thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-25 17:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'fix-docs' of github.com:qianmoQ/ClickHouse into fix-docs

Browse Source
This commit is contained in:
qianmoQ 2020-12-07 20:40:26 +08:00
commit 3ddd6ad471
895 changed files with 23901 additions and 7746 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

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

8
.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
@ -200,3 +202,7 @@
[submodule "contrib/xz"]
path = contrib/xz
url = https://github.com/xz-mirror/xz
[submodule "contrib/abseil-cpp"]
path = contrib/abseil-cpp
url = https://github.com/ClickHouse-Extras/abseil-cpp.git
branch = lts_2020_02_25

13
CHANGELOG.md
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

5
CMakeLists.txt
View File

@ -154,6 +154,7 @@ endif ()
# Make sure the final executable has symbols exported
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -rdynamic")
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}.")
@ -166,6 +167,7 @@ if (OBJCOPY_PATH)
else ()
message(FATAL_ERROR "Cannot find objcopy.")
endif ()
endif ()
if (OS_DARWIN)
set(WHOLE_ARCHIVE -all_load)
@ -475,9 +477,6 @@ 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 ()

8
README.md
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 +16,5 @@ 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 Meetup (online)](https://www.meetup.com/San-Francisco-Bay-Area-ClickHouse-Meetup/events/274498897/) on 2 December 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.

2
base/common/LineReader.cpp
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;

1
base/common/StringRef.h
View File

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

88
base/common/getMemoryAmount.cpp
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 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;
}

1
base/common/logger_useful.h
View File

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

2
base/common/types.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

17
base/daemon/SentryWriter.cpp
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");

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

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

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

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

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

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

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

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

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

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

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

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

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

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

44
cmake/Modules/Findbtrie.cmake
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
)

27
cmake/Modules/FindgRPC.cmake
View File

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

10
cmake/autogenerated_versions.txt
View File

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

8
cmake/darwin/default_libs.cmake
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

1
cmake/find/avro.cmake
View File

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

10
cmake/find/grpc.cmake
View File

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

2
cmake/find/ssl.cmake
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)

2
cmake/warnings.cmake
View File

@ -23,7 +23,7 @@ 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))
if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE) AND (NOT CMAKE_CXX_COMPILER_ID MATCHES "AppleClang"))
add_warning(frame-larger-than=32768)
endif ()

2
contrib/AMQP-CPP vendored

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

4
contrib/CMakeLists.txt vendored
View File

@ -66,10 +66,6 @@ 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

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

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

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

6
contrib/libbtrie/CMakeLists.txt
View File

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

23
contrib/libbtrie/LICENSE
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.

160
contrib/libbtrie/include/btrie.h
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

460
contrib/libbtrie/src/btrie.c
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;
}

103
contrib/libbtrie/test/test_btrie.c
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

9
contrib/libunwind-cmake/CMakeLists.txt
View File

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

2
contrib/mariadb-connector-c vendored

@ -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

96
debian/clickhouse-server.init vendored
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}"
}

2
docker/client/Dockerfile
View File

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

1
docker/packager/unbundled/Dockerfile
View File

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

2
docker/server/Dockerfile
View File

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

2
docker/test/Dockerfile
View File

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

8
docker/test/coverage/Dockerfile
View File

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

32
docker/test/fasttest/run.sh
View File

@ -15,6 +15,9 @@ stage=${stage:-}
# empty parameter.
read -ra FASTTEST_CMAKE_FLAGS <<< "${FASTTEST_CMAKE_FLAGS:-}"
# Run only matching tests.
FASTTEST_FOCUS=${FASTTEST_FOCUS:-""}
FASTTEST_WORKSPACE=$(readlink -f "${FASTTEST_WORKSPACE:-.}")
FASTTEST_SOURCE=$(readlink -f "${FASTTEST_SOURCE:-$FASTTEST_WORKSPACE/ch}")
FASTTEST_BUILD=$(readlink -f "${FASTTEST_BUILD:-${BUILD:-$FASTTEST_WORKSPACE/build}}")
@ -127,7 +130,31 @@ function clone_submodules
(
cd "$FASTTEST_SOURCE"
SUBMODULES_TO_UPDATE=(contrib/boost contrib/zlib-ng contrib/libxml2 contrib/poco contrib/libunwind contrib/ryu contrib/fmtlib contrib/base64 contrib/cctz contrib/libcpuid contrib/double-conversion contrib/libcxx contrib/libcxxabi contrib/libc-headers contrib/lz4 contrib/zstd contrib/fastops contrib/rapidjson contrib/re2 contrib/sparsehash-c11 contrib/croaring contrib/miniselect contrib/xz)
SUBMODULES_TO_UPDATE=(
contrib/boost
contrib/zlib-ng
contrib/libxml2
contrib/poco
contrib/libunwind
contrib/ryu
contrib/fmtlib
contrib/base64
contrib/cctz
contrib/libcpuid
contrib/double-conversion
contrib/libcxx
contrib/libcxxabi
contrib/libc-headers
contrib/lz4
contrib/zstd
contrib/fastops
contrib/rapidjson
contrib/re2
contrib/sparsehash-c11
contrib/croaring
contrib/miniselect
contrib/xz
)
git submodule sync
git submodule update --init --recursive "${SUBMODULES_TO_UPDATE[@]}"
@ -285,13 +312,14 @@ TESTS_TO_SKIP=(
# 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 "${TESTS_TO_SKIP[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
# substr is to remove semicolon after test name
readarray -t FAILED_TESTS < <(awk '/FAIL|TIMEOUT|ERROR/ { print substr($3, 1, length($3)-1) }' "$FASTTEST_OUTPUT/test_log.txt" | tee "$FASTTEST_OUTPUT/failed-parallel-tests.txt")

2
docker/test/integration/runner/compose/docker_compose_kerberized_kafka.yml
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

10
docker/test/integration/runner/compose/docker_compose_mysql_5_7_for_materialize_mysql.yml Normal file
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

2
docker/test/integration/runner/compose/docker_compose_mysql_8_0.yml → docker/test/integration/runner/compose/docker_compose_mysql_8_0_for_materialize_mysql.yml
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:

2
docker/test/integration/runner/compose/docker_compose_mysql_golang_client.yml
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

2
docker/test/integration/runner/compose/docker_compose_mysql_java_client.yml
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

2
docker/test/integration/runner/compose/docker_compose_mysql_js_client.yml
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

2
docker/test/integration/runner/compose/docker_compose_mysql_php_client.yml
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

2
docker/test/integration/runner/compose/docker_compose_postgesql_java_client.yml
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

3
docker/test/performance-comparison/Dockerfile
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 \

51
docker/test/performance-comparison/perf.py
View File

@ -14,10 +14,12 @@ import string
import sys
import time
import traceback
import logging
import xml.etree.ElementTree as et
from threading import Thread
from scipy import stats
logging.basicConfig(format='%(asctime)s: %(levelname)s: %(module)s: %(message)s', level='WARNING')
total_start_seconds = time.perf_counter()
stage_start_seconds = total_start_seconds
@ -46,6 +48,8 @@ parser.add_argument('--profile-seconds', type=int, default=0, help='For how many
parser.add_argument('--long', action='store_true', help='Do not skip the tests tagged as long.')
parser.add_argument('--print-queries', action='store_true', help='Print test queries and exit.')
parser.add_argument('--print-settings', action='store_true', help='Print test settings and exit.')
parser.add_argument('--keep-created-tables', action='store_true', help="Don't drop the created tables after the test.")
parser.add_argument('--use-existing-tables', action='store_true', help="Don't create or drop the tables, use the existing ones instead.")
args = parser.parse_args()
reportStageEnd('start')
@ -139,16 +143,18 @@ 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.
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):
@ -162,21 +168,12 @@ for conn_index, c in enumerate(all_connections):
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')
@ -194,16 +191,18 @@ 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')]
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.
# 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}'",
@ -215,7 +214,8 @@ def do_create(connection, index, 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))
threads = [
Thread(target = do_create, args = (connection, index, create_queries))
for index, connection in enumerate(all_connections)]
for t in threads:
@ -403,6 +403,7 @@ print(f'profile-total\t{profile_total_seconds}')
reportStageEnd('run')
# Run drop queries
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:

8
docker/test/pvs/Dockerfile
View File

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

4
docker/test/stateful_with_coverage/Dockerfile
View File

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

83
docker/test/stateful_with_coverage/run.sh
View File

@ -1,40 +1,44 @@
#!/bin/bash
kill_clickhouse () {
kill "$(pgrep -u clickhouse)" 2>/dev/null
echo "clickhouse pids $(pgrep -u clickhouse)" | ts '%Y-%m-%d %H:%M:%S'
pkill -f "clickhouse-server" 2>/dev/null
for _ in {1..10}
for _ in {1..120}
do
if ! kill -0 "$(pgrep -u clickhouse)"; then
echo "No clickhouse process"
break
else
echo "Process $(pgrep -u clickhouse) still alive"
sleep 10
fi
if ! pkill -0 -f "clickhouse-server" ; then break ; fi
echo "ClickHouse still alive" | ts '%Y-%m-%d %H:%M:%S'
sleep 1
done
if pkill -0 -f "clickhouse-server"
then
pstree -apgT
jobs
echo "Failed to kill the ClickHouse server" | ts '%Y-%m-%d %H:%M:%S'
return 1
fi
}
start_clickhouse () {
LLVM_PROFILE_FILE='server_%h_%p_%m.profraw' sudo -Eu clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml &
}
wait_llvm_profdata () {
while kill -0 "$(pgrep llvm-profdata-10)"
counter=0
until clickhouse-client --query "SELECT 1"
do
echo "Waiting for profdata $(pgrep llvm-profdata-10) still alive"
sleep 3
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
sleep 0.5
counter=$((counter + 1))
done
}
merge_client_files_in_background () {
client_files=$(ls /client_*profraw 2>/dev/null)
if [ -n "$client_files" ]
then
llvm-profdata-10 merge -sparse "$client_files" -o "merged_client_$(date +%s).profraw"
rm "$client_files"
fi
}
chmod 777 /
@ -51,26 +55,7 @@ chmod 777 -R /var/log/clickhouse-server/
# install test configs
/usr/share/clickhouse-test/config/install.sh
function start()
{
counter=0
until clickhouse-client --query "SELECT 1"
do
if [ "$counter" -gt 120 ]
then
echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
break
fi
timeout 120 service clickhouse-server start
sleep 0.5
counter=$((counter + 1))
done
}
start
start_clickhouse
# shellcheck disable=SC2086 # No quotes because I want to split it into words.
if ! /s3downloader --dataset-names $DATASETS; then
@ -81,10 +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 ||:

6
docker/test/stateless_with_coverage/Dockerfile
View File

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

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

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

2
docs/_includes/cmake_in_clickhouse_header.md
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
```

1
docs/en/development/contrib.md
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) |

4
docs/en/engines/table-engines/mergetree-family/collapsingmergetree.md
View File

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

7
docs/en/engines/table-engines/mergetree-family/replacingmergetree.md
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 can’t plan for it. Some of the data may remain unprocessed. Although you can run an unscheduled merge using the `OPTIMIZE` query, don’t 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**

38
docs/en/engines/table-engines/mergetree-family/replication.md
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 isn’t set in the config file, you can’t 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:

2
docs/en/getting-started/tutorial.md
View File

@ -11,7 +11,7 @@ By going through this tutorial, you’ll learn how to set up a simple ClickHouse
## Single Node Setup {#single-node-setup}
To postpone the complexities of a distributed environment, we’ll 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, we’ll 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:

2
docs/en/index.md
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:

29
docs/en/interfaces/formats.md
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}

4
docs/en/introduction/adopters.md
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) |

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

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

2
docs/en/operations/server-configuration-parameters/settings.md
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`.

41
docs/en/operations/settings/settings.md
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.

35
docs/en/operations/system-tables/databases.md
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-->

10
docs/en/operations/utilities/clickhouse-copier.md
View File

@ -70,11 +70,21 @@ Parameters:
<!-- Configuration of clusters as in an ordinary server config -->
<remote_servers>
<source_cluster>
<!--
source cluster & destination clusters accepts exactly the same
parameters as parameters for usual Distributed table
see https://clickhouse.tech/docs/en/engines/table-engines/special/distributed/
-->
<shard>
<internal_replication>false</internal_replication>
<replica>
<host>127.0.0.1</host>
<port>9000</port>
<!--
<user>default</user>
<password>default</password>
<secure>1</secure>
-->
</replica>
</shard>
...

50
docs/en/operations/utilities/clickhouse-obfuscator.md
View File

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

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

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

57
docs/en/sql-reference/aggregate-functions/reference/avg.md
View File

@ -4,4 +4,59 @@ toc_priority: 5
# avg {#agg_function-avg}
Calculates the average. Only works for numbers. The result is always Float64.
Calculates the arithmetic mean.
**Syntax**
``` sql
avgWeighted(x)
```
**Parameter**
- `x` — Values.
`x` must be
[Integer](../../../sql-reference/data-types/int-uint.md),
[floating-point](../../../sql-reference/data-types/float.md), or
[Decimal](../../../sql-reference/data-types/decimal.md).
**Returned value**
- `NaN` if the supplied parameter is empty.
- Mean otherwise.
**Return type** is always [Float64](../../../sql-reference/data-types/float.md).
**Example**
Query:
``` sql
SELECT avg(x) FROM values('x Int8', 0, 1, 2, 3, 4, 5)
```
Result:
``` text
┌─avg(x)─┐
│ 2.5 │
└────────┘
```
**Example**
Query:
``` sql
CREATE table test (t UInt8) ENGINE = Memory;
SELECT avg(t) FROM test
```
Result:
``` text
┌─avg(x)─┐
│ nan │
└────────┘
```

67
docs/en/sql-reference/aggregate-functions/reference/avgweighted.md
View File

@ -14,17 +14,21 @@ avgWeighted(x, weight)
**Parameters**
- `x` — Values. [Integer](../../../sql-reference/data-types/int-uint.md) or [floating-point](../../../sql-reference/data-types/float.md).
- `weight` — Weights of the values. [Integer](../../../sql-reference/data-types/int-uint.md) or [floating-point](../../../sql-reference/data-types/float.md).
- `x` — Values.
- `weight` — Weights of the values.
Type of `x` and `weight` must be the same.
`x` and `weight` must both be
[Integer](../../../sql-reference/data-types/int-uint.md),
[floating-point](../../../sql-reference/data-types/float.md), or
[Decimal](../../../sql-reference/data-types/decimal.md),
but may have different types.
**Returned value**
- Weighted mean.
- `NaN`. If all the weights are equal to 0.
- `NaN` if all the weights are equal to 0 or the supplied weights parameter is empty.
- Weighted mean otherwise.
Type: [Float64](../../../sql-reference/data-types/float.md).
**Return type** is always [Float64](../../../sql-reference/data-types/float.md).
**Example**
@ -42,3 +46,54 @@ Result:
│ 8 │
└────────────────────────┘
```
**Example**
Query:
``` sql
SELECT avgWeighted(x, w)
FROM values('x Int8, w Float64', (4, 1), (1, 0), (10, 2))
```
Result:
``` text
┌─avgWeighted(x, weight)─┐
│ 8 │
└────────────────────────┘
```
**Example**
Query:
``` sql
SELECT avgWeighted(x, w)
FROM values('x Int8, w Int8', (0, 0), (1, 0), (10, 0))
```
Result:
``` text
┌─avgWeighted(x, weight)─┐
│ nan │
└────────────────────────┘
```
**Example**
Query:
``` sql
CREATE table test (t UInt8) ENGINE = Memory;
SELECT avgWeighted(t) FROM test
```
Result:
``` text
┌─avgWeighted(x, weight)─┐
│ nan │
└────────────────────────┘
```

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

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

53
docs/en/sql-reference/aggregate-functions/reference/rankCorr.md Normal file
View File

@ -0,0 +1,53 @@
## rankCorr {#agg_function-rankcorr}
Computes a rank correlation coefficient.
**Syntax**
``` sql
rankCorr(x, y)
```
**Parameters**
- `x` — Arbitrary value. [Float32](../../../sql-reference/data-types/float.md#float32-float64) or [Float64](../../../sql-reference/data-types/float.md#float32-float64).
- `y` — Arbitrary value. [Float32](../../../sql-reference/data-types/float.md#float32-float64) or [Float64](../../../sql-reference/data-types/float.md#float32-float64).
**Returned value(s)**
- Returns a rank correlation coefficient of the ranks of x and y. The value of the correlation coefficient ranges from -1 to +1. If less than two arguments are passed, the function will return an exception. The value close to +1 denotes a high linear relationship, and with an increase of one random variable, the second random variable also increases. The value close to -1 denotes a high linear relationship, and with an increase of one random variable, the second random variable decreases. The value close or equal to 0 denotes no relationship between the two random variables.
Type: [Float64](../../../sql-reference/data-types/float.md#float32-float64).
**Example**
Query:
``` sql
SELECT rankCorr(number, number) FROM numbers(100);
```
Result:
``` text
┌─rankCorr(number, number)─┐
│ 1 │
└──────────────────────────┘
```
Query:
``` sql
SELECT roundBankers(rankCorr(exp(number), sin(number)), 3) FROM numbers(100);
```
Result:
``` text
┌─roundBankers(rankCorr(exp(number), sin(number)), 3)─┐
│ -0.037 │
└─────────────────────────────────────────────────────┘
```
**See Also**
- [Spearman's rank correlation coefficient](https://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient)

50
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -25,7 +25,37 @@ SELECT
## toTimeZone {#totimezone}
Convert time or date and time to the specified time zone.
Convert time or date and time to the specified time zone. The time zone is an attribute of the Date/DateTime types. The internal value (number of seconds) of the table field or of the resultset's column does not change, the column's type changes and its string representation changes accordingly.
```sql
SELECT
toDateTime('2019-01-01 00:00:00', 'UTC') AS time_utc,
toTypeName(time_utc) AS type_utc,
toInt32(time_utc) AS int32utc,
toTimeZone(time_utc, 'Asia/Yekaterinburg') AS time_yekat,
toTypeName(time_yekat) AS type_yekat,
toInt32(time_yekat) AS int32yekat,
toTimeZone(time_utc, 'US/Samoa') AS time_samoa,
toTypeName(time_samoa) AS type_samoa,
toInt32(time_samoa) AS int32samoa
FORMAT Vertical;
```
```text
Row 1:
──────
time_utc: 2019-01-01 00:00:00
type_utc: DateTime('UTC')
int32utc: 1546300800
time_yekat: 2019-01-01 05:00:00
type_yekat: DateTime('Asia/Yekaterinburg')
int32yekat: 1546300800
time_samoa: 2018-12-31 13:00:00
type_samoa: DateTime('US/Samoa')
int32samoa: 1546300800
```
`toTimeZone(time_utc, 'Asia/Yekaterinburg')` changes the `DateTime('UTC')` type to `DateTime('Asia/Yekaterinburg')`. The value (Unixtimestamp) 1546300800 stays the same, but the string representation (the result of the toString() function) changes from `time_utc: 2019-01-01 00:00:00` to `time_yekat: 2019-01-01 05:00:00`.
## toYear {#toyear}
@ -67,9 +97,8 @@ Leap seconds are not accounted for.
## toUnixTimestamp {#to-unix-timestamp}
For DateTime argument: converts value to its internal numeric representation (Unix Timestamp).
For String argument: parse datetime from string according to the timezone (optional second argument, server timezone is used by default) and returns the corresponding unix timestamp.
For Date argument: the behaviour is unspecified.
For DateTime argument: converts value to the number with type UInt32 -- Unix Timestamp (https://en.wikipedia.org/wiki/Unix_time).
For String argument: converts the input string to the datetime according to the timezone (optional second argument, server timezone is used by default) and returns the corresponding unix timestamp.
**Syntax**
@ -535,18 +564,7 @@ dateDiff('unit', startdate, enddate, [timezone])
- `unit` — Time unit, in which the returned value is expressed. [String](../../sql-reference/syntax.md#syntax-string-literal).
Supported values:
| unit |
| ---- |
|second |
|minute |
|hour |
|day |
|week |
|month |
|quarter |
|year |
Supported values: second, minute, hour, day, week, month, quarter, year.
- `startdate` — The first time value to compare. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).

12
docs/en/sql-reference/functions/in-functions.md
View File

@ -9,16 +9,4 @@ toc_title: IN Operator
See the section [IN operators](../../sql-reference/operators/in.md#select-in-operators).
## tuple(x, y, …), operator (x, y, …) {#tuplex-y-operator-x-y}
A function that allows grouping multiple columns.
For columns with the types T1, T2, …, it returns a Tuple(T1, T2, …) type tuple containing these columns. There is no cost to execute the function.
Tuples are normally used as intermediate values for an argument of IN operators, or for creating a list of formal parameters of lambda functions. Tuples can’t be written to a table.
## tupleElement(tuple, n), operator x.N {#tupleelementtuple-n-operator-x-n}
A function that allows getting a column from a tuple.
‘N’ is the column index, starting from 1. N must be a constant. ‘N’ must be a constant. ‘N’ must be a strict postive integer no greater than the size of the tuple.
There is no cost to execute the function.
[Original article](https://clickhouse.tech/docs/en/query_language/functions/in_functions/) <!--hide-->

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

@ -1,5 +1,5 @@
---
toc_priority: 66
toc_priority: 67
toc_title: Other
---

54
docs/en/sql-reference/functions/string-search-functions.md
View File

@ -536,4 +536,58 @@ For case-insensitive search or/and in UTF-8 format use functions `ngramSearchCas
!!! note "Note"
For UTF-8 case we use 3-gram distance. All these are not perfectly fair n-gram distances. We use 2-byte hashes to hash n-grams and then calculate the (non-)symmetric difference between these hash tables – collisions may occur. With UTF-8 case-insensitive format we do not use fair `tolower` function – we zero the 5-th bit (starting from zero) of each codepoint byte and first bit of zeroth byte if bytes more than one – this works for Latin and mostly for all Cyrillic letters.
## countSubstrings(haystack, needle) {#countSubstrings}
Count the number of substring occurrences
For a case-insensitive search, use the function `countSubstringsCaseInsensitive` (or `countSubstringsCaseInsensitiveUTF8`).
**Syntax**
``` sql
countSubstrings(haystack, needle[, start_pos])
```
**Parameters**
- `haystack` — The string to search in. [String](../../sql-reference/syntax.md#syntax-string-literal).
- `needle` — The substring to search for. [String](../../sql-reference/syntax.md#syntax-string-literal).
- `start_pos` – Optional parameter, position of the first character in the string to start search. [UInt](../../sql-reference/data-types/int-uint.md)
**Returned values**
- Number of occurrences.
Type: `Integer`.
**Examples**
Query:
``` sql
SELECT countSubstrings('foobar.com', '.')
```
Result:
``` text
┌─countSubstrings('foobar.com', '.')─┐
│ 1 │
└────────────────────────────────────┘
```
Query:
``` sql
SELECT countSubstrings('aaaa', 'aa')
```
Result:
``` text
┌─countSubstrings('aaaa', 'aa')─┐
│ 2 │
└───────────────────────────────┘
```
[Original article](https://clickhouse.tech/docs/en/query_language/functions/string_search_functions/) <!--hide-->

114
docs/en/sql-reference/functions/tuple-functions.md Normal file
View File

@ -0,0 +1,114 @@
---
toc_priority: 66
toc_title: Tuples
---
# Functions for Working with Tuples {#tuple-functions}
## tuple {#tuple}
A function that allows grouping multiple columns.
For columns with the types T1, T2, …, it returns a Tuple(T1, T2, …) type tuple containing these columns. There is no cost to execute the function.
Tuples are normally used as intermediate values for an argument of IN operators, or for creating a list of formal parameters of lambda functions. Tuples can’t be written to a table.
The function implements the operator `(x, y, …)`.
**Syntax**
``` sql
tuple(x, y, …)
```
## tupleElement {#tupleelement}
A function that allows getting a column from a tuple.
‘N’ is the column index, starting from 1. N must be a constant. ‘N’ must be a constant. ‘N’ must be a strict postive integer no greater than the size of the tuple.
There is no cost to execute the function.
The function implements the operator `x.N`.
**Syntax**
``` sql
tupleElement(tuple, n)
```
## untuple {#untuple}
Performs syntactic substitution of [tuple](../../sql-reference/data-types/tuple.md#tuplet1-t2) elements in the call location.
**Syntax**
``` sql
untuple(x)
```
You can use the `EXCEPT` expression to skip columns as a result of the query.
**Parameters**
- `x` - A `tuple` function, column, or tuple of elements. [Tuple](../../sql-reference/data-types/tuple.md).
**Returned value**
- None.
**Examples**
Input table:
``` text
┌─key─┬─v1─┬─v2─┬─v3─┬─v4─┬─v5─┬─v6────────┐
│ 1 │ 10 │ 20 │ 40 │ 30 │ 15 │ (33,'ab') │
│ 2 │ 25 │ 65 │ 70 │ 40 │ 6 │ (44,'cd') │
│ 3 │ 57 │ 30 │ 20 │ 10 │ 5 │ (55,'ef') │
│ 4 │ 55 │ 12 │ 7 │ 80 │ 90 │ (66,'gh') │
│ 5 │ 30 │ 50 │ 70 │ 25 │ 55 │ (77,'kl') │
└─────┴────┴────┴────┴────┴────┴───────────┘
```
Example of using a `Tuple`-type column as the `untuple` function parameter:
Query:
``` sql
SELECT untuple(v6) FROM kv;
```
Result:
``` text
┌─_ut_1─┬─_ut_2─┐
│ 33 │ ab │
│ 44 │ cd │
│ 55 │ ef │
│ 66 │ gh │
│ 77 │ kl │
└───────┴───────┘
```
Example of using an `EXCEPT` expression:
Query:
``` sql
SELECT untuple((* EXCEPT (v2, v3),)) FROM kv;
```
Result:
``` text
┌─key─┬─v1─┬─v4─┬─v5─┬─v6────────┐
│ 1 │ 10 │ 30 │ 15 │ (33,'ab') │
│ 2 │ 25 │ 40 │ 6 │ (44,'cd') │
│ 3 │ 57 │ 10 │ 5 │ (55,'ef') │
│ 4 │ 55 │ 80 │ 90 │ (66,'gh') │
│ 5 │ 30 │ 25 │ 55 │ (77,'kl') │
└─────┴────┴────┴────┴───────────┘
```
**See Also**
- [Tuple](../../sql-reference/data-types/tuple.md)
[Original article](https://clickhouse.tech/docs/en/sql-reference/functions/tuple-functions/) <!--hide-->

2
docs/en/sql-reference/statements/alter/index/index.md
View File

@ -14,7 +14,7 @@ The following operations are available:
- `ALTER TABLE [db.]table MATERIALIZE INDEX name IN PARTITION partition_name` - The query rebuilds the secondary index `name` in the partition `partition_name`. Implemented as a [mutation](../../../../sql-reference/statements/alter/index.md#mutations).
The first two commands areare lightweight in a sense that they only change metadata or remove files.
The first two commands are lightweight in a sense that they only change metadata or remove files.
Also, they are replicated, syncing indices metadata via ZooKeeper.

18
docs/en/sql-reference/statements/alter/partition.md
View File

@ -21,10 +21,10 @@ The following operations with [partitions](../../../engines/table-engines/merget
<!-- -->
## DETACH PARTITION {#alter_detach-partition}
## DETACH PARTITION\|PART {#alter_detach-partition}
``` sql
ALTER TABLE table_name DETACH PARTITION partition_expr
ALTER TABLE table_name DETACH PARTITION|PART partition_expr
```
Moves all data for the specified partition to the `detached` directory. The server forgets about the detached data partition as if it does not exist. The server will not know about this data until you make the [ATTACH](#alter_attach-partition) query.
@ -32,7 +32,8 @@ Moves all data for the specified partition to the `detached` directory. The serv
Example:
``` sql
ALTER TABLE visits DETACH PARTITION 201901
ALTER TABLE mt DETACH PARTITION '2020-11-21';
ALTER TABLE mt DETACH PART 'all_2_2_0';
```
Read about setting the partition expression in a section [How to specify the partition expression](#alter-how-to-specify-part-expr).
@ -41,10 +42,10 @@ After the query is executed, you can do whatever you want with the data in the `
This query is replicated – it moves the data to the `detached` directory on all replicas. Note that you can execute this query only on a leader replica. To find out if a replica is a leader, perform the `SELECT` query to the [system.replicas](../../../operations/system-tables/replicas.md#system_tables-replicas) table. Alternatively, it is easier to make a `DETACH` query on all replicas - all the replicas throw an exception, except the leader replica.
## DROP PARTITION {#alter_drop-partition}
## DROP PARTITION\|PART {#alter_drop-partition}
``` sql
ALTER TABLE table_name DROP PARTITION partition_expr
ALTER TABLE table_name DROP PARTITION|PART partition_expr
```
Deletes the specified partition from the table. This query tags the partition as inactive and deletes data completely, approximately in 10 minutes.
@ -53,6 +54,13 @@ Read about setting the partition expression in a section [How to specify the par
The query is replicated – it deletes data on all replicas.
Example:
``` sql
ALTER TABLE mt DROP PARTITION '2020-11-21';
ALTER TABLE mt DROP PART 'all_4_4_0';
```
## DROP DETACHED PARTITION\|PART {#alter_drop-detached}
``` sql

30
docs/en/sql-reference/statements/create/table.md
View File

@ -29,6 +29,8 @@ A column description is `name type` in the simplest case. Example: `RegionID UIn
Expressions can also be defined for default values (see below).
If necessary, primary key can be specified, with one or more key expressions.
### With a Schema Similar to Other Table {#with-a-schema-similar-to-other-table}
``` sql
@ -97,6 +99,34 @@ If you add a new column to a table but later change its default expression, the
It is not possible to set default values for elements in nested data structures.
## Primary Key {#primary-key}
You can define a [primary key](../../../engines/table-engines/mergetree-family/mergetree.md#primary-keys-and-indexes-in-queries) when creating a table. Primary key can be specified in two ways:
- inside the column list
``` sql
CREATE TABLE db.table_name
(
name1 type1, name2 type2, ...,
PRIMARY KEY(expr1[, expr2,...])]
)
ENGINE = engine;
```
- outside the column list
``` sql
CREATE TABLE db.table_name
(
name1 type1, name2 type2, ...
)
ENGINE = engine
PRIMARY KEY(expr1[, expr2,...]);
```
You can't combine both ways in one query.
## Constraints {#constraints}
Along with columns descriptions constraints could be defined:

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

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

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

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

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

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

1
docs/es/development/contrib.md
View File

@ -19,7 +19,6 @@ toc_title: Bibliotecas de terceros utilizadas
| Más información | [Licencia de 3 cláusulas BSD](https://github.com/google/googletest/blob/master/LICENSE) |
| H3 | [Licencia Apache 2.0](https://github.com/uber/h3/blob/master/LICENSE) |
| hyperscan | [Licencia de 3 cláusulas BSD](https://github.com/intel/hyperscan/blob/master/LICENSE) |
| libbtrie | [Licencia BSD de 2 cláusulas](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 | [Licencia Zlib](https://github.com/ClickHouse/ClickHouse/blob/master/contrib/libdivide/LICENSE.txt) |
| libgsasl | [Información adicional](https://github.com/ClickHouse-Extras/libgsasl/blob/3b8948a4042e34fb00b4fb987535dc9e02e39040/LICENSE) |

1
docs/fa/development/contrib.md
View File

@ -21,7 +21,6 @@ toc_title: "\u06A9\u062A\u0627\u0628\u062E\u0627\u0646\u0647 \u0647\u0627\u06CC
| googletest | [لیسانس 3 بند](https://github.com/google/googletest/blob/master/LICENSE) |
| اچ 3 | [نمایی مجوز 2.0](https://github.com/uber/h3/blob/master/LICENSE) |
| hyperscan | [لیسانس 3 بند](https://github.com/intel/hyperscan/blob/master/LICENSE) |
| لیبتری | [لیسانس 2 بند](https://github.com/ClickHouse/ClickHouse/blob/master/contrib/libbtrie/LICENSE) |
| شکنجه نوجوان | [BSD + MIT](https://github.com/ClickHouse/ClickHouse/blob/master/libs/libglibc-compatibility/libcxxabi/LICENSE.TXT) |
| لیبیدوید | [مجوز زلب](https://github.com/ClickHouse/ClickHouse/blob/master/contrib/libdivide/LICENSE.txt) |
| نوشیدن شراب | [الجی پی ال2.1](https://github.com/ClickHouse-Extras/libgsasl/blob/3b8948a4042e34fb00b4fb987535dc9e02e39040/LICENSE) |

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