Merge remote-tracking branch 'origin/master' into HEAD

This commit is contained in:
Alexander Kuzmenkov 2021-02-02 19:12:46 +03:00
commit 264aea20be
993 changed files with 24228 additions and 13395 deletions

View File

@ -0,0 +1,19 @@
---
name: Sanitizer alert
about: Potential issue has been found by special code instrumentation
title: ''
labels: testing
assignees: ''
---
(you don't have to strictly follow this form)
**Describe the bug**
A link to the report
**How to reproduce**
Try to reproduce the report and copy the tables and queries involved.
**Error message and/or stacktrace**
You can find additional information in server logs.

4
.gitmodules vendored
View File

@ -84,7 +84,7 @@
url = https://github.com/google/brotli.git
[submodule "contrib/h3"]
path = contrib/h3
url = https://github.com/uber/h3
url = https://github.com/ClickHouse-Extras/h3
[submodule "contrib/hyperscan"]
path = contrib/hyperscan
url = https://github.com/ClickHouse-Extras/hyperscan.git
@ -184,7 +184,7 @@
url = https://github.com/ClickHouse-Extras/krb5
[submodule "contrib/cyrus-sasl"]
path = contrib/cyrus-sasl
url = https://github.com/cyrusimap/cyrus-sasl
url = https://github.com/ClickHouse-Extras/cyrus-sasl
branch = cyrus-sasl-2.1
[submodule "contrib/croaring"]
path = contrib/croaring

45
.pylintrc Normal file
View File

@ -0,0 +1,45 @@
# vim: ft=config
[BASIC]
max-module-lines=2000
# due to SQL
max-line-length=200
# Drop/decrease them one day:
max-branches=50
max-nested-blocks=10
max-statements=200
[FORMAT]
ignore-long-lines = (# )?<?https?://\S+>?$
[MESSAGES CONTROL]
disable = bad-continuation,
missing-docstring,
bad-whitespace,
too-few-public-methods,
invalid-name,
too-many-arguments,
keyword-arg-before-vararg,
too-many-locals,
too-many-instance-attributes,
cell-var-from-loop,
fixme,
too-many-public-methods,
wildcard-import,
unused-wildcard-import,
singleton-comparison,
# pytest.mark.parametrize is not callable (not-callable)
not-callable,
# https://github.com/PyCQA/pylint/issues/3882
# [Python 3.9] Value 'Optional' is unsubscriptable (unsubscriptable-object) (also Union)
unsubscriptable-object,
# Drop them one day:
redefined-outer-name,
broad-except,
bare-except,
no-else-return,
global-statement
[SIMILARITIES]
# due to SQL
min-similarity-lines=1000

View File

@ -1,4 +1,4 @@
Copyright 2016-2020 Yandex LLC
Copyright 2016-2021 Yandex LLC
Apache License
Version 2.0, January 2004
@ -188,7 +188,7 @@ Copyright 2016-2020 Yandex LLC
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2016-2020 Yandex LLC
Copyright 2016-2021 Yandex LLC
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.

View File

@ -16,5 +16,4 @@ ClickHouse® is an open-source column-oriented database management system that a
* You can also [fill this form](https://clickhouse.tech/#meet) to meet Yandex ClickHouse team in person.
## Upcoming Events
* [SF Bay Area ClickHouse Virtual Office Hours (online)](https://www.meetup.com/San-Francisco-Bay-Area-ClickHouse-Meetup/events/274273549/) on 20 January 2020.
* [Chinese ClickHouse Meetup (online)](http://hdxu.cn/8KxZE) on 6 February 2020.
* [Chinese ClickHouse Meetup (online)](http://hdxu.cn/8KxZE) on 6 February 2021.

View File

@ -15,9 +15,13 @@ currently being supported with security updates:
| 20.4 | :x: |
| 20.5 | :x: |
| 20.6 | :x: |
| 20.7 | :white_check_mark: |
| 20.7 | :x: |
| 20.8 | :white_check_mark: |
| 20.9 | :white_check_mark: |
| 20.9 | :x: |
| 20.10 | :x: |
| 20.11 | :white_check_mark: |
| 20.12 | :white_check_mark: |
| 21.1 | :white_check_mark: |
## Reporting a Vulnerability

View File

@ -229,8 +229,12 @@ public:
inline UInt8 daysInMonth(UInt16 year, UInt8 month) const
{
UInt16 idx = year - DATE_LUT_MIN_YEAR;
if (unlikely(idx >= DATE_LUT_YEARS))
return 31; /// Implementation specific behaviour on overflow.
/// 32 makes arithmetic more simple.
DayNum any_day_of_month = DayNum(years_lut[year - DATE_LUT_MIN_YEAR] + 32 * (month - 1));
DayNum any_day_of_month = DayNum(years_lut[idx] + 32 * (month - 1));
return lut[any_day_of_month].days_in_month;
}
@ -767,7 +771,7 @@ public:
/// Adding calendar intervals.
/// Implementation specific behaviour when delta is too big.
inline time_t addDays(time_t t, Int64 delta) const
inline NO_SANITIZE_UNDEFINED time_t addDays(time_t t, Int64 delta) const
{
DayNum index = findIndex(t);
time_t time_offset = toHour(t) * 3600 + toMinute(t) * 60 + toSecond(t);
@ -780,7 +784,7 @@ public:
return lut[index].date + time_offset;
}
inline time_t addWeeks(time_t t, Int64 delta) const
inline NO_SANITIZE_UNDEFINED time_t addWeeks(time_t t, Int64 delta) const
{
return addDays(t, delta * 7);
}
@ -812,7 +816,7 @@ public:
return lut[result_day].date + time_offset;
}
inline DayNum addMonths(DayNum d, Int64 delta) const
inline NO_SANITIZE_UNDEFINED DayNum addMonths(DayNum d, Int64 delta) const
{
const Values & values = lut[d];
@ -836,18 +840,18 @@ public:
}
}
inline time_t addQuarters(time_t t, Int64 delta) const
inline NO_SANITIZE_UNDEFINED time_t addQuarters(time_t t, Int64 delta) const
{
return addMonths(t, delta * 3);
}
inline DayNum addQuarters(DayNum d, Int64 delta) const
inline NO_SANITIZE_UNDEFINED DayNum addQuarters(DayNum d, Int64 delta) const
{
return addMonths(d, delta * 3);
}
/// Saturation can occur if 29 Feb is mapped to non-leap year.
inline time_t addYears(time_t t, Int64 delta) const
inline NO_SANITIZE_UNDEFINED time_t addYears(time_t t, Int64 delta) const
{
DayNum result_day = addYears(toDayNum(t), delta);
@ -859,7 +863,7 @@ public:
return lut[result_day].date + time_offset;
}
inline DayNum addYears(DayNum d, Int64 delta) const
inline NO_SANITIZE_UNDEFINED DayNum addYears(DayNum d, Int64 delta) const
{
const Values & values = lut[d];

View File

@ -84,10 +84,12 @@
# define NO_SANITIZE_UNDEFINED __attribute__((__no_sanitize__("undefined")))
# define NO_SANITIZE_ADDRESS __attribute__((__no_sanitize__("address")))
# define NO_SANITIZE_THREAD __attribute__((__no_sanitize__("thread")))
# define ALWAYS_INLINE_NO_SANITIZE_UNDEFINED __attribute__((__always_inline__, __no_sanitize__("undefined")))
#else /// It does not work in GCC. GCC 7 cannot recognize this attribute and GCC 8 simply ignores it.
# define NO_SANITIZE_UNDEFINED
# define NO_SANITIZE_ADDRESS
# define NO_SANITIZE_THREAD
# define ALWAYS_INLINE_NO_SANITIZE_UNDEFINED ALWAYS_INLINE
#endif
/// A template function for suppressing warnings about unused variables or function results.

View File

@ -104,8 +104,3 @@ template <> struct is_big_int<wUInt256> { static constexpr bool value = true; };
template <typename T>
inline constexpr bool is_big_int_v = is_big_int<T>::value;
template <typename To, typename From>
inline To bigint_cast(const From & x [[maybe_unused]])
{
return static_cast<To>(x);
}

View File

@ -27,9 +27,12 @@ if (GLIBC_COMPATIBILITY)
list(APPEND glibc_compatibility_sources musl/getentropy.c)
endif()
add_library (clickhouse_memcpy OBJECT
${ClickHouse_SOURCE_DIR}/contrib/FastMemcpy/memcpy_wrapper.c
)
if (NOT ARCH_ARM)
# clickhouse_memcpy don't support ARCH_ARM, see https://github.com/ClickHouse/ClickHouse/issues/18951
add_library (clickhouse_memcpy OBJECT
${ClickHouse_SOURCE_DIR}/contrib/FastMemcpy/memcpy_wrapper.c
)
endif()
# Need to omit frame pointers to match the performance of glibc
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fomit-frame-pointer")

View File

@ -31,7 +31,7 @@ static void *volatile vdso_func = (void *)getcpu_init;
int sched_getcpu(void)
{
int r;
unsigned cpu;
unsigned cpu = 0;
#ifdef VDSO_GETCPU_SYM
getcpu_f f = (getcpu_f)vdso_func;

View File

@ -118,7 +118,9 @@ TRAP(logout)
TRAP(logwtmp)
TRAP(lrand48)
TRAP(mallinfo)
TRAP(mallopt)
#if !defined(SANITIZER)
TRAP(mallopt) // Used by tsan
#endif
TRAP(mblen)
TRAP(mbrlen)
TRAP(mbrtowc)
@ -193,7 +195,9 @@ TRAP(dbm_nextkey)
TRAP(dbm_open)
TRAP(dbm_store)
TRAP(dirname)
TRAP(dlerror)
#if !defined(SANITIZER)
TRAP(dlerror) // Used by tsan
#endif
TRAP(ftw)
TRAP(getc_unlocked)
//TRAP(getenv) // Ok at program startup

View File

@ -116,8 +116,8 @@ void Connection::connect(const char* db,
if (!mysql_real_connect(driver.get(), server, user, password, db, port, ifNotEmpty(socket), driver->client_flag))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
/// Sets UTF-8 as default encoding.
if (mysql_set_character_set(driver.get(), "UTF8"))
/// Sets UTF-8 as default encoding. See https://mariadb.com/kb/en/mysql_set_character_set/
if (mysql_set_character_set(driver.get(), "utf8mb4"))
throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
is_connected = true;

View File

@ -1,9 +1,9 @@
# This strings autochanged from release_lib.sh:
SET(VERSION_REVISION 54445)
SET(VERSION_REVISION 54448)
SET(VERSION_MAJOR 21)
SET(VERSION_MINOR 1)
SET(VERSION_MINOR 3)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 667dd0cf0ccecdaa6f334177b7ece2f53bd196a1)
SET(VERSION_DESCRIBE v21.1.1.5646-prestable)
SET(VERSION_STRING 21.1.1.5646)
SET(VERSION_GITHASH ef72ba7349f230321750c13ee63b49a11a7c0adc)
SET(VERSION_DESCRIBE v21.3.1.1-prestable)
SET(VERSION_STRING 21.3.1.1)
# end of autochange

View File

@ -1,10 +1,4 @@
if (NOT ARCH_ARM AND OPENSSL_FOUND)
option (ENABLE_RDKAFKA "Enable kafka" ${ENABLE_LIBRARIES})
elseif(ENABLE_RDKAFKA AND NOT OPENSSL_FOUND)
message (${RECONFIGURE_MESSAGE_LEVEL} "Can't use librdkafka without SSL")
elseif(ENABLE_RDKAFKA)
message (${RECONFIGURE_MESSAGE_LEVEL} "librdafka is not supported on ARM and on FreeBSD")
endif ()
option (ENABLE_RDKAFKA "Enable kafka" ${ENABLE_LIBRARIES})
if (NOT ENABLE_RDKAFKA)
if (USE_INTERNAL_RDKAFKA_LIBRARY)
@ -13,11 +7,7 @@ if (NOT ENABLE_RDKAFKA)
return()
endif()
if (NOT ARCH_ARM)
option (USE_INTERNAL_RDKAFKA_LIBRARY "Set to FALSE to use system librdkafka instead of the bundled" ${NOT_UNBUNDLED})
elseif(USE_INTERNAL_RDKAFKA_LIBRARY)
message (${RECONFIGURE_MESSAGE_LEVEL} "Can't use internal librdkafka with ARCH_ARM=${ARCH_ARM}")
endif ()
option (USE_INTERNAL_RDKAFKA_LIBRARY "Set to FALSE to use system librdkafka instead of the bundled" ${NOT_UNBUNDLED})
if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/cppkafka/CMakeLists.txt")
if(USE_INTERNAL_RDKAFKA_LIBRARY)
@ -67,14 +57,12 @@ if (RDKAFKA_LIB AND RDKAFKA_INCLUDE_DIR)
if (LZ4_LIBRARY)
list (APPEND RDKAFKA_LIBRARY ${LZ4_LIBRARY})
endif ()
elseif (NOT MISSING_INTERNAL_RDKAFKA_LIBRARY AND NOT MISSING_INTERNAL_CPPKAFKA_LIBRARY AND NOT ARCH_ARM)
elseif (NOT MISSING_INTERNAL_RDKAFKA_LIBRARY AND NOT MISSING_INTERNAL_CPPKAFKA_LIBRARY)
set (USE_INTERNAL_RDKAFKA_LIBRARY 1)
set (RDKAFKA_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/librdkafka/src")
set (RDKAFKA_LIBRARY rdkafka)
set (CPPKAFKA_LIBRARY cppkafka)
set (USE_RDKAFKA 1)
elseif(ARCH_ARM)
message (${RECONFIGURE_MESSAGE_LEVEL} "Using internal rdkafka on ARM is not supported")
endif ()
message (STATUS "Using librdkafka=${USE_RDKAFKA}: ${RDKAFKA_INCLUDE_DIR} : ${RDKAFKA_LIBRARY} ${CPPKAFKA_LIBRARY}")

View File

@ -35,6 +35,7 @@ if (NOT ZLIB_FOUND AND NOT MISSING_INTERNAL_ZLIB_LIBRARY)
set (ZLIB_INCLUDE_DIRECTORIES ${ZLIB_INCLUDE_DIR}) # for protobuf
set (ZLIB_FOUND 1) # for poco
set (ZLIB_LIBRARIES zlib CACHE INTERNAL "")
set (ZLIB_LIBRARY_NAME ${ZLIB_LIBRARIES}) # for cassandra
set (ZLIB_NAME "${INTERNAL_ZLIB_NAME}")
endif ()

2
contrib/aws vendored

@ -1 +1 @@
Subproject commit a220591e335923ce1c19bbf9eb925787f7ab6c13
Subproject commit 7d48b2c8193679cc4516e5bd68ae4a64b94dae7d

2
contrib/cassandra vendored

@ -1 +1 @@
Subproject commit d10187efb25b26da391def077edf3c6f2f3a23dd
Subproject commit b446d7eb68e6962f431e2b3771313bfe9a2bbd93

2
contrib/h3 vendored

@ -1 +1 @@
Subproject commit 6cfd649e8c0d3ed913e8aae928a669fc3b8a2365
Subproject commit e209086ae1b5477307f545a0f6111780edc59940

View File

@ -16,6 +16,7 @@ ${H3_SOURCE_DIR}/lib/mathExtensions.c
${H3_SOURCE_DIR}/lib/polygon.c
${H3_SOURCE_DIR}/lib/vec2d.c
${H3_SOURCE_DIR}/lib/vec3d.c
${H3_SOURCE_DIR}/lib/vertex.c
${H3_SOURCE_DIR}/lib/vertexGraph.c
)

2
contrib/hyperscan vendored

@ -1 +1 @@
Subproject commit 3907fd00ee8b2538739768fa9533f8635a276531
Subproject commit e9f08df0213fc637aac0a5bbde9beeaeba2fe9fa

2
contrib/libpq vendored

@ -1 +1 @@
Subproject commit 8e7e905854714a7fbb49c124dbc45c7bd4b98e07
Subproject commit 1f9c286dba60809edb64e384d6727d80d269b6cf

View File

@ -50,12 +50,12 @@ set(SRCS
${RDKAFKA_SOURCE_DIR}/rdkafka_request.c
${RDKAFKA_SOURCE_DIR}/rdkafka_roundrobin_assignor.c
${RDKAFKA_SOURCE_DIR}/rdkafka_sasl.c
# ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_cyrus.c # optionally included below
${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_oauthbearer.c
# ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_cyrus.c # optionally included below
# ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_oauthbearer.c # optionally included below
${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_plain.c
${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_scram.c
# ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_scram.c # optionally included below
# ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_win32.c
${RDKAFKA_SOURCE_DIR}/rdkafka_ssl.c
# ${RDKAFKA_SOURCE_DIR}/rdkafka_ssl.c # optionally included below
${RDKAFKA_SOURCE_DIR}/rdkafka_sticky_assignor.c
${RDKAFKA_SOURCE_DIR}/rdkafka_subscription.c
${RDKAFKA_SOURCE_DIR}/rdkafka_timer.c
@ -82,10 +82,33 @@ set(SRCS
if(${ENABLE_CYRUS_SASL})
message (STATUS "librdkafka with SASL support")
set(SRCS
${SRCS}
${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_cyrus.c # needed to support Kerberos, requires cyrus-sasl
)
set(WITH_SASL_CYRUS 1)
endif()
if(OPENSSL_FOUND)
message (STATUS "librdkafka with SSL support")
set(WITH_SSL 1)
if(${ENABLE_CYRUS_SASL})
set(WITH_SASL_SCRAM 1)
set(WITH_SASL_OAUTHBEARER 1)
endif()
endif()
if(WITH_SSL)
list(APPEND SRCS ${RDKAFKA_SOURCE_DIR}/rdkafka_ssl.c)
endif()
if(WITH_SASL_CYRUS)
list(APPEND SRCS ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_cyrus.c) # needed to support Kerberos, requires cyrus-sasl
endif()
if(WITH_SASL_SCRAM)
list(APPEND SRCS ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_scram.c)
endif()
if(WITH_SASL_OAUTHBEARER)
list(APPEND SRCS ${RDKAFKA_SOURCE_DIR}/rdkafka_sasl_oauthbearer.c)
endif()
add_library(rdkafka ${SRCS})
@ -101,7 +124,6 @@ if(OPENSSL_SSL_LIBRARY AND OPENSSL_CRYPTO_LIBRARY)
endif()
if(${ENABLE_CYRUS_SASL})
target_link_libraries(rdkafka PRIVATE ${CYRUS_SASL_LIBRARY})
set(WITH_SASL_CYRUS 1)
endif()
file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/auxdir)

View File

@ -1,7 +1,6 @@
// Originally generated by ./configure
#ifndef _CONFIG_H_
#define _CONFIG_H_
#define ARCH "x86_64"
#define BUILT_WITH "GCC GXX PKGCONFIG OSXLD LIBDL PLUGINS ZLIB SSL SASL_CYRUS ZSTD HDRHISTOGRAM LZ4_EXT SNAPPY SOCKEM SASL_SCRAM CRC32C_HW"
#define CPU "generic"
@ -60,14 +59,14 @@
// WITH_SOCKEM
#define WITH_SOCKEM 1
// libssl
#define WITH_SSL 1
#cmakedefine WITH_SSL 1
// WITH_SASL_SCRAM
#define WITH_SASL_SCRAM 1
#cmakedefine WITH_SASL_SCRAM 1
// WITH_SASL_OAUTHBEARER
#define WITH_SASL_OAUTHBEARER 1
#cmakedefine WITH_SASL_OAUTHBEARER 1
#cmakedefine WITH_SASL_CYRUS 1
// crc32chw
#if !defined(__PPC__)
#if !defined(__PPC__) && (!defined(__aarch64__) || defined(__ARM_FEATURE_CRC32))
#define WITH_CRC32C_HW 1
#endif
// regex

2
contrib/libuv vendored

@ -1 +1 @@
Subproject commit bc14c44b6269c458f2cc7e09eb300f4b64899903
Subproject commit e2e9b7e9f978ce8a1367b5fe781d97d1ce9f94ab

2
contrib/poco vendored

@ -1 +1 @@
Subproject commit 2c32e17c7dfee1f8bf24227b697cdef5fddf0823
Subproject commit e11f3c971570cf6a31006cd21cadf41a259c360a

4
debian/changelog vendored
View File

@ -1,5 +1,5 @@
clickhouse (21.1.0) unstable; urgency=low
clickhouse (21.3.1.1) unstable; urgency=low
* Modified source code
-- Alexey Milovidov <milovidov@yandex-team.ru> Mon, 11 Jan 2021 03:51:08 +0300
-- clickhouse-release <clickhouse-release@yandex-team.ru> Mon, 01 Feb 2021 12:50:53 +0300

View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.1.0
ARG version=21.3.1.*
RUN apt-get update \
&& apt-get install --yes --no-install-recommends \

View File

@ -1,7 +1,7 @@
FROM ubuntu:20.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.1.0
ARG version=21.3.1.*
ARG gosu_ver=1.10
# user/group precreated explicitly with fixed uid/gid on purpose.
@ -10,7 +10,6 @@ ARG gosu_ver=1.10
# We do that in advance at the begining of Dockerfile before any packages will be
# installed to prevent picking those uid / gid by some unrelated software.
# The same uid / gid (101) is used both for alpine and ubuntu.
# Number 101 is used by default in openshift
RUN groupadd -r clickhouse --gid=101 \
&& useradd -r -g clickhouse --uid=101 --home-dir=/var/lib/clickhouse --shell=/bin/bash clickhouse \
@ -37,7 +36,12 @@ RUN groupadd -r clickhouse --gid=101 \
/var/lib/apt/lists/* \
/var/cache/debconf \
/tmp/* \
&& apt-get clean
&& apt-get clean \
&& mkdir -p /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client \
&& chmod ugo+Xrw -R /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client
# we need to allow "others" access to clickhouse folder, because docker container
# can be started with arbitrary uid (openshift usecase)
ADD https://github.com/tianon/gosu/releases/download/$gosu_ver/gosu-amd64 /bin/gosu

View File

@ -14,16 +14,18 @@ COPY alpine-root/ /
# We do that in advance at the begining of Dockerfile before any packages will be
# installed to prevent picking those uid / gid by some unrelated software.
# The same uid / gid (101) is used both for alpine and ubuntu.
# Number 101 is used by default in openshift
RUN addgroup -S -g 101 clickhouse \
&& adduser -S -h /var/lib/clickhouse -s /bin/bash -G clickhouse -g "ClickHouse server" -u 101 clickhouse \
&& mkdir -p /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client \
&& chown clickhouse:clickhouse /var/lib/clickhouse \
&& chmod 700 /var/lib/clickhouse \
&& chown root:clickhouse /var/log/clickhouse-server \
&& chmod 775 /var/log/clickhouse-server \
&& chmod +x /entrypoint.sh \
&& apk add --no-cache su-exec bash
&& apk add --no-cache su-exec bash \
&& chmod ugo+Xrw -R /var/lib/clickhouse /var/log/clickhouse-server /etc/clickhouse-server /etc/clickhouse-client
# we need to allow "others" access to clickhouse folder, because docker container
# can be started with arbitrary uid (openshift usecase)
EXPOSE 9000 8123 9009

View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.1.0
ARG version=21.3.1.*
RUN apt-get update && \
apt-get install -y apt-transport-https dirmngr && \

View File

@ -43,6 +43,7 @@ RUN apt-get update \
clang-tidy-${LLVM_VERSION} \
cmake \
curl \
lsof \
expect \
fakeroot \
git \

View File

@ -251,8 +251,12 @@ function run_tests
00701_rollup
00834_cancel_http_readonly_queries_on_client_close
00911_tautological_compare
# Hyperscan
00926_multimatch
00929_multi_match_edit_distance
01681_hyperscan_debug_assertion
01031_mutations_interpreter_and_context
01053_ssd_dictionary # this test mistakenly requires acces to /var/lib/clickhouse -- can't run this locally, disabled
01083_expressions_in_engine_arguments
@ -269,6 +273,8 @@ function run_tests
01281_group_by_limit_memory_tracking # max_memory_usage_for_user can interfere another queries running concurrently
01318_encrypt # Depends on OpenSSL
01318_decrypt # Depends on OpenSSL
01663_aes_msan # Depends on OpenSSL
01667_aes_args_check # Depends on OpenSSL
01281_unsucceeded_insert_select_queries_counter
01292_create_user
01294_lazy_database_concurrent
@ -330,9 +336,12 @@ function run_tests
# nc - command not found
01601_proxy_protocol
01622_defaults_for_url_engine
# JSON functions
01666_blns
)
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 "$FASTTEST_OUTPUT/test_log.txt"
time clickhouse-test --hung-check -j 8 --order=random --use-skip-list --no-long --testname --shard --zookeeper --skip "${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")
@ -355,7 +364,7 @@ function run_tests
echo "Going to run again: ${FAILED_TESTS[*]}"
clickhouse-test --order=random --no-long --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_log.txt"
clickhouse-test --hung-check --order=random --no-long --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_log.txt"
else
echo "No failed tests"
fi

View File

@ -11,6 +11,10 @@
<max>10</max>
</max_execution_time>
<max_memory_usage>
<max>10G</max>
</max_memory_usage>
<!-- Not ready for production -->
<compile_expressions>
<readonly />

View File

@ -21,13 +21,16 @@ function clone
git init
git remote add origin https://github.com/ClickHouse/ClickHouse
git fetch --depth=1 origin "$SHA_TO_TEST"
git fetch --depth=1 origin master # Used to obtain the list of modified or added tests
# Network is unreliable. GitHub neither.
for _ in {1..100}; do git fetch --depth=100 origin "$SHA_TO_TEST" && break; sleep 1; done
# Used to obtain the list of modified or added tests
for _ in {1..100}; do git fetch --depth=100 origin master && break; sleep 1; done
# If not master, try to fetch pull/.../{head,merge}
if [ "$PR_TO_TEST" != "0" ]
then
git fetch --depth=1 origin "refs/pull/$PR_TO_TEST/*:refs/heads/pull/$PR_TO_TEST/*"
for _ in {1..100}; do git fetch --depth=100 origin "refs/pull/$PR_TO_TEST/*:refs/heads/pull/$PR_TO_TEST/*" && break; sleep 1; done
fi
git checkout "$SHA_TO_TEST"
@ -75,7 +78,7 @@ function fuzz
{
# Obtain the list of newly added tests. They will be fuzzed in more extreme way than other tests.
cd ch
NEW_TESTS=$(git diff --name-only master "$SHA_TO_TEST" | grep -P 'tests/queries/0_stateless/.*\.sql' | sed -r -e 's!^!ch/!' | sort -R)
NEW_TESTS=$(git diff --name-only "$(git merge-base origin/master "$SHA_TO_TEST"~)" "$SHA_TO_TEST" | grep -P 'tests/queries/0_stateless/.*\.sql' | sed -r -e 's!^!ch/!' | sort -R)
cd ..
if [[ -n "$NEW_TESTS" ]]
then
@ -85,6 +88,7 @@ function fuzz
fi
./clickhouse-server --config-file db/config.xml -- --path db 2>&1 | tail -100000 > server.log &
server_pid=$!
kill -0 $server_pid
while ! ./clickhouse-client --query "select 1" && kill -0 $server_pid ; do echo . ; sleep 1 ; done
@ -92,6 +96,17 @@ function fuzz
kill -0 $server_pid
echo Server started
echo "
handle all noprint
handle SIGSEGV stop print
handle SIGBUS stop print
continue
thread apply all backtrace
continue
" > script.gdb
gdb -batch -command script.gdb -p "$(pidof clickhouse-server)" &
fuzzer_exit_code=0
# SC2012: Use find instead of ls to better handle non-alphanumeric filenames. They are all alphanumeric.
# SC2046: Quote this to prevent word splitting. Actually I need word splitting.
@ -175,16 +190,16 @@ case "$stage" in
# Lost connection to the server. This probably means that the server died
# with abort.
echo "failure" > status.txt
if ! grep -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*" server.log > description.txt
if ! grep -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*" server.log > description.txt
then
echo "Lost connection to server. See the logs" > description.txt
echo "Lost connection to server. See the logs." > description.txt
fi
else
# Something different -- maybe the fuzzer itself died? Don't grep the
# server log in this case, because we will find a message about normal
# server termination (Received signal 15), which is confusing.
echo "failure" > status.txt
echo "Fuzzer failed ($fuzzer_exit_code). See the logs" > description.txt
echo "Fuzzer failed ($fuzzer_exit_code). See the logs." > description.txt
fi
;&
"report")

View File

@ -62,6 +62,7 @@ RUN python3 -m pip install \
avro \
cassandra-driver \
confluent-kafka \
dict2xml \
dicttoxml \
docker \
docker-compose==1.22.0 \

View File

@ -1,4 +1,4 @@
#!/usr/bin/python3
#!/usr/bin/env python3
import argparse
import clickhouse_driver

View File

@ -14,12 +14,12 @@ cd /sqlancer/sqlancer-master
export TIMEOUT=60
export NUM_QUERIES=1000
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere | tee /test_output/TLPWhere.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhere.err
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPGroupBy | tee /test_output/TLPGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPGroupBy.err
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPHaving | tee /test_output/TLPHaving.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPHaving.err
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere --oracle TLPGroupBy | tee /test_output/TLPWhereGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhereGroupBy.err
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPDistinct | tee /test_output/TLPDistinct.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPDistinct.err
( java -jar target/SQLancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPAggregate | tee /test_output/TLPAggregate.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPAggregate.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere | tee /test_output/TLPWhere.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhere.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPGroupBy | tee /test_output/TLPGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPGroupBy.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPHaving | tee /test_output/TLPHaving.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPHaving.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPWhere --oracle TLPGroupBy | tee /test_output/TLPWhereGroupBy.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPWhereGroupBy.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPDistinct | tee /test_output/TLPDistinct.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPDistinct.err
( java -jar target/sqlancer-*.jar --num-threads 10 --timeout-seconds $TIMEOUT --num-queries $NUM_QUERIES --username default --password "" clickhouse --oracle TLPAggregate | tee /test_output/TLPAggregate.out ) 3>&1 1>&2 2>&3 | tee /test_output/TLPAggregate.err
service clickhouse-server stop && sleep 10

View File

@ -53,14 +53,15 @@ function run_tests()
if [ "$NUM_TRIES" -gt "1" ]; then
ADDITIONAL_OPTIONS+=('--skip')
ADDITIONAL_OPTIONS+=('00000_no_tests_to_skip')
ADDITIONAL_OPTIONS+=('--jobs')
ADDITIONAL_OPTIONS+=('4')
fi
for _ in $(seq 1 "$NUM_TRIES"); do
clickhouse-test --testname --shard --zookeeper --hung-check --print-time "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a test_output/test_result.txt
if [ "${PIPESTATUS[0]}" -ne "0" ]; then
break;
fi
done
clickhouse-test --testname --shard --zookeeper --hung-check --print-time \
--test-runs "$NUM_TRIES" \
"$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \
| tee -a test_output/test_result.txt
}
export -f run_tests

View File

@ -1,12 +1,16 @@
# docker build -t yandex/clickhouse-style-test .
FROM ubuntu:20.04
RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git python3-pip && pip3 install codespell
RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git python3-pip pylint && pip3 install codespell
# For |& syntax
SHELL ["bash", "-c"]
CMD cd /ClickHouse/utils/check-style && \
./check-style -n | tee /test_output/style_output.txt && \
./check-typos | tee /test_output/typos_output.txt && \
./check-whitespaces -n | tee /test_output/whitespaces_output.txt && \
./check-duplicate-includes.sh | tee /test_output/duplicate_output.txt && \
./shellcheck-run.sh | tee /test_output/shellcheck_output.txt
./check-style -n |& tee /test_output/style_output.txt && \
./check-typos |& tee /test_output/typos_output.txt && \
./check-whitespaces -n |& tee /test_output/whitespaces_output.txt && \
./check-duplicate-includes.sh |& tee /test_output/duplicate_output.txt && \
./shellcheck-run.sh |& tee /test_output/shellcheck_output.txt && \
true

View File

@ -16,7 +16,7 @@ $ /usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/inst
## Install Required Compilers, Tools, and Libraries {#install-required-compilers-tools-and-libraries}
``` bash
$ brew install cmake ninja libtool gettext
$ brew install cmake ninja libtool gettext llvm
```
## Checkout ClickHouse Sources {#checkout-clickhouse-sources}
@ -40,7 +40,7 @@ $ cd ClickHouse
``` bash
$ mkdir build
$ cd build
$ cmake ..-DCMAKE_C_COMPILER=`brew --prefix llvm`/bin/clang -DCMAKE_CXX_COMPILER=`brew --prefix llvm`/bin/clang++ -DCMAKE_PREFIX_PATH=`brew --prefix llvm`
$ cmake .. -DCMAKE_C_COMPILER=`brew --prefix llvm`/bin/clang -DCMAKE_CXX_COMPILER=`brew --prefix llvm`/bin/clang++ -DCMAKE_PREFIX_PATH=`brew --prefix llvm`
$ ninja
$ cd ..
```

View File

@ -0,0 +1,17 @@
---
toc_priority: 32
toc_title: Atomic
---
# Atomic {#atomic}
It is supports non-blocking `DROP` and `RENAME TABLE` queries and atomic `EXCHANGE TABLES t1 AND t2` queries. Atomic database engine is used by default.
## Creating a Database {#creating-a-database}
```sql
CREATE DATABASE test ENGINE = Atomic;
```
[Original article](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide-->

View File

@ -8,14 +8,14 @@ toc_title: Introduction
Database engines allow you to work with tables.
By default, ClickHouse uses its native database engine, which provides configurable [table engines](../../engines/table-engines/index.md) and an [SQL dialect](../../sql-reference/syntax.md).
By default, ClickHouse uses database engine [Atomic](../../engines/database-engines/atomic.md). It is provides configurable [table engines](../../engines/table-engines/index.md) and an [SQL dialect](../../sql-reference/syntax.md).
You can also use the following database engines:
- [MySQL](../../engines/database-engines/mysql.md)
- [Lazy](../../engines/database-engines/lazy.md)
- [MaterializeMySQL](../../engines/database-engines/materialize-mysql.md)
- [Lazy](../../engines/database-engines/lazy.md)
[Original article](https://clickhouse.tech/docs/en/database_engines/) <!--hide-->

View File

@ -5,9 +5,11 @@ toc_title: MaterializeMySQL
# MaterializeMySQL {#materialize-mysql}
Creates ClickHouse database with all the tables existing in MySQL, and all the data in those tables.
Creates ClickHouse database with all the tables existing in MySQL, and all the data in those tables.
ClickHouse server works as MySQL replica. It reads binlog and performs DDL and DML queries.
ClickHouse server works as MySQL replica. It reads binlog and performs DDL and DML queries.
This feature is experimental.
## Creating a Database {#creating-a-database}
@ -25,12 +27,12 @@ ENGINE = MaterializeMySQL('host:port', ['database' | database], 'user', 'passwor
## Virtual columns {#virtual-columns}
When working with the `MaterializeMySQL` database engine, [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
When working with the `MaterializeMySQL` database engine, [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
- `_version` — Transaction counter. Type [UInt64](../../sql-reference/data-types/int-uint.md).
- `_sign` — Deletion mark. Type [Int8](../../sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `-1` — Row is deleted.
- `_version` — Transaction counter. Type [UInt64](../../sql-reference/data-types/int-uint.md).
- `_sign` — Deletion mark. Type [Int8](../../sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `-1` — Row is deleted.
## Data Types Support {#data_types-support}
@ -61,9 +63,9 @@ Other types are not supported. If MySQL table contains a column of such type, Cl
MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([ALTER](../../sql-reference/statements/alter/index.md), [CREATE](../../sql-reference/statements/create/index.md), [DROP](../../sql-reference/statements/drop.md), [RENAME](../../sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
### Data Replication {#data-replication}
### Data Replication {#data-replication}
MaterializeMySQL does not support direct `INSERT`, `DELETE` and `UPDATE` queries. However, they are supported in terms of data replication:
`MaterializeMySQL` does not support direct `INSERT`, `DELETE` and `UPDATE` queries. However, they are supported in terms of data replication:
- MySQL `INSERT` query is converted into `INSERT` with `_sign=1`.
@ -73,11 +75,11 @@ MaterializeMySQL does not support direct `INSERT`, `DELETE` and `UPDATE` queries
### Selecting from MaterializeMySQL Tables {#select}
`SELECT` query form MaterializeMySQL tables has some specifics:
`SELECT` query from `MaterializeMySQL` tables has some specifics:
- If `_version` is not specified in the `SELECT` query, [FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier is used. So only rows with `MAX(_version)` are selected.
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default, so the deleted rows are not included into the result set.
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not included into the result set.
### Index Conversion {#index-conversion}
@ -85,12 +87,12 @@ MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in
ClickHouse has only one physical order, which is determined by `ORDER BY` clause. To create a new physical order, use [materialized views](../../sql-reference/statements/create/view.md#materialized).
**Notes**
**Notes**
- Rows with `_sign=-1` are not deleted physically from the tables.
- Cascade `UPDATE/DELETE` queries are not supported by the `MaterializeMySQL` engine.
- Replication can be easily broken.
- Manual operations on database and tables are forbidden.
- Rows with `_sign=-1` are not deleted physically from the tables.
- Cascade `UPDATE/DELETE` queries are not supported by the `MaterializeMySQL` engine.
- Replication can be easily broken.
- Manual operations on database and tables are forbidden.
## Examples of Use {#examples-of-use}
@ -105,6 +107,7 @@ mysql> ALTER TABLE db.test ADD COLUMN c VARCHAR(16);
mysql> UPDATE db.test SET c='Wow!', b=222;
mysql> SELECT * FROM test;
```
```text
+---+------+------+
| a | b | c |

View File

@ -51,6 +51,23 @@ All other MySQL data types are converted into [String](../../sql-reference/data-
[Nullable](../../sql-reference/data-types/nullable.md) is supported.
## Global Variables Support {#global-variables-support}
For better compatibility you may address global variables in MySQL style, as `@@identifier`.
These variables are supported:
- `version`
- `max_allowed_packet`
!!! warning "Warning"
By now these variables are stubs and don't correspond to anything.
Example:
``` sql
SELECT @@version;
```
## Examples of Use {#examples-of-use}
Table in MySQL:

View File

@ -7,8 +7,6 @@ toc_title: EmbeddedRocksDB
This engine allows integrating ClickHouse with [rocksdb](http://rocksdb.org/).
`EmbeddedRocksDB` lets you:
## Creating a Table {#table_engine-EmbeddedRocksDB-creating-a-table}
``` sql
@ -23,6 +21,9 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
Required parameters:
- `primary_key_name` any column name in the column list.
- `primary key` must be specified, it supports only one column in the primary key. The primary key will be serialized in binary as a `rocksdb key`.
- columns other than the primary key will be serialized in binary as `rocksdb` value in corresponding order.
- queries with key `equals` or `in` filtering will be optimized to multi keys lookup from `rocksdb`.
Example:
@ -38,8 +39,4 @@ ENGINE = EmbeddedRocksDB
PRIMARY KEY key
```
## Description {#description}
- `primary key` must be specified, it only supports one column in primary key. The primary key will serialized in binary as rocksdb key.
- columns other than the primary key will be serialized in binary as rocksdb value in corresponding order.
- queries with key `equals` or `in` filtering will be optimized to multi keys lookup from rocksdb.
[Original article](https://clickhouse.tech/docs/en/operations/table_engines/embedded-rocksdb/) <!--hide-->

View File

@ -114,6 +114,10 @@ CREATE TABLE big_table (name String, value UInt32) ENGINE = S3('https://storage.
- `_path` — Path to the file.
- `_file` — Name of the file.
**See Also**
- [Virtual columns](../../../engines/table-engines/index.md#table_engines-virtual_columns)
## S3-related settings {#settings}
The following settings can be set before query execution or placed into configuration file.
@ -124,8 +128,29 @@ The following settings can be set before query execution or placed into configur
Security consideration: if malicious user can specify arbitrary S3 URLs, `s3_max_redirects` must be set to zero to avoid [SSRF](https://en.wikipedia.org/wiki/Server-side_request_forgery) attacks; or alternatively, `remote_host_filter` must be specified in server configuration.
**See Also**
### Endpoint-based settings {#endpointsettings}
- [Virtual columns](../../../engines/table-engines/index.md#table_engines-virtual_columns)
The following settings can be specified in configuration file for given endpoint (which will be matched by exact prefix of a URL):
- `endpoint` — Mandatory. Specifies prefix of an endpoint.
- `access_key_id` and `secret_access_key` — Optional. Specifies credentials to use with given endpoint.
- `use_environment_credentials` — Optional, default value is `false`. If set to `true`, S3 client will try to obtain credentials from environment variables and Amazon EC2 metadata for given endpoint.
- `header` — Optional, can be speficied multiple times. Adds specified HTTP header to a request to given endpoint.
This configuration also applies to S3 disks in `MergeTree` table engine family.
Example:
```
<s3>
<endpoint-name>
<endpoint>https://storage.yandexcloud.net/my-test-bucket-768/</endpoint>
<!-- <access_key_id>ACCESS_KEY_ID</access_key_id> -->
<!-- <secret_access_key>SECRET_ACCESS_KEY</secret_access_key> -->
<!-- <use_environment_credentials>false</use_environment_credentials> -->
<!-- <header>Authorization: Bearer SOME-TOKEN</header> -->
</endpoint-name>
</s3>
```
[Original article](https://clickhouse.tech/docs/en/operations/table_engines/s3/) <!--hide-->

View File

@ -45,7 +45,10 @@ ORDER BY expr
[PARTITION BY expr]
[PRIMARY KEY expr]
[SAMPLE BY expr]
[TTL expr [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'], ...]
[TTL expr
[DELETE|TO DISK 'xxx'|TO VOLUME 'xxx' [, ...] ]
[WHERE conditions]
[GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ] ]
[SETTINGS name=value, ...]
```
@ -80,7 +83,7 @@ For a description of parameters, see the [CREATE query description](../../../sql
Expression must have one `Date` or `DateTime` column as a result. Example:
`TTL date + INTERVAL 1 DAY`
Type of the rule `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'` specifies an action to be done with the part if the expression is satisfied (reaches current time): removal of expired rows, moving a part (if expression is satisfied for all rows in a part) to specified disk (`TO DISK 'xxx'`) or to volume (`TO VOLUME 'xxx'`). Default type of the rule is removal (`DELETE`). List of multiple rules can specified, but there should be no more than one `DELETE` rule.
Type of the rule `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'|GROUP BY` specifies an action to be done with the part if the expression is satisfied (reaches current time): removal of expired rows, moving a part (if expression is satisfied for all rows in a part) to specified disk (`TO DISK 'xxx'`) or to volume (`TO VOLUME 'xxx'`), or aggregating values in expired rows. Default type of the rule is removal (`DELETE`). List of multiple rules can specified, but there should be no more than one `DELETE` rule.
For more details, see [TTL for columns and tables](#table_engine-mergetree-ttl)
@ -455,18 +458,28 @@ ALTER TABLE example_table
Table can have an expression for removal of expired rows, and multiple expressions for automatic move of parts between [disks or volumes](#table_engine-mergetree-multiple-volumes). When rows in the table expire, ClickHouse deletes all corresponding rows. For parts moving feature, all rows of a part must satisfy the movement expression criteria.
``` sql
TTL expr [DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'], ...
TTL expr
[DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'][, DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'] ...
[WHERE conditions]
[GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ]
```
Type of TTL rule may follow each TTL expression. It affects an action which is to be done once the expression is satisfied (reaches current time):
- `DELETE` - delete expired rows (default action);
- `TO DISK 'aaa'` - move part to the disk `aaa`;
- `TO VOLUME 'bbb'` - move part to the disk `bbb`.
- `TO VOLUME 'bbb'` - move part to the disk `bbb`;
- `GROUP BY` - aggregate expired rows.
Examples:
With `WHERE` clause you may specify which of the expired rows to delete or aggregate (it cannot be applied to moves).
Creating a table with TTL
`GROUP BY` expression must be a prefix of the table primary key.
If a column is not part of the `GROUP BY` expression and is not set explicitely in the `SET` clause, in result row it contains an occasional value from the grouped rows (as if aggregate function `any` is applied to it).
**Examples**
Creating a table with TTL:
``` sql
CREATE TABLE example_table
@ -482,13 +495,43 @@ TTL d + INTERVAL 1 MONTH [DELETE],
d + INTERVAL 2 WEEK TO DISK 'bbb';
```
Altering TTL of the table
Altering TTL of the table:
``` sql
ALTER TABLE example_table
MODIFY TTL d + INTERVAL 1 DAY;
```
Creating a table, where the rows are expired after one month. The expired rows where dates are Mondays are deleted:
``` sql
CREATE TABLE table_with_where
(
d DateTime,
a Int
)
ENGINE = MergeTree
PARTITION BY toYYYYMM(d)
ORDER BY d
TTL d + INTERVAL 1 MONTH DELETE WHERE toDayOfWeek(d) = 1;
```
Creating a table, where expired rows are aggregated. In result rows `x` contains the maximum value accross the grouped rows, `y` — the minimum value, and `d` — any occasional value from grouped rows.
``` sql
CREATE TABLE table_for_aggregation
(
d DateTime,
k1 Int,
k2 Int,
x Int,
y Int
)
ENGINE = MergeTree
ORDER BY k1, k2
TTL d + INTERVAL 1 MONTH GROUP BY k1, k2 SET x = max(x), y = min(y);
```
**Removing Data**
Data with an expired TTL is removed when ClickHouse merges data parts.
@ -657,6 +700,96 @@ The `default` storage policy implies using only one volume, which consists of on
The number of threads performing background moves of data parts can be changed by [background_move_pool_size](../../../operations/settings/settings.md#background_move_pool_size) setting.
## Using S3 for Data Storage {#table_engine-mergetree-s3}
`MergeTree` family table engines is able to store data to [S3](https://aws.amazon.com/s3/) using a disk with type `s3`.
Configuration markup:
``` xml
<storage_configuration>
...
<disks>
<s3>
<type>s3</type>
<endpoint>https://storage.yandexcloud.net/my-bucket/root-path/</endpoint>
<access_key_id>your_access_key_id</access_key_id>
<secret_access_key>your_secret_access_key</secret_access_key>
<proxy>
<uri>http://proxy1</uri>
<uri>http://proxy2</uri>
</proxy>
<connect_timeout_ms>10000</connect_timeout_ms>
<request_timeout_ms>5000</request_timeout_ms>
<max_connections>100</max_connections>
<retry_attempts>10</retry_attempts>
<min_bytes_for_seek>1000</min_bytes_for_seek>
<metadata_path>/var/lib/clickhouse/disks/s3/</metadata_path>
<cache_enabled>true</cache_enabled>
<cache_path>/var/lib/clickhouse/disks/s3/cache/</cache_path>
<skip_access_check>false</skip_access_check>
</s3>
</disks>
...
</storage_configuration>
```
Required parameters:
- `endpoint` — S3 endpoint url in `path` or `virtual hosted` [styles](https://docs.aws.amazon.com/AmazonS3/latest/dev/VirtualHosting.html). Endpoint url should contain bucket and root path to store data.
- `access_key_id` — S3 access key id.
- `secret_access_key` — S3 secret access key.
Optional parameters:
- `use_environment_credentials` — Reads AWS credentials from the Environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN if they exist. Default value is `false`.
- `proxy` — Proxy configuration for S3 endpoint. Each `uri` element inside `proxy` block should contain a proxy URL.
- `connect_timeout_ms` — Socket connect timeout in milliseconds. Default value is `10 seconds`.
- `request_timeout_ms` — Request timeout in milliseconds. Default value is `5 seconds`.
- `max_connections` — S3 connections pool size. Default value is `100`.
- `retry_attempts` — Number of retry attempts in case of failed request. Default value is `10`.
- `min_bytes_for_seek` — Minimal number of bytes to use seek operation instead of sequential read. Default value is `1 Mb`.
- `metadata_path` — Path on local FS to store metadata files for S3. Default value is `/var/lib/clickhouse/disks/<disk_name>/`.
- `cache_enabled` — Allows to cache mark and index files on local FS. Default value is `true`.
- `cache_path` — Path on local FS where to store cached mark and index files. Default value is `/var/lib/clickhouse/disks/<disk_name>/cache/`.
- `skip_access_check` — If true disk access checks will not be performed on disk start-up. Default value is `false`.
S3 disk can be configured as `main` or `cold` storage:
``` xml
<storage_configuration>
...
<disks>
<s3>
<type>s3</type>
<endpoint>https://storage.yandexcloud.net/my-bucket/root-path/</endpoint>
<access_key_id>your_access_key_id</access_key_id>
<secret_access_key>your_secret_access_key</secret_access_key>
</s3>
</disks>
<policies>
<s3_main>
<volumes>
<main>
<disk>s3</disk>
</main>
</volumes>
</s3_main>
<s3_cold>
<volumes>
<main>
<disk>default</disk>
</main>
<external>
<disk>s3</disk>
</external>
</volumes>
<move_factor>0.2</move_factor>
</s3_cold>
</policies>
...
</storage_configuration>
```
In case of `cold` option a data can be moved to S3 if local disk free size will be smaller than `move_factor * disk_size` or by TTL move rule.
### Details {#details}
In the case of `MergeTree` tables, data is getting to disk in different ways:

View File

@ -254,7 +254,6 @@ ENGINE = MergeTree()
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
``` sql
@ -450,7 +449,6 @@ ENGINE = CollapsingMergeTree(Sign)
PARTITION BY toYYYYMM(StartDate)
ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
You can execute those queries using the interactive mode of `clickhouse-client` (just launch it in a terminal without specifying a query in advance) or try some [alternative interface](../interfaces/index.md) if you want.

View File

@ -515,9 +515,9 @@ 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.
In this format, a single JSON object is interpreted as a single value. If the input has several JSON objects (comma separated) they will be interpreted as separate 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.
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**
@ -526,7 +526,7 @@ 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}
INSERT INTO json_as_string (json) FORMAT JSONAsString {"foo":{"bar":{"x":"y"},"baz":1}},{},{"any json stucture":1}
SELECT * FROM json_as_string;
```
@ -540,7 +540,6 @@ Result:
└───────────────────────────────────┘
```
## JSONCompact {#jsoncompact}
## JSONCompactString {#jsoncompactstring}

View File

@ -8,117 +8,118 @@ toc_title: Adopters
!!! warning "Disclaimer"
The following list of companies using ClickHouse and their success stories is assembled from public sources, thus might differ from current reality. Wed appreciate it if you share the story of adopting ClickHouse in your company and [add it to the list](https://github.com/ClickHouse/ClickHouse/edit/master/docs/en/introduction/adopters.md), but please make sure you wont have any NDA issues by doing so. Providing updates with publications from other companies is also useful.
| Company | Industry | Usecase | Cluster Size | (Un)Compressed Data Size<abbr title="of single replica"><sup>\*</sup></abbr> | Reference |
|------------------------------------------------------------------------------------------------|---------------------------------|-----------------------|------------------------------------------------------------|------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <a href="https://2gis.ru" class="favicon">2gis</a> | Maps | Monitoring | — | — | [Talk in Russian, July 2019](https://youtu.be/58sPkXfq6nw) |
| <a href="https://getadmiral.com/" class="favicon">Admiral</a> | Martech | Engagement Management | — | — | [Webinar Slides, June 2020](https://altinity.com/presentations/2020/06/16/big-data-in-real-time-how-clickhouse-powers-admirals-visitor-relationships-for-publishers) |
| <a href="https://cn.aliyun.com/" class="favicon">Alibaba Cloud</a> | Cloud | Managed Service | — | — | [Official Website](https://help.aliyun.com/product/144466.html) |
| <a href="https://alohabrowser.com/" class="favicon">Aloha Browser</a> | Mobile App | Browser backend | — | — | [Slides in Russian, May 2019](https://presentations.clickhouse.tech/meetup22/aloha.pdf) |
| <a href="https://amadeus.com/" class="favicon">Amadeus</a> | Travel | Analytics | — | — | [Press Release, April 2018](https://www.altinity.com/blog/2018/4/5/amadeus-technologies-launches-investment-and-insights-tool-based-on-machine-learning-and-strategy-algorithms) |
| <a href="https://www.appsflyer.com" class="favicon">Appsflyer</a> | Mobile analytics | Main product | — | — | [Talk in Russian, July 2019](https://www.youtube.com/watch?v=M3wbRlcpBbY) |
| <a href="https://arenadata.tech/" class="favicon">ArenaData</a> | Data Platform | Main product | — | — | [Slides in Russian, December 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup38/indexes.pdf) |
| <a href="https://avito.ru/" class="favicon">Avito</a> | Classifieds | Monitoring | — | — | [Meetup, April 2020](https://www.youtube.com/watch?v=n1tm4j4W8ZQ) |
| <a href="https://badoo.com" class="favicon">Badoo</a> | Dating | Timeseries | — | — | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/forecast.pdf) |
| <a href="https://www.benocs.com/" class="favicon">Benocs</a> | Network Telemetry and Analytics | Main Product | — | — | [Slides in English, October 2017](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup9/lpm.pdf) |
| Company | Industry | Usecase | Cluster Size | (Un)Compressed Data Size<abbr title="of single replica"><sup>\*</sup></abbr> | Reference |
|---------|----------|---------|--------------|------------------------------------------------------------------------------|-----------|
| <a href="https://2gis.ru" class="favicon">2gis</a> | Maps | Monitoring | — | — | [Talk in Russian, July 2019](https://youtu.be/58sPkXfq6nw) |
| <a href="https://getadmiral.com/" class="favicon">Admiral</a> | Martech | Engagement Management | — | — | [Webinar Slides, June 2020](https://altinity.com/presentations/2020/06/16/big-data-in-real-time-how-clickhouse-powers-admirals-visitor-relationships-for-publishers) |
| <a href="https://cn.aliyun.com/" class="favicon">Alibaba Cloud</a> | Cloud | Managed Service | — | — | [Official Website](https://help.aliyun.com/product/144466.html) |
| <a href="https://alohabrowser.com/" class="favicon">Aloha Browser</a> | Mobile App | Browser backend | — | — | [Slides in Russian, May 2019](https://presentations.clickhouse.tech/meetup22/aloha.pdf) |
| <a href="https://amadeus.com/" class="favicon">Amadeus</a> | Travel | Analytics | — | — | [Press Release, April 2018](https://www.altinity.com/blog/2018/4/5/amadeus-technologies-launches-investment-and-insights-tool-based-on-machine-learning-and-strategy-algorithms) |
| <a href="https://www.appsflyer.com" class="favicon">Appsflyer</a> | Mobile analytics | Main product | — | — | [Talk in Russian, July 2019](https://www.youtube.com/watch?v=M3wbRlcpBbY) |
| <a href="https://arenadata.tech/" class="favicon">ArenaData</a> | Data Platform | Main product | — | — | [Slides in Russian, December 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup38/indexes.pdf) |
| <a href="https://avito.ru/" class="favicon">Avito</a> | Classifieds | Monitoring | — | — | [Meetup, April 2020](https://www.youtube.com/watch?v=n1tm4j4W8ZQ) |
| <a href="https://badoo.com" class="favicon">Badoo</a> | Dating | Timeseries | — | — | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/forecast.pdf) |
| <a href="https://www.benocs.com/" class="favicon">Benocs</a> | Network Telemetry and Analytics | Main Product | — | — | [Slides in English, October 2017](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup9/lpm.pdf) |
| <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://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/) |
| <a href="http://cisco.com/" class="favicon">Cisco</a> | Networking | Traffic analysis | — | — | [Lightning talk, October 2019](https://youtu.be/-hI1vDR2oPY?t=5057) |
| <a href="https://www.citadelsecurities.com/" class="favicon">Citadel Securities</a> | Finance | — | — | — | [Contribution, March 2019](https://github.com/ClickHouse/ClickHouse/pull/4774) |
| <a href="https://city-mobil.ru" class="favicon">Citymobil</a> | Taxi | Analytics | — | — | [Blog Post in Russian, March 2020](https://habr.com/en/company/citymobil/blog/490660/) |
| <a href="https://cloudflare.com" class="favicon">Cloudflare</a> | CDN | Traffic analysis | 36 servers | — | [Blog post, May 2017](https://blog.cloudflare.com/how-cloudflare-analyzes-1m-dns-queries-per-second/), [Blog post, March 2018](https://blog.cloudflare.com/http-analytics-for-6m-requests-per-second-using-clickhouse/) |
| <a href="https://corporate.comcast.com/" class="favicon">Comcast</a> | Media | CDN Traffic Analysis | — | — | [ApacheCon 2019 Talk](https://www.youtube.com/watch?v=e9TZ6gFDjNg) |
| <a href="https://contentsquare.com" class="favicon">ContentSquare</a> | Web analytics | Main product | — | — | [Blog post in French, November 2018](http://souslecapot.net/2018/11/21/patrick-chatain-vp-engineering-chez-contentsquare-penser-davantage-amelioration-continue-que-revolution-constante/) |
| <a href="https://coru.net/" class="favicon">Corunet</a> | Analytics | Main product | — | — | [Slides in English, April 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup21/predictive_models.pdf) |
| <a href="https://www.creditx.com" class="favicon">CraiditX 氪信</a> | Finance AI | Analysis | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/udf.pptx) |
| <a href="https://crazypanda.ru/en/" class="favicon">Crazypanda</a> | Games | | — | — | Live session on ClickHouse meetup |
| <a href="https://www.criteo.com/" class="favicon">Criteo</a> | Retail | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/3_storetail.pptx) |
| <a href="https://www.chinatelecomglobal.com/" class="favicon">Dataliance for China Telecom</a> | Telecom | Analytics | — | — | [Slides in Chinese, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/telecom.pdf) |
| <a href="https://db.com" class="favicon">Deutsche Bank</a> | Finance | BI Analytics | — | — | [Slides in English, October 2019](https://bigdatadays.ru/wp-content/uploads/2019/10/D2-H3-3_Yakunin-Goihburg.pdf) |
| <a href="https://deeplay.io/eng/" class="favicon">Deeplay</a> | Gaming Analytics | — | — | — | [Job advertisement, 2020](https://career.habr.com/vacancies/1000062568) |
| <a href="https://www.diva-e.com" class="favicon">Diva-e</a> | Digital consulting | Main Product | — | — | [Slides in English, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup29/ClickHouse-MeetUp-Unusual-Applications-sd-2019-09-17.pdf) |
| <a href="https://www.ecwid.com/" class="favicon">Ecwid</a> | E-commerce SaaS | Metrics, Logging | — | — | [Slides in Russian, April 2019](https://nastachku.ru/var/files/1/presentation/backend/2_Backend_6.pdf) |
| <a href="https://www.ebay.com/" class="favicon">eBay</a> | E-commerce | Logs, Metrics and Events | — | — | [Official website, Sep 2020](https://tech.ebayinc.com/engineering/ou-online-analytical-processing/) |
| <a href="https://www.exness.com" class="favicon">Exness</a> | Trading | Metrics, Logging | — | — | [Talk in Russian, May 2019](https://youtu.be/_rpU-TvSfZ8?t=3215) |
| <a href="https://fastnetmon.com/" class="favicon">FastNetMon</a> | DDoS Protection | Main Product | | — | [Official website](https://fastnetmon.com/docs-fnm-advanced/fastnetmon-advanced-traffic-persistency/) |
| <a href="https://www.flipkart.com/" class="favicon">Flipkart</a> | e-Commerce | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=239) |
| <a href="https://fun.co/rp" class="favicon">FunCorp</a> | Games | | — | — | [Article](https://www.altinity.com/blog/migrating-from-redshift-to-clickhouse) |
| <a href="https://geniee.co.jp" class="favicon">Geniee</a> | Ad network | Main product | — | — | [Blog post in Japanese, July 2017](https://tech.geniee.co.jp/entry/2017/07/20/160100) |
| <a href="https://www.genotek.ru/" class="favicon">Genotek</a> | Bioinformatics | Main product | — | — | [Video, August 2020](https://youtu.be/v3KyZbz9lEE) |
| <a href="https://www.huya.com/" class="favicon">HUYA</a> | Video Streaming | Analytics | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/7.%20ClickHouse万亿数据分析实践%20李本旺(sundy-li)%20虎牙.pdf) |
| <a href="https://www.the-ica.com/" class="favicon">ICA</a> | FinTech | Risk Management | — | — | [Blog Post in English, Sep 2020](https://altinity.com/blog/clickhouse-vs-redshift-performance-for-fintech-risk-management?utm_campaign=ClickHouse%20vs%20RedShift&utm_content=143520807&utm_medium=social&utm_source=twitter&hss_channel=tw-3894792263) |
| <a href="https://www.idealista.com" class="favicon">Idealista</a> | Real Estate | Analytics | — | — | [Blog Post in English, April 2019](https://clickhouse.tech/blog/en/clickhouse-meetup-in-madrid-on-april-2-2019) |
| <a href="https://www.infovista.com/" class="favicon">Infovista</a> | Networks | Analytics | — | — | [Slides in English, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup30/infovista.pdf) |
| <a href="https://www.innogames.com" class="favicon">InnoGames</a> | Games | Metrics, Logging | — | — | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/graphite_and_clickHouse.pdf) |
| <a href="https://www.instana.com" class="favicon">Instana</a> | APM Platform | Main product | — | — | [Twitter post](https://twitter.com/mieldonkers/status/1248884119158882304) |
| <a href="https://integros.com" class="favicon">Integros</a> | Platform for video services | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
| <a href="https://ippon.tech" class="favicon">Ippon Technologies</a> | Technology Consulting | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=205) |
| <a href="https://www.ivi.ru/" class="favicon">Ivi</a> | Online Cinema | Analytics, Monitoring | — | — | [Article in Russian, Jan 2018](https://habr.com/en/company/ivi/blog/347408/) |
| <a href="https://jinshuju.net" class="favicon">Jinshuju 金数据</a> | BI Analytics | Main product | — | — | [Slides in Chinese, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/3.%20金数据数据架构调整方案Public.pdf) |
| <a href="https://www.kodiakdata.com/" class="favicon">Kodiak Data</a> | Clouds | Main product | — | — | [Slides in Engish, April 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup13/kodiak_data.pdf) |
| <a href="https://kontur.ru" class="favicon">Kontur</a> | Software Development | Metrics | — | — | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY) |
| <a href="https://www.kuaishou.com/" class="favicon">Kuaishou</a> | Video | — | — | — | [ClickHouse Meetup, October 2018](https://clickhouse.tech/blog/en/2018/clickhouse-community-meetup-in-beijing-on-october-28-2018/) |
| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a> | Research | Traffic analysis | 1 server | 11.8 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) |
| <a href="https://lifestreet.com/" class="favicon">LifeStreet</a> | Ad network | Main product | 75 servers (3 replicas) | 5.27 PiB | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/) |
| <a href="https://mcs.mail.ru/" class="favicon">Mail.ru Cloud Solutions</a> | Cloud services | Main product | — | — | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#) |
| <a href="https://tech.mymarilyn.ru" class="favicon">Marilyn</a> | Advertising | Statistics | — | — | [Talk in Russian, June 2017](https://www.youtube.com/watch?v=iXlIgx2khwc) |
| <a href="https://mellodesign.ru/" class="favicon">Mello</a> | Marketing | Analytics | 1 server | — | [Article, Oct 2020](https://vc.ru/marketing/166180-razrabotka-tipovogo-otcheta-skvoznoy-analitiki) |
| <a href="https://www.messagebird.com" class="favicon">MessageBird</a> | Telecommunications | Statistics | — | — | [Slides in English, November 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup20/messagebird.pdf) |
| <a href="https://www.mindsdb.com/" class="favicon">MindsDB</a> | Machine Learning | Main Product | — | — | [Official Website](https://www.mindsdb.com/blog/machine-learning-models-as-tables-in-ch) |x
| <a href="https://mux.com/" class="favicon">MUX</a> | Online Video | Video Analytics | — | — | [Talk in English, August 2019](https://altinity.com/presentations/2019/8/13/how-clickhouse-became-the-default-analytics-database-for-mux/) |
| <a href="https://www.mgid.com/" class="favicon">MGID</a> | Ad network | Web-analytics | — | — | [Blog post in Russian, April 2020](http://gs-studio.com/news-about-it/32777----clickhouse---c) |
| <a href="https://getnoc.com/" class="favicon">NOC Project</a> | Network Monitoring | Analytics | Main Product | — | [Official Website](https://getnoc.com/features/big-data/) |
| <a href="https://www.nuna.com/" class="favicon">Nuna Inc.</a> | Health Data Analytics | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=170) |
| <a href="https://www.oneapm.com/" class="favicon">OneAPM</a> | Monitorings and Data Analysis | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/8.%20clickhouse在OneAPM的应用%20杜龙.pdf) |
| <a href="https://www.percent.cn/" class="favicon">Percent 百分点</a> | Analytics | Main Product | — | — | [Slides in Chinese, June 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/4.%20ClickHouse万亿数据双中心的设计与实践%20.pdf) |
| <a href="https://www.percona.com/" class="favicon">Percona</a> | Performance analysis | Percona Monitoring and Management | — | — | [Official website, Mar 2020](https://www.percona.com/blog/2020/03/30/advanced-query-analysis-in-percona-monitoring-and-management-with-direct-clickhouse-access/) |
| <a href="https://plausible.io/" class="favicon">Plausible</a> | Analytics | Main Product | — | — | [Blog post, June 2020](https://twitter.com/PlausibleHQ/status/1273889629087969280) |
| <a href="https://posthog.com/" class="favicon">PostHog</a> | Product Analytics | Main Product | — | — | [Release Notes, Oct 2020](https://posthog.com/blog/the-posthog-array-1-15-0) |
| <a href="https://postmates.com/" class="favicon">Postmates</a> | Delivery | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=188) |
| <a href="http://www.pragma-innovation.fr/" class="favicon">Pragma Innovation</a> | Telemetry and Big Data Analysis | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/4_pragma_innovation.pdf) |
| <a href="https://www.qingcloud.com/" class="favicon">QINGCLOUD</a> | Cloud services | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/4.%20Cloud%20%2B%20TSDB%20for%20ClickHouse%20张健%20QingCloud.pdf) |
| <a href="https://qrator.net" class="favicon">Qrator</a> | DDoS protection | Main product | — | — | [Blog Post, March 2019](https://blog.qrator.net/en/clickhouse-ddos-mitigation_37/) |
| <a href="https://www.rbinternational.com/" class="favicon">Raiffeisenbank</a> | Banking | Analytics | — | — | [Lecture in Russian, December 2020](https://cs.hse.ru/announcements/421965599.html) |
| <a href="https://rambler.ru" class="favicon">Rambler</a> | Internet services | Analytics | — | — | [Talk in Russian, April 2018](https://medium.com/@ramblertop/разработка-api-clickhouse-для-рамблер-топ-100-f4c7e56f3141) |
| <a href="https://retell.cc/" class="favicon">Retell</a> | Speech synthesis | Analytics | — | — | [Blog Article, August 2020](https://vc.ru/services/153732-kak-sozdat-audiostati-na-vashem-sayte-i-zachem-eto-nuzhno) |
| <a href="https://rspamd.com/" class="favicon">Rspamd</a> | Antispam | Analytics | — | — | [Official Website](https://rspamd.com/doc/modules/clickhouse.html) |
| <a href="https://rusiem.com/en" class="favicon">RuSIEM</a> | SIEM | Main Product | — | — | [Official Website](https://rusiem.com/en/products/architecture) |
| <a href="https://www.s7.ru" class="favicon">S7 Airlines</a> | Airlines | Metrics, Logging | — | — | [Talk in Russian, March 2019](https://www.youtube.com/watch?v=nwG68klRpPg&t=15s) |
| <a href="https://www.scireum.de/" class="favicon">scireum GmbH</a> | e-Commerce | Main product | — | — | [Talk in German, February 2020](https://www.youtube.com/watch?v=7QWAn5RbyR4) |
| <a href="https://segment.com/" class="favicon">Segment</a> | Data processing | Main product | 9 * i3en.3xlarge nodes 7.5TB NVME SSDs, 96GB Memory, 12 vCPUs | — | [Slides, 2019](https://slides.com/abraithwaite/segment-clickhouse) |
| <a href="https://www.semrush.com/" class="favicon">SEMrush</a> | Marketing | Main product | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/5_semrush.pdf) |
| <a href="https://sentry.io/" class="favicon">Sentry</a> | Software Development | Main product | — | — | [Blog Post in English, May 2019](https://blog.sentry.io/2019/05/16/introducing-snuba-sentrys-new-search-infrastructure) |
| <a href="https://seo.do/" class="favicon">seo.do</a> | Analytics | Main product | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/CH%20Presentation-%20Metehan%20Çetinkaya.pdf) |
| <a href="http://www.sgk.gov.tr/wps/portal/sgk/tr" class="favicon">SGK</a> | Goverment Social Security | Analytics | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/ClickHouse%20Meetup-Ramazan%20POLAT.pdf) |
| <a href="http://english.sina.com/index.html" class="favicon">Sina</a> | News | — | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/6.%20ClickHouse最佳实践%20高鹏_新浪.pdf) |
| <a href="https://smi2.ru/" class="favicon">SMI2</a> | News | Analytics | — | — | [Blog Post in Russian, November 2017](https://habr.com/ru/company/smi2/blog/314558/) |
| <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) |
| <a href="https://www.tencentmusic.com/" class="favicon">Tencent Music Entertainment (TME)</a> | BigData | Data processing | — | — | [Blog in Chinese, June 2020](https://cloud.tencent.com/developer/article/1637840) |
| <a href="https://trafficstars.com/" class="favicon">Traffic Stars</a> | AD network | — | — | — | [Slides in Russian, May 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup15/lightning/ninja.pdf) |
| <a href="https://www.uber.com" class="favicon">Uber</a> | Taxi | Logging | — | — | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/uber.pdf) |
| <a href="https://vk.com" class="favicon">VKontakte</a> | Social Network | Statistics, Logging | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/3_vk.pdf) |
| <a href="https://www.walmartlabs.com/" class="favicon">Walmart Labs</a> | Internet, Retail | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=144) |
| <a href="https://wargaming.com/en/" class="favicon">Wargaming</a> | Games | | — | — | [Interview](https://habr.com/en/post/496954/) |
| <a href="https://wisebits.com/" class="favicon">Wisebits</a> | IT Solutions | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
| <a href="https://www.workato.com/" class="favicon">Workato</a> | Automation Software | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=334) |
| <a href="http://www.xiaoxintech.cn/" class="favicon">Xiaoxin Tech</a> | Education | Common purpose | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/sync-clickhouse-with-mysql-mongodb.pptx) |
| <a href="https://www.ximalaya.com/" class="favicon">Ximalaya</a> | Audio sharing | OLAP | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/ximalaya.pdf) |
| <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 | 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) |
| <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/) |
| <a href="http://cisco.com/" class="favicon">Cisco</a> | Networking | Traffic analysis | — | — | [Lightning talk, October 2019](https://youtu.be/-hI1vDR2oPY?t=5057) |
| <a href="https://www.citadelsecurities.com/" class="favicon">Citadel Securities</a> | Finance | — | — | — | [Contribution, March 2019](https://github.com/ClickHouse/ClickHouse/pull/4774) |
| <a href="https://city-mobil.ru" class="favicon">Citymobil</a> | Taxi | Analytics | — | — | [Blog Post in Russian, March 2020](https://habr.com/en/company/citymobil/blog/490660/) |
| <a href="https://cloudflare.com" class="favicon">Cloudflare</a> | CDN | Traffic analysis | 36 servers | — | [Blog post, May 2017](https://blog.cloudflare.com/how-cloudflare-analyzes-1m-dns-queries-per-second/), [Blog post, March 2018](https://blog.cloudflare.com/http-analytics-for-6m-requests-per-second-using-clickhouse/) |
| <a href="https://corporate.comcast.com/" class="favicon">Comcast</a> | Media | CDN Traffic Analysis | — | — | [ApacheCon 2019 Talk](https://www.youtube.com/watch?v=e9TZ6gFDjNg) |
| <a href="https://contentsquare.com" class="favicon">ContentSquare</a> | Web analytics | Main product | — | — | [Blog post in French, November 2018](http://souslecapot.net/2018/11/21/patrick-chatain-vp-engineering-chez-contentsquare-penser-davantage-amelioration-continue-que-revolution-constante/) |
| <a href="https://coru.net/" class="favicon">Corunet</a> | Analytics | Main product | — | — | [Slides in English, April 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup21/predictive_models.pdf) |
| <a href="https://www.creditx.com" class="favicon">CraiditX 氪信</a> | Finance AI | Analysis | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/udf.pptx) |
| <a href="https://crazypanda.ru/en/" class="favicon">Crazypanda</a> | Games | | — | — | Live session on ClickHouse meetup |
| <a href="https://www.criteo.com/" class="favicon">Criteo</a> | Retail | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/3_storetail.pptx) |
| <a href="https://www.chinatelecomglobal.com/" class="favicon">Dataliance for China Telecom</a> | Telecom | Analytics | — | — | [Slides in Chinese, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/telecom.pdf) |
| <a href="https://db.com" class="favicon">Deutsche Bank</a> | Finance | BI Analytics | — | — | [Slides in English, October 2019](https://bigdatadays.ru/wp-content/uploads/2019/10/D2-H3-3_Yakunin-Goihburg.pdf) |
| <a href="https://deeplay.io/eng/" class="favicon">Deeplay</a> | Gaming Analytics | — | — | — | [Job advertisement, 2020](https://career.habr.com/vacancies/1000062568) |
| <a href="https://www.diva-e.com" class="favicon">Diva-e</a> | Digital consulting | Main Product | — | — | [Slides in English, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup29/ClickHouse-MeetUp-Unusual-Applications-sd-2019-09-17.pdf) |
| <a href="https://www.ecwid.com/" class="favicon">Ecwid</a> | E-commerce SaaS | Metrics, Logging | — | — | [Slides in Russian, April 2019](https://nastachku.ru/var/files/1/presentation/backend/2_Backend_6.pdf) |
| <a href="https://www.ebay.com/" class="favicon">eBay</a> | E-commerce | Logs, Metrics and Events | — | — | [Official website, Sep 2020](https://tech.ebayinc.com/engineering/ou-online-analytical-processing/) |
| <a href="https://www.exness.com" class="favicon">Exness</a> | Trading | Metrics, Logging | — | — | [Talk in Russian, May 2019](https://youtu.be/_rpU-TvSfZ8?t=3215) |
| <a href="https://fastnetmon.com/" class="favicon">FastNetMon</a> | DDoS Protection | Main Product | | — | [Official website](https://fastnetmon.com/docs-fnm-advanced/fastnetmon-advanced-traffic-persistency/) |
| <a href="https://www.flipkart.com/" class="favicon">Flipkart</a> | e-Commerce | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=239) |
| <a href="https://fun.co/rp" class="favicon">FunCorp</a> | Games | | — | — | [Article](https://www.altinity.com/blog/migrating-from-redshift-to-clickhouse) |
| <a href="https://geniee.co.jp" class="favicon">Geniee</a> | Ad network | Main product | — | — | [Blog post in Japanese, July 2017](https://tech.geniee.co.jp/entry/2017/07/20/160100) |
| <a href="https://www.genotek.ru/" class="favicon">Genotek</a> | Bioinformatics | Main product | — | — | [Video, August 2020](https://youtu.be/v3KyZbz9lEE) |
| <a href="https://www.huya.com/" class="favicon">HUYA</a> | Video Streaming | Analytics | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/7.%20ClickHouse万亿数据分析实践%20李本旺(sundy-li)%20虎牙.pdf) |
| <a href="https://www.the-ica.com/" class="favicon">ICA</a> | FinTech | Risk Management | — | — | [Blog Post in English, Sep 2020](https://altinity.com/blog/clickhouse-vs-redshift-performance-for-fintech-risk-management?utm_campaign=ClickHouse%20vs%20RedShift&utm_content=143520807&utm_medium=social&utm_source=twitter&hss_channel=tw-3894792263) |
| <a href="https://www.idealista.com" class="favicon">Idealista</a> | Real Estate | Analytics | — | — | [Blog Post in English, April 2019](https://clickhouse.tech/blog/en/clickhouse-meetup-in-madrid-on-april-2-2019) |
| <a href="https://www.infovista.com/" class="favicon">Infovista</a> | Networks | Analytics | — | — | [Slides in English, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup30/infovista.pdf) |
| <a href="https://www.innogames.com" class="favicon">InnoGames</a> | Games | Metrics, Logging | — | — | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/graphite_and_clickHouse.pdf) |
| <a href="https://www.instana.com" class="favicon">Instana</a> | APM Platform | Main product | — | — | [Twitter post](https://twitter.com/mieldonkers/status/1248884119158882304) |
| <a href="https://integros.com" class="favicon">Integros</a> | Platform for video services | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
| <a href="https://ippon.tech" class="favicon">Ippon Technologies</a> | Technology Consulting | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=205) |
| <a href="https://www.ivi.ru/" class="favicon">Ivi</a> | Online Cinema | Analytics, Monitoring | — | — | [Article in Russian, Jan 2018](https://habr.com/en/company/ivi/blog/347408/) |
| <a href="https://jinshuju.net" class="favicon">Jinshuju 金数据</a> | BI Analytics | Main product | — | — | [Slides in Chinese, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/3.%20金数据数据架构调整方案Public.pdf) |
| <a href="https://www.kodiakdata.com/" class="favicon">Kodiak Data</a> | Clouds | Main product | — | — | [Slides in Engish, April 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup13/kodiak_data.pdf) |
| <a href="https://kontur.ru" class="favicon">Kontur</a> | Software Development | Metrics | — | — | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY) |
| <a href="https://www.kuaishou.com/" class="favicon">Kuaishou</a> | Video | — | — | — | [ClickHouse Meetup, October 2018](https://clickhouse.tech/blog/en/2018/clickhouse-community-meetup-in-beijing-on-october-28-2018/) |
| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a> | Research | Traffic analysis | 1 server | 11.8 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) |
| <a href="https://lifestreet.com/" class="favicon">LifeStreet</a> | Ad network | Main product | 75 servers (3 replicas) | 5.27 PiB | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/) |
| <a href="https://mcs.mail.ru/" class="favicon">Mail.ru Cloud Solutions</a> | Cloud services | Main product | — | — | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#) |
| <a href="https://tech.mymarilyn.ru" class="favicon">Marilyn</a> | Advertising | Statistics | — | — | [Talk in Russian, June 2017](https://www.youtube.com/watch?v=iXlIgx2khwc) |
| <a href="https://mellodesign.ru/" class="favicon">Mello</a> | Marketing | Analytics | 1 server | — | [Article, Oct 2020](https://vc.ru/marketing/166180-razrabotka-tipovogo-otcheta-skvoznoy-analitiki) |
| <a href="https://www.messagebird.com" class="favicon">MessageBird</a> | Telecommunications | Statistics | — | — | [Slides in English, November 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup20/messagebird.pdf) |
| <a href="https://www.mindsdb.com/" class="favicon">MindsDB</a> | Machine Learning | Main Product | — | — | [Official Website](https://www.mindsdb.com/blog/machine-learning-models-as-tables-in-ch) |x
| <a href="https://mux.com/" class="favicon">MUX</a> | Online Video | Video Analytics | — | — | [Talk in English, August 2019](https://altinity.com/presentations/2019/8/13/how-clickhouse-became-the-default-analytics-database-for-mux/) |
| <a href="https://www.mgid.com/" class="favicon">MGID</a> | Ad network | Web-analytics | — | — | [Blog post in Russian, April 2020](http://gs-studio.com/news-about-it/32777----clickhouse---c) |
| <a href="https://getnoc.com/" class="favicon">NOC Project</a> | Network Monitoring | Analytics | Main Product | — | [Official Website](https://getnoc.com/features/big-data/) |
| <a href="https://www.nuna.com/" class="favicon">Nuna Inc.</a> | Health Data Analytics | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=170) |
| <a href="https://www.oneapm.com/" class="favicon">OneAPM</a> | Monitorings and Data Analysis | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/8.%20clickhouse在OneAPM的应用%20杜龙.pdf) |
| <a href="https://www.percent.cn/" class="favicon">Percent 百分点</a> | Analytics | Main Product | — | — | [Slides in Chinese, June 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/4.%20ClickHouse万亿数据双中心的设计与实践%20.pdf) |
| <a href="https://www.percona.com/" class="favicon">Percona</a> | Performance analysis | Percona Monitoring and Management | — | — | [Official website, Mar 2020](https://www.percona.com/blog/2020/03/30/advanced-query-analysis-in-percona-monitoring-and-management-with-direct-clickhouse-access/) |
| <a href="https://plausible.io/" class="favicon">Plausible</a> | Analytics | Main Product | — | — | [Blog post, June 2020](https://twitter.com/PlausibleHQ/status/1273889629087969280) |
| <a href="https://posthog.com/" class="favicon">PostHog</a> | Product Analytics | Main Product | — | — | [Release Notes, Oct 2020](https://posthog.com/blog/the-posthog-array-1-15-0) |
| <a href="https://postmates.com/" class="favicon">Postmates</a> | Delivery | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=188) |
| <a href="http://www.pragma-innovation.fr/" class="favicon">Pragma Innovation</a> | Telemetry and Big Data Analysis | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/4_pragma_innovation.pdf) |
| <a href="https://www.qingcloud.com/" class="favicon">QINGCLOUD</a> | Cloud services | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/4.%20Cloud%20%2B%20TSDB%20for%20ClickHouse%20张健%20QingCloud.pdf) |
| <a href="https://qrator.net" class="favicon">Qrator</a> | DDoS protection | Main product | — | — | [Blog Post, March 2019](https://blog.qrator.net/en/clickhouse-ddos-mitigation_37/) |
| <a href="https://www.rbinternational.com/" class="favicon">Raiffeisenbank</a> | Banking | Analytics | — | — | [Lecture in Russian, December 2020](https://cs.hse.ru/announcements/421965599.html) |
| <a href="https://rambler.ru" class="favicon">Rambler</a> | Internet services | Analytics | — | — | [Talk in Russian, April 2018](https://medium.com/@ramblertop/разработка-api-clickhouse-для-рамблер-топ-100-f4c7e56f3141) |
| <a href="https://retell.cc/" class="favicon">Retell</a> | Speech synthesis | Analytics | — | — | [Blog Article, August 2020](https://vc.ru/services/153732-kak-sozdat-audiostati-na-vashem-sayte-i-zachem-eto-nuzhno) |
| <a href="https://rspamd.com/" class="favicon">Rspamd</a> | Antispam | Analytics | — | — | [Official Website](https://rspamd.com/doc/modules/clickhouse.html) |
| <a href="https://rusiem.com/en" class="favicon">RuSIEM</a> | SIEM | Main Product | — | — | [Official Website](https://rusiem.com/en/products/architecture) |
| <a href="https://www.s7.ru" class="favicon">S7 Airlines</a> | Airlines | Metrics, Logging | — | — | [Talk in Russian, March 2019](https://www.youtube.com/watch?v=nwG68klRpPg&t=15s) |
| <a href="https://www.scireum.de/" class="favicon">scireum GmbH</a> | e-Commerce | Main product | — | — | [Talk in German, February 2020](https://www.youtube.com/watch?v=7QWAn5RbyR4) |
| <a href="https://segment.com/" class="favicon">Segment</a> | Data processing | Main product | 9 * i3en.3xlarge nodes 7.5TB NVME SSDs, 96GB Memory, 12 vCPUs | — | [Slides, 2019](https://slides.com/abraithwaite/segment-clickhouse) |
| <a href="https://www.semrush.com/" class="favicon">SEMrush</a> | Marketing | Main product | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/5_semrush.pdf) |
| <a href="https://sentry.io/" class="favicon">Sentry</a> | Software Development | Main product | — | — | [Blog Post in English, May 2019](https://blog.sentry.io/2019/05/16/introducing-snuba-sentrys-new-search-infrastructure) |
| <a href="https://seo.do/" class="favicon">seo.do</a> | Analytics | Main product | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/CH%20Presentation-%20Metehan%20Çetinkaya.pdf) |
| <a href="http://www.sgk.gov.tr/wps/portal/sgk/tr" class="favicon">SGK</a> | Goverment Social Security | Analytics | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/ClickHouse%20Meetup-Ramazan%20POLAT.pdf) |
| <a href="http://english.sina.com/index.html" class="favicon">Sina</a> | News | — | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/6.%20ClickHouse最佳实践%20高鹏_新浪.pdf) |
| <a href="https://smi2.ru/" class="favicon">SMI2</a> | News | Analytics | — | — | [Blog Post in Russian, November 2017](https://habr.com/ru/company/smi2/blog/314558/) |
| <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) |
| <a href="https://www.tencentmusic.com/" class="favicon">Tencent Music Entertainment (TME)</a> | BigData | Data processing | — | — | [Blog in Chinese, June 2020](https://cloud.tencent.com/developer/article/1637840) |
| <a href="https://trafficstars.com/" class="favicon">Traffic Stars</a> | AD network | — | — | — | [Slides in Russian, May 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup15/lightning/ninja.pdf) |
| <a href="https://www.uber.com" class="favicon">Uber</a> | Taxi | Logging | — | — | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/uber.pdf) |
| <a href="https://vk.com" class="favicon">VKontakte</a> | Social Network | Statistics, Logging | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/3_vk.pdf) |
| <a href="https://www.walmartlabs.com/" class="favicon">Walmart Labs</a> | Internet, Retail | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=144) |
| <a href="https://wargaming.com/en/" class="favicon">Wargaming</a> | Games | | — | — | [Interview](https://habr.com/en/post/496954/) |
| <a href="https://wisebits.com/" class="favicon">Wisebits</a> | IT Solutions | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
| <a href="https://www.workato.com/" class="favicon">Workato</a> | Automation Software | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=334) |
| <a href="http://www.xiaoxintech.cn/" class="favicon">Xiaoxin Tech</a> | Education | Common purpose | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/sync-clickhouse-with-mysql-mongodb.pptx) |
| <a href="https://www.ximalaya.com/" class="favicon">Ximalaya</a> | Audio sharing | OLAP | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/ximalaya.pdf) |
| <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 | 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) |
| <a href="https://www.kakaocorp.com/" class="favicon">kakaocorp</a> | Internet company | — | — | — | [if(kakao)2020 conference](https://if.kakao.com/session/117) |
[Original article](https://clickhouse.tech/docs/en/introduction/adopters/) <!--hide-->

View File

@ -27,6 +27,8 @@ We recommend using SQL-driven workflow. Both of the configuration methods work s
!!! note "Warning"
You cant manage the same access entity by both configuration methods simultaneously.
To see all users, roles, profiles, etc. and all their grants use [SHOW ACCESS](../sql-reference/statements/show.md#show-access-statement) statement.
## Usage {#access-control-usage}
By default, the ClickHouse server provides the `default` user account which is not allowed using SQL-driven access control and account management but has all the rights and permissions. The `default` user account is used in any cases when the username is not defined, for example, at login from client or in distributed queries. In distributed query processing a default user account is used, if the configuration of the server or cluster doesnt specify the [user and password](../engines/table-engines/special/distributed.md) properties.

View File

@ -0,0 +1,26 @@
---
toc_priority: 65
toc_title: Caches
---
# Cache Types {#cache-types}
When performing queries, ClichHouse uses different caches.
Main cache types:
- `mark_cache` — Cache of marks used by table engines of the [MergeTree](../engines/table-engines/mergetree-family/mergetree.md) family.
- `uncompressed_cache` — Cache of uncompressed data used by table engines of the [MergeTree](../engines/table-engines/mergetree-family/mergetree.md) family.
Additional cache types:
- DNS cache
- [regexp](../interfaces/formats.md#data-format-regexp) cache
- compiled expressions cache
- [Avro format](../interfaces/formats.md#data-format-avro) schemas cache
- [dictionaries data cache](../sql-reference/dictionaries/index.md)
Indirectly used:
- OS page cache
To drop cache, use [SYSTEM DROP ... CACHE](../sql-reference/statements/system.md) statements.
[Original article](https://clickhouse.tech/docs/en/operations/caches/) <!--hide-->

View File

@ -428,7 +428,7 @@ Possible values:
- `'basic'` — Use basic parser.
ClickHouse can parse only the basic `YYYY-MM-DD HH:MM:SS` or `YYYY-MM-DD` format. For example, `'2019-08-20 10:18:56'` or `2019-08-20`.
ClickHouse can parse only the basic `YYYY-MM-DD HH:MM:SS` or `YYYY-MM-DD` format. For example, `2019-08-20 10:18:56` or `2019-08-20`.
Default value: `'basic'`.
@ -443,19 +443,19 @@ Allows choosing different output formats of the text representation of date and
Possible values:
- `'simple'` - Simple output format.
- `simple` - Simple output format.
Clickhouse output date and time `YYYY-MM-DD hh:mm:ss` format. For example, `'2019-08-20 10:18:56'`. Calculation is performed according to the data type's time zone (if present) or server time zone.
Clickhouse output date and time `YYYY-MM-DD hh:mm:ss` format. For example, `2019-08-20 10:18:56`. The calculation is performed according to the data type's time zone (if present) or server time zone.
- `'iso'` - ISO output format.
- `iso` - ISO output format.
Clickhouse output date and time in [ISO 8601](https://en.wikipedia.org/wiki/ISO_8601) `YYYY-MM-DDThh:mm:ssZ` format. For example, `'2019-08-20T10:18:56Z'`. Note that output is in UTC (`Z` means UTC).
Clickhouse output date and time in [ISO 8601](https://en.wikipedia.org/wiki/ISO_8601) `YYYY-MM-DDThh:mm:ssZ` format. For example, `2019-08-20T10:18:56Z`. Note that output is in UTC (`Z` means UTC).
- `'unix_timestamp'` - Unix timestamp output format.
- `unix_timestamp` - Unix timestamp output format.
Clickhouse output date and time in [Unix timestamp](https://en.wikipedia.org/wiki/Unix_time) format. For example `'1566285536'`.
Clickhouse output date and time in [Unix timestamp](https://en.wikipedia.org/wiki/Unix_time) format. For example `1566285536`.
Default value: `'simple'`.
Default value: `simple`.
See also:
@ -1944,6 +1944,21 @@ Possible values:
Default value: 16.
## background_message_broker_schedule_pool_size {#background_message_broker_schedule_pool_size}
Sets the number of threads performing background tasks for message streaming. This setting is applied at the ClickHouse server start and cant be changed in a user session.
Possible values:
- Any positive integer.
Default value: 16.
**See Also**
- [Kafka](../../engines/table-engines/integrations/kafka.md#kafka) engine
- [RabbitMQ](../../engines/table-engines/integrations/rabbitmq.md#rabbitmq-engine) engine
## validate_polygons {#validate_polygons}
Enables or disables throwing an exception in the [pointInPolygon](../../sql-reference/functions/geo/index.md#pointinpolygon) function, if the polygon is self-intersecting or self-tangent.
@ -2489,7 +2504,6 @@ Possible values:
Default value: `0`.
## aggregate_functions_null_for_empty {#aggregate_functions_null_for_empty}
Enables or disables rewriting all aggregate functions in a query, adding [-OrNull](../../sql-reference/aggregate-functions/combinators.md#agg-functions-combinator-ornull) suffix to them. Enable it for SQL standard compatibility.
@ -2506,11 +2520,7 @@ Default value: 0.
Consider the following query with aggregate functions:
```sql
SELECT
SUM(-1),
MAX(0)
FROM system.one
WHERE 0
SELECT SUM(-1), MAX(0) FROM system.one WHERE 0;
```
With `aggregate_functions_null_for_empty = 0` it would produce:
@ -2527,7 +2537,6 @@ With `aggregate_functions_null_for_empty = 1` the result would be:
└───────────────┴──────────────┘
```
## union_default_mode {#union-default-mode}
Sets a mode for combining `SELECT` query results. The setting is only used when shared with [UNION](../../sql-reference/statements/select/union.md) without explicitly specifying the `UNION ALL` or `UNION DISTINCT`.
@ -2542,7 +2551,6 @@ Default value: `''`.
See examples in [UNION](../../sql-reference/statements/select/union.md).
## data_type_default_nullable {#data_type_default_nullable}
Allows data types without explicit modifiers [NULL or NOT NULL](../../sql-reference/statements/create/table.md#null-modifiers) in column definition will be [Nullable](../../sql-reference/data-types/nullable.md#data_type-nullable).
@ -2554,7 +2562,6 @@ Possible values:
Default value: `0`.
## execute_merges_on_single_replica_time_threshold {#execute-merges-on-single-replica-time-threshold}
Enables special logic to perform merges on replicas.
@ -2574,4 +2581,15 @@ High values for that threshold may lead to replication delays.
It can be useful when merges are CPU bounded not IO bounded (performing heavy data compression, calculating aggregate functions or default expressions that require a large amount of calculations, or just very high number of tiny merges).
## max_final_threads {#max-final-threads}
Sets the maximum number of parallel threads for the `SELECT` query data read phase with the [FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier.
Possible values:
- Positive integer.
- 0 or 1 — Disabled. `SELECT` queries are executed in a single thread.
Default value: `16`.
[Original article](https://clickhouse.tech/docs/en/operations/settings/settings/) <!-- hide -->

View File

@ -1,22 +1,21 @@
# system.distributed_ddl_queue {#system_tables-distributed_ddl_queue}
Contains information about distributed ddl queries (ON CLUSTER queries) that were executed on a cluster.
Contains information about [distributed ddl queries (ON CLUSTER clause)](../../sql-reference/distributed-ddl.md) that were executed on a cluster.
Columns:
- `entry` ([String](../../sql-reference/data-types/string.md)) - Query id.
- `host_name` ([String](../../sql-reference/data-types/string.md)) - Hostname.
- `host_address` ([String](../../sql-reference/data-types/string.md)) - IP address that the Hostname resolves to.
- `port` ([UInt16](../../sql-reference/data-types/int-uint.md)) - Host Port.
- `status` ([Enum](../../sql-reference/data-types/enum.md)) - Stats of the query.
- `cluster` ([String](../../sql-reference/data-types/string.md)) - Cluster name.
- `query` ([String](../../sql-reference/data-types/string.md)) - Query executed.
- `initiator` ([String](../../sql-reference/data-types/string.md)) - Nod that executed the query.
- `query_start_time` ([Date](../../sql-reference/data-types/date.md)) — Query start time.
- `query_finish_time` ([Date](../../sql-reference/data-types/date.md)) — Query finish time.
- `query_duration_ms` ([UInt64](../../sql-reference/data-types/datetime64.md)) — Duration of query execution in milliseconds.
- `exception_code` ([Enum](../../sql-reference/data-types/enum.md)) - Exception code from ZooKeeper.
- `entry` ([String](../../sql-reference/data-types/string.md)) — Query id.
- `host_name` ([String](../../sql-reference/data-types/string.md)) — Hostname.
- `host_address` ([String](../../sql-reference/data-types/string.md)) — IP address that the Hostname resolves to.
- `port` ([UInt16](../../sql-reference/data-types/int-uint.md)) — Host Port.
- `status` ([Enum8](../../sql-reference/data-types/enum.md)) — Status of the query.
- `cluster` ([String](../../sql-reference/data-types/string.md)) — Cluster name.
- `query` ([String](../../sql-reference/data-types/string.md)) — Query executed.
- `initiator` ([String](../../sql-reference/data-types/string.md)) — Node that executed the query.
- `query_start_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Query start time.
- `query_finish_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Query finish time.
- `query_duration_ms` ([UInt64](../../sql-reference/data-types/datetime64.md)) — Duration of query execution (in milliseconds).
- `exception_code` ([Enum8](../../sql-reference/data-types/enum.md)) — Exception code from [ZooKeeper](../../operations/tips.md#zookeeper).
**Example**
@ -62,6 +61,5 @@ exception_code: ZOK
2 rows in set. Elapsed: 0.025 sec.
```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/distributed_ddl_queuedistributed_ddl_queue.md) <!--hide-->

View File

@ -7,16 +7,16 @@ Columns:
- `id` ([UUID](../../sql-reference/data-types/uuid.md)) — Quota ID.
- `storage`([String](../../sql-reference/data-types/string.md)) — Storage of quotas. Possible value: “users.xml” if a quota configured in the users.xml file, “disk” if a quota configured by an SQL-query.
- `keys` ([Array](../../sql-reference/data-types/array.md)([Enum8](../../sql-reference/data-types/enum.md))) — Key specifies how the quota should be shared. If two connections use the same quota and key, they share the same amounts of resources. Values:
- `[]` — All users share the same quota.
- `['user_name']` — Connections with the same user name share the same quota.
- `['ip_address']` — Connections from the same IP share the same quota.
- `['client_key']` — Connections with the same key share the same quota. A key must be explicitly provided by a client. When using [clickhouse-client](../../interfaces/cli.md), pass a key value in the `--quota-key` parameter, or use the `quota_key` parameter in the client configuration file. When using HTTP interface, use the `X-ClickHouse-Quota` header.
- `['user_name', 'client_key']` — Connections with the same `client_key` share the same quota. If a key isnt provided by a client, the qouta is tracked for `user_name`.
- `['client_key', 'ip_address']` — Connections with the same `client_key` share the same quota. If a key isnt provided by a client, the qouta is tracked for `ip_address`.
- `[]` — All users share the same quota.
- `['user_name']` — Connections with the same user name share the same quota.
- `['ip_address']` — Connections from the same IP share the same quota.
- `['client_key']` — Connections with the same key share the same quota. A key must be explicitly provided by a client. When using [clickhouse-client](../../interfaces/cli.md), pass a key value in the `--quota-key` parameter, or use the `quota_key` parameter in the client configuration file. When using HTTP interface, use the `X-ClickHouse-Quota` header.
- `['user_name', 'client_key']` — Connections with the same `client_key` share the same quota. If a key isnt provided by a client, the qouta is tracked for `user_name`.
- `['client_key', 'ip_address']` — Connections with the same `client_key` share the same quota. If a key isnt provided by a client, the qouta is tracked for `ip_address`.
- `durations` ([Array](../../sql-reference/data-types/array.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Time interval lengths in seconds.
- `apply_to_all` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Logical value. It shows which users the quota is applied to. Values:
- `0` — The quota applies to users specify in the `apply_to_list`.
- `1` — The quota applies to all users except those listed in `apply_to_except`.
- `0` — The quota applies to users specify in the `apply_to_list`.
- `1` — The quota applies to all users except those listed in `apply_to_except`.
- `apply_to_list` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — List of user names/[roles](../../operations/access-rights.md#role-management) that the quota should be applied to.
- `apply_to_except` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — List of user names/roles that the quota should not apply to.

View File

@ -7,7 +7,7 @@ toc_title: clickhouse-benchmark
Connects to a ClickHouse server and repeatedly sends specified queries.
Syntax:
**Syntax**
``` bash
$ clickhouse-benchmark --query ["single query"] [keys]
@ -28,35 +28,35 @@ $ clickhouse-benchmark [keys] <<< "single query"
If you want to send a set of queries, create a text file and place each query on the individual string in this file. For example:
``` sql
SELECT * FROM system.numbers LIMIT 10000000
SELECT 1
SELECT * FROM system.numbers LIMIT 10000000;
SELECT 1;
```
Then pass this file to a standard input of `clickhouse-benchmark`.
Then pass this file to a standard input of `clickhouse-benchmark`:
``` bash
clickhouse-benchmark [keys] < queries_file
clickhouse-benchmark [keys] < queries_file;
```
## Keys {#clickhouse-benchmark-keys}
- `--query=WORD` - Query to execute. If this parameter is not passed clickhouse-benchmark will read queries from standard input.
- `--query=QUERY` — Query to execute. If this parameter is not passed, `clickhouse-benchmark` will read queries from standard input.
- `-c N`, `--concurrency=N` — Number of queries that `clickhouse-benchmark` sends simultaneously. Default value: 1.
- `-d N`, `--delay=N` — Interval in seconds between intermediate reports (set 0 to disable reports). Default value: 1.
- `-h WORD`, `--host=WORD` — Server host. Default value: `localhost`. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-h` keys.
- `-d N`, `--delay=N` — Interval in seconds between intermediate reports (to disable reports set 0). Default value: 1.
- `-h HOST`, `--host=HOST` — Server host. Default value: `localhost`. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-h` keys.
- `-p N`, `--port=N` — Server port. Default value: 9000. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-p` keys.
- `-i N`, `--iterations=N` — Total number of queries. Default value: 0 (repeat forever).
- `-r`, `--randomize` — Random order of queries execution if there is more then one input query.
- `-s`, `--secure` — Using TLS connection.
- `-r`, `--randomize` — Random order of queries execution if there is more than one input query.
- `-s`, `--secure` — Using `TLS` connection.
- `-t N`, `--timelimit=N` — Time limit in seconds. `clickhouse-benchmark` stops sending queries when the specified time limit is reached. Default value: 0 (time limit disabled).
- `--confidence=N` — Level of confidence for T-test. Possible values: 0 (80%), 1 (90%), 2 (95%), 3 (98%), 4 (99%), 5 (99.5%). Default value: 5. In the [comparison mode](#clickhouse-benchmark-comparison-mode) `clickhouse-benchmark` performs the [Independent two-sample Students t-test](https://en.wikipedia.org/wiki/Student%27s_t-test#Independent_two-sample_t-test) test to determine whether the two distributions arent different with the selected level of confidence.
- `--confidence=N` — Level of confidence for T-test. Possible values: 0 (80%), 1 (90%), 2 (95%), 3 (98%), 4 (99%), 5 (99.5%). Default value: 5. In the [comparison mode](#clickhouse-benchmark-comparison-mode) `clickhouse-benchmark` performs the [Independent two-sample Students t-test](https://en.wikipedia.org/wiki/Student%27s_t-test#Independent_two-sample_t-test) to determine whether the two distributions arent different with the selected level of confidence.
- `--cumulative` — Printing cumulative data instead of data per interval.
- `--database=DATABASE_NAME` — ClickHouse database name. Default value: `default`.
- `--json=FILEPATH` — JSON output. When the key is set, `clickhouse-benchmark` outputs a report to the specified JSON-file.
- `--json=FILEPATH``JSON` output. When the key is set, `clickhouse-benchmark` outputs a report to the specified JSON-file.
- `--user=USERNAME` — ClickHouse user name. Default value: `default`.
- `--password=PSWD` — ClickHouse user password. Default value: empty string.
- `--stacktrace` — Stack traces output. When the key is set, `clickhouse-bencmark` outputs stack traces of exceptions.
- `--stage=WORD` — Query processing stage at server. ClickHouse stops query processing and returns answer to `clickhouse-benchmark` at the specified stage. Possible values: `complete`, `fetch_columns`, `with_mergeable_state`. Default value: `complete`.
- `--stage=WORD` — Query processing stage at server. ClickHouse stops query processing and returns an answer to `clickhouse-benchmark` at the specified stage. Possible values: `complete`, `fetch_columns`, `with_mergeable_state`. Default value: `complete`.
- `--help` — Shows the help message.
If you want to apply some [settings](../../operations/settings/index.md) for queries, pass them as a key `--<session setting name>= SETTING_VALUE`. For example, `--max_memory_usage=1048576`.
@ -96,11 +96,11 @@ In the report you can find:
- Endpoint of ClickHouse server.
- Number of processed queries.
- QPS: QPS: How many queries server performed per second during a period specified in the `--delay` argument.
- RPS: How many rows server read per second during a period specified in the `--delay` argument.
- MiB/s: How many mebibytes server read per second during a period specified in the `--delay` argument.
- result RPS: How many rows placed by server to the result of a query per second during a period specified in the `--delay` argument.
- result MiB/s. How many mebibytes placed by server to the result of a query per second during a period specified in the `--delay` argument.
- QPS: How many queries the server performed per second during a period specified in the `--delay` argument.
- RPS: How many rows the server reads per second during a period specified in the `--delay` argument.
- MiB/s: How many mebibytes the server reads per second during a period specified in the `--delay` argument.
- result RPS: How many rows placed by the server to the result of a query per second during a period specified in the `--delay` argument.
- result MiB/s. How many mebibytes placed by the server to the result of a query per second during a period specified in the `--delay` argument.
- Percentiles of queries execution time.
@ -159,3 +159,5 @@ localhost:9000, queries 10, QPS: 6.082, RPS: 121959604.568, MiB/s: 930.478, resu
99.900% 0.172 sec.
99.990% 0.172 sec.
```
[Original article](https://clickhouse.tech/docs/en/operations/utilities/clickhouse-benchmark.md) <!--hide-->

View File

@ -71,8 +71,8 @@ Parameters:
<remote_servers>
<source_cluster>
<!--
source cluster & destination clusters accepts exactly the same
parameters as parameters for usual Distributed table
source cluster & destination clusters accept exactly the same
parameters as parameters for the usual Distributed table
see https://clickhouse.tech/docs/en/engines/table-engines/special/distributed/
-->
<shard>

View File

@ -16,7 +16,7 @@ By default `clickhouse-local` does not have access to data on the same host, but
!!! warning "Warning"
It is not recommended to load production server configuration into `clickhouse-local` because data can be damaged in case of human error.
For temporary data, a unique temporary data directory is created by default. If you want to override this behavior, the data directory can be explicitly specified with the `-- --path` option.
For temporary data, a unique temporary data directory is created by default.
## Usage {#usage}
@ -32,15 +32,22 @@ Arguments:
- `-S`, `--structure` — table structure for input data.
- `-if`, `--input-format` — input format, `TSV` by default.
- `-f`, `--file` — path to data, `stdin` by default.
- `-q` `--query` — queries to execute with `;` as delimeter. You must specify either `query` or `queries-file` option.
- `-qf` `--queries-file` - file path with queries to execute. You must specify either `query` or `queries-file` option.
- `-q`, `--query` — queries to execute with `;` as delimeter. You must specify either `query` or `queries-file` option.
- `-qf`, `--queries-file` - file path with queries to execute. You must specify either `query` or `queries-file` option.
- `-N`, `--table` — table name where to put output data, `table` by default.
- `-of`, `--format`, `--output-format` — output format, `TSV` by default.
- `-d`, `--database` — default database, `_local` by default.
- `--stacktrace` — whether to dump debug output in case of exception.
- `--echo` — print query before execution.
- `--verbose` — more details on query execution.
- `-s` — disables `stderr` logging.
- `--config-file` — path to configuration file in same format as for ClickHouse server, by default the configuration empty.
- `--logger.console` — Log to console.
- `--logger.log` — Log file name.
- `--logger.level` — Log level.
- `--ignore-error` — do not stop processing if a query failed.
- `-c`, `--config-file` — path to configuration file in same format as for ClickHouse server, by default the configuration empty.
- `--no-system-tables` — do not attach system tables.
- `--help` — arguments references for `clickhouse-local`.
- `-V`, `--version` — print version information and exit.
Also there are arguments for each ClickHouse configuration variable which are more commonly used instead of `--config-file`.

View File

@ -241,7 +241,7 @@ windowFunnel(window, [mode])(timestamp, cond1, cond2, ..., condN)
**Parameters**
- `window` — Length of the sliding window in seconds.
- `window` — Length of the sliding window. The unit of `window` depends on the timestamp itself and varies. Determined using the expression `timestamp of cond2 <= timestamp of cond1 + window`.
- `mode` - It is an optional argument.
- `'strict'` - When the `'strict'` is set, the windowFunnel() applies conditions only for the unique values.
- `timestamp` — Name of the column containing the timestamp. Data types supported: [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md#data_type-datetime) and other unsigned integer types (note that even though timestamp supports the `UInt64` type, its value cant exceed the Int64 maximum, which is 2^63 - 1).

View File

@ -4,6 +4,28 @@ toc_priority: 106
# argMax {#agg-function-argmax}
Syntax: `argMax(arg, val)`
Syntax: `argMax(arg, val)` or `argMax(tuple(arg, val))`
Calculates the `arg` value for a maximum `val` value. If there are several different values of `arg` for maximum values of `val`, the first of these values encountered is output.
Tuple version of this function will return the tuple with the maximum `val` value. It is convinient for use with `SimpleAggregateFunction`.
**Example:**
``` text
┌─user─────┬─salary─┐
│ director │ 5000 │
│ manager │ 3000 │
│ worker │ 1000 │
└──────────┴────────┘
```
``` sql
SELECT argMax(user, salary), argMax(tuple(user, salary)) FROM salary
```
``` text
┌─argMax(user, salary)─┬─argMax(tuple(user, salary))─┐
│ director │ ('director',5000) │
└──────────────────────┴─────────────────────────────┘
```

View File

@ -4,10 +4,12 @@ toc_priority: 105
# argMin {#agg-function-argmin}
Syntax: `argMin(arg, val)`
Syntax: `argMin(arg, val)` or `argMin(tuple(arg, val))`
Calculates the `arg` value for a minimal `val` value. If there are several different values of `arg` for minimal values of `val`, the first of these values encountered is output.
Tuple version of this function will return the tuple with the minimal `val` value. It is convinient for use with `SimpleAggregateFunction`.
**Example:**
``` text
@ -19,11 +21,11 @@ Calculates the `arg` value for a minimal `val` value. If there are several diffe
```
``` sql
SELECT argMin(user, salary) FROM salary
SELECT argMin(user, salary), argMin(tuple(user, salary)) FROM salary
```
``` text
┌─argMin(user, salary)─┐
│ worker │
└──────────────────────┘
┌─argMin(user, salary)─┬─argMin(tuple(user, salary))─
│ worker │ ('worker',1000) │
└──────────────────────┴─────────────────────────────
```

View File

@ -0,0 +1,29 @@
---
toc_priority: 61
toc_title: Multiword Type Names
---
# Multiword Types {#multiword-types}
When creating tables, you can use data types with a name consisting of several words. This is implemented for better SQL compatibility.
## Multiword Types Support {#multiword-types-support}
| Multiword types | Simple types |
|----------------------------------|--------------------------------------------------------------|
| DOUBLE PRECISION | [Float64](../../sql-reference/data-types/float.md) |
| CHAR LARGE OBJECT | [String](../../sql-reference/data-types/string.md) |
| CHAR VARYING | [String](../../sql-reference/data-types/string.md) |
| CHARACTER LARGE OBJECT | [String](../../sql-reference/data-types/string.md) |
| CHARACTER VARYING | [String](../../sql-reference/data-types/string.md) |
| NCHAR LARGE OBJECT | [String](../../sql-reference/data-types/string.md) |
| NCHAR VARYING | [String](../../sql-reference/data-types/string.md) |
| NATIONAL CHARACTER LARGE OBJECT | [String](../../sql-reference/data-types/string.md) |
| NATIONAL CHARACTER VARYING | [String](../../sql-reference/data-types/string.md) |
| NATIONAL CHAR VARYING | [String](../../sql-reference/data-types/string.md) |
| NATIONAL CHARACTER | [String](../../sql-reference/data-types/string.md) |
| NATIONAL CHAR | [String](../../sql-reference/data-types/string.md) |
| BINARY LARGE OBJECT | [String](../../sql-reference/data-types/string.md) |
| BINARY VARYING | [String](../../sql-reference/data-types/string.md) |
[Original article](https://clickhouse.tech/docs/en/sql-reference/data-types/multiword-types/) <!--hide-->

View File

@ -18,6 +18,8 @@ The following aggregate functions are supported:
- [`sumMap`](../../sql-reference/aggregate-functions/reference/summap.md#agg_functions-summap)
- [`minMap`](../../sql-reference/aggregate-functions/reference/minmap.md#agg_functions-minmap)
- [`maxMap`](../../sql-reference/aggregate-functions/reference/maxmap.md#agg_functions-maxmap)
- [`argMin`](../../sql-reference/aggregate-functions/reference/argmin.md)
- [`argMax`](../../sql-reference/aggregate-functions/reference/argmax.md)
Values of the `SimpleAggregateFunction(func, Type)` look and stored the same way as `Type`, so you do not need to apply functions with `-Merge`/`-State` suffixes. `SimpleAggregateFunction` has better performance than `AggregateFunction` with same aggregation function.

View File

@ -11,7 +11,7 @@ Key length depends on encryption mode. It is 16, 24, and 32 bytes long for `-128
Initialization vector length is always 16 bytes (bytes in excess of 16 are ignored).
Note that these functions work slowly.
Note that these functions work slowly until ClickHouse 21.1.
## encrypt {#encrypt}
@ -41,7 +41,7 @@ encrypt('mode', 'plaintext', 'key' [, iv, aad])
**Returned value**
- Ciphered String. [String](../../sql-reference/data-types/string.md#string).
- Ciphertext binary string. [String](../../sql-reference/data-types/string.md#string).
**Examples**
@ -52,57 +52,38 @@ Query:
``` sql
CREATE TABLE encryption_test
(
input String,
key String DEFAULT unhex('fb9958e2e897ef3fdb49067b51a24af645b3626eed2f9ea1dc7fd4dd71b7e38f9a68db2a3184f952382c783785f9d77bf923577108a88adaacae5c141b1576b0'),
iv String DEFAULT unhex('8CA3554377DFF8A369BC50A89780DD85'),
key32 String DEFAULT substring(key, 1, 32),
key24 String DEFAULT substring(key, 1, 24),
key16 String DEFAULT substring(key, 1, 16)
) Engine = Memory;
`comment` String,
`secret` String
)
ENGINE = Memory
```
Insert this data:
Insert some data (please avoid storing the keys/ivs in the database as this undermines the whole concept of encryption), also storing 'hints' is unsafe too and used only for illustrative purposes:
Query:
``` sql
INSERT INTO encryption_test (input) VALUES (''), ('text'), ('What Is ClickHouse?');
INSERT INTO encryption_test VALUES('aes-256-cfb128 no IV', encrypt('aes-256-cfb128', 'Secret', '12345678910121314151617181920212')),\
('aes-256-cfb128 no IV, different key', encrypt('aes-256-cfb128', 'Secret', 'keykeykeykeykeykeykeykeykeykeyke')),\
('aes-256-cfb128 with IV', encrypt('aes-256-cfb128', 'Secret', '12345678910121314151617181920212', 'iviviviviviviviv')),\
('aes-256-cbc no IV', encrypt('aes-256-cbc', 'Secret', '12345678910121314151617181920212'));
```
Example without `iv`:
Query:
``` sql
SELECT 'aes-128-ecb' AS mode, hex(encrypt(mode, input, key16)) FROM encryption_test;
SELECT comment, hex(secret) FROM encryption_test;
```
Result:
``` text
┌─mode────────┬─hex(encrypt('aes-128-ecb', input, key16))────────────────────────┐
│ aes-128-ecb │ 4603E6862B0D94BBEC68E0B0DF51D60F │
│ aes-128-ecb │ 3004851B86D3F3950672DE7085D27C03 │
│ aes-128-ecb │ E807F8C8D40A11F65076361AFC7D8B68D8658C5FAA6457985CAA380F16B3F7E4 │
└─────────────┴──────────────────────────────────────────────────────────────────┘
```
Example with `iv`:
Query:
``` sql
SELECT 'aes-256-ctr' AS mode, hex(encrypt(mode, input, key32, iv)) FROM encryption_test;
```
Result:
``` text
┌─mode────────┬─hex(encrypt('aes-256-ctr', input, key32, iv))─┐
│ aes-256-ctr │ │
│ aes-256-ctr │ 7FB039F7 │
│ aes-256-ctr │ 5CBD20F7ABD3AC41FCAA1A5C0E119E2B325949 │
└─────────────┴───────────────────────────────────────────────┘
┌─comment─────────────────────────────┬─hex(secret)──────────────────────┐
│ aes-256-cfb128 no IV │ B4972BDC4459 │
│ aes-256-cfb128 no IV, different key │ 2FF57C092DC9 │
│ aes-256-cfb128 with IV │ 5E6CB398F653 │
│ aes-256-cbc no IV │ 1BC0629A92450D9E73A00E7D02CF4142 │
└─────────────────────────────────────┴──────────────────────────────────┘
```
Example with `-gcm`:
@ -110,40 +91,26 @@ Example with `-gcm`:
Query:
``` sql
SELECT 'aes-256-gcm' AS mode, hex(encrypt(mode, input, key32, iv)) FROM encryption_test;
INSERT INTO encryption_test VALUES('aes-256-gcm', encrypt('aes-256-gcm', 'Secret', '12345678910121314151617181920212', 'iviviviviviviviv')), \
('aes-256-gcm with AAD', encrypt('aes-256-gcm', 'Secret', '12345678910121314151617181920212', 'iviviviviviviviv', 'aad'));
SELECT comment, hex(secret) FROM encryption_test WHERE comment LIKE '%gcm%';
```
Result:
``` text
┌─mode────────┬─hex(encrypt('aes-256-gcm', input, key32, iv))──────────────────────────┐
│ aes-256-gcm │ E99DBEBC01F021758352D7FBD9039EFA │
│ aes-256-gcm │ 8742CE3A7B0595B281C712600D274CA881F47414 │
│ aes-256-gcm │ A44FD73ACEB1A64BDE2D03808A2576EDBB60764CC6982DB9AF2C33C893D91B00C60DC5 │
└─────────────┴────────────────────────────────────────────────────────────────────────┘
```
Example with `-gcm` mode and with `aad`:
Query:
``` sql
SELECT 'aes-192-gcm' AS mode, hex(encrypt(mode, input, key24, iv, 'AAD')) FROM encryption_test;
```
Result:
``` text
┌─mode────────┬─hex(encrypt('aes-192-gcm', input, key24, iv, 'AAD'))───────────────────┐
│ aes-192-gcm │ 04C13E4B1D62481ED22B3644595CB5DB │
│ aes-192-gcm │ 9A6CF0FD2B329B04EAD18301818F016DF8F77447 │
│ aes-192-gcm │ B961E9FD9B940EBAD7ADDA75C9F198A40797A5EA1722D542890CC976E21113BBB8A7AA │
└─────────────┴────────────────────────────────────────────────────────────────────────┘
┌─comment──────────────┬─hex(secret)──────────────────────────────────┐
│ aes-256-gcm │ A8A3CCBC6426CFEEB60E4EAE03D3E94204C1B09E0254 │
│ aes-256-gcm with AAD │ A8A3CCBC6426D9A1017A0A932322F1852260A4AD6837 │
└──────────────────────┴──────────────────────────────────────────────┘
```
## aes_encrypt_mysql {#aes_encrypt_mysql}
Compatible with mysql encryption and can be decrypted with [AES_DECRYPT](https://dev.mysql.com/doc/refman/8.0/en/encryption-functions.html#function_aes-decrypt) function.
Compatible with mysql encryption and resulting ciphertext can be decrypted with [AES_DECRYPT](https://dev.mysql.com/doc/refman/8.0/en/encryption-functions.html#function_aes-decrypt) function.
Will produce same ciphertext as `encrypt` on equal inputs. But when `key` or `iv` are longer than they should normally be, `aes_encrypt_mysql` will stick to what MySQL's `aes_encrypt` does: 'fold' `key` and ignore excess bits of `IV`.
Supported encryption modes:
@ -156,7 +123,7 @@ Supported encryption modes:
**Syntax**
```sql
``` sql
aes_encrypt_mysql('mode', 'plaintext', 'key' [, iv])
```
@ -164,78 +131,98 @@ aes_encrypt_mysql('mode', 'plaintext', 'key' [, iv])
- `mode` — Encryption mode. [String](../../sql-reference/data-types/string.md#string).
- `plaintext` — Text that needs to be encrypted. [String](../../sql-reference/data-types/string.md#string).
- `key` — Encryption key. [String](../../sql-reference/data-types/string.md#string).
- `iv` — Initialization vector. Optinal. [String](../../sql-reference/data-types/string.md#string).
- `key` — Encryption key. If key is longer than required by mode, MySQL-specific key folding is performed. [String](../../sql-reference/data-types/string.md#string).
- `iv` — Initialization vector. Optinal, only first 16 bytes are taken into account [String](../../sql-reference/data-types/string.md#string).
**Returned value**
- Ciphered String. [String](../../sql-reference/data-types/string.md#string).
- Ciphertext binary string. [String](../../sql-reference/data-types/string.md#string).
**Examples**
Create this table:
Given equal input `encrypt` and `aes_encrypt_mysql` produce the same ciphertext:
Query:
``` sql
CREATE TABLE encryption_test
(
input String,
key String DEFAULT unhex('fb9958e2e897ef3fdb49067b51a24af645b3626eed2f9ea1dc7fd4dd71b7e38f9a68db2a3184f952382c783785f9d77bf923577108a88adaacae5c141b1576b0'),
iv String DEFAULT unhex('8CA3554377DFF8A369BC50A89780DD85'),
key32 String DEFAULT substring(key, 1, 32),
key24 String DEFAULT substring(key, 1, 24),
key16 String DEFAULT substring(key, 1, 16)
) Engine = Memory;
SELECT encrypt('aes-256-cfb128', 'Secret', '12345678910121314151617181920212', 'iviviviviviviviv') = aes_encrypt_mysql('aes-256-cfb128', 'Secret', '12345678910121314151617181920212', 'iviviviviviviviv') AS ciphertexts_equal;
```
Insert this data:
Result:
Query:
``` sql
INSERT INTO encryption_test (input) VALUES (''), ('text'), ('What Is ClickHouse?');
```
┌─ciphertexts_equal─┐
│ 1 │
└───────────────────┘
```
Example without `iv`:
But `encrypt` fails when `key` or `iv` is longer than expected:
Query:
``` sql
SELECT 'aes-128-cbc' AS mode, hex(aes_encrypt_mysql(mode, input, key32)) FROM encryption_test;
SELECT encrypt('aes-256-cfb128', 'Secret', '123456789101213141516171819202122', 'iviviviviviviviv123');
```
Result:
``` text
┌─mode────────┬─hex(aes_encrypt_mysql('aes-128-cbc', input, key32))──────────────┐
│ aes-128-cbc │ FEA8CFDE6EE2C6E7A2CC6ADDC9F62C83 │
│ aes-128-cbc │ 78B16CD4BE107660156124C5FEE6454A │
│ aes-128-cbc │ 67C0B119D96F18E2823968D42871B3D179221B1E7EE642D628341C2B29BA2E18 │
└─────────────┴──────────────────────────────────────────────────────────────────┘
Received exception from server (version 21.1.2):
Code: 36. DB::Exception: Received from localhost:9000. DB::Exception: Invalid key size: 33 expected 32: While processing encrypt('aes-256-cfb128', 'Secret', '123456789101213141516171819202122', 'iviviviviviviviv123').
```
Example with `iv`:
While `aes_encrypt_mysql` produces MySQL-compatitalbe output:
Query:
``` sql
SELECT 'aes-256-cfb128' AS mode, hex(aes_encrypt_mysql(mode, input, key32, iv)) FROM encryption_test;
SELECT hex(aes_encrypt_mysql('aes-256-cfb128', 'Secret', '123456789101213141516171819202122', 'iviviviviviviviv123')) AS ciphertext;
```
Result:
```text
┌─ciphertext───┐
│ 24E9E4966469 │
└──────────────┘
```
Notice how supplying even longer `IV` produces the same result
Query:
``` sql
SELECT hex(aes_encrypt_mysql('aes-256-cfb128', 'Secret', '123456789101213141516171819202122', 'iviviviviviviviv123456')) AS ciphertext
```
Result:
``` text
┌─mode───────────┬─hex(aes_encrypt_mysql('aes-256-cfb128', input, key32, iv))─┐
│ aes-256-cfb128 │ │
│ aes-256-cfb128 │ 7FB039F7 │
│ aes-256-cfb128 │ 5CBD20F7ABD3AC41FCAA1A5C0E119E2BB5174F │
└────────────────┴────────────────────────────────────────────────────────────┘
┌─ciphertext───┐
│ 24E9E4966469 │
└──────────────┘
```
Which is binary equal to what MySQL produces on same inputs:
``` sql
mysql> SET block_encryption_mode='aes-256-cfb128';
Query OK, 0 rows affected (0.00 sec)
mysql> SELECT aes_encrypt('Secret', '123456789101213141516171819202122', 'iviviviviviviviv123456') as ciphertext;
+------------------------+
| ciphertext |
+------------------------+
| 0x24E9E4966469 |
+------------------------+
1 row in set (0.00 sec)
```
## decrypt {#decrypt}
This function decrypts data using these modes:
This function decrypts ciphertext into a plaintext using these modes:
- aes-128-ecb, aes-192-ecb, aes-256-ecb
- aes-128-cbc, aes-192-cbc, aes-256-cbc
@ -247,7 +234,7 @@ This function decrypts data using these modes:
**Syntax**
```sql
``` sql
decrypt('mode', 'ciphertext', 'key' [, iv, aad])
```
@ -265,51 +252,56 @@ decrypt('mode', 'ciphertext', 'key' [, iv, aad])
**Examples**
Create this table:
Re-using table from [encrypt](./encryption-functions.md#encrypt).
Query:
``` sql
CREATE TABLE encryption_test
(
input String,
key String DEFAULT unhex('fb9958e2e897ef3fdb49067b51a24af645b3626eed2f9ea1dc7fd4dd71b7e38f9a68db2a3184f952382c783785f9d77bf923577108a88adaacae5c141b1576b0'),
iv String DEFAULT unhex('8CA3554377DFF8A369BC50A89780DD85'),
key32 String DEFAULT substring(key, 1, 32),
key24 String DEFAULT substring(key, 1, 24),
key16 String DEFAULT substring(key, 1, 16)
) Engine = Memory;
```
Insert this data:
Query:
``` sql
INSERT INTO encryption_test (input) VALUES (''), ('text'), ('What Is ClickHouse?');
```
Query:
``` sql
SELECT 'aes-128-ecb' AS mode, decrypt(mode, encrypt(mode, input, key16), key16) FROM encryption_test;
SELECT comment, hex(secret) FROM encryption_test;
```
Result:
```text
┌─mode────────┬─decrypt('aes-128-ecb', encrypt('aes-128-ecb', input, key16), key16)─┐
│ aes-128-ecb │ │
│ aes-128-ecb │ text │
│ aes-128-ecb │ What Is ClickHouse? │
└─────────────┴─────────────────────────────────────────────────────────────────────┘
``` text
┌─comment──────────────┬─hex(secret)──────────────────────────────────┐
│ aes-256-gcm │ A8A3CCBC6426CFEEB60E4EAE03D3E94204C1B09E0254 │
│ aes-256-gcm with AAD │ A8A3CCBC6426D9A1017A0A932322F1852260A4AD6837 │
└──────────────────────┴──────────────────────────────────────────────┘
┌─comment─────────────────────────────┬─hex(secret)──────────────────────┐
│ aes-256-cfb128 no IV │ B4972BDC4459 │
│ aes-256-cfb128 no IV, different key │ 2FF57C092DC9 │
│ aes-256-cfb128 with IV │ 5E6CB398F653 │
│ aes-256-cbc no IV │ 1BC0629A92450D9E73A00E7D02CF4142 │
└─────────────────────────────────────┴──────────────────────────────────┘
```
Now let's try to decrypt all that data.
Query:
``` sql
SELECT comment, decrypt('aes-256-cfb128', secret, '12345678910121314151617181920212') as plaintext FROM encryption_test
```
Result:
``` text
┌─comment─────────────────────────────┬─plaintext─┐
│ aes-256-cfb128 no IV │ Secret │
│ aes-256-cfb128 no IV, different key │ <20>4<EFBFBD>
<20>
│ aes-256-cfb128 with IV │ <20><><EFBFBD>6<EFBFBD>~ │
│aes-256-cbc no IV │ <20>2*4<>h3c<33>4w<34><77>@
└─────────────────────────────────────┴───────────┘
```
Notice how only portion of the data was properly decrypted, and the rest is gibberish since either `mode`, `key`, or `iv` were different upon encryption.
## aes_decrypt_mysql {#aes_decrypt_mysql}
Compatible with mysql encryption and decrypts data encrypted with [AES_ENCRYPT](https://dev.mysql.com/doc/refman/8.0/en/encryption-functions.html#function_aes-encrypt) function.
Will produce same plaintext as `decrypt` on equal inputs. But when `key` or `iv` are longer than they should normally be, `aes_decrypt_mysql` will stick to what MySQL's `aes_decrypt` does: 'fold' `key` and ignore excess bits of `IV`.
Supported decryption modes:
- aes-128-ecb, aes-192-ecb, aes-256-ecb
@ -321,7 +313,7 @@ Supported decryption modes:
**Syntax**
```sql
``` sql
aes_decrypt_mysql('mode', 'ciphertext', 'key' [, iv])
```
@ -338,44 +330,30 @@ aes_decrypt_mysql('mode', 'ciphertext', 'key' [, iv])
**Examples**
Create this table:
Query:
Let's decrypt data we've previously encrypted with MySQL:
``` sql
CREATE TABLE encryption_test
(
input String,
key String DEFAULT unhex('fb9958e2e897ef3fdb49067b51a24af645b3626eed2f9ea1dc7fd4dd71b7e38f9a68db2a3184f952382c783785f9d77bf923577108a88adaacae5c141b1576b0'),
iv String DEFAULT unhex('8CA3554377DFF8A369BC50A89780DD85'),
key32 String DEFAULT substring(key, 1, 32),
key24 String DEFAULT substring(key, 1, 24),
key16 String DEFAULT substring(key, 1, 16)
) Engine = Memory;
```
mysql> SET block_encryption_mode='aes-256-cfb128';
Query OK, 0 rows affected (0.00 sec)
Insert this data:
Query:
``` sql
INSERT INTO encryption_test (input) VALUES (''), ('text'), ('What Is ClickHouse?');
mysql> SELECT aes_encrypt('Secret', '123456789101213141516171819202122', 'iviviviviviviviv123456') as ciphertext;
+------------------------+
| ciphertext |
+------------------------+
| 0x24E9E4966469 |
+------------------------+
1 row in set (0.00 sec)
```
Query:
``` sql
SELECT 'aes-128-cbc' AS mode, aes_decrypt_mysql(mode, aes_encrypt_mysql(mode, input, key), key) FROM encryption_test;
SELECT aes_decrypt_mysql('aes-256-cfb128', unhex('24E9E4966469'), '123456789101213141516171819202122', 'iviviviviviviviv123456') AS plaintext
```
Result:
``` text
┌─mode────────┬─aes_decrypt_mysql('aes-128-cbc', aes_encrypt_mysql('aes-128-cbc', input, key), key)─┐
│ aes-128-cbc │ │
│ aes-128-cbc │ text │
│ aes-128-cbc │ What Is ClickHouse? │
└─────────────┴─────────────────────────────────────────────────────────────────────────────────────┘
┌─plaintext─┐
│ Secret │
└───────────┘
```
[Original article](https://clickhouse.tech/docs/en/sql-reference/functions/encryption_functions/) <!--hide-->

View File

@ -115,9 +115,20 @@ LIMIT 10
## IPv6StringToNum(s) {#ipv6stringtonums}
The reverse function of IPv6NumToString. If the IPv6 address has an invalid format, it returns a string of null bytes.
The reverse function of IPv6NumToString. If the IPv6 address has an invalid format, it returns a string of null bytes.
If the IP address is a valid IPv4 address then the IPv6 equivalent of the IPv4 address is returned.
HEX can be uppercase or lowercase.
``` sql
SELECT cutIPv6(IPv6StringToNum('127.0.0.1'), 0, 0);
```
``` text
┌─cutIPv6(IPv6StringToNum('127.0.0.1'), 0, 0)─┐
│ ::ffff:127.0.0.1 │
└─────────────────────────────────────────────┘
```
## IPv4ToIPv6(x) {#ipv4toipv6x}
Takes a `UInt32` number. Interprets it as an IPv4 address in [big endian](https://en.wikipedia.org/wiki/Endianness). Returns a `FixedString(16)` value containing the IPv6 address in binary format. Examples:
@ -214,6 +225,7 @@ SELECT
## toIPv6(string) {#toipv6string}
An alias to `IPv6StringToNum()` that takes a string form of IPv6 address and returns value of [IPv6](../../sql-reference/data-types/domains/ipv6.md) type, which is binary equal to value returned by `IPv6StringToNum()`.
If the IP address is a valid IPv4 address then the IPv6 equivalent of the IPv4 address is returned.
``` sql
WITH
@ -243,4 +255,42 @@ SELECT
└───────────────────────────────────┴──────────────────────────────────┘
```
``` sql
SELECT toIPv6('127.0.0.1')
```
``` text
┌─toIPv6('127.0.0.1')─┐
│ ::ffff:127.0.0.1 │
└─────────────────────┘
```
## isIPv4String
Determines if the input string is an IPv4 address or not. Returns `1` if true `0` otherwise.
``` sql
SELECT isIPv4String('127.0.0.1')
```
``` text
┌─isIPv4String('127.0.0.1')─┐
│ 1 │
└───────────────────────────┘
```
## isIPv6String
Determines if the input string is an IPv6 address or not. Returns `1` if true `0` otherwise.
``` sql
SELECT isIPv6String('2001:438:ffff::407d:1bc1')
```
``` text
┌─isIPv6String('2001:438:ffff::407d:1bc1')─┐
│ 1 │
└──────────────────────────────────────────┘
```
[Original article](https://clickhouse.tech/docs/en/query_language/functions/ip_address_functions/) <!--hide-->

View File

@ -413,4 +413,68 @@ Result:
- [log(x)](../../sql-reference/functions/math-functions.md#logx-lnx)
## sign(x) {#signx}
The `sign` function can extract the sign of a real number.
**Syntax**
``` sql
sign(x)
```
**Parameters**
- `x` — Values from `-∞` to `+∞`. Support all numeric types in ClickHouse.
**Returned value**
- -1 for `x < 0`
- 0 for `x = 0`
- 1 for `x > 0`
**Example**
Query:
``` sql
SELECT sign(0);
```
Result:
``` text
┌─sign(0)─┐
│ 0 │
└─────────┘
```
Query:
``` sql
SELECT sign(1);
```
Result:
``` text
┌─sign(1)─┐
│ 1 │
└─────────┘
```
Query:
``` sql
SELECT sign(-1);
```
Result:
``` text
┌─sign(-1)─┐
│ -1 │
└──────────┘
```
[Original article](https://clickhouse.tech/docs/en/query_language/functions/math_functions/) <!--hide-->

View File

@ -1468,7 +1468,7 @@ Code: 395. DB::Exception: Received from localhost:9000. DB::Exception: Too many.
## identity {#identity}
Returns the same value that was used as its argument. Used for debugging and testing, allows to cancel using index, and get the query performance of a full scan. When query is analyzed for possible use of index, the analyzer doesnt look inside `identity` functions.
Returns the same value that was used as its argument. Used for debugging and testing, allows to cancel using index, and get the query performance of a full scan. When query is analyzed for possible use of index, the analyzer doesnt look inside `identity` functions. Also constant folding is not applied too.
**Syntax**

View File

@ -574,7 +574,7 @@ encodeXMLComponent(x)
- `x` — The sequence of characters. [String](../../sql-reference/data-types/string.md).
**Returned value(s)**
**Returned value**
- The sequence of characters with escape characters.

View File

@ -5,16 +5,35 @@ toc_title: QUOTA
# ALTER QUOTA {#alter-quota-statement}
Changes quotas.
Changes [quotas](../../../operations/access-rights.md#quotas-management).
Syntax:
``` sql
ALTER QUOTA [IF EXISTS] name [ON CLUSTER cluster_name]
[RENAME TO new_name]
[KEYED BY {'none' | 'user name' | 'ip address' | 'client key' | 'client key or user name' | 'client key or ip address'}]
[FOR [RANDOMIZED] INTERVAL number {SECOND | MINUTE | HOUR | DAY | WEEK | MONTH | QUARTER | YEAR}
{MAX { {QUERIES | ERRORS | RESULT ROWS | RESULT BYTES | READ ROWS | READ BYTES | EXECUTION TIME} = number } [,...] |
[KEYED BY {user_name | ip_address | client_key | client_key,user_name | client_key,ip_address} | NOT KEYED]
[FOR [RANDOMIZED] INTERVAL number {second | minute | hour | day | week | month | quarter | year}
{MAX { {queries | errors | result_rows | result_bytes | read_rows | read_bytes | execution_time} = number } [,...] |
NO LIMITS | TRACKING ONLY} [,...]]
[TO {role [,...] | ALL | ALL EXCEPT role [,...]}]
```
Keys `user_name`, `ip_address`, `client_key`, `client_key, user_name` and `client_key, ip_address` correspond to the fields in the [system.quotas](../../../operations/system-tables/quotas.md) table.
Parameters `queries`, `errors`, `result_rows`, `result_bytes`, `read_rows`, `read_bytes`, `execution_time` correspond to the fields in the [system.quotas_usage](../../../operations/system-tables/quotas_usage.md) table.
`ON CLUSTER` clause allows creating quotas on a cluster, see [Distributed DDL](../../../sql-reference/distributed-ddl.md).
**Examples**
Limit the maximum number of queries for the current user with 123 queries in 15 months constraint:
``` sql
ALTER QUOTA IF EXISTS qA FOR INTERVAL 15 month MAX queries = 123 TO CURRENT_USER;
```
For the default user limit the maximum execution time with half a second in 30 minutes, and limit the maximum number of queries with 321 and the maximum number of errors with 10 in 5 quaters:
``` sql
ALTER QUOTA IF EXISTS qB FOR INTERVAL 30 minute MAX execution_time = 0.5, FOR INTERVAL 5 quarter MAX queries = 321, errors = 10 TO default;
```

View File

@ -10,7 +10,7 @@ Changes roles.
Syntax:
``` sql
ALTER ROLE [IF EXISTS] name [ON CLUSTER cluster_name]
[RENAME TO new_name]
ALTER ROLE [IF EXISTS] name1 [ON CLUSTER cluster_name1] [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] [RENAME TO new_name2] ...]
[SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...]
```

View File

@ -10,8 +10,8 @@ Changes row policy.
Syntax:
``` sql
ALTER [ROW] POLICY [IF EXISTS] name [ON CLUSTER cluster_name] ON [database.]table
[RENAME TO new_name]
ALTER [ROW] POLICY [IF EXISTS] name1 [ON CLUSTER cluster_name1] ON [database1.]table1 [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] ON [database2.]table2 [RENAME TO new_name2] ...]
[AS {PERMISSIVE | RESTRICTIVE}]
[FOR SELECT]
[USING {condition | NONE}][,...]

View File

@ -10,7 +10,7 @@ Changes settings profiles.
Syntax:
``` sql
ALTER SETTINGS PROFILE [IF EXISTS] TO name [ON CLUSTER cluster_name]
[RENAME TO new_name]
ALTER SETTINGS PROFILE [IF EXISTS] TO name1 [ON CLUSTER cluster_name1] [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] [RENAME TO new_name2] ...]
[SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | INHERIT 'profile_name'] [,...]
```

View File

@ -10,8 +10,8 @@ Changes ClickHouse user accounts.
Syntax:
``` sql
ALTER USER [IF EXISTS] name [ON CLUSTER cluster_name]
[RENAME TO new_name]
ALTER USER [IF EXISTS] name1 [ON CLUSTER cluster_name1] [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] [RENAME TO new_name2] ...]
[IDENTIFIED [WITH {PLAINTEXT_PASSWORD|SHA256_PASSWORD|DOUBLE_SHA1_PASSWORD}] BY {'password'|'hash'}]
[[ADD|DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[DEFAULT ROLE role [,...] | ALL | ALL EXCEPT role [,...] ]

View File

@ -11,19 +11,29 @@ Syntax:
``` sql
CREATE QUOTA [IF NOT EXISTS | OR REPLACE] name [ON CLUSTER cluster_name]
[KEYED BY {'none' | 'user name' | 'ip address' | 'forwarded ip address' | 'client key' | 'client key or user name' | 'client key or ip address'}]
[FOR [RANDOMIZED] INTERVAL number {SECOND | MINUTE | HOUR | DAY | WEEK | MONTH | QUARTER | YEAR}
{MAX { {QUERIES | ERRORS | RESULT ROWS | RESULT BYTES | READ ROWS | READ BYTES | EXECUTION TIME} = number } [,...] |
[KEYED BY {user_name | ip_address | client_key | client_key,user_name | client_key,ip_address} | NOT KEYED]
[FOR [RANDOMIZED] INTERVAL number {second | minute | hour | day | week | month | quarter | year}
{MAX { {queries | errors | result_rows | result_bytes | read_rows | read_bytes | execution_time} = number } [,...] |
NO LIMITS | TRACKING ONLY} [,...]]
[TO {role [,...] | ALL | ALL EXCEPT role [,...]}]
```
Keys `user_name`, `ip_address`, `client_key`, `client_key, user_name` and `client_key, ip_address` correspond to the fields in the [system.quotas](../../../operations/system-tables/quotas.md) table.
Parameters `queries`, `errors`, `result_rows`, `result_bytes`, `read_rows`, `read_bytes`, `execution_time` correspond to the fields in the [system.quotas_usage](../../../operations/system-tables/quotas_usage.md) table.
`ON CLUSTER` clause allows creating quotas on a cluster, see [Distributed DDL](../../../sql-reference/distributed-ddl.md).
## Example {#create-quota-example}
**Examples**
Limit the maximum number of queries for the current user with 123 queries in 15 months constraint:
``` sql
CREATE QUOTA qA FOR INTERVAL 15 MONTH MAX QUERIES 123 TO CURRENT_USER
CREATE QUOTA qA FOR INTERVAL 15 month MAX queries = 123 TO CURRENT_USER;
```
For the default user limit the maximum execution time with half a second in 30 minutes, and limit the maximum number of queries with 321 and the maximum number of errors with 10 in 5 quaters:
``` sql
CREATE QUOTA qB FOR INTERVAL 30 minute MAX execution_time = 0.5, FOR INTERVAL 5 quarter MAX queries = 321, errors = 10 TO default;
```

View File

@ -5,12 +5,12 @@ toc_title: ROLE
# CREATE ROLE {#create-role-statement}
Creates a new [role](../../../operations/access-rights.md#role-management). Role is a set of [privileges](../../../sql-reference/statements/grant.md#grant-privileges). A [user](../../../sql-reference/statements/create/user.md) assigned a role gets all the privileges of this role.
Creates new [roles](../../../operations/access-rights.md#role-management). Role is a set of [privileges](../../../sql-reference/statements/grant.md#grant-privileges). A [user](../../../sql-reference/statements/create/user.md) assigned a role gets all the privileges of this role.
Syntax:
``` sql
CREATE ROLE [IF NOT EXISTS | OR REPLACE] name
CREATE ROLE [IF NOT EXISTS | OR REPLACE] name1 [, name2 ...]
[SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | PROFILE 'profile_name'] [,...]
```

View File

@ -5,16 +5,17 @@ toc_title: ROW POLICY
# CREATE ROW POLICY {#create-row-policy-statement}
Creates a [filter for rows](../../../operations/access-rights.md#row-policy-management), which a user can read from a table.
Creates [filters for rows](../../../operations/access-rights.md#row-policy-management), which a user can read from a table.
Syntax:
``` sql
CREATE [ROW] POLICY [IF NOT EXISTS | OR REPLACE] policy_name [ON CLUSTER cluster_name] ON [db.]table
CREATE [ROW] POLICY [IF NOT EXISTS | OR REPLACE] policy_name1 [ON CLUSTER cluster_name1] ON [db1.]table1
[, policy_name2 [ON CLUSTER cluster_name2] ON [db2.]table2 ...]
[AS {PERMISSIVE | RESTRICTIVE}]
[FOR SELECT]
[USING condition]
[TO {role [,...] | ALL | ALL EXCEPT role [,...]}]
[TO {role1 [, role2 ...] | ALL | ALL EXCEPT role1 [, role2 ...]}]
```
`ON CLUSTER` clause allows creating row policies on a cluster, see [Distributed DDL](../../../sql-reference/distributed-ddl.md).

View File

@ -5,12 +5,13 @@ toc_title: SETTINGS PROFILE
# CREATE SETTINGS PROFILE {#create-settings-profile-statement}
Creates a [settings profile](../../../operations/access-rights.md#settings-profiles-management) that can be assigned to a user or a role.
Creates [settings profiles](../../../operations/access-rights.md#settings-profiles-management) that can be assigned to a user or a role.
Syntax:
``` sql
CREATE SETTINGS PROFILE [IF NOT EXISTS | OR REPLACE] TO name [ON CLUSTER cluster_name]
CREATE SETTINGS PROFILE [IF NOT EXISTS | OR REPLACE] TO name1 [ON CLUSTER cluster_name1]
[, name2 [ON CLUSTER cluster_name2] ...]
[SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY|WRITABLE] | INHERIT 'profile_name'] [,...]
```

View File

@ -23,7 +23,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
```
Creates a table named `name` in the `db` database or the current database if `db` is not set, with the structure specified in brackets and the `engine` engine.
The structure of the table is a list of column descriptions, secondary indexes and constraints . If primary key is supported by the engine, it will be indicated as parameter for the table engine.
The structure of the table is a list of column descriptions, secondary indexes and constraints . If [primary key](#primary-key) is supported by the engine, it will be indicated as parameter for the table engine.
A column description is `name type` in the simplest case. Example: `RegionID UInt32`.
@ -39,13 +39,13 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name AS [db2.]name2 [ENGINE = engine]
Creates a table with the same structure as another table. You can specify a different engine for the table. If the engine is not specified, the same engine will be used as for the `db2.name2` table.
## From a Table Function {#from-a-table-function}
### From a Table Function {#from-a-table-function}
``` sql
CREATE TABLE [IF NOT EXISTS] [db.]table_name AS table_function()
```
Creates a table with the structure and data returned by a [table function](../../../sql-reference/table-functions/index.md#table-functions).
Creates a table with the same result as that of the [table function](../../../sql-reference/table-functions/index.md#table-functions) specified. The created table will also work in the same way as the corresponding table function that was specified.
``` sql
CREATE TABLE [IF NOT EXISTS] [db.]table_name ENGINE = engine AS SELECT ...
@ -111,7 +111,7 @@ It is not possible to set default values for elements in nested data structures.
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
- Inside the column list
``` sql
CREATE TABLE db.table_name
@ -122,7 +122,7 @@ CREATE TABLE db.table_name
ENGINE = engine;
```
- outside the column list
- Outside the column list
``` sql
CREATE TABLE db.table_name
@ -133,7 +133,8 @@ ENGINE = engine
PRIMARY KEY(expr1[, expr2,...]);
```
You can't combine both ways in one query.
!!! warning "Warning"
You can't combine both ways in one query.
## Constraints {#constraints}
@ -259,3 +260,78 @@ CREATE TEMPORARY TABLE [IF NOT EXISTS] table_name
In most cases, temporary tables are not created manually, but when using external data for a query, or for distributed `(GLOBAL) IN`. For more information, see the appropriate sections
Its possible to use tables with [ENGINE = Memory](../../../engines/table-engines/special/memory.md) instead of temporary tables.
## REPLACE TABLE {#replace-table-query}
'REPLACE' query allows you to update the table atomically.
!!!note "Note"
This query is supported only for [Atomic](../../../engines/database-engines/atomic.md) database engine.
If you need to delete some data from a table, you can create a new table and fill it with a `SELECT` statement that doesn't retrieve unwanted data, then drop the old table and rename the new one:
```sql
CREATE TABLE myNewTable AS myOldTable;
INSERT INTO myNewTable SELECT * FROM myOldTable WHERE CounterID <12345;
DROP TABLE myOldTable;
RENAME TABLE myNewTable TO myOldTable;
```
Instead of above, you can use the following:
```sql
REPLACE TABLE myOldTable SELECT * FROM myOldTable WHERE CounterID <12345;
```
### Syntax
{CREATE [OR REPLACE]|REPLACE} TABLE [db.]table_name
All syntax forms for `CREATE` query also work for this query. `REPLACE` for a non-existent table will cause an error.
### Examples:
Consider the table:
```sql
CREATE DATABASE base ENGINE = Atomic;
CREATE OR REPLACE TABLE base.t1 (n UInt64, s String) ENGINE = MergeTree ORDER BY n;
INSERT INTO base.t1 VALUES (1, 'test');
SELECT * FROM base.t1;
```
```text
┌─n─┬─s────┐
│ 1 │ test │
└───┴──────┘
```
Using `REPLACE` query to clear all data:
```sql
CREATE OR REPLACE TABLE base.t1 (n UInt64, s Nullable(String)) ENGINE = MergeTree ORDER BY n;
INSERT INTO base.t1 VALUES (2, null);
SELECT * FROM base.t1;
```
```text
┌─n─┬─s──┐
│ 2 │ \N │
└───┴────┘
```
Using `REPLACE` query to change table structure:
```sql
REPLACE TABLE base.t1 (n UInt64) ENGINE = MergeTree ORDER BY n;
INSERT INTO base.t1 VALUES (3);
SELECT * FROM base.t1;
```
```text
┌─n─┐
│ 3 │
└───┘
```
[Original article](https://clickhouse.tech/docs/en/sql-reference/statements/create/table) <!--hide-->

View File

@ -5,12 +5,13 @@ toc_title: USER
# CREATE USER {#create-user-statement}
Creates a [user account](../../../operations/access-rights.md#user-account-management).
Creates [user accounts](../../../operations/access-rights.md#user-account-management).
Syntax:
``` sql
CREATE USER [IF NOT EXISTS | OR REPLACE] name [ON CLUSTER cluster_name]
CREATE USER [IF NOT EXISTS | OR REPLACE] name1 [ON CLUSTER cluster_name1]
[, name2 [ON CLUSTER cluster_name2] ...]
[IDENTIFIED [WITH {NO_PASSWORD|PLAINTEXT_PASSWORD|SHA256_PASSWORD|SHA256_HASH|DOUBLE_SHA1_PASSWORD|DOUBLE_SHA1_HASH}] BY {'password'|'hash'}]
[HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[DEFAULT ROLE role [,...]]
@ -69,7 +70,7 @@ CREATE USER john DEFAULT ROLE role1, role2
Create the user account `john` and make all his future roles default:
``` sql
ALTER USER user DEFAULT ROLE ALL
CREATE USER user DEFAULT ROLE ALL
```
When some role is assigned to `john` in the future, it will become default automatically.
@ -77,5 +78,5 @@ When some role is assigned to `john` in the future, it will become default autom
Create the user account `john` and make all his future roles default excepting `role1` and `role2`:
``` sql
ALTER USER john DEFAULT ROLE ALL EXCEPT role1, role2
CREATE USER john DEFAULT ROLE ALL EXCEPT role1, role2
```

View File

@ -13,7 +13,7 @@ Basic query format:
INSERT INTO [db.]table [(c1, c2, c3)] VALUES (v11, v12, v13), (v21, v22, v23), ...
```
You can specify a list of columns to insert using the `(c1, c2, c3)`. You can also use an expression with column [matcher](../../sql-reference/statements/select/index.md#asterisk) such as `*` and/or [modifiers](../../sql-reference/statements/select/index.md#select-modifiers) such as [APPLY](../../sql-reference/statements/select/index.md#apply-modifier), [EXCEPT](../../sql-reference/statements/select/index.md#apply-modifier), [REPLACE](../../sql-reference/statements/select/index.md#replace-modifier).
You can specify a list of columns to insert using the `(c1, c2, c3)`. You can also use an expression with column [matcher](../../sql-reference/statements/select/index.md#asterisk) such as `*` and/or [modifiers](../../sql-reference/statements/select/index.md#select-modifiers) such as [APPLY](../../sql-reference/statements/select/index.md#apply-modifier), [EXCEPT](../../sql-reference/statements/select/index.md#except-modifier), [REPLACE](../../sql-reference/statements/select/index.md#replace-modifier).
For example, consider the table:
@ -30,7 +30,6 @@ CREATE TABLE insert_select_testtable
)
ENGINE = MergeTree()
ORDER BY a
SETTINGS index_granularity = 8192
```
``` sql
@ -55,7 +54,7 @@ SELECT * FROM insert_select_testtable;
│ 1 │ a │ 1 │
└───┴───┴───┘
```
In this example, we see that the second inserted row has `a` and `c` columns filled by the passed values, and `b` filled with value by default.
If a list of columns doesn't include all existing columns, the rest of the columns are filled with:

View File

@ -25,6 +25,8 @@ It is applicable when selecting data from tables that use the [MergeTree](../../
- [Replicated](../../../engines/table-engines/mergetree-family/replication.md) versions of `MergeTree` engines.
- [View](../../../engines/table-engines/special/view.md), [Buffer](../../../engines/table-engines/special/buffer.md), [Distributed](../../../engines/table-engines/special/distributed.md), and [MaterializedView](../../../engines/table-engines/special/materializedview.md) engines that operate over other engines, provided they were created over `MergeTree`-engine tables.
Now `SELECT` queries with `FINAL` are executed in parallel and slightly faster. But there are drawbacks (see below). The [max_final_threads](../../../operations/settings/settings.md#max-final-threads) setting limits the number of threads used.
### Drawbacks {#drawbacks}
Queries that use `FINAL` are executed slightly slower than similar queries that dont, because:

View File

@ -278,5 +278,4 @@ Other ways to make settings see [here](../../../operations/settings/index.md).
SELECT * FROM some_table SETTINGS optimize_read_in_order=1, cast_keep_nullable=1;
```
[Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/)
<!--hide-->
[Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/)<!--hide-->

View File

@ -231,7 +231,7 @@ Shows privileges for a user.
### Syntax {#show-grants-syntax}
``` sql
SHOW GRANTS [FOR user]
SHOW GRANTS [FOR user1 [, user2 ...]]
```
If user is not specified, the query returns privileges for the current user.
@ -245,7 +245,7 @@ Shows parameters that were used at a [user creation](../../sql-reference/stateme
### Syntax {#show-create-user-syntax}
``` sql
SHOW CREATE USER [name | CURRENT_USER]
SHOW CREATE USER [name1 [, name2 ...] | CURRENT_USER]
```
## SHOW CREATE ROLE {#show-create-role-statement}
@ -255,7 +255,7 @@ Shows parameters that were used at a [role creation](../../sql-reference/stateme
### Syntax {#show-create-role-syntax}
``` sql
SHOW CREATE ROLE name
SHOW CREATE ROLE name1 [, name2 ...]
```
## SHOW CREATE ROW POLICY {#show-create-row-policy-statement}
@ -265,7 +265,7 @@ Shows parameters that were used at a [row policy creation](../../sql-reference/s
### Syntax {#show-create-row-policy-syntax}
``` sql
SHOW CREATE [ROW] POLICY name ON [database.]table
SHOW CREATE [ROW] POLICY name ON [database1.]table1 [, [database2.]table2 ...]
```
## SHOW CREATE QUOTA {#show-create-quota-statement}
@ -275,7 +275,7 @@ Shows parameters that were used at a [quota creation](../../sql-reference/statem
### Syntax {#show-create-quota-syntax}
``` sql
SHOW CREATE QUOTA [name | CURRENT]
SHOW CREATE QUOTA [name1 [, name2 ...] | CURRENT]
```
## SHOW CREATE SETTINGS PROFILE {#show-create-settings-profile-statement}
@ -285,7 +285,7 @@ Shows parameters that were used at a [settings profile creation](../../sql-refer
### Syntax {#show-create-settings-profile-syntax}
``` sql
SHOW CREATE [SETTINGS] PROFILE name
SHOW CREATE [SETTINGS] PROFILE name1 [, name2 ...]
```
## SHOW USERS {#show-users-statement}
@ -307,7 +307,6 @@ Returns a list of [roles](../../operations/access-rights.md#role-management). To
``` sql
SHOW [CURRENT|ENABLED] ROLES
```
## SHOW PROFILES {#show-profiles-statement}
Returns a list of [setting profiles](../../operations/access-rights.md#settings-profiles-management). To view user accounts parameters, see the system table [settings_profiles](../../operations/system-tables/settings_profiles.md#system_tables-settings_profiles).
@ -347,7 +346,15 @@ Returns a [quota](../../operations/quotas.md) consumption for all users or for c
``` sql
SHOW [CURRENT] QUOTA
```
## SHOW ACCESS {#show-access-statement}
Shows all [users](../../operations/access-rights.md#user-account-management), [roles](../../operations/access-rights.md#role-management), [profiles](../../operations/access-rights.md#settings-profiles-management), etc. and all their [grants](../../sql-reference/statements/grant.md#grant-privileges).
### Syntax {#show-access-syntax}
``` sql
SHOW ACCESS
```
## SHOW CLUSTER(s) {#show-cluster-statement}
Returns a list of clusters. All available clusters are listed in the [system.clusters](../../operations/system-tables/clusters.md) table.

View File

@ -5,7 +5,11 @@ toc_title: file
# file {#file}
Creates a table from a file. This table function is similar to [url](../../sql-reference/table-functions/url.md) and [hdfs](../../sql-reference/table-functions/hdfs.md) ones.
Creates a table from a file. This table function is similar to [url](../../sql-reference/table-functions/url.md) and [hdfs](../../sql-reference/table-functions/hdfs.md) ones.
`file` function can be used in `SELECT` and `INSERT` queries on data in [File](../../engines/table-engines/special/file.md) tables.
**Syntax**
``` sql
file(path, format, structure)
@ -13,15 +17,15 @@ file(path, format, structure)
**Input parameters**
- `path` — The relative path to the file from [user_files_path](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-user_files_path). Path to file support following globs in readonly mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, \``'abc', 'def'` — strings.
- `path` — The relative path to the file from [user_files_path](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-user_files_path). Path to file support following globs in readonly mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc', 'def'` — strings.
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
- `structure` — Structure of the table. Format: `'column1_name column1_type, column2_name column2_type, ...'`.
**Returned value**
A table with the specified structure for reading or writing data in the specified file.
**Example**
**Examples**
Setting `user_files_path` and the contents of the file `test.csv`:
@ -35,12 +39,29 @@ $ cat /var/lib/clickhouse/user_files/test.csv
78,43,45
```
Table from`test.csv` and selection of the first two rows from it:
Getting data from a table in `test.csv` and selecting first two rows from it:
``` sql
SELECT *
FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32')
LIMIT 2
SELECT * FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32') LIMIT 2;
```
``` text
┌─column1─┬─column2─┬─column3─┐
│ 1 │ 2 │ 3 │
│ 3 │ 2 │ 1 │
└─────────┴─────────┴─────────┘
```
Getting the first 10 lines of a table that contains 3 columns of UInt32 type from a CSV file:
``` sql
SELECT * FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32') LIMIT 10;
```
Inserting data from a file into a table:
``` sql
INSERT INTO FUNCTION file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32') VALUES (1, 2, 3), (3, 2, 1);
SELECT * FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32');
```
``` text
@ -50,12 +71,8 @@ LIMIT 2
└─────────┴─────────┴─────────┘
```
``` sql
-- getting the first 10 lines of a table that contains 3 columns of UInt32 type from a CSV file
SELECT * FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32') LIMIT 10
```
**Globs in path**
## Globs in Path {#globs-in-path}
Multiple path components can have globs. For being processed file should exists and matches to the whole path pattern (not only suffix or prefix).
@ -68,31 +85,25 @@ Constructions with `{}` are similar to the [remote table function](../../sql-ref
**Example**
1. Suppose we have several files with the following relative paths:
Suppose we have several files with the following relative paths:
- some_dir/some_file_1
- some_dir/some_file_2
- some_dir/some_file_3
- another_dir/some_file_1
- another_dir/some_file_2
- another_dir/some_file_3
- 'some_dir/some_file_1'
- 'some_dir/some_file_2'
- 'some_dir/some_file_3'
- 'another_dir/some_file_1'
- 'another_dir/some_file_2'
- 'another_dir/some_file_3'
1. Query the amount of rows in these files:
<!-- -->
Query the amount of rows in these files:
``` sql
SELECT count(*)
FROM file('{some,another}_dir/some_file_{1..3}', 'TSV', 'name String, value UInt32')
SELECT count(*) FROM file('{some,another}_dir/some_file_{1..3}', 'TSV', 'name String, value UInt32');
```
1. Query the amount of rows in all files of these two directories:
<!-- -->
Query the amount of rows in all files of these two directories:
``` sql
SELECT count(*)
FROM file('{some,another}_dir/*', 'TSV', 'name String, value UInt32')
SELECT count(*) FROM file('{some,another}_dir/*', 'TSV', 'name String, value UInt32');
```
!!! warning "Warning"
@ -103,8 +114,7 @@ FROM file('{some,another}_dir/*', 'TSV', 'name String, value UInt32')
Query the data from files named `file000`, `file001`, … , `file999`:
``` sql
SELECT count(*)
FROM file('big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name String, value UInt32')
SELECT count(*) FROM file('big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name String, value UInt32');
```
## Virtual Columns {#virtual-columns}
@ -116,4 +126,4 @@ FROM file('big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name String, value UInt32')
- [Virtual columns](https://clickhouse.tech/docs/en/operations/table_engines/#table_engines-virtual_columns)
[Original article](https://clickhouse.tech/docs/en/query_language/table_functions/file/) <!--hide-->
[Original article](https://clickhouse.tech/docs/en/sql-reference/table-functions/file/) <!--hide-->

View File

@ -5,9 +5,11 @@ toc_title: remote
# remote, remoteSecure {#remote-remotesecure}
Allows you to access remote servers without creating a `Distributed` table.
Allows to access remote servers without creating a [Distributed](../../engines/table-engines/special/distributed.md) table. `remoteSecure` - same as `remote` but with secured connection.
Signatures:
Both functions can be used in `SELECT` and `INSERT` queries.
**Syntax**
``` sql
remote('addresses_expr', db, table[, 'user'[, 'password'], sharding_key])
@ -16,13 +18,40 @@ remoteSecure('addresses_expr', db, table[, 'user'[, 'password'], sharding_key])
remoteSecure('addresses_expr', db.table[, 'user'[, 'password'], sharding_key])
```
`addresses_expr` An expression that generates addresses of remote servers. This may be just one server address. The server address is `host:port`, or just `host`. The host can be specified as the server name, or as the IPv4 or IPv6 address. An IPv6 address is specified in square brackets. The port is the TCP port on the remote server. If the port is omitted, it uses `tcp_port` from the servers config file (by default, 9000).
`sharding_key` - We can specify sharding key to support distributing data across nodes. For example: `insert into remote('127.0.0.1:9000,127.0.0.2', db, table, 'default', rand())`.
**Input parameters**
- `addresses_expr` An expression that generates addresses of remote servers. This may be just one server address. The server address is `host:port`, or just `host`.
The host can be specified as the server name, or as the IPv4 or IPv6 address. An IPv6 address is specified in square brackets.
The port is the TCP port on the remote server. If the port is omitted, it uses [tcp_port](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-tcp_port) from the servers config file in `remote` (by default, 9000) and [tcp_port_secure](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-tcp_port_secure) in `remoteSecure` (by default, 9440).
!!! important "Important"
The port is required for an IPv6 address.
Examples:
Type: [String](../../sql-reference/data-types/string.md).
- `db` - Database name. Type: [String](../../sql-reference/data-types/string.md).
- `table` - Table name. Type: [String](../../sql-reference/data-types/string.md).
- `user` - User name. If the user is not specified, `default` is used. Type: [String](../../sql-reference/data-types/string.md).
- `password` - User password. If the password is not specified, an empty password is used. Type: [String](../../sql-reference/data-types/string.md).
- `sharding_key` - Sharding key to support distributing data across nodes. For example: `insert into remote('127.0.0.1:9000,127.0.0.2', db, table, 'default', rand())`. Type: [UInt32](../../sql-reference/data-types/int-uint.md).
**Returned value**
Dataset from remote servers.
**Usage**
Using the `remote` table function is less optimal than creating a `Distributed` table, because in this case the server connection is re-established for every request. In addition, if host names are set, the names are resolved, and errors are not counted when working with various replicas. When processing a large number of queries, always create the `Distributed` table ahead of time, and dont use the `remote` table function.
The `remote` table function can be useful in the following cases:
- Accessing a specific server for data comparison, debugging, and testing.
- Queries between various ClickHouse clusters for research purposes.
- Infrequent distributed requests that are made manually.
- Distributed requests where the set of servers is re-defined each time.
**Adresses**
``` text
example01-01-1
@ -33,9 +62,7 @@ localhost
[2a02:6b8:0:1111::11]:9000
```
Multiple addresses can be comma-separated. In this case, ClickHouse will use distributed processing, so it will send the query to all specified addresses (like to shards with different data).
Example:
Multiple addresses can be comma-separated. In this case, ClickHouse will use distributed processing, so it will send the query to all specified addresses (like to shards with different data). Example:
``` text
example01-01-1,example01-02-1
@ -55,30 +82,28 @@ example01-{01..02}-1
If you have multiple pairs of curly brackets, it generates the direct product of the corresponding sets.
Addresses and parts of addresses in curly brackets can be separated by the pipe symbol (\|). In this case, the corresponding sets of addresses are interpreted as replicas, and the query will be sent to the first healthy replica. However, the replicas are iterated in the order currently set in the [load_balancing](../../operations/settings/settings.md) setting.
Example:
Addresses and parts of addresses in curly brackets can be separated by the pipe symbol (\|). In this case, the corresponding sets of addresses are interpreted as replicas, and the query will be sent to the first healthy replica. However, the replicas are iterated in the order currently set in the [load_balancing](../../operations/settings/settings.md) setting. This example specifies two shards that each have two replicas:
``` text
example01-{01..02}-{1|2}
```
This example specifies two shards that each have two replicas.
The number of addresses generated is limited by a constant. Right now this is 1000 addresses.
Using the `remote` table function is less optimal than creating a `Distributed` table, because in this case, the server connection is re-established for every request. In addition, if host names are set, the names are resolved, and errors are not counted when working with various replicas. When processing a large number of queries, always create the `Distributed` table ahead of time, and dont use the `remote` table function.
**Examples**
The `remote` table function can be useful in the following cases:
Selecting data from a remote server:
- Accessing a specific server for data comparison, debugging, and testing.
- Queries between various ClickHouse clusters for research purposes.
- Infrequent distributed requests that are made manually.
- Distributed requests where the set of servers is re-defined each time.
``` sql
SELECT * FROM remote('127.0.0.1', db.remote_engine_table) LIMIT 3;
```
If the user is not specified, `default` is used.
If the password is not specified, an empty password is used.
Inserting data from a remote server into a table:
`remoteSecure` - same as `remote` but with secured connection. Default port — [tcp_port_secure](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-tcp_port_secure) from config or 9440.
``` sql
CREATE TABLE remote_table (name String, value UInt32) ENGINE=Memory;
INSERT INTO FUNCTION remote('127.0.0.1', currentDatabase(), 'remote_table') VALUES ('test', 42);
SELECT * FROM remote_table;
```
[Original article](https://clickhouse.tech/docs/en/query_language/table_functions/remote/) <!--hide-->
[Original article](https://clickhouse.tech/docs/en/sql-reference/table-functions/remote/) <!--hide-->

View File

@ -5,20 +5,40 @@ toc_title: url
# url {#url}
`url(URL, format, structure)` - returns a table created from the `URL` with given
`format` and `structure`.
`url` function creates a table from the `URL` with given `format` and `structure`.
URL - HTTP or HTTPS server address, which can accept `GET` and/or `POST` requests.
`url` function may be used in `SELECT` and `INSERT` queries on data in [URL](../../engines/table-engines/special/url.md) tables.
format - [format](../../interfaces/formats.md#formats) of the data.
structure - table structure in `'UserID UInt64, Name String'` format. Determines column names and types.
**Example**
**Syntax**
``` sql
-- getting the first 3 lines of a table that contains columns of String and UInt32 type from HTTP-server which answers in CSV format.
SELECT * FROM url('http://127.0.0.1:12345/', CSV, 'column1 String, column2 UInt32') LIMIT 3
url(URL, format, structure)
```
[Original article](https://clickhouse.tech/docs/en/query_language/table_functions/url/) <!--hide-->
**Input parameters**
- `URL` - HTTP or HTTPS server address, which can accept `GET` (for `SELECT`) or `POST` (for `INSERT`) requests. Type: [String](../../sql-reference/data-types/string.md).
- `format` - [Format](../../interfaces/formats.md#formats) of the data. Type: [String](../../sql-reference/data-types/string.md).
- `structure` - Table structure in `'UserID UInt64, Name String'` format. Determines column names and types. Type: [String](../../sql-reference/data-types/string.md).
**Returned value**
A table with the specified format and structure and with data from the defined URL.
**Examples**
Getting the first 3 lines of a table that contains columns of `String` and `UInt32` type from HTTP-server which answers in `CSV` format.
``` sql
SELECT * FROM url('http://127.0.0.1:12345/', CSV, 'column1 String, column2 UInt32') LIMIT 3;
```
Inserting data from a URL into a table:
``` sql
CREATE TABLE test_table (column1 String, column2 UInt32) ENGINE=Memory;
INSERT INTO FUNCTION url('http://127.0.0.1:8123/?query=INSERT+INTO+test_table+FORMAT+CSV', 'CSV', 'column1 String, column2 UInt32') VALUES ('http interface', 42);
SELECT * FROM test_table;
```
[Original article](https://clickhouse.tech/docs/en/sql-reference/table-functions/url/) <!--hide-->

View File

@ -5,6 +5,6 @@ toc_title: Roadmap
# Roadmap {#roadmap}
The roadmap for year 2021 is published for open discussion [here](https://github.com/ClickHouse/ClickHouse/issues/17623).
The roadmap for the year 2021 is published for open discussion [here](https://github.com/ClickHouse/ClickHouse/issues/17623).
{## [Original article](https://clickhouse.tech/docs/en/roadmap/) ##}

View File

@ -0,0 +1,17 @@
---
toc_priority: 32
toc_title: Atomic
---
# Atomic {#atomic}
It is supports non-blocking `DROP` and `RENAME TABLE` queries and atomic `EXCHANGE TABLES t1 AND t2` queries. Atomic database engine is used by default.
## Creating a Database {#creating-a-database}
```sql
CREATE DATABASE test ENGINE = Atomic;
```
[Original article](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide-->

View File

@ -256,7 +256,6 @@ ENGINE = MergeTree()
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
``` sql
@ -452,7 +451,6 @@ ENGINE = CollapsingMergeTree(Sign)
PARTITION BY toYYYYMM(StartDate)
ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
Puede ejecutar esas consultas utilizando el modo interactivo de `clickhouse-client` (simplemente ejecútelo en un terminal sin especificar una consulta por adelantado) o pruebe algunos [interfaz alternativa](../interfaces/index.md) Si quieres.

View File

@ -0,0 +1,17 @@
---
toc_priority: 32
toc_title: Atomic
---
# Atomic {#atomic}
It is supports non-blocking `DROP` and `RENAME TABLE` queries and atomic `EXCHANGE TABLES t1 AND t2` queries. Atomic database engine is used by default.
## Creating a Database {#creating-a-database}
```sql
CREATE DATABASE test ENGINE = Atomic;
```
[Original article](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide-->

View File

@ -256,7 +256,6 @@ ENGINE = MergeTree()
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
``` sql
@ -452,7 +451,6 @@ ENGINE = CollapsingMergeTree(Sign)
PARTITION BY toYYYYMM(StartDate)
ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
Vous pouvez exécuter ces requêtes en utilisant le mode interactif de `clickhouse-client` (lancez - le simplement dans un terminal sans spécifier une requête à l'avance) ou essayez-en [interface de rechange](../interfaces/index.md) Si tu veux.

View File

@ -0,0 +1,17 @@
---
toc_priority: 32
toc_title: Atomic
---
# Atomic {#atomic}
It is supports non-blocking `DROP` and `RENAME TABLE` queries and atomic `EXCHANGE TABLES t1 AND t2` queries. Atomic database engine is used by default.
## Creating a Database {#creating-a-database}
```sql
CREATE DATABASE test ENGINE = Atomic;
```
[Original article](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide-->

View File

@ -262,7 +262,6 @@ ENGINE = MergeTree()
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
``` sql
@ -458,7 +457,6 @@ ENGINE = CollapsingMergeTree(Sign)
PARTITION BY toYYYYMM(StartDate)
ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
SAMPLE BY intHash32(UserID)
SETTINGS index_granularity = 8192
```
これらのクエリは、`clickhouse-client` の対話型モード(事前にクエリを指定せずにターミナルで起動するだけです)を使って実行するか、[代替インターフェイス](../interfaces/index.md) で実行できます。

View File

@ -210,7 +210,7 @@ Mac OS X:
Для запуска сервера из под текущего пользователя, с выводом логов в терминал и с использованием примеров конфигурационных файлов, расположенных в исходниках, перейдите в директорию `ClickHouse/programs/server/` (эта директория находится не в директории build) и выполните:
../../../build/programs/clickhouse server
../../build/programs/clickhouse server
В этом случае, ClickHouse будет использовать конфигурационные файлы, расположенные в текущей директории. Вы можете запустить `clickhouse server` из любой директории, передав ему путь к конфигурационному файлу в аргументе командной строки `--config-file`.

View File

@ -4,7 +4,6 @@ toc_priority: 27
toc_title: "\u0412\u0432\u0435\u0434\u0435\u043d\u0438\u0435"
---
# Движки баз данных {#dvizhki-baz-dannykh}
Движки баз данных обеспечивают работу с таблицами.
@ -13,4 +12,10 @@ toc_title: "\u0412\u0432\u0435\u0434\u0435\u043d\u0438\u0435"
Также можно использовать следующие движки баз данных:
- [MySQL](mysql.md)
- [MySQL](../../engines/database-engines/mysql.md)
- [MaterializeMySQL](../../engines/database-engines/materialize-mysql.md)
- [Lazy](../../engines/database-engines/lazy.md)
[Оригинальная статья](https://clickhouse.tech/docs/ru/database_engines/) <!--hide-->

View File

@ -0,0 +1,159 @@
---
toc_priority: 29
toc_title: MaterializeMySQL
---
# MaterializeMySQL {#materialize-mysql}
Создает базу данных ClickHouse со всеми таблицами, существующими в MySQL, и всеми данными в этих таблицах.
Сервер ClickHouse работает как реплика MySQL. Он читает файл binlog и выполняет DDL and DML-запросы.
`MaterializeMySQL` — экспериментальный движок баз данных.
## Создание базы данных {#creating-a-database}
``` sql
CREATE DATABASE [IF NOT EXISTS] db_name [ON CLUSTER cluster]
ENGINE = MaterializeMySQL('host:port', ['database' | database], 'user', 'password') [SETTINGS ...]
```
**Параметры движка**
- `host:port` — адрес сервера MySQL.
- `database` — имя базы данных на удалённом сервере.
- `user` — пользователь MySQL.
- `password` — пароль пользователя.
## Виртуальные столбцы {#virtual-columns}
При работе с движком баз данных `MaterializeMySQL` используются таблицы семейства [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) с виртуальными столбцами `_sign` и `_version`.
- `_version` — счетчик транзакций. Тип [UInt64](../../sql-reference/data-types/int-uint.md).
- `_sign` — метка удаления. Тип [Int8](../../sql-reference/data-types/int-uint.md). Возможные значения:
- `1` — строка не удалена,
- `-1` — строка удалена.
## Поддержка типов данных {#data_types-support}
| MySQL | ClickHouse |
|-------------------------|--------------------------------------------------------------|
| TINY | [Int8](../../sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](../../sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](../../sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](../../sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](../../sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](../../sql-reference/data-types/float.md) |
| DOUBLE | [Float64](../../sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](../../sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](../../sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](../../sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](../../sql-reference/data-types/datetime64.md) |
| STRING | [String](../../sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) |
| BLOB | [String](../../sql-reference/data-types/string.md) |
Другие типы не поддерживаются. Если таблица MySQL содержит столбец другого типа, ClickHouse выдаст исключение "Неподдерживаемый тип данных" ("Unhandled data type") и остановит репликацию.
Тип [Nullable](../../sql-reference/data-types/nullable.md) поддерживается.
## Особенности и рекомендации {#specifics-and-recommendations}
### DDL-запросы {#ddl-queries}
DDL-запросы в MySQL конвертируются в соответствующие DDL-запросы в ClickHouse ([ALTER](../../sql-reference/statements/alter/index.md), [CREATE](../../sql-reference/statements/create/index.md), [DROP](../../sql-reference/statements/drop.md), [RENAME](../../sql-reference/statements/rename.md)). Если ClickHouse не может конвертировать какой-либо DDL-запрос, он его игнорирует.
### Репликация данных {#data-replication}
Данные являются неизменяемыми со стороны пользователя ClickHouse, но автоматически обновляются путём репликации следующих запросов из MySQL:
- Запрос `INSERT` конвертируется в ClickHouse в `INSERT` с `_sign=1`.
- Запрос `DELETE` конвертируется в ClickHouse в `INSERT` с `_sign=-1`.
- Запрос `UPDATE` конвертируется в ClickHouse в `INSERT` с `_sign=-1` и `INSERT` с `_sign=1`.
### Выборка из таблиц движка MaterializeMySQL {#select}
Запрос `SELECT` из таблиц движка `MaterializeMySQL` имеет некоторую специфику:
- Если в запросе `SELECT` напрямую не указан столбец `_version`, то используется модификатор [FINAL](../../sql-reference/statements/select/from.md#select-from-final). Таким образом, выбираются только строки с `MAX(_version)`.
- Если в запросе `SELECT` напрямую не указан столбец `_sign`, то по умолчанию используется `WHERE _sign=1`. Таким образом, удаленные строки не включаются в результирующий набор.
### Конвертация индексов {#index-conversion}
Секции `PRIMARY KEY` и `INDEX` в MySQL конвертируются в кортежи `ORDER BY` в таблицах ClickHouse.
В таблицах ClickHouse данные физически хранятся в том порядке, который определяется секцией `ORDER BY`. Чтобы физически перегруппировать данные, используйте [материализованные представления](../../sql-reference/statements/create/view.md#materialized).
**Примечание**
- Строки с `_sign=-1` физически не удаляются из таблиц.
- Каскадные запросы `UPDATE/DELETE` не поддерживаются движком `MaterializeMySQL`.
- Репликация может быть легко нарушена.
- Прямые операции изменения данных в таблицах и базах данных `MaterializeMySQL` запрещены.
## Примеры использования {#examples-of-use}
Запросы в MySQL:
``` sql
mysql> CREATE DATABASE db;
mysql> CREATE TABLE db.test (a INT PRIMARY KEY, b INT);
mysql> INSERT INTO db.test VALUES (1, 11), (2, 22);
mysql> DELETE FROM db.test WHERE a=1;
mysql> ALTER TABLE db.test ADD COLUMN c VARCHAR(16);
mysql> UPDATE db.test SET c='Wow!', b=222;
mysql> SELECT * FROM test;
```
```text
+---+------+------+
| a | b | c |
+---+------+------+
| 2 | 222 | Wow! |
+---+------+------+
```
База данных в ClickHouse, обмен данными с сервером MySQL:
База данных и созданная таблица:
``` sql
CREATE DATABASE mysql ENGINE = MaterializeMySQL('localhost:3306', 'db', 'user', '***');
SHOW TABLES FROM mysql;
```
``` text
┌─name─┐
│ test │
└──────┘
```
После вставки данных:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬──b─┐
│ 1 │ 11 │
│ 2 │ 22 │
└───┴────┘
```
После удаления данных, добавления столбца и обновления:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬───b─┬─c────┐
│ 2 │ 222 │ Wow! │
└───┴─────┴──────┘
```
[Оригинальная статья](https://clickhouse.tech/docs/ru/database_engines/materialize-mysql/) <!--hide-->

View File

@ -51,6 +51,23 @@ ENGINE = MySQL('host:port', ['database' | database], 'user', 'password')
[Nullable](../../engines/database-engines/mysql.md) поддержан.
## Использование глобальных переменных {#global-variables-support}
Для лучшей совместимости к глобальным переменным можно обращаться в формате MySQL, как `@@identifier`.
Поддерживаются следующие переменные:
- `version`
- `max_allowed_packet`
!!! warning "Предупреждение"
В настоящее время эти переменные реализованы только как "заглушки" и не содержат актуальных данных.
Пример:
``` sql
SELECT @@version;
```
## Примеры использования {#primery-ispolzovaniia}
Таблица в MySQL:

View File

@ -0,0 +1,44 @@
---
toc_priority: 6
toc_title: EmbeddedRocksDB
---
# Движок EmbeddedRocksDB {#EmbeddedRocksDB-engine}
Этот движок позволяет интегрировать ClickHouse с [rocksdb](http://rocksdb.org/).
## Создание таблицы {#table_engine-EmbeddedRocksDB-creating-a-table}
``` sql
CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
(
name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1],
name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2],
...
) ENGINE = EmbeddedRocksDB
PRIMARY KEY(primary_key_name);
```
Обязательные параметры:
- `primary_key_name` может быть любое имя столбца из списка столбцов.
- Указание первичного ключа `primary key` является обязательным. Он будет сериализован в двоичном формате как ключ `rocksdb`.
- Поддерживается только один столбец в первичном ключе.
- Столбцы, которые отличаются от первичного ключа, будут сериализованы в двоичном формате как значение `rockdb` в соответствующем порядке.
- Запросы с фильтрацией по ключу `equals` или `in` оптимизируются для поиска по нескольким ключам из `rocksdb`.
Пример:
``` sql
CREATE TABLE test
(
`key` String,
`v1` UInt32,
`v2` String,
`v3` Float32,
)
ENGINE = EmbeddedRocksDB
PRIMARY KEY key;
```
[Оригинальная статья](https://clickhouse.tech/docs/ru/operations/table_engines/embedded-rocksdb/) <!--hide-->

View File

@ -37,7 +37,10 @@ ORDER BY expr
[PARTITION BY expr]
[PRIMARY KEY expr]
[SAMPLE BY expr]
[TTL expr [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'], ...]
[TTL expr
[DELETE|TO DISK 'xxx'|TO VOLUME 'xxx' [, ...] ]
[WHERE conditions]
[GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ] ]
[SETTINGS name=value, ...]
```
@ -71,7 +74,7 @@ ORDER BY expr
Выражение должно возвращать столбец `Date` или `DateTime`. Пример: `TTL date + INTERVAL 1 DAY`.
Тип правила `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'` указывает действие, которое будет выполнено с частью, удаление строк (прореживание), перемещение (при выполнении условия для всех строк части) на определённый диск (`TO DISK 'xxx'`) или том (`TO VOLUME 'xxx'`). Поведение по умолчанию соответствует удалению строк (`DELETE`). В списке правил может быть указано только одно выражение с поведением `DELETE`.
Тип правила `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'|GROUP BY` указывает действие, которое будет выполнено с частью: удаление строк (прореживание), перемещение (при выполнении условия для всех строк части) на определённый диск (`TO DISK 'xxx'`) или том (`TO VOLUME 'xxx'`), или агрегирование данных в устаревших строках. Поведение по умолчанию соответствует удалению строк (`DELETE`). В списке правил может быть указано только одно выражение с поведением `DELETE`.
Дополнительные сведения смотрите в разделе [TTL для столбцов и таблиц](#table_engine-mergetree-ttl)
@ -88,6 +91,7 @@ ORDER BY expr
- `merge_max_block_size` — максимальное количество строк в блоке для операций слияния. Значение по умолчанию: 8192.
- `storage_policy` — политика хранения данных. Смотрите [Хранение данных таблицы на нескольких блочных устройствах](#table_engine-mergetree-multiple-volumes).
- `min_bytes_for_wide_part`, `min_rows_for_wide_part` — минимальное количество байт/строк в куске данных для хранения в формате `Wide`. Можно задать одну или обе настройки или не задавать ни одной. Подробнее см. в разделе [Хранение данных](#mergetree-data-storage).
- `max_parts_in_total` — максимальное количество кусков во всех партициях.
- `max_compress_block_size` — максимальный размер блоков несжатых данных перед сжатием для записи в таблицу. Вы также можете задать этот параметр в глобальных настройках (смотрите [max_compress_block_size](../../../operations/settings/settings.md#max-compress-block-size)). Настройка, которая задается при создании таблицы, имеет более высокий приоритет, чем глобальная.
- `min_compress_block_size` — минимальный размер блоков несжатых данных, необходимых для сжатия при записи следующей засечки. Вы также можете задать этот параметр в глобальных настройках (смотрите [min_compress_block_size](../../../operations/settings/settings.md#min-compress-block-size)). Настройка, которая задается при создании таблицы, имеет более высокий приоритет, чем глобальная.
@ -442,16 +446,28 @@ ALTER TABLE example_table
Для таблицы можно задать одно выражение для устаревания данных, а также несколько выражений, по срабатывании которых данные переместятся на [некоторый диск или том](#table_engine-mergetree-multiple-volumes). Когда некоторые данные в таблице устаревают, ClickHouse удаляет все соответствующие строки.
``` sql
TTL expr [DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'], ...
TTL expr
[DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'][, DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'] ...
[WHERE conditions]
[GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ]
```
За каждым TTL выражением может следовать тип действия, которое выполняется после достижения времени, соответствующего результату TTL выражения:
- `DELETE` - удалить данные (действие по умолчанию);
- `TO DISK 'aaa'` - переместить данные на диск `aaa`;
- `TO VOLUME 'bbb'` - переместить данные на том `bbb`.
- `TO VOLUME 'bbb'` - переместить данные на том `bbb`;
- `GROUP BY` - агрегировать данные.
Примеры:
В секции `WHERE` можно задать условие удаления или агрегирования устаревших строк (для перемещения условие `WHERE` не применимо).
Колонки, по которым агрегируются данные в `GROUP BY`, должны являться префиксом первичного ключа таблицы.
Если колонка не является частью выражения `GROUP BY` и не задается напрямую в секции `SET`, в результирующих строках она будет содержать случайное значение, взятое из одной из сгруппированных строк (как будто к ней применяется агрегирующая функция `any`).
**Примеры**
Создание таблицы с TTL:
``` sql
CREATE TABLE example_table
@ -467,13 +483,43 @@ TTL d + INTERVAL 1 MONTH [DELETE],
d + INTERVAL 2 WEEK TO DISK 'bbb';
```
Изменение TTL
Изменение TTL:
``` sql
ALTER TABLE example_table
MODIFY TTL d + INTERVAL 1 DAY;
```
Создание таблицы, в которой строки устаревают через месяц. Устаревшие строки удаляются, если дата выпадает на понедельник:
``` sql
CREATE TABLE table_with_where
(
d DateTime,
a Int
)
ENGINE = MergeTree
PARTITION BY toYYYYMM(d)
ORDER BY d
TTL d + INTERVAL 1 MONTH DELETE WHERE toDayOfWeek(d) = 1;
```
Создание таблицы, где устаревшие строки агрегируются. В результирующих строках колонка `x` содержит максимальное значение по сгруппированным строкам, `y` — минимальное значение, а `d` — случайное значение из одной из сгуппированных строк.
``` sql
CREATE TABLE table_for_aggregation
(
d DateTime,
k1 Int,
k2 Int,
x Int,
y Int
)
ENGINE = MergeTree
ORDER BY k1, k2
TTL d + INTERVAL 1 MONTH GROUP BY k1, k2 SET x = max(x), y = min(y);
```
**Удаление данных**
Данные с истекшим TTL удаляются, когда ClickHouse мёржит куски данных.

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