Merge branch 'master' of github.com:ClickHouse/ClickHouse into optimize-data-on-insert

This commit is contained in:
Pavel Kruglov 2020-12-04 18:56:46 +03:00
commit 905ba78adc
1254 changed files with 64387 additions and 9616 deletions

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
---

13
.gitignore vendored
View File

@ -124,3 +124,16 @@ website/package-lock.json
# Toolchains
/cmake/toolchain/*
# ANTLR extension cache
.antlr
# ANTLR generated files
/src/Parsers/New/*.interp
/src/Parsers/New/*.tokens
/src/Parsers/New/ClickHouseParserBaseVisitor.*
# pytest-profiling
/prof
*.iml

15
.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
@ -155,7 +157,7 @@
url = https://github.com/ClickHouse-Extras/libcpuid.git
[submodule "contrib/openldap"]
path = contrib/openldap
url = https://github.com/openldap/openldap.git
url = https://github.com/ClickHouse-Extras/openldap.git
[submodule "contrib/AMQP-CPP"]
path = contrib/AMQP-CPP
url = https://github.com/ClickHouse-Extras/AMQP-CPP.git
@ -170,6 +172,9 @@
[submodule "contrib/fmtlib"]
path = contrib/fmtlib
url = https://github.com/fmtlib/fmt.git
[submodule "contrib/antlr4-runtime"]
path = contrib/antlr4-runtime
url = https://github.com/ClickHouse-Extras/antlr4-runtime.git
[submodule "contrib/sentry-native"]
path = contrib/sentry-native
url = https://github.com/ClickHouse-Extras/sentry-native.git
@ -198,5 +203,9 @@
url = https://github.com/facebook/rocksdb
branch = v6.14.5
[submodule "contrib/xz"]
path = contrib/xz
url = https://github.com/xz-mirror/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

View File

@ -16,6 +16,7 @@
* Remove `ANALYZE` and `AST` queries, and make the setting `enable_debug_queries` obsolete since now it is the part of full featured `EXPLAIN` query. [#16536](https://github.com/ClickHouse/ClickHouse/pull/16536) ([Ivan](https://github.com/abyss7)).
* Aggregate functions `boundingRatio`, `rankCorr`, `retention`, `timeSeriesGroupSum`, `timeSeriesGroupRateSum`, `windowFunnel` were erroneously made case-insensitive. Now their names are made case sensitive as designed. Only functions that are specified in SQL standard or made for compatibility with other DBMS or functions similar to those should be case-insensitive. [#16407](https://github.com/ClickHouse/ClickHouse/pull/16407) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Make `rankCorr` function return nan on insufficient data https://github.com/ClickHouse/ClickHouse/issues/16124. [#16135](https://github.com/ClickHouse/ClickHouse/pull/16135) ([hexiaoting](https://github.com/hexiaoting)).
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
@ -154,6 +155,7 @@
* Change default value of `format_regexp_escaping_rule` setting (it's related to `Regexp` format) to `Raw` (it means - read whole subpattern as a value) to make the behaviour more like to what users expect. [#15426](https://github.com/ClickHouse/ClickHouse/pull/15426) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Add support for nested multiline comments `/* comment /* comment */ */` in SQL. This conforms to the SQL standard. [#14655](https://github.com/ClickHouse/ClickHouse/pull/14655) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Added MergeTree settings (`max_replicated_merges_with_ttl_in_queue` and `max_number_of_merges_with_ttl_in_pool`) to control the number of merges with TTL in the background pool and replicated queue. This change breaks compatibility with older versions only if you use delete TTL. Otherwise, replication will stay compatible. You can avoid incompatibility issues if you update all shard replicas at once or execute `SYSTEM STOP TTL MERGES` until you finish the update of all replicas. If you'll get an incompatible entry in the replication queue, first of all, execute `SYSTEM STOP TTL MERGES` and after `ALTER TABLE ... DETACH PARTITION ...` the partition where incompatible TTL merge was assigned. Attach it back on a single replica. [#14490](https://github.com/ClickHouse/ClickHouse/pull/14490) ([alesapin](https://github.com/alesapin)).
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
@ -438,6 +440,10 @@
### ClickHouse release v20.9.2.20, 2020-09-22
#### Backward Incompatible Change
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
* Added column transformers `EXCEPT`, `REPLACE`, `APPLY`, which can be applied to the list of selected columns (after `*` or `COLUMNS(...)`). For example, you can write `SELECT * EXCEPT(URL) REPLACE(number + 1 AS number)`. Another example: `select * apply(length) apply(max) from wide_string_table` to find out the maxium length of all string columns. [#14233](https://github.com/ClickHouse/ClickHouse/pull/14233) ([Amos Bird](https://github.com/amosbird)).
@ -621,6 +627,7 @@
* Now `OPTIMIZE FINAL` query doesn't recalculate TTL for parts that were added before TTL was created. Use `ALTER TABLE ... MATERIALIZE TTL` once to calculate them, after that `OPTIMIZE FINAL` will evaluate TTL's properly. This behavior never worked for replicated tables. [#14220](https://github.com/ClickHouse/ClickHouse/pull/14220) ([alesapin](https://github.com/alesapin)).
* Extend `parallel_distributed_insert_select` setting, adding an option to run `INSERT` into local table. The setting changes type from `Bool` to `UInt64`, so the values `false` and `true` are no longer supported. If you have these values in server configuration, the server will not start. Please replace them with `0` and `1`, respectively. [#14060](https://github.com/ClickHouse/ClickHouse/pull/14060) ([Azat Khuzhin](https://github.com/azat)).
* Remove support for the `ODBCDriver` input/output format. This was a deprecated format once used for communication with the ClickHouse ODBC driver, now long superseded by the `ODBCDriver2` format. Resolves [#13629](https://github.com/ClickHouse/ClickHouse/issues/13629). [#13847](https://github.com/ClickHouse/ClickHouse/pull/13847) ([hexiaoting](https://github.com/hexiaoting)).
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
@ -765,6 +772,7 @@
* The function `groupArrayMoving*` was not working for distributed queries. It's result was calculated within incorrect data type (without promotion to the largest type). The function `groupArrayMovingAvg` was returning integer number that was inconsistent with the `avg` function. This fixes [#12568](https://github.com/ClickHouse/ClickHouse/issues/12568). [#12622](https://github.com/ClickHouse/ClickHouse/pull/12622) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Add sanity check for MergeTree settings. If the settings are incorrect, the server will refuse to start or to create a table, printing detailed explanation to the user. [#13153](https://github.com/ClickHouse/ClickHouse/pull/13153) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. It will throw exception explaining what to do. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
@ -951,6 +959,10 @@
### ClickHouse release v20.6.3.28-stable
#### Backward Incompatible Change
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature
* Added an initial implementation of `EXPLAIN` query. Syntax: `EXPLAIN SELECT ...`. This fixes [#1118](https://github.com/ClickHouse/ClickHouse/issues/1118). [#11873](https://github.com/ClickHouse/ClickHouse/pull/11873) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
@ -1139,6 +1151,7 @@
* Update `zstd` to 1.4.4. It has some minor improvements in performance and compression ratio. If you run replicas with different versions of ClickHouse you may see reasonable error messages `Data after merge is not byte-identical to data on another replicas.` with explanation. These messages are Ok and you should not worry. This change is backward compatible but we list it here in changelog in case you will wonder about these messages. [#10663](https://github.com/ClickHouse/ClickHouse/pull/10663) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Added a check for meaningless codecs and a setting `allow_suspicious_codecs` to control this check. This closes [#4966](https://github.com/ClickHouse/ClickHouse/issues/4966). [#10645](https://github.com/ClickHouse/ClickHouse/pull/10645) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Several Kafka setting changes their defaults. See [#11388](https://github.com/ClickHouse/ClickHouse/pull/11388).
* When upgrading from versions older than 20.5, if rolling update is performed and cluster contains both versions 20.5 or greater and less than 20.5, if ClickHouse nodes with old versions are restarted and old version has been started up in presence of newer versions, it may lead to `Part ... intersects previous part` errors. To prevent this error, first install newer clickhouse-server packages on all cluster nodes and then do restarts (so, when clickhouse-server is restarted, it will start up with the new version).
#### New Feature

View File

@ -154,17 +154,19 @@ endif ()
# Make sure the final executable has symbols exported
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -rdynamic")
find_program (OBJCOPY_PATH NAMES "llvm-objcopy" "llvm-objcopy-11" "llvm-objcopy-10" "llvm-objcopy-9" "llvm-objcopy-8" "objcopy")
if (OBJCOPY_PATH)
message(STATUS "Using objcopy: ${OBJCOPY_PATH}.")
if (OS_LINUX)
find_program (OBJCOPY_PATH NAMES "llvm-objcopy" "llvm-objcopy-11" "llvm-objcopy-10" "llvm-objcopy-9" "llvm-objcopy-8" "objcopy")
if (OBJCOPY_PATH)
message(STATUS "Using objcopy: ${OBJCOPY_PATH}.")
if (ARCH_AMD64)
set(OBJCOPY_ARCH_OPTIONS -O elf64-x86-64 -B i386)
elseif (ARCH_AARCH64)
set(OBJCOPY_ARCH_OPTIONS -O elf64-aarch64 -B aarch64)
if (ARCH_AMD64)
set(OBJCOPY_ARCH_OPTIONS -O elf64-x86-64 -B i386)
elseif (ARCH_AARCH64)
set(OBJCOPY_ARCH_OPTIONS -O elf64-aarch64 -B aarch64)
endif ()
else ()
message(FATAL_ERROR "Cannot find objcopy.")
endif ()
else ()
message(FATAL_ERROR "Cannot find objcopy.")
endif ()
if (OS_DARWIN)
@ -255,6 +257,8 @@ if (WITH_COVERAGE AND COMPILER_GCC)
set(WITHOUT_COVERAGE "-fno-profile-arcs -fno-test-coverage")
endif()
set(COMPILER_FLAGS "${COMPILER_FLAGS}")
set (CMAKE_BUILD_COLOR_MAKEFILE ON)
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${COMPILER_FLAGS} ${PLATFORM_EXTRA_CXX_FLAG} ${COMMON_WARNING_FLAGS} ${CXX_WARNING_FLAGS}")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -O3 ${CMAKE_CXX_FLAGS_ADD}")
@ -475,9 +479,6 @@ find_contrib_lib(cityhash)
find_contrib_lib(farmhash)
set (USE_INTERNAL_BTRIE_LIBRARY ON CACHE INTERNAL "")
find_contrib_lib(btrie)
if (ENABLE_TESTS)
include (cmake/find/gtest.cmake)
endif ()

View File

@ -1,6 +1,6 @@
[![ClickHouse — open source distributed column-oriented DBMS](https://github.com/ClickHouse/ClickHouse/raw/master/website/images/logo-400x240.png)](https://clickhouse.tech)
ClickHouse is an open-source column-oriented database management system that allows generating analytical data reports in real time.
ClickHouse® is an open-source column-oriented database management system that allows generating analytical data reports in real time.
## Useful Links
@ -16,7 +16,4 @@ ClickHouse is an open-source column-oriented database management system that all
* You can also [fill this form](https://clickhouse.tech/#meet) to meet Yandex ClickHouse team in person.
## Upcoming Events
* [The Second ClickHouse Meetup East (online)](https://www.eventbrite.com/e/the-second-clickhouse-meetup-east-tickets-126787955187) on October 31, 2020.
* [ClickHouse for Enterprise Meetup (online in Russian)](https://arenadata-events.timepad.ru/event/1465249/) on November 10, 2020.
* [SF Bay Area ClickHouse Virtual Office Hours (online)](https://www.meetup.com/San-Francisco-Bay-Area-ClickHouse-Meetup/events/274273549/) on 20 January 2020.

View File

@ -127,7 +127,7 @@ String LineReader::readLine(const String & first_prompt, const String & second_p
}
#endif
line += (line.empty() ? "" : " ") + input;
line += (line.empty() ? "" : "\n") + input;
if (!need_next_line)
break;

View File

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

View File

@ -76,12 +76,6 @@
# define NO_SANITIZE_THREAD
#endif
#if defined __GNUC__ && !defined __clang__
# define OPTIMIZE(x) __attribute__((__optimize__(x)))
#else
# define OPTIMIZE(x)
#endif
/// A macro for suppressing warnings about unused variables or function results.
/// Useful for structured bindings which have no standard way to declare this.
#define UNUSED(...) (void)(__VA_ARGS__)

View File

@ -1,100 +1,28 @@
#include <stdexcept>
#include "common/getMemoryAmount.h"
// http://nadeausoftware.com/articles/2012/09/c_c_tip_how_get_physical_memory_size_system
/*
* Author: David Robert Nadeau
* Site: http://NadeauSoftware.com/
* License: Creative Commons Attribution 3.0 Unported License
* http://creativecommons.org/licenses/by/3.0/deed.en_US
*/
#if defined(WIN32) || defined(_WIN32)
#include <Windows.h>
#else
#include <unistd.h>
#include <sys/types.h>
#include <sys/param.h>
#if defined(BSD)
#include <sys/sysctl.h>
#endif
#endif
/**
* Returns the size of physical memory (RAM) in bytes.
* Returns 0 on unsupported platform
*/
/** Returns the size of physical memory (RAM) in bytes.
* Returns 0 on unsupported platform
*/
uint64_t getMemoryAmountOrZero()
{
#if defined(_WIN32) && (defined(__CYGWIN__) || defined(__CYGWIN32__))
/* Cygwin under Windows. ------------------------------------ */
/* New 64-bit MEMORYSTATUSEX isn't available. Use old 32.bit */
MEMORYSTATUS status;
status.dwLength = sizeof(status);
GlobalMemoryStatus(&status);
return status.dwTotalPhys;
int64_t num_pages = sysconf(_SC_PHYS_PAGES);
if (num_pages <= 0)
return 0;
#elif defined(WIN32) || defined(_WIN32)
/* Windows. ------------------------------------------------- */
/* Use new 64-bit MEMORYSTATUSEX, not old 32-bit MEMORYSTATUS */
MEMORYSTATUSEX status;
status.dwLength = sizeof(status);
GlobalMemoryStatusEx(&status);
return status.ullTotalPhys;
int64_t page_size = sysconf(_SC_PAGESIZE);
if (page_size <= 0)
return 0;
#else
/* UNIX variants. ------------------------------------------- */
/* Prefer sysctl() over sysconf() except sysctl() HW_REALMEM and HW_PHYSMEM */
#if defined(CTL_HW) && (defined(HW_MEMSIZE) || defined(HW_PHYSMEM64))
int mib[2];
mib[0] = CTL_HW;
#if defined(HW_MEMSIZE)
mib[1] = HW_MEMSIZE; /* OSX. --------------------- */
#elif defined(HW_PHYSMEM64)
mib[1] = HW_PHYSMEM64; /* NetBSD, OpenBSD. --------- */
#endif
uint64_t size = 0; /* 64-bit */
size_t len = sizeof(size);
if (sysctl(mib, 2, &size, &len, nullptr, 0) == 0)
return size;
return 0; /* Failed? */
#elif defined(_SC_AIX_REALMEM)
/* AIX. ----------------------------------------------------- */
return sysconf(_SC_AIX_REALMEM) * 1024;
#elif defined(_SC_PHYS_PAGES) && defined(_SC_PAGESIZE)
/* FreeBSD, Linux, OpenBSD, and Solaris. -------------------- */
return uint64_t(sysconf(_SC_PHYS_PAGES))
*uint64_t(sysconf(_SC_PAGESIZE));
#elif defined(_SC_PHYS_PAGES) && defined(_SC_PAGE_SIZE)
/* Legacy. -------------------------------------------------- */
return uint64_t(sysconf(_SC_PHYS_PAGES))
* uint64_t(sysconf(_SC_PAGE_SIZE));
#elif defined(CTL_HW) && (defined(HW_PHYSMEM) || defined(HW_REALMEM))
/* DragonFly BSD, FreeBSD, NetBSD, OpenBSD, and OSX. -------- */
int mib[2];
mib[0] = CTL_HW;
#if defined(HW_REALMEM)
mib[1] = HW_REALMEM; /* FreeBSD. ----------------- */
#elif defined(HW_PYSMEM)
mib[1] = HW_PHYSMEM; /* Others. ------------------ */
#endif
unsigned int size = 0; /* 32-bit */
size_t len = sizeof(size);
if (sysctl(mib, 2, &size, &len, nullptr, 0) == 0)
return size;
return 0; /* Failed? */
#endif /* sysctl and sysconf variants */
#endif
return num_pages * page_size;
}

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>

View File

@ -8,7 +8,7 @@ using Int16 = int16_t;
using Int32 = int32_t;
using Int64 = int64_t;
#if __cplusplus <= 201703L
#ifndef __cpp_char8_t
using char8_t = unsigned char;
#endif

View File

@ -5,7 +5,6 @@ LIBRARY()
ADDINCL(
GLOBAL clickhouse/base
GLOBAL contrib/libs/cctz/include
)
CFLAGS (GLOBAL -DARCADIA_BUILD)
@ -24,7 +23,7 @@ ELSEIF (OS_LINUX)
ENDIF ()
PEERDIR(
contrib/libs/cctz/src
contrib/libs/cctz
contrib/libs/cxxsupp/libcxx-filesystem
contrib/libs/poco/Net
contrib/libs/poco/Util

View File

@ -4,7 +4,6 @@ LIBRARY()
ADDINCL(
GLOBAL clickhouse/base
GLOBAL contrib/libs/cctz/include
)
CFLAGS (GLOBAL -DARCADIA_BUILD)
@ -23,7 +22,7 @@ ELSEIF (OS_LINUX)
ENDIF ()
PEERDIR(
contrib/libs/cctz/src
contrib/libs/cctz
contrib/libs/cxxsupp/libcxx-filesystem
contrib/libs/poco/Net
contrib/libs/poco/Util

View File

@ -6,10 +6,12 @@
#include <common/defines.h>
#include <common/getFQDNOrHostName.h>
#include <common/getMemoryAmount.h>
#include <common/logger_useful.h>
#include <Common/SymbolIndex.h>
#include <Common/StackTrace.h>
#include <Common/getNumberOfPhysicalCPUCores.h>
#if !defined(ARCADIA_BUILD)
# include "Common/config_version.h"
@ -28,14 +30,13 @@ namespace
bool initialized = false;
bool anonymize = false;
std::string server_data_path;
void setExtras()
{
if (!anonymize)
{
sentry_set_extra("server_name", sentry_value_new_string(getFQDNOrHostName().c_str()));
}
sentry_set_tag("version", VERSION_STRING);
sentry_set_extra("version_githash", sentry_value_new_string(VERSION_GITHASH));
sentry_set_extra("version_describe", sentry_value_new_string(VERSION_DESCRIBE));
@ -44,6 +45,15 @@ void setExtras()
sentry_set_extra("version_major", sentry_value_new_int32(VERSION_MAJOR));
sentry_set_extra("version_minor", sentry_value_new_int32(VERSION_MINOR));
sentry_set_extra("version_patch", sentry_value_new_int32(VERSION_PATCH));
sentry_set_extra("version_official", sentry_value_new_string(VERSION_OFFICIAL));
/// Sentry does not support 64-bit integers.
sentry_set_extra("total_ram", sentry_value_new_string(formatReadableSizeWithBinarySuffix(getMemoryAmountOrZero()).c_str()));
sentry_set_extra("physical_cpu_cores", sentry_value_new_int32(getNumberOfPhysicalCPUCores()));
if (!server_data_path.empty())
sentry_set_extra("disk_free_space", sentry_value_new_string(formatReadableSizeWithBinarySuffix(
Poco::File(server_data_path).freeSpace()).c_str()));
}
void sentry_logger(sentry_level_e level, const char * message, va_list args, void *)
@ -98,6 +108,7 @@ void SentryWriter::initialize(Poco::Util::LayeredConfiguration & config)
}
if (enabled)
{
server_data_path = config.getString("path", "");
const std::filesystem::path & default_tmp_path = std::filesystem::path(config.getString("tmp_path", Poco::Path::temp())) / "sentry";
const std::string & endpoint
= config.getString("send_crash_reports.endpoint");

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;
}

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);
}

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;
}

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;
}

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);
}

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

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;

View File

@ -104,6 +104,11 @@ void Connection::connect(const char* db,
if (mysql_options(driver.get(), MYSQL_OPT_LOCAL_INFILE, &enable_local_infile_arg))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
/// Enables auto-reconnect.
bool reconnect = true;
if (mysql_options(driver.get(), MYSQL_OPT_RECONNECT, reinterpret_cast<const char *>(&reconnect)))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
/// Specifies particular ssl key and certificate if it needs
if (mysql_ssl_set(driver.get(), ifNotEmpty(ssl_key), ifNotEmpty(ssl_cert), ifNotEmpty(ssl_ca), nullptr, nullptr))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
@ -115,11 +120,6 @@ void Connection::connect(const char* db,
if (mysql_set_character_set(driver.get(), "UTF8"))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
/// Enables auto-reconnect.
bool reconnect = true;
if (mysql_options(driver.get(), MYSQL_OPT_RECONNECT, reinterpret_cast<const char *>(&reconnect)))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
is_connected = true;
}

View File

@ -26,6 +26,7 @@ void Pool::Entry::incrementRefCount()
mysql_thread_init();
}
void Pool::Entry::decrementRefCount()
{
if (!data)
@ -150,28 +151,39 @@ Pool::Entry Pool::tryGet()
initialize();
/// Searching for connection which was established but wasn't used.
for (auto & connection : connections)
/// Try to pick an idle connection from already allocated
for (auto connection_it = connections.cbegin(); connection_it != connections.cend();)
{
if (connection->ref_count == 0)
Connection * connection_ptr = *connection_it;
/// Fixme: There is a race condition here b/c we do not synchronize with Pool::Entry's copy-assignment operator
if (connection_ptr->ref_count == 0)
{
Entry res(connection, this);
return res.tryForceConnected() ? res : Entry();
Entry res(connection_ptr, this);
if (res.tryForceConnected()) /// Tries to reestablish connection as well
return res;
auto & logger = Poco::Util::Application::instance().logger();
logger.information("Idle connection to mysql server cannot be recovered, dropping it.");
/// This one is disconnected, cannot be reestablished and so needs to be disposed of.
connection_it = connections.erase(connection_it);
::delete connection_ptr; /// TODO: Manual memory management is awkward (matches allocConnection() method)
}
else
++connection_it;
}
/// Throws if pool is overflowed.
if (connections.size() >= max_connections)
throw Poco::Exception("mysqlxx::Pool is full");
/// Allocates new connection.
Connection * conn = allocConnection(true);
if (conn)
return Entry(conn, this);
Connection * connection_ptr = allocConnection(true);
if (connection_ptr)
return {connection_ptr, this};
return Entry();
return {};
}
void Pool::removeConnection(Connection* connection)
{
std::lock_guard<std::mutex> lock(mutex);
@ -199,11 +211,9 @@ void Pool::Entry::forceConnected() const
throw Poco::RuntimeException("Tried to access NULL database connection.");
Poco::Util::Application & app = Poco::Util::Application::instance();
if (data->conn.ping())
return;
bool first = true;
do
while (!tryForceConnected())
{
if (first)
first = false;
@ -225,7 +235,26 @@ void Pool::Entry::forceConnected() const
pool->rw_timeout,
pool->enable_local_infile);
}
while (!data->conn.ping());
}
bool Pool::Entry::tryForceConnected() const
{
auto * const mysql_driver = data->conn.getDriver();
const auto prev_connection_id = mysql_thread_id(mysql_driver);
if (data->conn.ping()) /// Attempts to reestablish lost connection
{
const auto current_connection_id = mysql_thread_id(mysql_driver);
if (prev_connection_id != current_connection_id)
{
auto & logger = Poco::Util::Application::instance().logger();
logger.information("Connection to mysql server has been reestablished. Connection id changed: %d -> %d",
prev_connection_id, current_connection_id);
}
return true;
}
return false;
}

View File

@ -127,10 +127,7 @@ public:
void forceConnected() const;
/// Connects to database. If connection is failed then returns false.
bool tryForceConnected() const
{
return data->conn.ping();
}
bool tryForceConnected() const;
void incrementRefCount();
void decrementRefCount();

View File

@ -1,2 +1,5 @@
add_executable (mysqlxx_test mysqlxx_test.cpp)
target_link_libraries (mysqlxx_test PRIVATE mysqlxx)
add_executable (mysqlxx_pool_test mysqlxx_pool_test.cpp)
target_link_libraries (mysqlxx_pool_test PRIVATE mysqlxx)

View File

@ -0,0 +1,98 @@
#include <mysqlxx/mysqlxx.h>
#include <chrono>
#include <iostream>
#include <sstream>
#include <thread>
namespace
{
mysqlxx::Pool::Entry getWithFailover(mysqlxx::Pool & connections_pool)
{
using namespace std::chrono;
constexpr size_t max_tries = 3;
mysqlxx::Pool::Entry worker_connection;
for (size_t try_no = 1; try_no <= max_tries; ++try_no)
{
try
{
worker_connection = connections_pool.tryGet();
if (!worker_connection.isNull())
{
return worker_connection;
}
}
catch (const Poco::Exception & e)
{
if (e.displayText().find("mysqlxx::Pool is full") != std::string::npos)
{
std::cerr << e.displayText() << std::endl;
}
std::cerr << "Connection to " << connections_pool.getDescription() << " failed: " << e.displayText() << std::endl;
}
std::clog << "Connection to all replicas failed " << try_no << " times" << std::endl;
std::this_thread::sleep_for(1s);
}
std::stringstream message;
message << "Connections to all replicas failed: " << connections_pool.getDescription();
throw Poco::Exception(message.str());
}
}
int main(int, char **)
{
using namespace std::chrono;
const char * remote_mysql = "localhost";
const std::string test_query = "SHOW DATABASES";
mysqlxx::Pool mysql_conn_pool("", remote_mysql, "default", "10203040", 3306);
size_t iteration = 0;
while (++iteration)
{
std::clog << "Iteration: " << iteration << std::endl;
try
{
std::clog << "Acquiring DB connection ...";
mysqlxx::Pool::Entry worker = getWithFailover(mysql_conn_pool);
std::clog << "ok" << std::endl;
std::clog << "Preparing query (5s sleep) ...";
std::this_thread::sleep_for(5s);
mysqlxx::Query query = worker->query();
query << test_query;
std::clog << "ok" << std::endl;
std::clog << "Querying result (5s sleep) ...";
std::this_thread::sleep_for(5s);
mysqlxx::UseQueryResult result = query.use();
std::clog << "ok" << std::endl;
std::clog << "Fetching result data (5s sleep) ...";
std::this_thread::sleep_for(5s);
size_t rows_count = 0;
while (result.fetch())
++rows_count;
std::clog << "ok" << std::endl;
std::clog << "Read " << rows_count << " rows." << std::endl;
}
catch (const Poco::Exception & e)
{
std::cerr << "Iteration FAILED:\n" << e.displayText() << std::endl;
}
std::clog << "====================" << std::endl;
std::this_thread::sleep_for(3s);
}
}

View File

@ -1,44 +0,0 @@
# - Try to find btrie headers and libraries.
#
# Usage of this module as follows:
#
# find_package(btrie)
#
# Variables used by this module, they can change the default behaviour and need
# to be set before calling find_package:
#
# BTRIE_ROOT_DIR Set this variable to the root installation of
# btrie if the module has problems finding
# the proper installation path.
#
# Variables defined by this module:
#
# BTRIE_FOUND System has btrie libs/headers
# BTRIE_LIBRARIES The btrie library/libraries
# BTRIE_INCLUDE_DIR The location of btrie headers
find_path(BTRIE_ROOT_DIR
NAMES include/btrie.h
)
find_library(BTRIE_LIBRARIES
NAMES btrie
PATHS ${BTRIE_ROOT_DIR}/lib ${BTRIE_LIBRARIES_PATHS}
)
find_path(BTRIE_INCLUDE_DIR
NAMES btrie.h
PATHS ${BTRIE_ROOT_DIR}/include ${BTRIE_INCLUDE_PATHS}
)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(btrie DEFAULT_MSG
BTRIE_LIBRARIES
BTRIE_INCLUDE_DIR
)
mark_as_advanced(
BTRIE_ROOT_DIR
BTRIE_LIBRARIES
BTRIE_INCLUDE_DIR
)

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()

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

View File

@ -12,13 +12,7 @@ set(CMAKE_CXX_STANDARD_LIBRARIES ${DEFAULT_LIBS})
set(CMAKE_C_STANDARD_LIBRARIES ${DEFAULT_LIBS})
# Minimal supported SDK version
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mmacosx-version-min=10.15")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mmacosx-version-min=10.15")
set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} -mmacosx-version-min=10.15")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -mmacosx-version-min=10.15")
set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -mmacosx-version-min=10.15")
set(CMAKE_OSX_DEPLOYMENT_TARGET 10.15)
# Global libraries

View File

@ -1,3 +1,4 @@
# Needed when using Apache Avro serialization format
option (ENABLE_AVRO "Enable Avro" ${ENABLE_LIBRARIES})
if (NOT ENABLE_AVRO)

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}")

View File

@ -1,3 +1,5 @@
# Needed when securely connecting to an external server, e.g.
# clickhouse-client --host ... --secure
option(ENABLE_SSL "Enable ssl" ${ENABLE_LIBRARIES})
if(NOT ENABLE_SSL)

View File

@ -23,8 +23,8 @@ option (WEVERYTHING "Enable -Weverything option with some exceptions." ON)
# Control maximum size of stack frames. It can be important if the code is run in fibers with small stack size.
# Only in release build because debug has too large stack frames.
if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE))
add_warning(frame-larger-than=32768)
if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE) AND (NOT CMAKE_CXX_COMPILER_ID MATCHES "AppleClang"))
add_warning(frame-larger-than=65536)
endif ()
if (COMPILER_CLANG)

2
contrib/AMQP-CPP vendored

@ -1 +1 @@
Subproject commit d63e1f016582e9faaaf279aa24513087a07bc6e7
Subproject commit 03781aaff0f10ef41f902b8cf865fe0067180c10

View File

@ -21,6 +21,7 @@ endif()
set_property(DIRECTORY PROPERTY EXCLUDE_FROM_ALL 1)
add_subdirectory (antlr4-runtime-cmake)
add_subdirectory (boost-cmake)
add_subdirectory (cctz-cmake)
add_subdirectory (consistent-hashing-sumbur)
@ -66,10 +67,6 @@ if (USE_INTERNAL_FARMHASH_LIBRARY)
add_subdirectory (libfarmhash)
endif ()
if (USE_INTERNAL_BTRIE_LIBRARY)
add_subdirectory (libbtrie)
endif ()
if (USE_INTERNAL_ZLIB_LIBRARY)
set (ZLIB_ENABLE_TESTS 0 CACHE INTERNAL "")
set (SKIP_INSTALL_ALL 1 CACHE INTERNAL "")

1
contrib/abseil-cpp vendored Submodule

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

1
contrib/antlr4-runtime vendored Submodule

@ -0,0 +1 @@
Subproject commit a2fa7b76e2ee16d2ad955e9214a90bbf79da66fc

View File

@ -0,0 +1,156 @@
set (LIBRARY_DIR ${ClickHouse_SOURCE_DIR}/contrib/antlr4-runtime)
set (SRCS
${LIBRARY_DIR}/ANTLRErrorListener.cpp
${LIBRARY_DIR}/ANTLRErrorStrategy.cpp
${LIBRARY_DIR}/ANTLRFileStream.cpp
${LIBRARY_DIR}/ANTLRInputStream.cpp
${LIBRARY_DIR}/atn/AbstractPredicateTransition.cpp
${LIBRARY_DIR}/atn/ActionTransition.cpp
${LIBRARY_DIR}/atn/AmbiguityInfo.cpp
${LIBRARY_DIR}/atn/ArrayPredictionContext.cpp
${LIBRARY_DIR}/atn/ATN.cpp
${LIBRARY_DIR}/atn/ATNConfig.cpp
${LIBRARY_DIR}/atn/ATNConfigSet.cpp
${LIBRARY_DIR}/atn/ATNDeserializationOptions.cpp
${LIBRARY_DIR}/atn/ATNDeserializer.cpp
${LIBRARY_DIR}/atn/ATNSerializer.cpp
${LIBRARY_DIR}/atn/ATNSimulator.cpp
${LIBRARY_DIR}/atn/ATNState.cpp
${LIBRARY_DIR}/atn/AtomTransition.cpp
${LIBRARY_DIR}/atn/BasicBlockStartState.cpp
${LIBRARY_DIR}/atn/BasicState.cpp
${LIBRARY_DIR}/atn/BlockEndState.cpp
${LIBRARY_DIR}/atn/BlockStartState.cpp
${LIBRARY_DIR}/atn/ContextSensitivityInfo.cpp
${LIBRARY_DIR}/atn/DecisionEventInfo.cpp
${LIBRARY_DIR}/atn/DecisionInfo.cpp
${LIBRARY_DIR}/atn/DecisionState.cpp
${LIBRARY_DIR}/atn/EmptyPredictionContext.cpp
${LIBRARY_DIR}/atn/EpsilonTransition.cpp
${LIBRARY_DIR}/atn/ErrorInfo.cpp
${LIBRARY_DIR}/atn/LexerAction.cpp
${LIBRARY_DIR}/atn/LexerActionExecutor.cpp
${LIBRARY_DIR}/atn/LexerATNConfig.cpp
${LIBRARY_DIR}/atn/LexerATNSimulator.cpp
${LIBRARY_DIR}/atn/LexerChannelAction.cpp
${LIBRARY_DIR}/atn/LexerCustomAction.cpp
${LIBRARY_DIR}/atn/LexerIndexedCustomAction.cpp
${LIBRARY_DIR}/atn/LexerModeAction.cpp
${LIBRARY_DIR}/atn/LexerMoreAction.cpp
${LIBRARY_DIR}/atn/LexerPopModeAction.cpp
${LIBRARY_DIR}/atn/LexerPushModeAction.cpp
${LIBRARY_DIR}/atn/LexerSkipAction.cpp
${LIBRARY_DIR}/atn/LexerTypeAction.cpp
${LIBRARY_DIR}/atn/LL1Analyzer.cpp
${LIBRARY_DIR}/atn/LookaheadEventInfo.cpp
${LIBRARY_DIR}/atn/LoopEndState.cpp
${LIBRARY_DIR}/atn/NotSetTransition.cpp
${LIBRARY_DIR}/atn/OrderedATNConfigSet.cpp
${LIBRARY_DIR}/atn/ParseInfo.cpp
${LIBRARY_DIR}/atn/ParserATNSimulator.cpp
${LIBRARY_DIR}/atn/PlusBlockStartState.cpp
${LIBRARY_DIR}/atn/PlusLoopbackState.cpp
${LIBRARY_DIR}/atn/PrecedencePredicateTransition.cpp
${LIBRARY_DIR}/atn/PredicateEvalInfo.cpp
${LIBRARY_DIR}/atn/PredicateTransition.cpp
${LIBRARY_DIR}/atn/PredictionContext.cpp
${LIBRARY_DIR}/atn/PredictionMode.cpp
${LIBRARY_DIR}/atn/ProfilingATNSimulator.cpp
${LIBRARY_DIR}/atn/RangeTransition.cpp
${LIBRARY_DIR}/atn/RuleStartState.cpp
${LIBRARY_DIR}/atn/RuleStopState.cpp
${LIBRARY_DIR}/atn/RuleTransition.cpp
${LIBRARY_DIR}/atn/SemanticContext.cpp
${LIBRARY_DIR}/atn/SetTransition.cpp
${LIBRARY_DIR}/atn/SingletonPredictionContext.cpp
${LIBRARY_DIR}/atn/StarBlockStartState.cpp
${LIBRARY_DIR}/atn/StarLoopbackState.cpp
${LIBRARY_DIR}/atn/StarLoopEntryState.cpp
${LIBRARY_DIR}/atn/TokensStartState.cpp
${LIBRARY_DIR}/atn/Transition.cpp
${LIBRARY_DIR}/atn/WildcardTransition.cpp
${LIBRARY_DIR}/BailErrorStrategy.cpp
${LIBRARY_DIR}/BaseErrorListener.cpp
${LIBRARY_DIR}/BufferedTokenStream.cpp
${LIBRARY_DIR}/CharStream.cpp
${LIBRARY_DIR}/CommonToken.cpp
${LIBRARY_DIR}/CommonTokenFactory.cpp
${LIBRARY_DIR}/CommonTokenStream.cpp
${LIBRARY_DIR}/ConsoleErrorListener.cpp
${LIBRARY_DIR}/DefaultErrorStrategy.cpp
${LIBRARY_DIR}/dfa/DFA.cpp
${LIBRARY_DIR}/dfa/DFASerializer.cpp
${LIBRARY_DIR}/dfa/DFAState.cpp
${LIBRARY_DIR}/dfa/LexerDFASerializer.cpp
${LIBRARY_DIR}/DiagnosticErrorListener.cpp
${LIBRARY_DIR}/Exceptions.cpp
${LIBRARY_DIR}/FailedPredicateException.cpp
${LIBRARY_DIR}/InputMismatchException.cpp
${LIBRARY_DIR}/InterpreterRuleContext.cpp
${LIBRARY_DIR}/IntStream.cpp
${LIBRARY_DIR}/Lexer.cpp
${LIBRARY_DIR}/LexerInterpreter.cpp
${LIBRARY_DIR}/LexerNoViableAltException.cpp
${LIBRARY_DIR}/ListTokenSource.cpp
${LIBRARY_DIR}/misc/InterpreterDataReader.cpp
${LIBRARY_DIR}/misc/Interval.cpp
${LIBRARY_DIR}/misc/IntervalSet.cpp
${LIBRARY_DIR}/misc/MurmurHash.cpp
${LIBRARY_DIR}/misc/Predicate.cpp
${LIBRARY_DIR}/NoViableAltException.cpp
${LIBRARY_DIR}/Parser.cpp
${LIBRARY_DIR}/ParserInterpreter.cpp
${LIBRARY_DIR}/ParserRuleContext.cpp
${LIBRARY_DIR}/ProxyErrorListener.cpp
${LIBRARY_DIR}/RecognitionException.cpp
${LIBRARY_DIR}/Recognizer.cpp
${LIBRARY_DIR}/RuleContext.cpp
${LIBRARY_DIR}/RuleContextWithAltNum.cpp
${LIBRARY_DIR}/RuntimeMetaData.cpp
${LIBRARY_DIR}/support/Any.cpp
${LIBRARY_DIR}/support/Arrays.cpp
${LIBRARY_DIR}/support/CPPUtils.cpp
${LIBRARY_DIR}/support/guid.cpp
${LIBRARY_DIR}/support/StringUtils.cpp
${LIBRARY_DIR}/Token.cpp
${LIBRARY_DIR}/TokenSource.cpp
${LIBRARY_DIR}/TokenStream.cpp
${LIBRARY_DIR}/TokenStreamRewriter.cpp
${LIBRARY_DIR}/tree/ErrorNode.cpp
${LIBRARY_DIR}/tree/ErrorNodeImpl.cpp
${LIBRARY_DIR}/tree/IterativeParseTreeWalker.cpp
${LIBRARY_DIR}/tree/ParseTree.cpp
${LIBRARY_DIR}/tree/ParseTreeListener.cpp
${LIBRARY_DIR}/tree/ParseTreeVisitor.cpp
${LIBRARY_DIR}/tree/ParseTreeWalker.cpp
${LIBRARY_DIR}/tree/pattern/Chunk.cpp
${LIBRARY_DIR}/tree/pattern/ParseTreeMatch.cpp
${LIBRARY_DIR}/tree/pattern/ParseTreePattern.cpp
${LIBRARY_DIR}/tree/pattern/ParseTreePatternMatcher.cpp
${LIBRARY_DIR}/tree/pattern/RuleTagToken.cpp
${LIBRARY_DIR}/tree/pattern/TagChunk.cpp
${LIBRARY_DIR}/tree/pattern/TextChunk.cpp
${LIBRARY_DIR}/tree/pattern/TokenTagToken.cpp
${LIBRARY_DIR}/tree/TerminalNode.cpp
${LIBRARY_DIR}/tree/TerminalNodeImpl.cpp
${LIBRARY_DIR}/tree/Trees.cpp
${LIBRARY_DIR}/tree/xpath/XPath.cpp
${LIBRARY_DIR}/tree/xpath/XPathElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathLexer.cpp
${LIBRARY_DIR}/tree/xpath/XPathLexerErrorListener.cpp
${LIBRARY_DIR}/tree/xpath/XPathRuleAnywhereElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathRuleElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathTokenAnywhereElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathTokenElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathWildcardAnywhereElement.cpp
${LIBRARY_DIR}/tree/xpath/XPathWildcardElement.cpp
${LIBRARY_DIR}/UnbufferedCharStream.cpp
${LIBRARY_DIR}/UnbufferedTokenStream.cpp
${LIBRARY_DIR}/Vocabulary.cpp
${LIBRARY_DIR}/WritableToken.cpp
)
add_library (antlr4-runtime ${SRCS})
target_include_directories (antlr4-runtime SYSTEM PUBLIC ${LIBRARY_DIR})

2
contrib/cassandra vendored

@ -1 +1 @@
Subproject commit a49b4e0e2696a4b8ef286a5b9538d1cbe8490509
Subproject commit d10187efb25b26da391def077edf3c6f2f3a23dd

2
contrib/cctz vendored

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

2
contrib/grpc vendored

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

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")

View File

@ -1,6 +0,0 @@
add_library(btrie
src/btrie.c
include/btrie.h
)
target_include_directories (btrie SYSTEM PUBLIC include)

View File

@ -1,23 +0,0 @@
Copyright (c) 2013, CobbLiu
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
Redistributions in binary form must reproduce the above copyright notice, this
list of conditions and the following disclaimer in the documentation and/or
other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

View File

@ -1,160 +0,0 @@
#pragma once
#if defined (__cplusplus)
extern "C" {
#endif
#include <stdlib.h>
#include <stdint.h>
/**
* In btrie, each leaf means one bit in ip tree.
* Left means 0, and right means 1.
*/
#define BTRIE_NULL (uintptr_t) -1
#if !defined(BTRIE_MAX_PAGES)
/// 54 ip per page. 8 bytes memory per page when empty
#define BTRIE_MAX_PAGES 1024 * 2048 /// 128m ips , ~16mb ram when empty
// #define BTRIE_MAX_PAGES 1024 * 65535 /// 4g ips (whole ipv4), ~512mb ram when empty
#endif
typedef struct btrie_node_s btrie_node_t;
struct btrie_node_s {
btrie_node_t *right;
btrie_node_t *left;
btrie_node_t *parent;
uintptr_t value;
};
typedef struct btrie_s {
btrie_node_t *root;
btrie_node_t *free; /* free list of btrie */
char *start;
size_t size;
/*
* memory pool.
* memory management(esp free) will be so easy by using this facility.
*/
char *pools[BTRIE_MAX_PAGES];
size_t len;
} btrie_t;
/**
* Create an empty btrie
*
* @Return:
* An ip radix_tree created.
* NULL if creation failed.
*/
btrie_t *btrie_create();
/**
* Destroy the ip radix_tree
*
* @Return:
* OK if deletion succeed.
* ERROR if error occurs while deleting.
*/
int btrie_destroy(btrie_t *tree);
/**
* Count the nodes in the radix tree.
*/
size_t btrie_count(btrie_t *tree);
/**
* Return the allocated number of bytes.
*/
size_t btrie_allocated(btrie_t *tree);
/**
* Add an ipv4 into btrie
*
* @Args:
* key: ip address
* mask: key's mask
* value: value of this IP, may be NULL.
*
* @Return:
* OK for success.
* ERROR for failure.
*/
int btrie_insert(btrie_t *tree, uint32_t key, uint32_t mask,
uintptr_t value);
/**
* Delete an ipv4 from btrie
*
* @Args:
*
* @Return:
* OK for success.
* ERROR for failure.
*/
int btrie_delete(btrie_t *tree, uint32_t key, uint32_t mask);
/**
* Find an ipv4 from btrie
*
* @Args:
*
* @Return:
* Value if succeed.
* NULL if failed.
*/
uintptr_t btrie_find(btrie_t *tree, uint32_t key);
/**
* Add an ipv6 into btrie
*
* @Args:
* key: ip address
* mask: key's mask
* value: value of this IP, may be NULL.
*
* @Return:
* OK for success.
* ERROR for failure.
*/
int btrie_insert_a6(btrie_t *tree, const uint8_t *key, const uint8_t *mask,
uintptr_t value);
/**
* Delete an ipv6 from btrie
*
* @Args:
*
* @Return:
* OK for success.
* ERROR for failure.
*/
int btrie_delete_a6(btrie_t *tree, const uint8_t *key, const uint8_t *mask);
/**
* Find an ipv6 from btrie
*
* @Args:
*
* @Return:
* Value if succeed.
* NULL if failed.
*/
uintptr_t btrie_find_a6(btrie_t *tree, const uint8_t *key);
#if defined (__cplusplus)
}
#endif

View File

@ -1,460 +0,0 @@
#include <stdlib.h>
#include <string.h>
#include <btrie.h>
#define PAGE_SIZE 4096
static btrie_node_t *
btrie_alloc(btrie_t *tree)
{
btrie_node_t *p;
if (tree->free) {
p = tree->free;
tree->free = tree->free->right;
return p;
}
if (tree->size < sizeof(btrie_node_t)) {
tree->start = (char *) calloc(sizeof(char), PAGE_SIZE);
if (tree->start == NULL) {
return NULL;
}
tree->pools[tree->len++] = tree->start;
tree->size = PAGE_SIZE;
}
p = (btrie_node_t *) tree->start;
tree->start += sizeof(btrie_node_t);
tree->size -= sizeof(btrie_node_t);
return p;
}
btrie_t *
btrie_create()
{
btrie_t *tree = (btrie_t *) malloc(sizeof(btrie_t));
if (tree == NULL) {
return NULL;
}
tree->free = NULL;
tree->start = NULL;
tree->size = 0;
memset(tree->pools, 0, sizeof(btrie_t *) * BTRIE_MAX_PAGES);
tree->len = 0;
tree->root = btrie_alloc(tree);
if (tree->root == NULL) {
return NULL;
}
tree->root->right = NULL;
tree->root->left = NULL;
tree->root->parent = NULL;
tree->root->value = BTRIE_NULL;
return tree;
}
static size_t
subtree_weight(btrie_node_t *node)
{
size_t weight = 1;
if (node->left) {
weight += subtree_weight(node->left);
}
if (node->right) {
weight += subtree_weight(node->right);
}
return weight;
}
size_t
btrie_count(btrie_t *tree)
{
if (tree->root == NULL) {
return 0;
}
return subtree_weight(tree->root);
}
size_t
btrie_allocated(btrie_t *tree)
{
return tree->len * PAGE_SIZE;
}
int
btrie_insert(btrie_t *tree, uint32_t key, uint32_t mask,
uintptr_t value)
{
uint32_t bit;
btrie_node_t *node, *next;
bit = 0x80000000;
node = tree->root;
next = tree->root;
while (bit & mask) {
if (key & bit) {
next = node->right;
} else {
next = node->left;
}
if (next == NULL) {
break;
}
bit >>= 1;
node = next;
}
if (next) {
if (node->value != BTRIE_NULL) {
return -1;
}
node->value = value;
return 0;
}
while (bit & mask) {
next = btrie_alloc(tree);
if (next == NULL) {
return -1;
}
next->right = NULL;
next->left = NULL;
next->parent = node;
next->value = BTRIE_NULL;
if (key & bit) {
node->right = next;
} else {
node->left = next;
}
bit >>= 1;
node = next;
}
node->value = value;
return 0;
}
int
btrie_delete(btrie_t *tree, uint32_t key, uint32_t mask)
{
uint32_t bit;
btrie_node_t *node;
bit = 0x80000000;
node = tree->root;
while (node && (bit & mask)) {
if (key & bit) {
node = node->right;
} else {
node = node->left;
}
bit >>= 1;
}
if (node == NULL) {
return -1;
}
if (node->right || node->left) {
if (node->value != BTRIE_NULL) {
node->value = BTRIE_NULL;
return 0;
}
return -1;
}
for ( ;; ) {
if (node->parent->right == node) {
node->parent->right = NULL;
} else {
node->parent->left = NULL;
}
node->right = tree->free;
tree->free = node;
node = node->parent;
if (node->right || node->left) {
break;
}
if (node->value != BTRIE_NULL) {
break;
}
if (node->parent == NULL) {
break;
}
}
return 0;
}
uintptr_t
btrie_find(btrie_t *tree, uint32_t key)
{
uint32_t bit;
uintptr_t value;
btrie_node_t *node;
bit = 0x80000000;
value = BTRIE_NULL;
node = tree->root;
while (node) {
if (node->value != BTRIE_NULL) {
value = node->value;
}
if (key & bit) {
node = node->right;
} else {
node = node->left;
}
bit >>= 1;
}
return value;
}
int
btrie_insert_a6(btrie_t *tree, const uint8_t *key, const uint8_t *mask,
uintptr_t value)
{
uint8_t bit;
unsigned int i;
btrie_node_t *node, *next;
i = 0;
bit = 0x80;
node = tree->root;
next = tree->root;
while (bit & mask[i]) {
if (key[i] & bit) {
next = node->right;
} else {
next = node->left;
}
if (next == NULL) {
break;
}
bit >>= 1;
node = next;
if (bit == 0) {
if (++i == 16) {
break;
}
bit = 0x80;
}
}
if (next) {
if (node->value != BTRIE_NULL) {
return -1;
}
node->value = value;
return 0;
}
while (bit & mask[i]) {
next = btrie_alloc(tree);
if (next == NULL) {
return -1;
}
next->right = NULL;
next->left = NULL;
next->parent = node;
next->value = BTRIE_NULL;
if (key[i] & bit) {
node->right = next;
} else {
node->left = next;
}
bit >>= 1;
node = next;
if (bit == 0) {
if (++i == 16) {
break;
}
bit = 0x80;
}
}
node->value = value;
return 0;
}
int
btrie_delete_a6(btrie_t *tree, const uint8_t *key, const uint8_t *mask)
{
uint8_t bit;
unsigned int i;
btrie_node_t *node;
i = 0;
bit = 0x80;
node = tree->root;
while (node && (bit & mask[i])) {
if (key[i] & bit) {
node = node->right;
} else {
node = node->left;
}
bit >>= 1;
if (bit == 0) {
if (++i == 16) {
break;
}
bit = 0x80;
}
}
if (node == NULL) {
return -1;
}
if (node->right || node->left) {
if (node->value != BTRIE_NULL) {
node->value = BTRIE_NULL;
return 0;
}
return -1;
}
for ( ;; ) {
if (node->parent->right == node) {
node->parent->right = NULL;
} else {
node->parent->left = NULL;
}
node->right = tree->free;
tree->free = node;
node = node->parent;
if (node->right || node->left) {
break;
}
if (node->value != BTRIE_NULL) {
break;
}
if (node->parent == NULL) {
break;
}
}
return 0;
}
uintptr_t
btrie_find_a6(btrie_t *tree, const uint8_t *key)
{
uint8_t bit;
uintptr_t value;
unsigned int i;
btrie_node_t *node;
i = 0;
bit = 0x80;
value = BTRIE_NULL;
node = tree->root;
while (node) {
if (node->value != BTRIE_NULL) {
value = node->value;
}
if (key[i] & bit) {
node = node->right;
} else {
node = node->left;
}
bit >>= 1;
if (bit == 0) {
i++;
bit = 0x80;
}
}
return value;
}
int
btrie_destroy(btrie_t *tree)
{
size_t i;
/* free memory pools */
for (i = 0; i < tree->len; i++) {
free(tree->pools[i]);
}
free(tree);
return 0;
}

View File

@ -1,103 +0,0 @@
#include <stdio.h>
#include <btrie.h>
int main()
{
btrie_t *it;
int ret;
uint8_t prefix_v6[16] = {0xde, 0xad, 0xbe, 0xef};
uint8_t mask_v6[16] = {0xff, 0xff, 0xff};
uint8_t ip_v6[16] = {0xde, 0xad, 0xbe, 0xef, 0xde};
it = btrie_create();
if (it == NULL) {
printf("create error!\n");
return 0;
}
//add 101.45.69.50/16
ret = btrie_insert(it, 1697465650, 0xffff0000, 1);
if (ret != 0) {
printf("insert 1 error.\n");
goto error;
}
//add 10.45.69.50/16
ret = btrie_insert(it, 170738994, 0xffff0000, 1);
if (ret != 0) {
printf("insert 2 error.\n");
goto error;
}
//add 10.45.79.50/16
ret = btrie_insert(it, 170741554, 0xffff0000, 1);
if (ret == 0) {
printf("insert 3 error.\n");
goto error;
}
//add 102.45.79.50/24
ret = btrie_insert(it, 1714245426, 0xffffff00, 1);
if (ret != 0) {
printf("insert 4 error.\n");
goto error;
}
ret = btrie_find(it, 170741554);
if (ret == 1) {
printf("test case 1 passed\n");
} else {
printf("test case 1 error\n");
}
ret = btrie_find(it, 170786817);
if (ret != 1) {
printf("test case 2 passed\n");
} else {
printf("test case 2 error\n");
}
ret = btrie_delete(it, 1714245426, 0xffffff00);
if (ret != 0) {
printf("delete 1 error\n");
goto error;
}
ret = btrie_find(it, 1714245426);
if (ret != 1) {
printf("test case 3 passed\n");
} else {
printf("test case 3 error\n");
}
//add dead:beef::/32
ret = btrie_insert_a6(it, prefix_v6, mask_v6, 1);
if (ret != 0) {
printf("insert 5 error\n");
goto error;
}
ret = btrie_find_a6(it, ip_v6);
if (ret == 1) {
printf("test case 4 passed\n");
} else {
printf("test case 4 error\n");
}
// insert 4m ips
for (size_t ip = 1; ip < 1024 * 1024 * 4; ++ip) {
ret = btrie_insert(it, ip, 0xffffffff, 1);
if (ret != 0) {
printf("insert 5 error (%d) (%zu) .\n", ret, ip);
goto error;
}
}
return 0;
error:
btrie_destroy(it);
printf("test failed\n");
return 1;
}

2
contrib/librdkafka vendored

@ -1 +1 @@
Subproject commit 2090cbf56b715247ec2be7f768707a7ab1bf7ede
Subproject commit 9902bc4fb18bb441fa55ca154b341cdda191e5d3

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}

@ -1 +1 @@
Subproject commit 1485b0de3eaa1508dfe49a5ba1e4aa2a71fd8335
Subproject commit e05523ca7c1fb8d095b612a1b1cfe96e199ffb17

2
contrib/openldap vendored

@ -1 +1 @@
Subproject commit 34b9ba94b30319ed6389a4e001d057f7983fe363
Subproject commit 0208811b6043ca06fda8631a5e473df1ec515ccb

2
contrib/poco vendored

@ -1 +1 @@
Subproject commit f49c6ab8d3aa71828bd1b411485c21722e8c9d82
Subproject commit f3d791f6568b99366d089b4479f76a515beb66d5

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

View File

@ -67,26 +67,6 @@ if uname -mpi | grep -q 'x86_64'; then
fi
is_running()
{
pgrep --pidfile "$CLICKHOUSE_PIDFILE" $(echo "${PROGRAM}" | cut -c1-15) 1> /dev/null 2> /dev/null
}
wait_for_done()
{
timeout=$1
attempts=0
while is_running; do
attempts=$(($attempts + 1))
if [ -n "$timeout" ] && [ $attempts -gt $timeout ]; then
return 1
fi
sleep 1
done
}
die()
{
echo $1 >&2
@ -105,49 +85,7 @@ check_config()
initdb()
{
if [ -x "$CLICKHOUSE_BINDIR/$EXTRACT_FROM_CONFIG" ]; then
CLICKHOUSE_DATADIR_FROM_CONFIG=$(su -s $SHELL ${CLICKHOUSE_USER} -c "$CLICKHOUSE_BINDIR/$EXTRACT_FROM_CONFIG --config-file=\"$CLICKHOUSE_CONFIG\" --key=path")
if [ "(" "$?" -ne "0" ")" -o "(" -z "${CLICKHOUSE_DATADIR_FROM_CONFIG}" ")" ]; then
die "Cannot obtain value of path from config file: ${CLICKHOUSE_CONFIG}";
fi
echo "Path to data directory in ${CLICKHOUSE_CONFIG}: ${CLICKHOUSE_DATADIR_FROM_CONFIG}"
else
CLICKHOUSE_DATADIR_FROM_CONFIG=$CLICKHOUSE_DATADIR
fi
if ! getent passwd ${CLICKHOUSE_USER} >/dev/null; then
echo "Can't chown to non-existing user ${CLICKHOUSE_USER}"
return
fi
if ! getent group ${CLICKHOUSE_GROUP} >/dev/null; then
echo "Can't chown to non-existing group ${CLICKHOUSE_GROUP}"
return
fi
if ! $(su -s $SHELL ${CLICKHOUSE_USER} -c "test -r ${CLICKHOUSE_CONFIG}"); then
echo "Warning! clickhouse config [${CLICKHOUSE_CONFIG}] not readable by user [${CLICKHOUSE_USER}]"
fi
if ! $(su -s $SHELL ${CLICKHOUSE_USER} -c "test -O \"${CLICKHOUSE_DATADIR_FROM_CONFIG}\" && test -G \"${CLICKHOUSE_DATADIR_FROM_CONFIG}\""); then
if [ $(dirname "${CLICKHOUSE_DATADIR_FROM_CONFIG}") = "/" ]; then
echo "Directory ${CLICKHOUSE_DATADIR_FROM_CONFIG} seems too dangerous to chown."
else
if [ ! -e "${CLICKHOUSE_DATADIR_FROM_CONFIG}" ]; then
echo "Creating directory ${CLICKHOUSE_DATADIR_FROM_CONFIG}"
mkdir -p "${CLICKHOUSE_DATADIR_FROM_CONFIG}"
fi
echo "Changing owner of [${CLICKHOUSE_DATADIR_FROM_CONFIG}] to [${CLICKHOUSE_USER}:${CLICKHOUSE_GROUP}]"
chown -R ${CLICKHOUSE_USER}:${CLICKHOUSE_GROUP} "${CLICKHOUSE_DATADIR_FROM_CONFIG}"
fi
fi
if ! $(su -s $SHELL ${CLICKHOUSE_USER} -c "test -w ${CLICKHOUSE_LOGDIR}"); then
echo "Changing owner of [${CLICKHOUSE_LOGDIR}/*] to [${CLICKHOUSE_USER}:${CLICKHOUSE_GROUP}]"
chown -R ${CLICKHOUSE_USER}:${CLICKHOUSE_GROUP} ${CLICKHOUSE_LOGDIR}/*
echo "Changing owner of [${CLICKHOUSE_LOGDIR}] to [${CLICKHOUSE_LOGDIR_USER}:${CLICKHOUSE_GROUP}]"
chown ${CLICKHOUSE_LOGDIR_USER}:${CLICKHOUSE_GROUP} ${CLICKHOUSE_LOGDIR}
fi
${CLICKHOUSE_GENERIC_PROGRAM} install --user "${CLICKHOUSE_USER}" --pid-path "${CLICKHOUSE_PIDDIR}" --config-path "${CLICKHOUSE_CONFDIR}" --binary-path "${CLICKHOUSE_BINDIR}"
}
@ -171,17 +109,7 @@ restart()
forcestop()
{
local EXIT_STATUS
EXIT_STATUS=0
echo -n "Stop forcefully $PROGRAM service: "
kill -KILL $(cat "$CLICKHOUSE_PIDFILE")
wait_for_done
echo "DONE"
return $EXIT_STATUS
${CLICKHOUSE_GENERIC_PROGRAM} stop --force --pid-path "${CLICKHOUSE_PIDDIR}"
}
@ -261,16 +189,16 @@ main()
service_or_func restart
;;
condstart)
is_running || service_or_func start
service_or_func start
;;
condstop)
is_running && service_or_func stop
service_or_func stop
;;
condrestart)
is_running && service_or_func restart
service_or_func restart
;;
condreload)
is_running && service_or_func restart
service_or_func restart
;;
initdb)
initdb
@ -293,17 +221,7 @@ main()
status()
{
if is_running; then
echo "$PROGRAM service is running"
exit 0
else
if is_cron_disabled; then
echo "$PROGRAM service is stopped";
else
echo "$PROGRAM: process unexpectedly terminated"
fi
exit 3
fi
${CLICKHOUSE_GENERIC_PROGRAM} status --pid-path "${CLICKHOUSE_PIDDIR}"
}

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 \

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 \

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 \

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 && \

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}

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}}")
@ -101,223 +104,249 @@ function start_server
function clone_root
{
git clone https://github.com/ClickHouse/ClickHouse.git -- "$FASTTEST_SOURCE" | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/clone_log.txt"
git clone https://github.com/ClickHouse/ClickHouse.git -- "$FASTTEST_SOURCE" | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/clone_log.txt"
(
cd "$FASTTEST_SOURCE"
if [ "$PULL_REQUEST_NUMBER" != "0" ]; then
if git fetch origin "+refs/pull/$PULL_REQUEST_NUMBER/merge"; then
git checkout FETCH_HEAD
echo 'Clonned merge head'
else
git fetch
git checkout "$COMMIT_SHA"
echo 'Checked out to commit'
fi
else
if [ -v COMMIT_SHA ]; then
git checkout "$COMMIT_SHA"
fi
fi
)
(
cd "$FASTTEST_SOURCE"
if [ "$PULL_REQUEST_NUMBER" != "0" ]; then
if git fetch origin "+refs/pull/$PULL_REQUEST_NUMBER/merge"; then
git checkout FETCH_HEAD
echo 'Clonned merge head'
else
git fetch
git checkout "$COMMIT_SHA"
echo 'Checked out to commit'
fi
else
if [ -v COMMIT_SHA ]; then
git checkout "$COMMIT_SHA"
fi
fi
)
}
function clone_submodules
{
(
cd "$FASTTEST_SOURCE"
(
cd "$FASTTEST_SOURCE"
SUBMODULES_TO_UPDATE=(contrib/boost contrib/zlib-ng contrib/libxml2 contrib/poco contrib/libunwind contrib/ryu contrib/fmtlib contrib/base64 contrib/cctz contrib/libcpuid contrib/double-conversion contrib/libcxx contrib/libcxxabi contrib/libc-headers contrib/lz4 contrib/zstd contrib/fastops contrib/rapidjson contrib/re2 contrib/sparsehash-c11 contrib/croaring contrib/miniselect contrib/xz)
SUBMODULES_TO_UPDATE=(
contrib/antlr4-runtime
contrib/boost
contrib/zlib-ng
contrib/libxml2
contrib/poco
contrib/libunwind
contrib/ryu
contrib/fmtlib
contrib/base64
contrib/cctz
contrib/libcpuid
contrib/double-conversion
contrib/libcxx
contrib/libcxxabi
contrib/libc-headers
contrib/lz4
contrib/zstd
contrib/fastops
contrib/rapidjson
contrib/re2
contrib/sparsehash-c11
contrib/croaring
contrib/miniselect
contrib/xz
)
git submodule sync
git submodule update --init --recursive "${SUBMODULES_TO_UPDATE[@]}"
git submodule foreach git reset --hard
git submodule foreach git checkout @ -f
git submodule foreach git clean -xfd
)
git submodule sync
git submodule update --init --recursive "${SUBMODULES_TO_UPDATE[@]}"
git submodule foreach git reset --hard
git submodule foreach git checkout @ -f
git submodule foreach git clean -xfd
)
}
function run_cmake
{
CMAKE_LIBS_CONFIG=(
"-DENABLE_LIBRARIES=0"
"-DENABLE_TESTS=0"
"-DENABLE_UTILS=0"
"-DENABLE_EMBEDDED_COMPILER=0"
"-DENABLE_THINLTO=0"
"-DUSE_UNWIND=1"
)
CMAKE_LIBS_CONFIG=(
"-DENABLE_LIBRARIES=0"
"-DENABLE_TESTS=0"
"-DENABLE_UTILS=0"
"-DENABLE_EMBEDDED_COMPILER=0"
"-DENABLE_THINLTO=0"
"-DUSE_UNWIND=1"
)
# TODO remove this? we don't use ccache anyway. An option would be to download it
# from S3 simultaneously with cloning.
export CCACHE_DIR="$FASTTEST_WORKSPACE/ccache"
export CCACHE_BASEDIR="$FASTTEST_SOURCE"
export CCACHE_NOHASHDIR=true
export CCACHE_COMPILERCHECK=content
export CCACHE_MAXSIZE=15G
# TODO remove this? we don't use ccache anyway. An option would be to download it
# from S3 simultaneously with cloning.
export CCACHE_DIR="$FASTTEST_WORKSPACE/ccache"
export CCACHE_BASEDIR="$FASTTEST_SOURCE"
export CCACHE_NOHASHDIR=true
export CCACHE_COMPILERCHECK=content
export CCACHE_MAXSIZE=15G
ccache --show-stats ||:
ccache --zero-stats ||:
ccache --show-stats ||:
ccache --zero-stats ||:
mkdir "$FASTTEST_BUILD" ||:
mkdir "$FASTTEST_BUILD" ||:
(
cd "$FASTTEST_BUILD"
cmake "$FASTTEST_SOURCE" -DCMAKE_CXX_COMPILER=clang++-10 -DCMAKE_C_COMPILER=clang-10 "${CMAKE_LIBS_CONFIG[@]}" "${FASTTEST_CMAKE_FLAGS[@]}" | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/cmake_log.txt"
)
(
cd "$FASTTEST_BUILD"
cmake "$FASTTEST_SOURCE" -DCMAKE_CXX_COMPILER=clang++-10 -DCMAKE_C_COMPILER=clang-10 "${CMAKE_LIBS_CONFIG[@]}" "${FASTTEST_CMAKE_FLAGS[@]}" | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/cmake_log.txt"
)
}
function build
{
(
cd "$FASTTEST_BUILD"
time ninja clickhouse-bundle | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/build_log.txt"
if [ "$COPY_CLICKHOUSE_BINARY_TO_OUTPUT" -eq "1" ]; then
cp programs/clickhouse "$FASTTEST_OUTPUT/clickhouse"
fi
ccache --show-stats ||:
)
(
cd "$FASTTEST_BUILD"
time ninja clickhouse-bundle | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/build_log.txt"
if [ "$COPY_CLICKHOUSE_BINARY_TO_OUTPUT" -eq "1" ]; then
cp programs/clickhouse "$FASTTEST_OUTPUT/clickhouse"
fi
ccache --show-stats ||:
)
}
function configure
{
clickhouse-client --version
clickhouse-test --help
clickhouse-client --version
clickhouse-test --help
mkdir -p "$FASTTEST_DATA"{,/client-config}
cp -a "$FASTTEST_SOURCE/programs/server/"{config,users}.xml "$FASTTEST_DATA"
"$FASTTEST_SOURCE/tests/config/install.sh" "$FASTTEST_DATA" "$FASTTEST_DATA/client-config"
cp -a "$FASTTEST_SOURCE/programs/server/config.d/log_to_console.xml" "$FASTTEST_DATA/config.d"
# doesn't support SSL
rm -f "$FASTTEST_DATA/config.d/secure_ports.xml"
mkdir -p "$FASTTEST_DATA"{,/client-config}
cp -a "$FASTTEST_SOURCE/programs/server/"{config,users}.xml "$FASTTEST_DATA"
"$FASTTEST_SOURCE/tests/config/install.sh" "$FASTTEST_DATA" "$FASTTEST_DATA/client-config"
cp -a "$FASTTEST_SOURCE/programs/server/config.d/log_to_console.xml" "$FASTTEST_DATA/config.d"
# doesn't support SSL
rm -f "$FASTTEST_DATA/config.d/secure_ports.xml"
}
function run_tests
{
clickhouse-server --version
clickhouse-test --help
clickhouse-server --version
clickhouse-test --help
# Kill the server in case we are running locally and not in docker
stop_server ||:
start_server
TESTS_TO_SKIP=(
00105_shard_collations
00109_shard_totals_after_having
00110_external_sort
00302_http_compression
00417_kill_query
00436_convert_charset
00490_special_line_separators_and_characters_outside_of_bmp
00652_replicated_mutations_zookeeper
00682_empty_parts_merge
00701_rollup
00834_cancel_http_readonly_queries_on_client_close
00911_tautological_compare
00926_multimatch
00929_multi_match_edit_distance
01031_mutations_interpreter_and_context
01053_ssd_dictionary # this test mistakenly requires acces to /var/lib/clickhouse -- can't run this locally, disabled
01083_expressions_in_engine_arguments
01092_memory_profiler
01098_msgpack_format
01098_temporary_and_external_tables
01103_check_cpu_instructions_at_startup # avoid dependency on qemu -- invonvenient when running locally
01193_metadata_loading
01238_http_memory_tracking # max_memory_usage_for_user can interfere another queries running concurrently
01251_dict_is_in_infinite_loop
01259_dictionary_custom_settings_ddl
01268_dictionary_direct_layout
01280_ssd_complex_key_dictionary
01281_group_by_limit_memory_tracking # max_memory_usage_for_user can interfere another queries running concurrently
01318_encrypt # Depends on OpenSSL
01318_decrypt # Depends on OpenSSL
01281_unsucceeded_insert_select_queries_counter
01292_create_user
01294_lazy_database_concurrent
01305_replica_create_drop_zookeeper
01354_order_by_tuple_collate_const
01355_ilike
01411_bayesian_ab_testing
01532_collate_in_low_cardinality
01533_collate_in_nullable
01542_collate_in_array
01543_collate_in_tuple
_orc_
arrow
avro
base64
brotli
capnproto
client
ddl_dictionaries
h3
hashing
hdfs
java_hash
json
limit_memory
live_view
memory_leak
memory_limit
mysql
odbc
parallel_alter
parquet
protobuf
secure
sha256
xz
# Not sure why these two fail even in sequential mode. Disabled for now
# to make some progress.
00646_url_engine
00974_query_profiler
# In fasttest, ENABLE_LIBRARIES=0, so rocksdb engine is not enabled by default
01504_rocksdb
# Look at DistributedFilesToInsert, so cannot run in parallel.
01460_DistributedFilesToInsert
01541_max_memory_usage_for_user
# Require python libraries like scipy, pandas and numpy
01322_ttest_scipy
01545_system_errors
# Checks system.errors
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"
# 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 "$FASTTEST_OUTPUT/failed-parallel-tests.txt")
# We will rerun sequentially any tests that have failed during parallel run.
# They might have failed because there was some interference from other tests
# running concurrently. If they fail even in seqential mode, we will report them.
# FIXME All tests that require exclusive access to the server must be
# explicitly marked as `sequential`, and `clickhouse-test` must detect them and
# run them in a separate group after all other tests. This is faster and also
# explicit instead of guessing.
if [[ -n "${FAILED_TESTS[*]}" ]]
then
# Kill the server in case we are running locally and not in docker
stop_server ||:
# Clean the data so that there is no interference from the previous test run.
rm -rf "$FASTTEST_DATA"/{{meta,}data,user_files} ||:
start_server
echo "Going to run again: ${FAILED_TESTS[*]}"
TESTS_TO_SKIP=(
00105_shard_collations
00109_shard_totals_after_having
00110_external_sort
00302_http_compression
00417_kill_query
00436_convert_charset
00490_special_line_separators_and_characters_outside_of_bmp
00652_replicated_mutations_zookeeper
00682_empty_parts_merge
00701_rollup
00834_cancel_http_readonly_queries_on_client_close
00911_tautological_compare
00926_multimatch
00929_multi_match_edit_distance
01031_mutations_interpreter_and_context
01053_ssd_dictionary # this test mistakenly requires acces to /var/lib/clickhouse -- can't run this locally, disabled
01083_expressions_in_engine_arguments
01092_memory_profiler
01098_msgpack_format
01098_temporary_and_external_tables
01103_check_cpu_instructions_at_startup # avoid dependency on qemu -- invonvenient when running locally
01193_metadata_loading
01238_http_memory_tracking # max_memory_usage_for_user can interfere another queries running concurrently
01251_dict_is_in_infinite_loop
01259_dictionary_custom_settings_ddl
01268_dictionary_direct_layout
01280_ssd_complex_key_dictionary
01281_group_by_limit_memory_tracking # max_memory_usage_for_user can interfere another queries running concurrently
01318_encrypt # Depends on OpenSSL
01318_decrypt # Depends on OpenSSL
01281_unsucceeded_insert_select_queries_counter
01292_create_user
01294_lazy_database_concurrent
01305_replica_create_drop_zookeeper
01354_order_by_tuple_collate_const
01355_ilike
01411_bayesian_ab_testing
01532_collate_in_low_cardinality
01533_collate_in_nullable
01542_collate_in_array
01543_collate_in_tuple
_orc_
arrow
avro
base64
brotli
capnproto
client
ddl_dictionaries
h3
hashing
hdfs
java_hash
json
limit_memory
live_view
memory_leak
memory_limit
mysql
odbc
parallel_alter
parquet
protobuf
secure
sha256
xz
clickhouse-test --order=random --no-long --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_log.txt"
else
echo "No failed tests"
fi
# Not sure why these two fail even in sequential mode. Disabled for now
# to make some progress.
00646_url_engine
00974_query_profiler
# In fasttest, ENABLE_LIBRARIES=0, so rocksdb engine is not enabled by default
01504_rocksdb
# Look at DistributedFilesToInsert, so cannot run in parallel.
01460_DistributedFilesToInsert
01541_max_memory_usage_for_user
# Require python libraries like scipy, pandas and numpy
01322_ttest_scipy
01561_mann_whitney_scipy
01545_system_errors
# Checks system.errors
01563_distributed_query_finish
)
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${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 "$FASTTEST_OUTPUT/failed-parallel-tests.txt")
# We will rerun sequentially any tests that have failed during parallel run.
# They might have failed because there was some interference from other tests
# running concurrently. If they fail even in seqential mode, we will report them.
# FIXME All tests that require exclusive access to the server must be
# explicitly marked as `sequential`, and `clickhouse-test` must detect them and
# run them in a separate group after all other tests. This is faster and also
# explicit instead of guessing.
if [[ -n "${FAILED_TESTS[*]}" ]]
then
stop_server ||:
# Clean the data so that there is no interference from the previous test run.
rm -rf "$FASTTEST_DATA"/{{meta,}data,user_files} ||:
start_server
echo "Going to run again: ${FAILED_TESTS[*]}"
clickhouse-test --order=random --no-long --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_log.txt"
else
echo "No failed tests"
fi
}
case "$stage" in

View File

@ -28,6 +28,7 @@ RUN apt-get update \
libssl-dev \
libcurl4-openssl-dev \
gdb \
software-properties-common \
&& rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \
@ -37,6 +38,22 @@ RUN apt-get update \
ENV TZ=Europe/Moscow
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
ENV DOCKER_CHANNEL stable
ENV DOCKER_VERSION 5:19.03.13~3-0~ubuntu-bionic
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
RUN add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -c -s) ${DOCKER_CHANNEL}"
RUN apt-get update \
&& env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
docker-ce \
&& rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \
/tmp/* \
&& apt-get clean
RUN dockerd --version; docker --version
RUN python3 -m pip install \
PyMySQL \
aerospike \
@ -60,28 +77,6 @@ RUN python3 -m pip install \
tzlocal \
urllib3
ENV DOCKER_CHANNEL stable
ENV DOCKER_VERSION 17.09.1-ce
RUN set -eux; \
\
# this "case" statement is generated via "update.sh"
\
if ! wget -nv -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/x86_64/docker-${DOCKER_VERSION}.tgz"; then \
echo >&2 "error: failed to download 'docker-${DOCKER_VERSION}' from '${DOCKER_CHANNEL}' for '${x86_64}'"; \
exit 1; \
fi; \
\
tar --extract \
--file docker.tgz \
--strip-components 1 \
--directory /usr/local/bin/ \
; \
rm docker.tgz; \
\
dockerd --version; \
docker --version
COPY modprobe.sh /usr/local/bin/modprobe
COPY dockerd-entrypoint.sh /usr/local/bin/
COPY compose/ /compose/

View File

@ -50,7 +50,7 @@ services:
- label:disable
kafka_kerberos:
image: yandex/clickhouse-kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG}
image: yandex/clickhouse-kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG:-latest}
hostname: kafka_kerberos
volumes:
- ${KERBERIZED_KAFKA_DIR}/secrets:/tmp/keytab

View File

@ -0,0 +1,10 @@
version: '2.3'
services:
mysql1:
image: mysql:5.7
restart: 'no'
environment:
MYSQL_ROOT_PASSWORD: clickhouse
ports:
- 3308:3306
command: --server_id=100 --log-bin='mysql-bin-1.log' --default-time-zone='+3:00' --gtid-mode="ON" --enforce-gtid-consistency

View File

@ -2,7 +2,7 @@ version: '2.3'
services:
mysql8_0:
image: mysql:8.0
restart: always
restart: 'no'
environment:
MYSQL_ROOT_PASSWORD: clickhouse
ports:

View File

@ -1,6 +1,6 @@
version: '2.3'
services:
golang1:
image: yandex/clickhouse-mysql-golang-client:${DOCKER_MYSQL_GOLANG_CLIENT_TAG}
image: yandex/clickhouse-mysql-golang-client:${DOCKER_MYSQL_GOLANG_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity

View File

@ -1,6 +1,6 @@
version: '2.3'
services:
java1:
image: yandex/clickhouse-mysql-java-client:${DOCKER_MYSQL_JAVA_CLIENT_TAG}
image: yandex/clickhouse-mysql-java-client:${DOCKER_MYSQL_JAVA_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity

View File

@ -1,6 +1,6 @@
version: '2.3'
services:
mysqljs1:
image: yandex/clickhouse-mysql-js-client:${DOCKER_MYSQL_JS_CLIENT_TAG}
image: yandex/clickhouse-mysql-js-client:${DOCKER_MYSQL_JS_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity

View File

@ -1,6 +1,6 @@
version: '2.3'
services:
php1:
image: yandex/clickhouse-mysql-php-client:${DOCKER_MYSQL_PHP_CLIENT_TAG}
image: yandex/clickhouse-mysql-php-client:${DOCKER_MYSQL_PHP_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity

View File

@ -1,6 +1,6 @@
version: '2.2'
services:
java:
image: yandex/clickhouse-postgresql-java-client:${DOCKER_POSTGRESQL_JAVA_CLIENT_TAG}
image: yandex/clickhouse-postgresql-java-client:${DOCKER_POSTGRESQL_JAVA_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity

View File

@ -25,12 +25,13 @@ RUN apt-get update \
python3 \
python3-dev \
python3-pip \
python3-setuptools \
rsync \
tree \
tzdata \
vim \
wget \
&& pip3 --no-cache-dir install clickhouse_driver scipy \
&& pip3 --no-cache-dir install 'git+https://github.com/mymarilyn/clickhouse-driver.git' scipy \
&& apt-get purge --yes python3-dev g++ \
&& apt-get autoremove --yes \
&& apt-get clean \

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')
@ -139,44 +143,37 @@ reportStageEnd('before-connect')
# Open connections
servers = [{'host': host or args.host[0], 'port': port or args.port[0]} for (host, port) in itertools.zip_longest(args.host, args.port)]
all_connections = [clickhouse_driver.Client(**server) for server in servers]
# Force settings_is_important to fail queries on unknown settings.
all_connections = [clickhouse_driver.Client(**server, settings_is_important=True) for server in servers]
for i, s in enumerate(servers):
print(f'server\t{i}\t{s["host"]}\t{s["port"]}')
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
# that is not in master, but the queries can still run. If we have multiple
# settings and one of them throws an exception, all previous settings for this
# connection will be reset, because the driver reconnects on error (not
# configurable). So the end result is uncertain, but hopefully we'll be able to
# run at least some queries.
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 +191,40 @@ 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 +403,11 @@ 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')
reportStageEnd('drop-2')

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

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

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
@ -81,10 +66,6 @@ fi
chmod 777 -R /var/lib/clickhouse
while /bin/true; do
merge_client_files_in_background
sleep 2
done &
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"
@ -93,14 +74,13 @@ LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-client --query "CREATE DA
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"
if grep -q -- "--use-skip-list" /usr/bin/clickhouse-test; then
SKIP_LIST_OPT="--use-skip-list"
fi
@ -113,11 +93,6 @@ LLVM_PROFILE_FILE='client_coverage.profraw' clickhouse-test --testname --shard -
kill_clickhouse
wait_llvm_profdata
sleep 3
wait_llvm_profdata # 100% merged all parts
cp /*.profraw /profraw ||:

View File

@ -8,6 +8,7 @@ RUN apt-get update -y \
apt-get install --yes --no-install-recommends \
brotli \
expect \
zstd \
lsof \
ncdu \
netcat-openbsd \

View File

@ -8,6 +8,7 @@ RUN apt-get --allow-unauthenticated update -y \
apt-get --allow-unauthenticated install --yes --no-install-recommends \
alien \
brotli \
zstd \
cmake \
devscripts \
expect \

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
@ -24,11 +24,14 @@ RUN apt-get update -y \
tree \
moreutils \
brotli \
zstd \
gdb \
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 \

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

View File

@ -13,9 +13,9 @@ cmake .. \
-DENABLE_CLICKHOUSE_SERVER=ON \
-DENABLE_CLICKHOUSE_CLIENT=ON \
-DUSE_STATIC_LIBRARIES=OFF \
-DCLICKHOUSE_SPLIT_BINARY=ON \
-DSPLIT_SHARED_LIBRARIES=ON \
-DENABLE_LIBRARIES=OFF \
-DUSE_UNWIND=ON \
-DENABLE_UTILS=OFF \
-DENABLE_TESTS=OFF
```

View File

@ -17,7 +17,6 @@ toc_title: Third-Party Libraries Used
| googletest | [BSD 3-Clause License](https://github.com/google/googletest/blob/master/LICENSE) |
| h3 | [Apache License 2.0](https://github.com/uber/h3/blob/master/LICENSE) |
| hyperscan | [BSD 3-Clause License](https://github.com/intel/hyperscan/blob/master/LICENSE) |
| libbtrie | [BSD 2-Clause License](https://github.com/ClickHouse/ClickHouse/blob/master/contrib/libbtrie/LICENSE) |
| libcxxabi | [BSD + MIT](https://github.com/ClickHouse/ClickHouse/blob/master/libs/libglibc-compatibility/libcxxabi/LICENSE.TXT) |
| libdivide | [Zlib License](https://github.com/ClickHouse/ClickHouse/blob/master/contrib/libdivide/LICENSE.txt) |
| libgsasl | [LGPL v2.1](https://github.com/ClickHouse-Extras/libgsasl/blob/3b8948a4042e34fb00b4fb987535dc9e02e39040/LICENSE) |

View File

@ -273,13 +273,15 @@ SELECT
sum(Duration) AS Duration
FROM UAct
GROUP BY UserID
```text
```
``` text
┌──────────────UserID─┬─PageViews─┬─Duration─┐
│ 4324182021466249494 │ 6 │ 185 │
└─────────────────────┴───────────┴──────────┘
```
``` sqk
``` sql
select count() FROM UAct
```

View File

@ -579,6 +579,7 @@ Tags:
- `disk` — a disk within a volume.
- `max_data_part_size_bytes` — the maximum size of a part that can be stored on any of the volumes disks.
- `move_factor` — when the amount of available space gets lower than this factor, data automatically start to move on the next volume if any (by default, 0.1).
- `prefer_not_to_merge` — Disables merging of data parts on this volume. When this setting is enabled, merging data on this volume is not allowed. This allows controlling how ClickHouse works with slow disks.
Cofiguration examples:
@ -607,6 +608,18 @@ Cofiguration examples:
</volumes>
<move_factor>0.2</move_factor>
</moving_from_ssd_to_hdd>
<small_jbod_with_external_no_merges>
<volumes>
<main>
<disk>jbod1</disk>
</main>
<external>
<disk>external</disk>
<prefer_not_to_merge>true</prefer_not_to_merge>
</external>
</volumes>
</small_jbod_with_external_no_merges>
</policies>
...
</storage_configuration>

View File

@ -5,7 +5,7 @@ toc_title: ReplacingMergeTree
# ReplacingMergeTree {#replacingmergetree}
The engine differs from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree) in that it removes duplicate entries with the same [sorting key](../../../engines/table-engines/mergetree-family/mergetree.md) value.
The engine differs from [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree) in that it removes duplicate entries with the same [sorting key](../../../engines/table-engines/mergetree-family/mergetree.md) value (`ORDER BY` table section, not `PRIMARY KEY`).
Data deduplication occurs only during a merge. Merging occurs in the background at an unknown time, so you cant plan for it. Some of the data may remain unprocessed. Although you can run an unscheduled merge using the `OPTIMIZE` query, dont count on using it, because the `OPTIMIZE` query will read and write a large amount of data.
@ -29,13 +29,16 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
For a description of request parameters, see [statement description](../../../sql-reference/statements/create/table.md).
!!! note "Attention"
Uniqueness of rows is determined by the `ORDER BY` table section, not `PRIMARY KEY`.
**ReplacingMergeTree Parameters**
- `ver` — column with version. Type `UInt*`, `Date` or `DateTime`. Optional parameter.
When merging, `ReplacingMergeTree` from all the rows with the same sorting key leaves only one:
- Last in the selection, if `ver` not set.
- The last in the selection, if `ver` not set. A selection is a set of rows in a set of parts participating in the merge. The most recently created part (the last insert) will be the last one in the selection. Thus, after deduplication, the very last row from the most recent insert will remain for each unique sorting key.
- With the maximum version, if `ver` specified.
**Query clauses**

View File

@ -53,6 +53,42 @@ Example of setting the addresses of the ZooKeeper cluster:
</zookeeper>
```
ClickHouse also supports to store replicas meta information in the auxiliary ZooKeeper cluster by providing ZooKeeper cluster name and path as engine arguments.
In other word, it supports to store the metadata of differnt tables in different ZooKeeper clusters.
Example of setting the addresses of the auxiliary ZooKeeper cluster:
``` xml
<auxiliary_zookeepers>
<zookeeper2>
<node index="1">
<host>example_2_1</host>
<port>2181</port>
</node>
<node index="2">
<host>example_2_2</host>
<port>2181</port>
</node>
<node index="3">
<host>example_2_3</host>
<port>2181</port>
</node>
</zookeeper2>
<zookeeper3>
<node index="1">
<host>example_3_1</host>
<port>2181</port>
</node>
</zookeeper3>
</auxiliary_zookeepers>
```
To store table datameta in a auxiliary ZooKeeper cluster instead of default ZooKeeper cluster, we can use the SQL to create table with
ReplicatedMergeTree engine as follow:
```
CREATE TABLE table_name ( ... ) ENGINE = ReplicatedMergeTree('zookeeper_name_configured_in_auxiliary_zookeepers:path', 'replica_name') ...
```
You can specify any existing ZooKeeper cluster and the system will use a directory on it for its own data (the directory is specified when creating a replicatable table).
If ZooKeeper isnt set in the config file, you cant create replicated tables, and any existing replicated tables will be read-only.
@ -152,7 +188,7 @@ 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:

View File

@ -11,7 +11,7 @@ By going through this tutorial, youll learn how to set up a simple ClickHouse
## Single Node Setup {#single-node-setup}
To postpone the complexities of a distributed environment, well start with deploying ClickHouse on a single server or virtual machine. ClickHouse is usually installed from [deb](../getting-started/install.md#install-from-deb-packages) or [rpm](../getting-started/install.md#from-rpm-packages) packages, but there are [alternatives](../getting-started/install.md#from-docker-image) for the operating systems that do no support them.
To postpone the complexities of a distributed environment, well start with deploying ClickHouse on a single server or virtual machine. ClickHouse is usually installed from [deb](../getting-started/install.md#install-from-deb-packages) or [rpm](../getting-started/install.md#from-rpm-packages) packages, but there are [alternatives](../getting-started/install.md#from-docker-image) for the operating systems that do not support them.
For example, you have chosen `deb` packages and executed:

View File

@ -5,7 +5,7 @@ toc_title: Overview
# What Is ClickHouse? {#what-is-clickhouse}
ClickHouse is a column-oriented database management system (DBMS) for online analytical processing of queries (OLAP).
ClickHouse® is a column-oriented database management system (DBMS) for online analytical processing of queries (OLAP).
In a “normal” row-oriented DBMS, data is stored in this order:

View File

@ -25,6 +25,7 @@ The supported formats are:
| [Vertical](#vertical) | ✗ | ✔ |
| [VerticalRaw](#verticalraw) | ✗ | ✔ |
| [JSON](#json) | ✗ | ✔ |
| [JSONAsString](#jsonasstring) | ✔ | ✗ |
| [JSONString](#jsonstring) | ✗ | ✔ |
| [JSONCompact](#jsoncompact) | ✗ | ✔ |
| [JSONCompactString](#jsoncompactstring) | ✗ | ✔ |
@ -507,6 +508,34 @@ Example:
}
```
## JSONAsString {#jsonasstring}
In this format, a single JSON object is interpreted as a single value. If input has several JSON objects (comma separated) they will be interpreted as a sepatate rows.
This format can only be parsed for table with a single field of type [String](../sql-reference/data-types/string.md). The remaining columns must be set to [DEFAULT](../sql-reference/statements/create/table.md#default) or [MATERIALIZED](../sql-reference/statements/create/table.md#materialized), or omitted. Once you collect whole JSON object to string you can use [JSON functions](../sql-reference/functions/json-functions.md) to process it.
**Example**
Query:
``` sql
DROP TABLE IF EXISTS json_as_string;
CREATE TABLE json_as_string (json String) ENGINE = Memory;
INSERT INTO json_as_string FORMAT JSONAsString {"foo":{"bar":{"x":"y"},"baz":1}},{},{"any json stucture":1}
SELECT * FROM json_as_string;
```
Result:
``` text
┌─json──────────────────────────────┐
│ {"foo":{"bar":{"x":"y"},"baz":1}} │
│ {} │
│ {"any json stucture":1} │
└───────────────────────────────────┘
```
## JSONCompact {#jsoncompact}
## JSONCompactString {#jsoncompactstring}

View File

@ -23,6 +23,7 @@ toc_title: Adopters
| <a href="https://www.bigo.sg/" class="favicon">BIGO</a> | Video | Computing Platform | — | — | [Blog Article, August 2020](https://www.programmersought.com/article/44544895251/) |
| <a href="https://www.bloomberg.com/" class="favicon">Bloomberg</a> | Finance, Media | Monitoring | 102 servers | — | [Slides, May 2018](https://www.slideshare.net/Altinity/http-analytics-for-6m-requests-per-second-using-clickhouse-by-alexander-bocharov) |
| <a href="https://bloxy.info" class="favicon">Bloxy</a> | Blockchain | Analytics | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/4_bloxy.pptx) |
| <a href="https://www.bytedance.com" class="favicon">Bytedance</a> | Social platforms | — | — | — | [The ClickHouse Meetup East, October 2020](https://www.youtube.com/watch?v=ckChUkC3Pns) |
| <a href="https://cardsmobile.ru/" class="favicon">CardsMobile</a> | Finance | Analytics | — | — | [VC.ru](https://vc.ru/s/cardsmobile/143449-rukovoditel-gruppy-analiza-dannyh) |
| <a href="https://carto.com/" class="favicon">CARTO</a> | Business Intelligence | Geo analytics | — | — | [Geospatial processing with ClickHouse](https://carto.com/blog/geospatial-processing-with-clickhouse/) |
| <a href="http://public.web.cern.ch/public/" class="favicon">CERN</a> | Research | Experiment | — | — | [Press release, April 2012](https://www.yandex.com/company/press_center/press_releases/2012/2012-04-10/) |
@ -96,6 +97,7 @@ toc_title: Adopters
| <a href="https://www.splunk.com/" class="favicon">Splunk</a> | Business Analytics | Main product | — | — | [Slides in English, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/splunk.pdf) |
| <a href="https://www.spotify.com" class="favicon">Spotify</a> | Music | Experimentation | — | — | [Slides, July 2018](https://www.slideshare.net/glebus/using-clickhouse-for-experimentation-104247173) |
| <a href="https://www.staffcop.ru/" class="favicon">Staffcop</a> | Information Security | Main Product | — | — | [Official website, Documentation](https://www.staffcop.ru/sce43) |
| <a href="https://www.suning.com/" class="favicon">Suning</a> | E-Commerce | User behaviour analytics | — | — | [Blog article](https://www.sohu.com/a/434152235_411876) |
| <a href="https://www.teralytics.net/" class="favicon">Teralytics</a> | Mobility | Analytics | — | — | [Tech blog](https://www.teralytics.net/knowledge-hub/visualizing-mobility-data-the-scalability-challenge) |
| <a href="https://www.tencent.com" class="favicon">Tencent</a> | Big Data | Data processing | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/5.%20ClickHouse大数据集群应用_李俊飞腾讯网媒事业部.pdf) |
| <a href="https://www.tencent.com" class="favicon">Tencent</a> | Messaging | Logging | — | — | [Talk in Chinese, November 2019](https://youtu.be/T-iVQRuw-QY?t=5050) |
@ -111,7 +113,7 @@ toc_title: Adopters
| <a href="https://cloud.yandex.ru/services/managed-clickhouse" class="favicon">Yandex Cloud</a> | Public Cloud | Main product | — | — | [Talk in Russian, December 2019](https://www.youtube.com/watch?v=pgnak9e_E0o) |
| <a href="https://cloud.yandex.ru/services/datalens" class="favicon">Yandex DataLens</a> | Business Intelligence | Main product | — | — | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/datalens.pdf) |
| <a href="https://market.yandex.ru/" class="favicon">Yandex Market</a> | e-Commerce | Metrics, Logging | — | — | [Talk in Russian, January 2019](https://youtu.be/_l1qP0DyBcA?t=478) |
| <a href="https://metrica.yandex.com" class="favicon">Yandex Metrica</a> | Web analytics | Main product | 360 servers in one cluster, 1862 servers in one department | 66.41 PiB / 5.68 PiB | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/introduction/#13) |
| <a href="https://metrica.yandex.com" class="favicon">Yandex Metrica</a> | Web analytics | Main product | 630 servers in one cluster, 360 servers in another cluster, 1862 servers in one department | 133 PiB / 8.31 PiB / 120 trillion records | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/introduction/#13) |
| <a href="https://htc-cs.ru/" class="favicon">ЦВТ</a> | Software Development | Metrics, Logging | — | — | [Blog Post, March 2019, in Russian](https://vc.ru/dev/62715-kak-my-stroili-monitoring-na-prometheus-clickhouse-i-elk) |
| <a href="https://mkb.ru/" class="favicon">МКБ</a> | Bank | Web-system monitoring | — | — | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/mkb.pdf) |
| <a href="https://cft.ru/" class="favicon">ЦФТ</a> | Banking, Financial products, Payments | — | — | — | [Meetup in Russian, April 2020](https://team.cft.ru/events/162) |

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.

View File

@ -139,7 +139,7 @@ Lazy loading of dictionaries.
If `true`, then each dictionary is created on first use. If dictionary creation failed, the function that was using the dictionary throws an exception.
If `false`, all dictionaries are created when the server starts, and if there is an error, the server shuts down.
If `false`, all dictionaries are created when the server starts, if the dictionary or dictionaries are created too long or are created with errors, then the server boots without of these dictionaries and continues to try to create these dictionaries.
The default is `true`.

View File

@ -2293,6 +2293,47 @@ Result:
└─────────────────────────┴─────────┘
```
## system_events_show_zero_values {#system_events_show_zero_values}
Allows to select zero-valued events from [`system.events`](../../operations/system-tables/events.md).
Some monitoring systems require passing all the metrics values to them for each checkpoint, even if the metric value is zero.
Possible values:
- 0 — Disabled.
- 1 — Enabled.
Default value: `0`.
**Examples**
Query
```sql
SELECT * FROM system.events WHERE event='QueryMemoryLimitExceeded';
```
Result
```text
Ok.
```
Query
```sql
SET system_events_show_zero_values = 1;
SELECT * FROM system.events WHERE event='QueryMemoryLimitExceeded';
```
Result
```text
┌─event────────────────────┬─value─┬─description───────────────────────────────────────────┐
│ QueryMemoryLimitExceeded │ 0 │ Number of times when memory limit exceeded for query. │
└──────────────────────────┴───────┴───────────────────────────────────────────────────────┘
```
## allow_experimental_bigint_types {#allow_experimental_bigint_types}
Enables or disables integer values exceeding the range that is supported by the int data type.

View File

@ -23,4 +23,44 @@ Please note that `errors_count` is updated once per query to the cluster, but `e
- [distributed_replica_error_cap setting](../../operations/settings/settings.md#settings-distributed_replica_error_cap)
- [distributed_replica_error_half_life setting](../../operations/settings/settings.md#settings-distributed_replica_error_half_life)
**Example**
```sql
:) SELECT * FROM system.clusters LIMIT 2 FORMAT Vertical;
```
```text
Row 1:
──────
cluster: test_cluster
shard_num: 1
shard_weight: 1
replica_num: 1
host_name: clickhouse01
host_address: 172.23.0.11
port: 9000
is_local: 1
user: default
default_database:
errors_count: 0
estimated_recovery_time: 0
Row 2:
──────
cluster: test_cluster
shard_num: 1
shard_weight: 1
replica_num: 2
host_name: clickhouse02
host_address: 172.23.0.12
port: 9000
is_local: 0
user: default
default_database:
errors_count: 0
estimated_recovery_time: 0
2 rows in set. Elapsed: 0.002 sec.
```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/clusters) <!--hide-->

View File

@ -23,4 +23,50 @@ The `system.columns` table contains the following columns (the column type is sh
- `is_in_sampling_key` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Flag that indicates whether the column is in the sampling key expression.
- `compression_codec` ([String](../../sql-reference/data-types/string.md)) — Compression codec name.
**Example**
```sql
:) select * from system.columns LIMIT 2 FORMAT Vertical;
```
```text
Row 1:
──────
database: system
table: aggregate_function_combinators
name: name
type: String
default_kind:
default_expression:
data_compressed_bytes: 0
data_uncompressed_bytes: 0
marks_bytes: 0
comment:
is_in_partition_key: 0
is_in_sorting_key: 0
is_in_primary_key: 0
is_in_sampling_key: 0
compression_codec:
Row 2:
──────
database: system
table: aggregate_function_combinators
name: is_internal
type: UInt8
default_kind:
default_expression:
data_compressed_bytes: 0
data_uncompressed_bytes: 0
marks_bytes: 0
comment:
is_in_partition_key: 0
is_in_sorting_key: 0
is_in_primary_key: 0
is_in_sampling_key: 0
compression_codec:
2 rows in set. Elapsed: 0.002 sec.
```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/columns) <!--hide-->

View File

@ -1,9 +1,38 @@
# system.databases {#system-databases}
This table contains a single String column called name the name of a database.
Contains information about the databases that are available to the current user.
Each database that the server knows about has a corresponding entry in the table.
Columns:
This system table is used for implementing the `SHOW DATABASES` query.
- `name` ([String](../../sql-reference/data-types/string.md)) — Database name.
- `engine` ([String](../../sql-reference/data-types/string.md)) — [Database engine](../../engines/database-engines/index.md).
- `data_path` ([String](../../sql-reference/data-types/string.md)) — Data path.
- `metadata_path` ([String](../../sql-reference/data-types/enum.md)) — Metadata path.
- `uuid` ([UUID](../../sql-reference/data-types/uuid.md)) — Database UUID.
The `name` column from this system table is used for implementing the `SHOW DATABASES` query.
**Example**
Create a database.
``` sql
CREATE DATABASE test
```
Check all of the available databases to the user.
``` sql
SELECT * FROM system.databases
```
``` text
┌─name───────────────────────────┬─engine─┬─data_path──────────────────┬─metadata_path───────────────────────────────────────────────────────┬─────────────────────────────────uuid─┐
│ _temporary_and_external_tables │ Memory │ /var/lib/clickhouse/ │ │ 00000000-0000-0000-0000-000000000000 │
│ default │ Atomic │ /var/lib/clickhouse/store/ │ /var/lib/clickhouse/store/d31/d317b4bd-3595-4386-81ee-c2334694128a/ │ d317b4bd-3595-4386-81ee-c2334694128a │
│ test │ Atomic │ /var/lib/clickhouse/store/ │ /var/lib/clickhouse/store/39b/39bf0cc5-4c06-4717-87fe-c75ff3bd8ebb/ │ 39bf0cc5-4c06-4717-87fe-c75ff3bd8ebb │
│ system │ Atomic │ /var/lib/clickhouse/store/ │ /var/lib/clickhouse/store/1d1/1d1c869d-e465-4b1b-a51f-be033436ebf9/ │ 1d1c869d-e465-4b1b-a51f-be033436ebf9 │
└────────────────────────────────┴────────┴────────────────────────────┴─────────────────────────────────────────────────────────────────────┴──────────────────────────────────────┘
```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/databases) <!--hide-->

View File

@ -11,3 +11,21 @@ Columns:
- `keep_free_space` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Amount of disk space that should stay free on disk in bytes. Defined in the `keep_free_space_bytes` parameter of disk configuration.
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/disks) <!--hide-->
**Example**
```sql
:) SELECT * FROM system.disks;
```
```text
┌─name────┬─path─────────────────┬───free_space─┬──total_space─┬─keep_free_space─┐
│ default │ /var/lib/clickhouse/ │ 276392587264 │ 490652508160 │ 0 │
└─────────┴──────────────────────┴──────────────┴──────────────┴─────────────────┘
1 rows in set. Elapsed: 0.001 sec.
```

View File

@ -8,3 +8,26 @@ Columns:
- `is_aggregate`(`UInt8`) — Whether the function is aggregate.
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/functions) <!--hide-->
**Example**
```sql
SELECT * FROM system.functions LIMIT 10;
```
```text
┌─name─────────────────────┬─is_aggregate─┬─case_insensitive─┬─alias_to─┐
│ sumburConsistentHash │ 0 │ 0 │ │
│ yandexConsistentHash │ 0 │ 0 │ │
│ demangle │ 0 │ 0 │ │
│ addressToLine │ 0 │ 0 │ │
│ JSONExtractRaw │ 0 │ 0 │ │
│ JSONExtractKeysAndValues │ 0 │ 0 │ │
│ JSONExtract │ 0 │ 0 │ │
│ JSONExtractString │ 0 │ 0 │ │
│ JSONExtractFloat │ 0 │ 0 │ │
│ JSONExtractInt │ 0 │ 0 │ │
└──────────────────────────┴──────────────┴──────────────────┴──────────┘
10 rows in set. Elapsed: 0.002 sec.
```

View File

@ -10,4 +10,45 @@ Columns:
- `type` (String) — Setting type (implementation specific string value).
- `changed` (UInt8) — Whether the setting was explicitly defined in the config or explicitly changed.
**Example**
```sql
:) SELECT * FROM system.merge_tree_settings LIMIT 4 FORMAT Vertical;
```
```text
Row 1:
──────
name: index_granularity
value: 8192
changed: 0
description: How many rows correspond to one primary key value.
type: SettingUInt64
Row 2:
──────
name: min_bytes_for_wide_part
value: 0
changed: 0
description: Minimal uncompressed size in bytes to create part in wide format instead of compact
type: SettingUInt64
Row 3:
──────
name: min_rows_for_wide_part
value: 0
changed: 0
description: Minimal number of rows to create part in wide format instead of compact
type: SettingUInt64
Row 4:
──────
name: merge_max_block_size
value: 8192
changed: 0
description: How many rows in blocks should be formed for merge operations.
type: SettingUInt64
4 rows in set. Elapsed: 0.001 sec.
```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/merge_tree_settings) <!--hide-->

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