run_div">
<button class="shadow" id="run">Run</button>
<span class="hint">&nbsp;(Ctrl+Enter)</span>
<span id="hourglass">⧗</span>
<span id="check-mark">✔</span>
<span id="stats"></span>
<span id="toggle-dark">🌑</span><span id="toggle-light">🌞</span>
</div>
@ -299,50 +303,117 @@
<script type="text/javascript">
/// Incremental request number. When response is received,
/// if it's request number does not equal to the current request number, response will be ignored.
/// This is to avoid race conditions.
var request_num = 0;
/// Save query in history only if it is different.
var previous_query = '';
/// Substitute the address of the server where the page is served.
if (location.protocol != 'file:') {
document.getElementById('url').value = location.origin;
}
function post()
/// Substitute user name if it's specified in the query string
var user_from_url = (new URL(window.location)).searchParams.get('user');
if (user_from_url) {
document.getElementById('user').value = user_from_url;
}
function postImpl(posted_request_num, query)
{
/// TODO: Avoid race condition on subsequent requests when responses may come out of order.
/// TODO: Check if URL already contains query string (append parameters).
var user = document.getElementById('user').value;
var password = document.getElementById('password').value;
var url = document.getElementById('url').value +
/// Ask server to allow cross-domain requests.
'?add_http_cors_header=1' +
'&user=' + encodeURIComponent(document.getElementById('user').value) +
'&password=' + encodeURIComponent(document.getElementById('password').value) +
'&user=' + encodeURIComponent(user) +
'&password=' + encodeURIComponent(password) +
'&default_format=JSONCompact' +
/// Safety settings to prevent results that browser cannot display.
'&max_result_rows=1000&max_result_bytes=10000000&result_overflow_mode=break';
var query = document.getElementById('query').value;
var xhr = new XMLHttpRequest;
xhr.open('POST', url, true);
xhr.send(query);
xhr.onreadystatechange = function()
{
if (this.readyState === XMLHttpRequest.DONE) {
if (this.status === 200) {
var json;
try { json = JSON.parse(this.response); } catch (e) {}
if (json !== undefined && json.statistics !== undefined) {
renderResult(json);
} else {
renderUnparsedResult(this.response);
}
} else {
/// TODO: Proper rendering of network errors.
renderError(this.response);
if (posted_request_num != request_num) {
return;
} else if (this.readyState === XMLHttpRequest.DONE) {
renderResponse(this.status, this.response);
/// The query is saved in browser history (in state JSON object)
/// as well as in URL fragment identifier.
if (query != previous_query) {
previous_query = query;
var title = "ClickHouse Query: " + query;
history.pushState(
{
query: query,
status: this.status,
response: this.response.length > 100000 ? null : this.response /// Lower than the browser's limit.
},
title,
window.location.pathname + '?user=' + encodeURIComponent(user) + '#' + window.btoa(query));
document.title = title;
}
} else {
//console.log(this);
}
}
document.getElementById('check-mark').style.display = 'none';
document.getElementById('hourglass').style.display = 'inline';
xhr.send(query);
}
function renderResponse(status, response) {
document.getElementById('hourglass').style.display = 'none';
if (status === 200) {
var json;
try { json = JSON.parse(response); } catch (e) {}
if (json !== undefined && json.statistics !== undefined) {
renderResult(json);
} else {
renderUnparsedResult(response);
}
document.getElementById('check-mark').style.display = 'inline';
} else {
/// TODO: Proper rendering of network errors.
renderError(response);
}
}
window.onpopstate = function(event) {
if (!event.state) {
return;
}
document.getElementById('query').value = event.state.query;
if (!event.state.response) {
clear();
return;
}
renderResponse(event.state.status, event.state.response);
};
if (window.location.hash) {
document.getElementById('query').value = window.atob(window.location.hash.substr(1));
}
function post()
{
++request_num;
var query = document.getElementById('query').value;
postImpl(request_num, query);
}
document.getElementById('run').onclick = function()
@ -350,7 +421,7 @@
post();
}
document.getElementById('query').onkeypress = function(event)
document.onkeypress = function(event)
{
/// Firefox has code 13 for Enter and Chromium has code 10.
if (event.ctrlKey && (event.charCode == 13 || event.charCode == 10)) {
@ -372,6 +443,9 @@
document.getElementById('error').style.display = 'none';
document.getElementById('stats').innerText = '';
document.getElementById('hourglass').style.display = 'none';
document.getElementById('check-mark').style.display = 'none';
}
function renderResult(response)
@ -443,7 +517,7 @@
function renderError(response)
{
clear();
document.getElementById('error').innerText = response;
document.getElementById('error').innerText = response ? response : "No response.";
document.getElementById('error').style.display = 'block';
}

2
src/AggregateFunctions/AggregateFunctionGroupArrayInsertAt.h
View File

@ -80,7 +80,7 @@ public:
}
if (!isUnsignedInteger(arguments[1]))
throw Exception("Second argument of aggregate function " + getName() + " must be integer.", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
throw Exception("Second argument of aggregate function " + getName() + " must be unsigned integer.", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
if (default_value.isNull())
default_value = type->getDefault();

32
src/AggregateFunctions/AggregateFunctionMLMethod.cpp
View File

@ -143,7 +143,7 @@ void LinearModelData::updateState()
void LinearModelData::predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const Context & context) const
@ -264,8 +264,8 @@ void Adam::merge(const IWeightsUpdater & rhs, Float64 frac, Float64 rhs_frac)
average_gradient[i] = average_gradient[i] * frac + adam_rhs.average_gradient[i] * rhs_frac;
average_squared_gradient[i] = average_squared_gradient[i] * frac + adam_rhs.average_squared_gradient[i] * rhs_frac;
}
beta1_powered_ *= adam_rhs.beta1_powered_;
beta2_powered_ *= adam_rhs.beta2_powered_;
beta1_powered *= adam_rhs.beta1_powered;
beta2_powered *= adam_rhs.beta2_powered;
}
void Adam::update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient)
@ -282,21 +282,21 @@ void Adam::update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & b
for (size_t i = 0; i != average_gradient.size(); ++i)
{
Float64 normed_gradient = batch_gradient[i] / batch_size;
average_gradient[i] = beta1_ * average_gradient[i] + (1 - beta1_) * normed_gradient;
average_squared_gradient[i] = beta2_ * average_squared_gradient[i] +
(1 - beta2_) * normed_gradient * normed_gradient;
average_gradient[i] = beta1 * average_gradient[i] + (1 - beta1) * normed_gradient;
average_squared_gradient[i] = beta2 * average_squared_gradient[i] +
(1 - beta2) * normed_gradient * normed_gradient;
}
for (size_t i = 0; i < weights.size(); ++i)
{
weights[i] += (learning_rate * average_gradient[i]) /
((1 - beta1_powered_) * (sqrt(average_squared_gradient[i] / (1 - beta2_powered_)) + eps_));
((1 - beta1_powered) * (sqrt(average_squared_gradient[i] / (1 - beta2_powered)) + eps));
}
bias += (learning_rate * average_gradient[weights.size()]) /
((1 - beta1_powered_) * (sqrt(average_squared_gradient[weights.size()] / (1 - beta2_powered_)) + eps_));
((1 - beta1_powered) * (sqrt(average_squared_gradient[weights.size()] / (1 - beta2_powered)) + eps));
beta1_powered_ *= beta1_;
beta2_powered_ *= beta2_;
beta1_powered *= beta1;
beta2_powered *= beta2;
}
void Adam::addToBatch(
@ -348,7 +348,7 @@ void Nesterov::update(UInt64 batch_size, std::vector<Float64> & weights, Float64
for (size_t i = 0; i < batch_gradient.size(); ++i)
{
accumulated_gradient[i] = accumulated_gradient[i] * alpha_ + (learning_rate * batch_gradient[i]) / batch_size;
accumulated_gradient[i] = accumulated_gradient[i] * alpha + (learning_rate * batch_gradient[i]) / batch_size;
}
for (size_t i = 0; i < weights.size(); ++i)
{
@ -375,9 +375,9 @@ void Nesterov::addToBatch(
std::vector<Float64> shifted_weights(weights.size());
for (size_t i = 0; i != shifted_weights.size(); ++i)
{
shifted_weights[i] = weights[i] + accumulated_gradient[i] * alpha_;
shifted_weights[i] = weights[i] + accumulated_gradient[i] * alpha;
}
auto shifted_bias = bias + accumulated_gradient[weights.size()] * alpha_;
auto shifted_bias = bias + accumulated_gradient[weights.size()] * alpha;
gradient_computer.compute(batch_gradient, shifted_weights, shifted_bias, l2_reg_coef, target, columns, row_num);
}
@ -411,7 +411,7 @@ void Momentum::update(UInt64 batch_size, std::vector<Float64> & weights, Float64
for (size_t i = 0; i < batch_gradient.size(); ++i)
{
accumulated_gradient[i] = accumulated_gradient[i] * alpha_ + (learning_rate * batch_gradient[i]) / batch_size;
accumulated_gradient[i] = accumulated_gradient[i] * alpha + (learning_rate * batch_gradient[i]) / batch_size;
}
for (size_t i = 0; i < weights.size(); ++i)
{
@ -448,7 +448,7 @@ void IWeightsUpdater::addToBatch(
void LogisticRegression::predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const std::vector<Float64> & weights,
@ -516,7 +516,7 @@ void LogisticRegression::compute(
void LinearRegression::predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const std::vector<Float64> & weights,

44
src/AggregateFunctions/AggregateFunctionMLMethod.h
View File

@ -23,7 +23,7 @@ GradientComputer class computes gradient according to its loss function
class IGradientComputer
{
public:
IGradientComputer() {}
IGradientComputer() = default;
virtual ~IGradientComputer() = default;
@ -39,7 +39,7 @@ public:
virtual void predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const std::vector<Float64> & weights,
@ -51,7 +51,7 @@ public:
class LinearRegression : public IGradientComputer
{
public:
LinearRegression() {}
LinearRegression() = default;
void compute(
std::vector<Float64> & batch_gradient,
@ -64,7 +64,7 @@ public:
void predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const std::vector<Float64> & weights,
@ -76,7 +76,7 @@ public:
class LogisticRegression : public IGradientComputer
{
public:
LogisticRegression() {}
LogisticRegression() = default;
void compute(
std::vector<Float64> & batch_gradient,
@ -89,7 +89,7 @@ public:
void predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const std::vector<Float64> & weights,
@ -147,9 +147,9 @@ public:
class Momentum : public IWeightsUpdater
{
public:
Momentum() {}
Momentum() = default;
Momentum(Float64 alpha) : alpha_(alpha) {}
explicit Momentum(Float64 alpha_) : alpha(alpha_) {}
void update(UInt64 batch_size, std::vector<Float64> & weights, Float64 & bias, Float64 learning_rate, const std::vector<Float64> & batch_gradient) override;
@ -160,7 +160,7 @@ public:
void read(ReadBuffer & buf) override;
private:
Float64 alpha_{0.1};
Float64 alpha{0.1};
std::vector<Float64> accumulated_gradient;
};
@ -168,9 +168,9 @@ private:
class Nesterov : public IWeightsUpdater
{
public:
Nesterov() {}
Nesterov() = default;
Nesterov(Float64 alpha) : alpha_(alpha) {}
explicit Nesterov(Float64 alpha_) : alpha(alpha_) {}
void addToBatch(
std::vector<Float64> & batch_gradient,
@ -191,7 +191,7 @@ public:
void read(ReadBuffer & buf) override;
private:
const Float64 alpha_ = 0.9;
const Float64 alpha = 0.9;
std::vector<Float64> accumulated_gradient;
};
@ -201,8 +201,8 @@ class Adam : public IWeightsUpdater
public:
Adam()
{
beta1_powered_ = beta1_;
beta2_powered_ = beta2_;
beta1_powered = beta1;
beta2_powered = beta2;
}
void addToBatch(
@ -225,11 +225,11 @@ public:
private:
/// beta1 and beta2 hyperparameters have such recommended values
const Float64 beta1_ = 0.9;
const Float64 beta2_ = 0.999;
const Float64 eps_ = 0.000001;
Float64 beta1_powered_;
Float64 beta2_powered_;
const Float64 beta1 = 0.9;
const Float64 beta2 = 0.999;
const Float64 eps = 0.000001;
Float64 beta1_powered;
Float64 beta2_powered;
std::vector<Float64> average_gradient;
std::vector<Float64> average_squared_gradient;
@ -241,7 +241,7 @@ private:
class LinearModelData
{
public:
LinearModelData() {}
LinearModelData() = default;
LinearModelData(
Float64 learning_rate_,
@ -261,7 +261,7 @@ public:
void predict(
ColumnVector<Float64>::Container & container,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const Context & context) const;
@ -360,7 +360,7 @@ public:
void predictValues(
ConstAggregateDataPtr place,
IColumn & to,
ColumnsWithTypeAndName & arguments,
const ColumnsWithTypeAndName & arguments,
size_t offset,
size_t limit,
const Context & context) const override

4
src/AggregateFunctions/IAggregateFunction.h
View File

@ -61,7 +61,7 @@ public:
throw Exception("Prediction is not supported for " + getName(), ErrorCodes::NOT_IMPLEMENTED);
}
virtual ~IAggregateFunction() {}
virtual ~IAggregateFunction() = default;
/** Data manipulating functions. */
@ -114,7 +114,7 @@ public:
virtual void predictValues(
ConstAggregateDataPtr /* place */,
IColumn & /*to*/,
ColumnsWithTypeAndName & /*arguments*/,
const ColumnsWithTypeAndName & /*arguments*/,
size_t /*offset*/,
size_t /*limit*/,
const Context & /*context*/) const

4
src/CMakeLists.txt
View File

@ -381,6 +381,10 @@ if (USE_PROTOBUF)
dbms_target_include_directories (SYSTEM BEFORE PRIVATE ${Protobuf_INCLUDE_DIR})
endif ()
if (USE_GRPC)
dbms_target_link_libraries (PUBLIC clickhouse_grpc_protos)
endif()
if (USE_HDFS)
target_link_libraries (clickhouse_common_io PUBLIC ${HDFS3_LIBRARY})
target_include_directories (clickhouse_common_io SYSTEM BEFORE PUBLIC ${HDFS3_INCLUDE_DIR})

6
src/Client/Connection.cpp
View File

@ -207,6 +207,12 @@ void Connection::receiveHello()
/// Receive hello packet.
UInt64 packet_type = 0;
/// Prevent read after eof in readVarUInt in case of reset connection
/// (Poco should throw such exception while reading from socket but
/// sometimes it doesn't for unknown reason)
if (in->eof())
throw Poco::Net::NetException("Connection reset by peer");
readVarUInt(packet_type, *in);
if (packet_type == Protocol::Server::Hello)
{

2
src/Columns/ColumnAggregateFunction.cpp
View File

@ -161,7 +161,7 @@ MutableColumnPtr ColumnAggregateFunction::convertToValues(MutableColumnPtr colum
return res;
}
MutableColumnPtr ColumnAggregateFunction::predictValues(ColumnsWithTypeAndName & arguments, const Context & context) const
MutableColumnPtr ColumnAggregateFunction::predictValues(const ColumnsWithTypeAndName & arguments, const Context & context) const
{
MutableColumnPtr res = func->getReturnTypeToPredict()->createColumn();
res->reserve(data.size());

2
src/Columns/ColumnAggregateFunction.h
View File

@ -119,7 +119,7 @@ public:
const char * getFamilyName() const override { return "AggregateFunction"; }
TypeIndex getDataType() const override { return TypeIndex::AggregateFunction; }
MutableColumnPtr predictValues(ColumnsWithTypeAndName & arguments, const Context & context) const;
MutableColumnPtr predictValues(const ColumnsWithTypeAndName & arguments, const Context & context) const;
size_t size() const override
{

3
src/Common/ErrorCodes.cpp
View File

@ -523,6 +523,9 @@
M(554, LZMA_STREAM_DECODER_FAILED) \
M(555, ROCKSDB_ERROR) \
M(556, SYNC_MYSQL_USER_ACCESS_ERROR)\
M(557, UNKNOWN_UNION) \
M(558, EXPECTED_ALL_OR_DISTINCT) \
M(559, INVALID_GRPC_QUERY_INFO) \
\
M(999, KEEPER_EXCEPTION) \
M(1000, POCO_EXCEPTION) \

21
src/Common/OpenTelemetryTraceContext.h Normal file
View File

@ -0,0 +1,21 @@
#pragma once
namespace DB
{
// The runtime info we need to create new OpenTelemetry spans.
struct OpenTelemetryTraceContext
{
__uint128_t trace_id = 0;
UInt64 span_id = 0;
// The incoming tracestate header and the trace flags, we just pass them
// downstream. See https://www.w3.org/TR/trace-context/
String tracestate;
__uint8_t trace_flags = 0;
// Parse/compose OpenTelemetry traceparent header.
bool parseTraceparentHeader(const std::string & traceparent, std::string & error);
std::string composeTraceparentHeader() const;
};
}

3
src/Common/ProfileEvents.cpp
View File

@ -97,9 +97,6 @@
M(DistributedConnectionStaleReplica, "") \
M(DistributedConnectionFailAtAll, "Total count when distributed connection fails after all retries finished") \
\
M(CompileAttempt, "Number of times a compilation of generated C++ code was initiated.") \
M(CompileSuccess, "Number of times a compilation of generated C++ code was successful.") \
\
M(CompileFunction, "Number of times a compilation of generated LLVM code (to create fused function for complex expressions) was initiated.") \
M(CompiledFunctionExecute, "Number of times a compiled function was executed.") \
M(CompileExpressionsMicroseconds, "Total time spent for compilation of expressions to LLVM code.") \

2
src/Common/QueryProfiler.cpp
View File

@ -176,7 +176,7 @@ template class QueryProfilerBase<QueryProfilerReal>;
template class QueryProfilerBase<QueryProfilerCpu>;
QueryProfilerReal::QueryProfilerReal(const UInt64 thread_id, const UInt32 period)
: QueryProfilerBase(thread_id, CLOCK_REALTIME, period, SIGUSR1)
: QueryProfilerBase(thread_id, CLOCK_MONOTONIC, period, SIGUSR1)
{}
void QueryProfilerReal::signalHandler(int sig, siginfo_t * info, void * context)

1
src/Common/ThreadStatus.cpp
View File

@ -2,6 +2,7 @@
#include <Common/ThreadProfileEvents.h>
#include <Common/QueryProfiler.h>
#include <Common/ThreadStatus.h>
#include <Interpreters/OpenTelemetrySpanLog.h>
#include <Poco/Logger.h>
#include <common/getThreadId.h>

85
src/Common/ThreadStatus.h
View File

@ -3,6 +3,7 @@
#include <common/StringRef.h>
#include <Common/ProfileEvents.h>
#include <Common/MemoryTracker.h>
#include <Common/OpenTelemetryTraceContext.h>
#include <Core/SettingsEnums.h>
@ -31,6 +32,7 @@ class ThreadStatus;
class QueryProfilerReal;
class QueryProfilerCpu;
class QueryThreadLog;
struct OpenTelemetrySpanHolder;
class TasksStatsCounters;
struct RUsageCounters;
struct PerfEventsCounters;
@ -86,9 +88,6 @@ extern thread_local ThreadStatus * current_thread;
class ThreadStatus : public boost::noncopyable
{
public:
ThreadStatus();
~ThreadStatus();
/// Linux's PID (or TGID) (the same id is shown by ps util)
const UInt64 thread_id = 0;
/// Also called "nice" value. If it was changed to non-zero (when attaching query) - will be reset to zero when query is detached.
@ -110,6 +109,52 @@ public:
using Deleter = std::function<void()>;
Deleter deleter;
// This is the current most-derived OpenTelemetry span for this thread. It
// can be changed throughout the query execution, whenever we enter a new
// span or exit it. See OpenTelemetrySpanHolder that is normally responsible
// for these changes.
OpenTelemetryTraceContext thread_trace_context;
protected:
ThreadGroupStatusPtr thread_group;
std::atomic<int> thread_state{ThreadState::DetachedFromQuery};
/// Is set once
Context * global_context = nullptr;
/// Use it only from current thread
Context * query_context = nullptr;
String query_id;
/// A logs queue used by TCPHandler to pass logs to a client
InternalTextLogsQueueWeakPtr logs_queue_ptr;
bool performance_counters_finalized = false;
UInt64 query_start_time_nanoseconds = 0;
UInt64 query_start_time_microseconds = 0;
time_t query_start_time = 0;
size_t queries_started = 0;
// CPU and Real time query profilers
std::unique_ptr<QueryProfilerReal> query_profiler_real;
std::unique_ptr<QueryProfilerCpu> query_profiler_cpu;
Poco::Logger * log = nullptr;
friend class CurrentThread;
/// Use ptr not to add extra dependencies in the header
std::unique_ptr<RUsageCounters> last_rusage;
std::unique_ptr<TasksStatsCounters> taskstats;
/// Is used to send logs from logs_queue to client in case of fatal errors.
std::function<void()> fatal_error_callback;
public:
ThreadStatus();
~ThreadStatus();
ThreadGroupStatusPtr getThreadGroup() const
{
return thread_group;
@ -176,40 +221,6 @@ protected:
void assertState(const std::initializer_list<int> & permitted_states, const char * description = nullptr) const;
ThreadGroupStatusPtr thread_group;
std::atomic<int> thread_state{ThreadState::DetachedFromQuery};
/// Is set once
Context * global_context = nullptr;
/// Use it only from current thread
Context * query_context = nullptr;
String query_id;
/// A logs queue used by TCPHandler to pass logs to a client
InternalTextLogsQueueWeakPtr logs_queue_ptr;
bool performance_counters_finalized = false;
UInt64 query_start_time_nanoseconds = 0;
UInt64 query_start_time_microseconds = 0;
time_t query_start_time = 0;
size_t queries_started = 0;
// CPU and Real time query profilers
std::unique_ptr<QueryProfilerReal> query_profiler_real;
std::unique_ptr<QueryProfilerCpu> query_profiler_cpu;
Poco::Logger * log = nullptr;
friend class CurrentThread;
/// Use ptr not to add extra dependencies in the header
std::unique_ptr<RUsageCounters> last_rusage;
std::unique_ptr<TasksStatsCounters> taskstats;
/// Is used to send logs from logs_queue to client in case of fatal errors.
std::function<void()> fatal_error_callback;
private:
void setupState(const ThreadGroupStatusPtr & thread_group_);

10
src/Common/XDBCBridgeHelper.h
View File

@ -326,6 +326,16 @@ struct ODBCBridgeMixin
cmd_args.push_back("--err-log-path");
cmd_args.push_back(config.getString("logger." + configPrefix() + "_errlog"));
}
if (config.has("logger." + configPrefix() + "_stdout"))
{
cmd_args.push_back("--stdout-path");
cmd_args.push_back(config.getString("logger." + configPrefix() + "_stdout"));
}
if (config.has("logger." + configPrefix() + "_stderr"))
{
cmd_args.push_back("--stderr-path");
cmd_args.push_back(config.getString("logger." + configPrefix() + "_stderr"));
}
if (config.has("logger." + configPrefix() + "_level"))
{
cmd_args.push_back("--log-level");

27
src/Common/ZooKeeper/TestKeeper.cpp
View File

@ -511,19 +511,30 @@ void TestKeeper::processingThread()
if (expired)
break;
if (info.watch)
{
auto & watches_type = dynamic_cast<const ListRequest *>(info.request.get())
? list_watches
: watches;
watches_type[info.request->getPath()].emplace_back(std::move(info.watch));
}
++zxid;
info.request->addRootPath(root_path);
auto [response, _] = info.request->process(container, zxid);
if (info.watch)
{
/// To be compatible with real ZooKeeper we add watch if request was successful (i.e. node exists)
/// or if it was exists request which allows to add watches for non existing nodes.
if (response->error == Error::ZOK)
{
auto & watches_type = dynamic_cast<const ListRequest *>(info.request.get())
? list_watches
: watches;
watches_type[info.request->getPath()].emplace_back(std::move(info.watch));
}
else if (response->error == Error::ZNONODE && dynamic_cast<const ExistsRequest *>(info.request.get()))
{
watches[info.request->getPath()].emplace_back(std::move(info.watch));
}
}
if (response->error == Error::ZOK)
info.request->processWatches(watches, list_watches);

27
src/Common/ZooKeeper/ZooKeeperImpl.cpp
View File

@ -1114,6 +1114,7 @@ void ZooKeeper::sendThread()
info.request->probably_sent = true;
info.request->write(*out);
/// We sent close request, exit
if (info.request->xid == close_xid)
break;
}
@ -1342,21 +1343,25 @@ void ZooKeeper::receiveEvent()
void ZooKeeper::finalize(bool error_send, bool error_receive)
{
/// If some thread (send/receive) already finalizing session don't try to do it
if (finalization_started.exchange(true))
return;
auto expire_session_if_not_expired = [&]
{
std::lock_guard lock(push_request_mutex);
if (expired)
return;
expired = true;
}
active_session_metric_increment.destroy();
if (!expired)
{
expired = true;
active_session_metric_increment.destroy();
}
};
try
{
if (!error_send)
{
/// Send close event. This also signals sending thread to wakeup and then stop.
/// Send close event. This also signals sending thread to stop.
try
{
close();
@ -1364,12 +1369,18 @@ void ZooKeeper::finalize(bool error_send, bool error_receive)
catch (...)
{
/// This happens for example, when "Cannot push request to queue within operation timeout".
/// Just mark session expired in case of error on close request, otherwise sendThread may not stop.
expire_session_if_not_expired();
tryLogCurrentException(__PRETTY_FUNCTION__);
}
/// Send thread will exit after sending close request or on expired flag
send_thread.join();
}
/// Set expired flag after we sent close event
expire_session_if_not_expired();
try
{
/// This will also wakeup the receiving thread.

3
src/Common/ZooKeeper/ZooKeeperImpl.h
View File

@ -187,6 +187,9 @@ private:
std::atomic<XID> next_xid {1};
std::atomic<bool> expired {false};
/// Mark session finalization start. Used to avoid simultaneous
/// finalization from different threads. One-shot flag.
std::atomic<bool> finalization_started {false};
std::mutex push_request_mutex;
using clock = std::chrono::steady_clock;

17
src/Core/MySQL/MySQLClient.cpp
View File

@ -6,6 +6,7 @@
#include <Core/MySQL/PacketsProtocolText.h>
#include <Core/MySQL/PacketsReplication.h>
#include <Core/MySQL/MySQLReplication.h>
#include <Poco/String.h>
namespace DB
{
@ -132,11 +133,19 @@ void MySQLClient::ping()
writeCommand(Command::COM_PING, "");
}
void MySQLClient::startBinlogDumpGTID(UInt32 slave_id, String replicate_db, String gtid_str)
void MySQLClient::setBinlogChecksum(const String & binlog_checksum)
{
/// Set binlog checksum to CRC32.
String checksum = "CRC32";
writeCommand(Command::COM_QUERY, "SET @master_binlog_checksum = '" + checksum + "'");
replication.setChecksumSignatureLength(Poco::toUpper(binlog_checksum) == "NONE" ? 0 : 4);
}
void MySQLClient::startBinlogDumpGTID(UInt32 slave_id, String replicate_db, String gtid_str, const String & binlog_checksum)
{
/// Maybe CRC32 or NONE. mysqlbinlog.cc use NONE, see its below comments:
/// Make a notice to the server that this client is checksum-aware.
/// It does not need the first fake Rotate necessary checksummed.
writeCommand(Command::COM_QUERY, "SET @master_binlog_checksum = 'CRC32'");
setBinlogChecksum(binlog_checksum);
/// Set heartbeat 1s.
UInt64 period_ns = (1 * 1e9);

4
src/Core/MySQL/MySQLClient.h
View File

@ -29,10 +29,12 @@ public:
void disconnect();
void ping();
void setBinlogChecksum(const String & binlog_checksum);
/// Start replication stream by GTID.
/// replicate_db: replication database schema, events from other databases will be ignored.
/// gtid: executed gtid sets format like 'hhhhhhhh-hhhh-hhhh-hhhh-hhhhhhhhhhhh:x-y'.
void startBinlogDumpGTID(UInt32 slave_id, String replicate_db, String gtid);
void startBinlogDumpGTID(UInt32 slave_id, String replicate_db, String gtid, const String & binlog_checksum);
BinlogEventPtr readOneBinlogEvent(UInt64 milliseconds = 0);
Position getPosition() const { return replication.getPosition(); }

3
src/Core/MySQL/MySQLReplication.cpp
View File

@ -57,7 +57,6 @@ namespace MySQLReplication
payload.readStrict(reinterpret_cast<char *>(&create_timestamp), 4);
payload.readStrict(reinterpret_cast<char *>(&event_header_length), 1);
assert(event_header_length == EVENT_HEADER_LENGTH);
readStringUntilEOF(event_type_header_length, payload);
}
@ -745,7 +744,7 @@ namespace MySQLReplication
// skip the generic response packets header flag.
payload.ignore(1);
MySQLBinlogEventReadBuffer event_payload(payload);
MySQLBinlogEventReadBuffer event_payload(payload, checksum_signature_length);
EventHeader event_header;
event_header.parse(event_payload);

4
src/Core/MySQL/MySQLReplication.h
View File

@ -526,6 +526,8 @@ namespace MySQLReplication
virtual BinlogEventPtr readOneEvent() = 0;
virtual void setReplicateDatabase(String db) = 0;
virtual void setGTIDSets(GTIDSets sets) = 0;
virtual void setChecksumSignatureLength(size_t checksum_signature_length_) = 0;
virtual ~IFlavor() override = default;
};
@ -538,12 +540,14 @@ namespace MySQLReplication
BinlogEventPtr readOneEvent() override { return event; }
void setReplicateDatabase(String db) override { replicate_do_db = std::move(db); }
void setGTIDSets(GTIDSets sets) override { position.gtid_sets = std::move(sets); }
void setChecksumSignatureLength(size_t checksum_signature_length_) override { checksum_signature_length = checksum_signature_length_; }
private:
Position position;
BinlogEventPtr event;
String replicate_do_db;
std::shared_ptr<TableMapEvent> table_map;
size_t checksum_signature_length = 4;
inline bool do_replicate() { return (replicate_do_db.empty() || table_map->schema == replicate_do_db); }
};

3
src/Core/Settings.h
View File

@ -65,6 +65,7 @@ class IColumn;
M(UInt64, distributed_connections_pool_size, DBMS_DEFAULT_DISTRIBUTED_CONNECTIONS_POOL_SIZE, "Maximum number of connections with one remote server in the pool.", 0) \
M(UInt64, connections_with_failover_max_tries, DBMS_CONNECTION_POOL_WITH_FAILOVER_DEFAULT_MAX_TRIES, "The maximum number of attempts to connect to replicas.", 0) \
M(UInt64, s3_min_upload_part_size, 512*1024*1024, "The minimum size of part to upload during multipart upload to S3.", 0) \
M(UInt64, s3_max_redirects, 10, "Max number of S3 redirects hops allowed.", 0) \
M(Bool, extremes, false, "Calculate minimums and maximums of the result columns. They can be output in JSON-formats.", IMPORTANT) \
M(Bool, use_uncompressed_cache, true, "Whether to use the cache of uncompressed blocks.", 0) \
M(Bool, replace_running_query, false, "Whether the running request should be canceled with the same id as the new one.", 0) \
@ -406,6 +407,7 @@ class IColumn;
M(Bool, force_optimize_skip_unused_shards_no_nested, false, "Obsolete setting, does nothing. Will be removed after 2020-12-01. Use force_optimize_skip_unused_shards_nesting instead.", 0) \
M(Bool, enable_debug_queries, false, "Enabled debug queries, but now is obsolete", 0) \
M(Bool, allow_experimental_database_atomic, true, "Obsolete setting, does nothing. Will be removed after 2021-02-12", 0) \
M(UnionMode, union_default_mode, UnionMode::DISTINCT, "Set default Union Mode in SelectWithUnion query. Possible values: empty string, 'ALL', 'DISTINCT'. If empty, query without Union Mode will throw exception.", 0)
// End of COMMON_SETTINGS
// Please add settings related to formats into the FORMAT_FACTORY_SETTINGS below.
@ -441,6 +443,7 @@ class IColumn;
M(Bool, output_format_json_quote_denormals, false, "Enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format.", 0) \
\
M(Bool, output_format_json_escape_forward_slashes, true, "Controls escaping forward slashes for string outputs in JSON output format. This is intended for compatibility with JavaScript. Don't confuse with backslashes that are always escaped.", 0) \
M(Bool, output_format_json_named_tuples_as_objects, false, "Serialize named tuple columns as JSON objects.", 0) \
M(Bool, output_format_json_array_of_rows, false, "Output a JSON array of all rows in JSONEachRow(Compact) format.", 0) \
\
M(UInt64, output_format_pretty_max_rows, 10000, "Rows limit for Pretty formats.", 0) \

6
src/Core/SettingsEnums.cpp
View File

@ -12,6 +12,7 @@ namespace ErrorCodes
extern const int UNKNOWN_JOIN;
extern const int BAD_ARGUMENTS;
extern const int UNKNOWN_MYSQL_DATATYPES_SUPPORT_LEVEL;
extern const int UNKNOWN_UNION;
}
@ -96,4 +97,9 @@ IMPLEMENT_SETTING_MULTI_ENUM(MySQLDataTypesSupport, ErrorCodes::UNKNOWN_MYSQL_DA
{{"decimal", MySQLDataTypesSupport::DECIMAL},
{"datetime64", MySQLDataTypesSupport::DATETIME64}})
IMPLEMENT_SETTING_ENUM(UnionMode, ErrorCodes::UNKNOWN_UNION,
{{"", UnionMode::Unspecified},
{"ALL", UnionMode::ALL},
{"DISTINCT", UnionMode::DISTINCT}})
}

9
src/Core/SettingsEnums.h
View File

@ -129,4 +129,13 @@ enum class MySQLDataTypesSupport
DECLARE_SETTING_MULTI_ENUM(MySQLDataTypesSupport)
enum class UnionMode
{
Unspecified = 0, // Query UNION without UnionMode will throw exception
ALL, // Query UNION without UnionMode -> SELECT ... UNION ALL SELECT ...
DISTINCT // Query UNION without UnionMode -> SELECT ... UNION DISTINCT SELECT ...
};
DECLARE_SETTING_ENUM(UnionMode)
}

13
src/Core/include/config_core.h Normal file
View File

@ -0,0 +1,13 @@
#pragma once
// .h autogenerated by cmake!
#define USE_ICU 1
#define USE_MYSQL 1
#define USE_RDKAFKA 1
#define USE_AMQPCPP 1
#define USE_EMBEDDED_COMPILER 0
#define USE_INTERNAL_LLVM_LIBRARY 0
#define USE_SSL 1
#define USE_OPENCL 0
#define USE_LDAP 1

6
src/Core/tests/mysql_protocol.cpp
View File

@ -304,7 +304,8 @@ int main(int argc, char ** argv)
"user", boost::program_options::value<std::string>()->default_value("root"), "master user")(
"password", boost::program_options::value<std::string>()->required(), "master password")(
"gtid", boost::program_options::value<std::string>()->default_value(""), "executed GTID sets")(
"db", boost::program_options::value<std::string>()->required(), "replicate do db");
"db", boost::program_options::value<std::string>()->required(), "replicate do db")(
"binlog_checksum", boost::program_options::value<std::string>()->default_value("CRC32"), "master binlog_checksum");
boost::program_options::variables_map options;
boost::program_options::store(boost::program_options::parse_command_line(argc, argv, desc), options);
@ -319,6 +320,7 @@ int main(int argc, char ** argv)
auto master_password = options.at("password").as<DB::String>();
auto gtid_sets = options.at("gtid").as<DB::String>();
auto replicate_db = options.at("db").as<DB::String>();
auto binlog_checksum = options.at("binlog_checksum").as<String>();
std::cerr << "Master Host: " << host << ", Port: " << port << ", User: " << master_user << ", Password: " << master_password
<< ", Replicate DB: " << replicate_db << ", GTID: " << gtid_sets << std::endl;
@ -328,7 +330,7 @@ int main(int argc, char ** argv)
/// Connect to the master.
slave.connect();
slave.startBinlogDumpGTID(slave_id, replicate_db, gtid_sets);
slave.startBinlogDumpGTID(slave_id, replicate_db, gtid_sets, binlog_checksum);
WriteBufferFromOStream cerr(std::cerr);

5
src/DataStreams/RemoteBlockOutputStream.cpp
View File

@ -27,6 +27,11 @@ RemoteBlockOutputStream::RemoteBlockOutputStream(Connection & connection_,
{
ClientInfo modified_client_info = client_info_;
modified_client_info.query_kind = ClientInfo::QueryKind::SECONDARY_QUERY;
if (CurrentThread::isInitialized())
{
modified_client_info.client_trace_context
= CurrentThread::get().thread_trace_context;
}
/** Send query and receive "header", that describes table structure.
* Header is needed to know, what structure is required for blocks to be passed to 'write' method.

4
src/DataStreams/RemoteQueryExecutor.cpp
View File

@ -156,6 +156,10 @@ void RemoteQueryExecutor::sendQuery()
auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(settings);
ClientInfo modified_client_info = context.getClientInfo();
modified_client_info.query_kind = ClientInfo::QueryKind::SECONDARY_QUERY;
if (CurrentThread::isInitialized())
{
modified_client_info.client_trace_context = CurrentThread::get().thread_trace_context;
}
multiplexed_connections->sendQuery(timeouts, query, query_id, stage, modified_client_info, true);

125
src/DataTypes/DataTypeTuple.cpp
View File

@ -25,12 +25,13 @@ namespace DB
namespace ErrorCodes
{
extern const int LOGICAL_ERROR;
extern const int EMPTY_DATA_PASSED;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
extern const int DUPLICATE_COLUMN;
extern const int BAD_ARGUMENTS;
extern const int DUPLICATE_COLUMN;
extern const int EMPTY_DATA_PASSED;
extern const int LOGICAL_ERROR;
extern const int NOT_FOUND_COLUMN_IN_BLOCK;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
extern const int SIZES_OF_COLUMNS_IN_TUPLE_DOESNT_MATCH;
}
@ -145,6 +146,20 @@ static void addElementSafe(const DataTypes & elems, IColumn & column, F && impl)
try
{
impl();
// Check that all columns now have the same size.
size_t new_size = column.size();
for (auto i : ext::range(1, ext::size(elems)))
{
const auto & element_column = extractElementColumn(column, i);
if (element_column.size() != new_size)
{
// This is not a logical error because it may work with
// user-supplied data.
throw Exception(ErrorCodes::SIZES_OF_COLUMNS_IN_TUPLE_DOESNT_MATCH,
"Cannot read a tuple because not all elements are present");
}
}
}
catch (...)
{
@ -213,37 +228,93 @@ void DataTypeTuple::deserializeText(IColumn & column, ReadBuffer & istr, const F
void DataTypeTuple::serializeTextJSON(const IColumn & column, size_t row_num, WriteBuffer & ostr, const FormatSettings & settings) const
{
writeChar('[', ostr);
for (const auto i : ext::range(0, ext::size(elems)))
if (settings.json.named_tuples_as_objects
&& have_explicit_names)
{
if (i != 0)
writeChar(',', ostr);
elems[i]->serializeAsTextJSON(extractElementColumn(column, i), row_num, ostr, settings);
writeChar('{', ostr);
for (const auto i : ext::range(0, ext::size(elems)))
{
if (i != 0)
{
writeChar(',', ostr);
}
writeJSONString(names[i], ostr, settings);
writeChar(':', ostr);
elems[i]->serializeAsTextJSON(extractElementColumn(column, i), row_num, ostr, settings);
}
writeChar('}', ostr);
}
else
{
writeChar('[', ostr);
for (const auto i : ext::range(0, ext::size(elems)))
{
if (i != 0)
writeChar(',', ostr);
elems[i]->serializeAsTextJSON(extractElementColumn(column, i), row_num, ostr, settings);
}
writeChar(']', ostr);
}
writeChar(']', ostr);
}
void DataTypeTuple::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
{
const size_t size = elems.size();
assertChar('[', istr);
addElementSafe(elems, column, [&]
if (settings.json.named_tuples_as_objects
&& have_explicit_names)
{
for (const auto i : ext::range(0, size))
{
skipWhitespaceIfAny(istr);
if (i != 0)
{
assertChar(',', istr);
skipWhitespaceIfAny(istr);
}
elems[i]->deserializeAsTextJSON(extractElementColumn(column, i), istr, settings);
}
});
skipWhitespaceIfAny(istr);
assertChar('{', istr);
skipWhitespaceIfAny(istr);
skipWhitespaceIfAny(istr);
assertChar(']', istr);
addElementSafe(elems, column, [&]
{
// Require all elements but in arbitrary order.
for (auto i : ext::range(0, ext::size(elems)))
{
if (i > 0)
{
skipWhitespaceIfAny(istr);
assertChar(',', istr);
skipWhitespaceIfAny(istr);
}
std::string name;
readDoubleQuotedString(name, istr);
skipWhitespaceIfAny(istr);
assertChar(':', istr);
skipWhitespaceIfAny(istr);
const size_t element_pos = getPositionByName(name);
auto & element_column = extractElementColumn(column, element_pos);
elems[element_pos]->deserializeAsTextJSON(element_column, istr, settings);
}
});
skipWhitespaceIfAny(istr);
assertChar('}', istr);
}
else
{
const size_t size = elems.size();
assertChar('[', istr);
addElementSafe(elems, column, [&]
{
for (const auto i : ext::range(0, size))
{
skipWhitespaceIfAny(istr);
if (i != 0)
{
assertChar(',', istr);
skipWhitespaceIfAny(istr);
}
elems[i]->deserializeAsTextJSON(extractElementColumn(column, i), istr, settings);
}
});
skipWhitespaceIfAny(istr);
assertChar(']', istr);
}
}
void DataTypeTuple::serializeTextXML(const IColumn & column, size_t row_num, WriteBuffer & ostr, const FormatSettings & settings) const

4
src/Databases/DatabaseDictionary.cpp
View File

@ -44,10 +44,10 @@ namespace
}
}
DatabaseDictionary::DatabaseDictionary(const String & name_, const Context & global_context_)
DatabaseDictionary::DatabaseDictionary(const String & name_, const Context & context_)
: IDatabase(name_)
, log(&Poco::Logger::get("DatabaseDictionary(" + database_name + ")"))
, global_context(global_context_.getGlobalContext())
, global_context(context_.getGlobalContext())
{
}

2
src/Databases/DatabaseDictionary.h
View File

@ -22,7 +22,7 @@ namespace DB
class DatabaseDictionary final : public IDatabase
{
public:
DatabaseDictionary(const String & name_, const Context & global_context);
DatabaseDictionary(const String & name_, const Context & context_);
String getEngineName() const override
{

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