thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-23 08:02:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:ClickHouse/ClickHouse into ADQM-623

Browse Source
This commit is contained in:
Roman Vasin 2022-11-11 07:35:44 +00:00
commit 35a1c406ad
338 changed files with 10180 additions and 1806 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/ISSUE_TEMPLATE/85_bug-report.md vendored
View File

@ -13,6 +13,8 @@ assignees: ''
> A clear and concise description of what works not as it is supposed to.
> A link to reproducer in [https://fiddle.clickhouse.com/](https://fiddle.clickhouse.com/).
**Does it reproduce on recent release?**
[The list of releases](https://github.com/ClickHouse/ClickHouse/blob/master/utils/list-versions/version_date.tsv)

2
.github/workflows/debug.yml vendored
View File

@ -2,7 +2,7 @@
name: Debug
'on':
[push, pull_request, release, workflow_dispatch]
[push, pull_request, release, workflow_dispatch, workflow_call]
jobs:
DebugInfo:

33
.github/workflows/jepsen.yml vendored
View File

@ -32,10 +32,41 @@ jobs:
mkdir -p "$TEMP_PATH"
cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
cd "$REPO_COPY/tests/ci"
python3 keeper_jepsen_check.py
python3 jepsen_check.py keeper
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
# ServerJepsenRelease:
# runs-on: [self-hosted, style-checker]
# if: ${{ always() }}
# needs: [KeeperJepsenRelease]
# steps:
# - name: Set envs
# run: |
# cat >> "$GITHUB_ENV" << 'EOF'
# TEMP_PATH=${{runner.temp}}/server_jepsen
# REPO_COPY=${{runner.temp}}/server_jepsen/ClickHouse
# EOF
# - name: Clear repository
# run: |
# sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
# - name: Check out repository code
# uses: actions/checkout@v2
# with:
# fetch-depth: 0
# - name: Jepsen Test
# run: |
# sudo rm -fr "$TEMP_PATH"
# mkdir -p "$TEMP_PATH"
# cp -r "$GITHUB_WORKSPACE" "$TEMP_PATH"
# cd "$REPO_COPY/tests/ci"
# python3 jepsen_check.py server
# - name: Cleanup
# if: always()
# run: |
# docker ps --quiet | xargs --no-run-if-empty docker kill ||:
# docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
# sudo rm -fr "$TEMP_PATH"

19
.github/workflows/master.yml vendored
View File

@ -1056,6 +1056,23 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
MarkReleaseReady:
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Mark Commit Release Ready
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
@ -3069,6 +3086,8 @@ jobs:
needs:
- DockerHubPush
- BuilderReport
- BuilderSpecialReport
- MarkReleaseReady
- FunctionalStatelessTestDebug0
- FunctionalStatelessTestDebug1
- FunctionalStatelessTestDebug2

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

@ -10,6 +10,9 @@ env:
workflow_dispatch:
jobs:
Debug:
# The task for having a preserved ENV and event.json for later investigation
uses: ./.github/workflows/debug.yml
DockerHubPushAarch64:
runs-on: [self-hosted, style-checker-aarch64]
steps:

1
.github/workflows/pull_request.yml vendored
View File

@ -3579,6 +3579,7 @@ jobs:
- DockerServerImages
- CheckLabels
- BuilderReport
- BuilderSpecialReport
- FastTest
- FunctionalStatelessTestDebug0
- FunctionalStatelessTestDebug1

18
.github/workflows/release_branches.yml vendored
View File

@ -615,6 +615,23 @@ jobs:
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"
MarkReleaseReady:
needs:
- BuilderBinDarwin
- BuilderBinDarwinAarch64
- BuilderDebRelease
- BuilderDebAarch64
runs-on: [self-hosted, style-checker]
steps:
- name: Clear repository
run: |
sudo rm -fr "$GITHUB_WORKSPACE" && mkdir "$GITHUB_WORKSPACE"
- name: Check out repository code
uses: actions/checkout@v2
- name: Mark Commit Release Ready
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 mark_release_ready.py
##############################################################################################
########################### FUNCTIONAl STATELESS TESTS #######################################
##############################################################################################
@ -1888,6 +1905,7 @@ jobs:
- DockerServerImages
- BuilderReport
- BuilderSpecialReport
- MarkReleaseReady
- FunctionalStatelessTestDebug0
- FunctionalStatelessTestDebug1
- FunctionalStatelessTestDebug2

4
CMakeLists.txt
View File

@ -202,7 +202,7 @@ option(ADD_GDB_INDEX_FOR_GOLD "Add .gdb-index to resulting binaries for gold lin
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# Can be lld or ld-lld or lld-13 or /path/to/lld.
if (LINKER_NAME MATCHES "lld")
if (LINKER_NAME MATCHES "lld" AND OS_LINUX)
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--gdb-index")
set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,--gdb-index")
message (STATUS "Adding .gdb-index via --gdb-index linker option.")
@ -248,7 +248,7 @@ endif ()
# Create BuildID when using lld. For other linkers it is created by default.
# (NOTE: LINKER_NAME can be either path or name, and in different variants)
if (LINKER_NAME MATCHES "lld")
if (LINKER_NAME MATCHES "lld" AND OS_LINUX)
# SHA1 is not cryptographically secure but it is the best what lld is offering.
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--build-id=sha1")
endif ()

2
base/base/safeExit.cpp
View File

@ -1,8 +1,10 @@
#if defined(OS_LINUX)
# include <sys/syscall.h>
#endif
#include <cstdlib>
#include <unistd.h>
#include <base/safeExit.h>
#include <base/defines.h> /// for THREAD_SANITIZER
[[noreturn]] void safeExit(int code)
{

17
base/glibc-compatibility/musl/getauxval.c
View File

@ -8,6 +8,14 @@
#include <link.h> // ElfW
#include <errno.h>
#include "syscall.h"
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#include <sanitizer/msan_interface.h>
#endif
#endif
#define ARRAY_SIZE(a) sizeof((a))/sizeof((a[0]))
/// Suppress TSan since it is possible for this code to be called from multiple threads,
@ -39,7 +47,9 @@ ssize_t __retry_read(int fd, void * buf, size_t count)
{
for (;;)
{
ssize_t ret = read(fd, buf, count);
// We cannot use the read syscall as it will be intercept by sanitizers, which aren't
// initialized yet. Emit syscall directly.
ssize_t ret = __syscall_ret(__syscall(SYS_read, fd, buf, count));
if (ret == -1)
{
if (errno == EINTR)
@ -90,6 +100,11 @@ static unsigned long NO_SANITIZE_THREAD __auxv_init_procfs(unsigned long type)
_Static_assert(sizeof(aux) < 4096, "Unexpected sizeof(aux)");
while (__retry_read(fd, &aux, sizeof(aux)) == sizeof(aux))
{
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
__msan_unpoison(&aux, sizeof(aux));
#endif
#endif
if (aux.a_type == AT_NULL)
{
break;

12
cmake/tools.cmake
View File

@ -58,13 +58,19 @@ if (NOT LINKER_NAME)
find_program (LLD_PATH NAMES "ld.lld")
find_program (GOLD_PATH NAMES "ld.gold")
elseif (COMPILER_CLANG)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "lld-${COMPILER_VERSION_MAJOR}" "ld.lld" "lld")
# llvm lld is a generic driver.
# Invoke ld.lld (Unix), ld64.lld (macOS), lld-link (Windows), wasm-ld (WebAssembly) instead
if (OS_LINUX)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
elseif (OS_DARWIN)
find_program (LLD_PATH NAMES "ld64.lld-${COMPILER_VERSION_MAJOR}" "ld64.lld")
endif ()
find_program (GOLD_PATH NAMES "ld.gold" "gold")
endif ()
endif()
if (OS_LINUX AND NOT LINKER_NAME)
# prefer lld linker over gold or ld on linux
if ((OS_LINUX OR OS_DARWIN) AND NOT LINKER_NAME)
# prefer lld linker over gold or ld on linux and macos
if (LLD_PATH)
if (COMPILER_GCC)
# GCC driver requires one of supported linker names like "lld".

7
docker/test/fuzzer/run-fuzzer.sh
View File

@ -178,7 +178,7 @@ function fuzz
# interferes with gdb
export CLICKHOUSE_WATCHDOG_ENABLE=0
# NOTE: we use process substitution here to preserve keep $! as a pid of clickhouse-server
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db > >(tail -100000 > server.log) 2>&1 &
clickhouse-server --config-file db/config.xml --pid-file /var/run/clickhouse-server/clickhouse-server.pid -- --path db 2>&1 | pigz > server.log.gz &
server_pid=$!
kill -0 $server_pid
@ -297,7 +297,7 @@ quit
# The server has died.
task_exit_code=210
echo "failure" > status.txt
if ! grep --text -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: AddressSanitizer:.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*\|.*_LIBCPP_ASSERT.*" server.log > description.txt
if ! zgrep --text -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: AddressSanitizer:.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*\|.*_LIBCPP_ASSERT.*" server.log.gz > description.txt
then
echo "Lost connection to server. See the logs." > description.txt
fi
@ -391,8 +391,9 @@ th { cursor: pointer; }
<h1>AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST}</h1>
<p class="links">
<a href="runlog.log">runlog.log</a>
<a href="fuzzer.log">fuzzer.log</a>
<a href="server.log">server.log</a>
<a href="server.log.gz">server.log.gz</a>
<a href="main.log">main.log</a>
${CORE_LINK}
</p>

4
docker/test/keeper-jepsen/run.sh
View File

@ -15,8 +15,8 @@ if [ -z "$CLICKHOUSE_REPO_PATH" ]; then
ls -lath ||:
fi
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse-keeper"
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse"
(lein run test-all --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --snapshot-distance 100 --stale-log-gap 100 --reserved-log-items 10 --lightweight-run --clickhouse-source "$CLICKHOUSE_PACKAGE" -q --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
(lein run keeper test-all --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --snapshot-distance 100 --stale-log-gap 100 --reserved-log-items 10 --lightweight-run --clickhouse-source "$CLICKHOUSE_PACKAGE" -q --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
mv store "$TEST_OUTPUT/"

43
docker/test/server-jepsen/Dockerfile Normal file
View File

@ -0,0 +1,43 @@
# rebuild in #33610
# docker build -t clickhouse/server-jepsen-test .
ARG FROM_TAG=latest
FROM clickhouse/test-base:$FROM_TAG
ENV DEBIAN_FRONTEND=noninteractive
ENV CLOJURE_VERSION=1.10.3.814
# arguments
ENV PR_TO_TEST=""
ENV SHA_TO_TEST=""
ENV NODES_USERNAME="root"
ENV NODES_PASSWORD=""
ENV TESTS_TO_RUN="8"
ENV TIME_LIMIT="30"
ENV KEEPER_NODE=""
# volumes
ENV NODES_FILE_PATH="/nodes.txt"
ENV TEST_OUTPUT="/test_output"
RUN mkdir "/root/.ssh"
RUN touch "/root/.ssh/known_hosts"
# install java
RUN apt-get update && apt-get install default-jre default-jdk libjna-java libjna-jni ssh gnuplot graphviz --yes --no-install-recommends
# install clojure
RUN curl -O "https://download.clojure.org/install/linux-install-${CLOJURE_VERSION}.sh" && \
chmod +x "linux-install-${CLOJURE_VERSION}.sh" && \
bash "./linux-install-${CLOJURE_VERSION}.sh"
# install leiningen
RUN curl -O "https://raw.githubusercontent.com/technomancy/leiningen/stable/bin/lein" && \
chmod +x ./lein && \
mv ./lein /usr/bin
COPY run.sh /
CMD ["/bin/bash", "/run.sh"]

22
docker/test/server-jepsen/run.sh Normal file
View File

@ -0,0 +1,22 @@
#!/usr/bin/env bash
set -euo pipefail
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-15_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}
if [ -z "$CLICKHOUSE_REPO_PATH" ]; then
CLICKHOUSE_REPO_PATH=ch
rm -rf ch ||:
mkdir ch ||:
wget -nv -nd -c "https://clickhouse-test-reports.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/repo/clickhouse_no_subs.tar.gz"
tar -C ch --strip-components=1 -xf clickhouse_no_subs.tar.gz
ls -lath ||:
fi
cd "$CLICKHOUSE_REPO_PATH/tests/jepsen.clickhouse"
(lein run server test-all --keeper "$KEEPER_NODE" --nodes-file "$NODES_FILE_PATH" --username "$NODES_USERNAME" --logging-json --password "$NODES_PASSWORD" --time-limit "$TIME_LIMIT" --concurrency 50 -r 50 --clickhouse-source "$CLICKHOUSE_PACKAGE" --test-count "$TESTS_TO_RUN" || true) | tee "$TEST_OUTPUT/jepsen_run_all_tests.log"
mv store "$TEST_OUTPUT/"

1
docker/test/stress/run.sh
View File

@ -481,6 +481,7 @@ else
-e "The set of parts restored in place of" \
-e "(ReplicatedMergeTreeAttachThread): Initialization failed. Error" \
-e "Code: 269. DB::Exception: Destination table is myself" \
-e "Coordination::Exception: Connection loss" \
/var/log/clickhouse-server/clickhouse-server.backward.clean.log | zgrep -Fa "<Error>" > /test_output/bc_check_error_messages.txt \
&& echo -e 'Backward compatibility check: Error message in clickhouse-server.log (see bc_check_error_messages.txt)\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'Backward compatibility check: No Error messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv

4
docker/test/style/Dockerfile
View File

@ -1,7 +1,7 @@
# docker build -t clickhouse/style-test .
FROM ubuntu:20.04
ARG ACT_VERSION=0.2.25
ARG ACTIONLINT_VERSION=1.6.8
ARG ACT_VERSION=0.2.33
ARG ACTIONLINT_VERSION=1.6.22
# ARG for quick switch to a given ubuntu mirror
ARG apt_archive="http://archive.ubuntu.com"

78
docs/en/engines/database-engines/materialized-mysql.md
View File

@ -77,15 +77,15 @@ While turning on `gtid_mode` you should also specify `enforce_gtid_consistency =
## Virtual Columns {#virtual-columns}
When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
### \_version
`_version` — Transaction counter. Type [UInt64](../../sql-reference/data-types/int-uint.md).
`_version` — Transaction counter. Type [UInt64](/docs/en/sql-reference/data-types/int-uint.md).
### \_sign
`_sign` — Deletion mark. Type [Int8](../../sql-reference/data-types/int-uint.md). Possible values:
`_sign` — Deletion mark. Type [Int8](/docs/en/sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `-1` — Row is deleted.
@ -93,29 +93,29 @@ When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](
| 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) |
| YEAR | [UInt16](../../sql-reference/data-types/int-uint.md) |
| TIME | [Int64](../../sql-reference/data-types/int-uint.md) |
| ENUM | [Enum](../../sql-reference/data-types/enum.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) |
| GEOMETRY | [String](../../sql-reference/data-types/string.md) |
| BINARY | [FixedString](../../sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](../../sql-reference/data-types/int-uint.md) |
| SET | [UInt64](../../sql-reference/data-types/int-uint.md) |
| TINY | [Int8](/docs/en/sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](/docs/en/sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](/docs/en/sql-reference/data-types/float.md) |
| DOUBLE | [Float64](/docs/en/sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](/docs/en/sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](/docs/en/sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](/docs/en/sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| YEAR | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) |
| TIME | [Int64](/docs/en/sql-reference/data-types/int-uint.md) |
| ENUM | [Enum](/docs/en/sql-reference/data-types/enum.md) |
| STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| BLOB | [String](/docs/en/sql-reference/data-types/string.md) |
| GEOMETRY | [String](/docs/en/sql-reference/data-types/string.md) |
| BINARY | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| SET | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
[Nullable](../../sql-reference/data-types/nullable.md) is supported.
[Nullable](/docs/en/sql-reference/data-types/nullable.md) is supported.
The data of TIME type in MySQL is converted to microseconds in ClickHouse.
@ -133,7 +133,7 @@ Apart of the data types limitations there are few restrictions comparing to `MyS
### DDL Queries {#ddl-queries}
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), [RENAME](../../sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([ALTER](/docs/en/sql-reference/statements/alter/index.md), [CREATE](/docs/en/sql-reference/statements/create/index.md), [DROP](/docs/en/sql-reference/statements/drop.md), [RENAME](/docs/en/sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
### Data Replication {#data-replication}
@ -151,7 +151,7 @@ MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([
`SELECT` query from `MaterializedMySQL` tables has some specifics:
- If `_version` is not specified in the `SELECT` query, the
[FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier is used, so only rows with
[FINAL](/docs/en/sql-reference/statements/select/from.md/#select-from-final) modifier is used, so only rows with
`MAX(_version)` are returned for each primary key value.
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not
@ -164,7 +164,7 @@ MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([
MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in ClickHouse tables.
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).
[materialized views](/docs/en/sql-reference/statements/create/view.md/#materialized).
**Notes**
@ -173,7 +173,7 @@ ClickHouse has only one physical order, which is determined by `ORDER BY` clause
MySQL binlog.
- Replication can be easily broken.
- Manual operations on database and tables are forbidden.
- `MaterializedMySQL` is affected by the [optimize_on_insert](../../operations/settings/settings.md#optimize-on-insert)
- `MaterializedMySQL` is affected by the [optimize_on_insert](/docs/en/operations/settings/settings.md/#optimize-on-insert)
setting. Data is merged in the corresponding table in the `MaterializedMySQL` database when a table in the MySQL
server changes.
@ -187,19 +187,19 @@ These are the schema conversion manipulations you can do with table overrides fo
* Modify column type. Must be compatible with the original type, or replication will fail. For example,
you can modify a UInt32 column to UInt64, but you can not modify a String column to Array(String).
* Modify [column TTL](../table-engines/mergetree-family/mergetree/#mergetree-column-ttl).
* Modify [column compression codec](../../sql-reference/statements/create/table/#codecs).
* Add [ALIAS columns](../../sql-reference/statements/create/table/#alias).
* Add [skipping indexes](../table-engines/mergetree-family/mergetree/#table_engine-mergetree-data_skipping-indexes)
* Add [projections](../table-engines/mergetree-family/mergetree/#projections). Note that projection optimizations are
* Modify [column TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-column-ttl).
* Modify [column compression codec](/docs/en/sql-reference/statements/create/table.md/#codecs).
* Add [ALIAS columns](/docs/en/sql-reference/statements/create/table.md/#alias).
* Add [skipping indexes](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-data_skipping-indexes)
* Add [projections](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#projections). Note that projection optimizations are
disabled when using `SELECT ... FINAL` (which MaterializedMySQL does by default), so their utility is limited here.
`INDEX ... TYPE hypothesis` as [described in the v21.12 blog post]](https://clickhouse.com/blog/en/2021/clickhouse-v21.12-released/)
may be more useful in this case.
* Modify [PARTITION BY](../table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Modify [PRIMARY KEY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [SAMPLE BY](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Add [table TTL](../table-engines/mergetree-family/mergetree/#mergetree-query-clauses)
* Modify [PARTITION BY](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Modify [PRIMARY KEY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [SAMPLE BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [table TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
```sql
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)

2
docs/en/engines/database-engines/replicated.md
View File

@ -86,7 +86,7 @@ node1 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY
``` text
┌─hosts─┬─groupArray(n)─┐
│ node1 │ [1,3,5,7,9] │
│ node3 │ [1,3,5,7,9] │
│ node2 │ [0,2,4,6,8] │
└───────┴───────────────┘
```

10
docs/en/engines/table-engines/log-family/index.md
View File

@ -10,11 +10,11 @@ These engines were developed for scenarios when you need to quickly write many s
Engines of the family:
- [StripeLog](../../../engines/table-engines/log-family/stripelog.md)
- [Log](../../../engines/table-engines/log-family/log.md)
- [TinyLog](../../../engines/table-engines/log-family/tinylog.md)
- [StripeLog](/docs/en/engines/table-engines/log-family/stripelog.md)
- [Log](/docs/en/engines/table-engines/log-family/log.md)
- [TinyLog](/docs/en/engines/table-engines/log-family/tinylog.md)
`Log` family table engines can store data to [HDFS](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-hdfs) or [S3](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-s3) distributed file systems.
`Log` family table engines can store data to [HDFS](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-hdfs) or [S3](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3) distributed file systems.
## Common Properties {#common-properties}
@ -28,7 +28,7 @@ Engines:
During `INSERT` queries, the table is locked, and other queries for reading and writing data both wait for the table to unlock. If there are no data writing queries, any number of data reading queries can be performed concurrently.
- Do not support [mutations](../../../sql-reference/statements/alter/index.md#alter-mutations).
- Do not support [mutations](/docs/en/sql-reference/statements/alter/index.md/#alter-mutations).
- Do not support indexes.

114
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -16,20 +16,20 @@ Main features:
This allows you to create a small sparse index that helps find data faster.
- Partitions can be used if the [partitioning key](../../../engines/table-engines/mergetree-family/custom-partitioning-key.md) is specified.
- Partitions can be used if the [partitioning key](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md) is specified.
ClickHouse supports certain operations with partitions that are more efficient than general operations on the same data with the same result. ClickHouse also automatically cuts off the partition data where the partitioning key is specified in the query.
- Data replication support.
The family of `ReplicatedMergeTree` tables provides data replication. For more information, see [Data replication](../../../engines/table-engines/mergetree-family/replication.md).
The family of `ReplicatedMergeTree` tables provides data replication. For more information, see [Data replication](/docs/en/engines/table-engines/mergetree-family/replication.md).
- Data sampling support.
If necessary, you can set the data sampling method in the table.
:::info
The [Merge](../../../engines/table-engines/special/merge.md#merge) engine does not belong to the `*MergeTree` family.
The [Merge](/docs/en/engines/table-engines/special/merge.md/#merge) engine does not belong to the `*MergeTree` family.
:::
## Creating a Table {#table_engine-mergetree-creating-a-table}
@ -57,7 +57,7 @@ ORDER BY expr
[SETTINGS name=value, ...]
```
For a description of parameters, see the [CREATE query description](../../../sql-reference/statements/create/table.md).
For a description of parameters, see the [CREATE query description](/docs/en/sql-reference/statements/create/table.md).
### Query Clauses {#mergetree-query-clauses}
@ -77,9 +77,9 @@ Use the `ORDER BY tuple()` syntax, if you do not need sorting. See [Selecting th
#### PARTITION BY
`PARTITION BY` — The [partitioning key](../../../engines/table-engines/mergetree-family/custom-partitioning-key.md). Optional. In most cases you don't need partition key, and in most other cases you don't need partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression). You should never use too granular partitioning. Don't partition your data by client identifiers or names (instead make client identifier or name the first column in the ORDER BY expression).
`PARTITION BY` — The [partitioning key](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md). Optional. In most cases you don't need partition key, and in most other cases you don't need partition key more granular than by months. Partitioning does not speed up queries (in contrast to the ORDER BY expression). You should never use too granular partitioning. Don't partition your data by client identifiers or names (instead make client identifier or name the first column in the ORDER BY expression).
For partitioning by month, use the `toYYYYMM(date_column)` expression, where `date_column` is a column with a date of the type [Date](../../../sql-reference/data-types/date.md). The partition names here have the `"YYYYMM"` format.
For partitioning by month, use the `toYYYYMM(date_column)` expression, where `date_column` is a column with a date of the type [Date](/docs/en/sql-reference/data-types/date.md). The partition names here have the `"YYYYMM"` format.
#### PRIMARY KEY
@ -127,7 +127,7 @@ Additional parameters that control the behavior of the `MergeTree` (optional):
#### use_minimalistic_part_header_in_zookeeper
`use_minimalistic_part_header_in_zookeeper` — Storage method of the data parts headers in ZooKeeper. If `use_minimalistic_part_header_in_zookeeper=1`, then ZooKeeper stores less data. For more information, see the [setting description](../../../operations/server-configuration-parameters/settings.md#server-settings-use_minimalistic_part_header_in_zookeeper) in “Server configuration parameters”.
`use_minimalistic_part_header_in_zookeeper` — Storage method of the data parts headers in ZooKeeper. If `use_minimalistic_part_header_in_zookeeper=1`, then ZooKeeper stores less data. For more information, see the [setting description](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings-use_minimalistic_part_header_in_zookeeper) in “Server configuration parameters”.
#### min_merge_bytes_to_use_direct_io
@ -166,15 +166,15 @@ Additional parameters that control the behavior of the `MergeTree` (optional):
#### max_compress_block_size
`max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](../../../operations/settings/settings.md#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
`max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](/docs/en/operations/settings/settings.md/#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
#### min_compress_block_size
`min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](../../../operations/settings/settings.md#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
`min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](/docs/en/operations/settings/settings.md/#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
#### max_partitions_to_read
`max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](../../../operations/settings/merge-tree-settings.md#max-partitions-to-read) in the global setting.
`max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](/docs/en/operations/settings/merge-tree-settings.md/#max-partitions-to-read) in the global setting.
**Example of Sections Setting**
@ -184,7 +184,7 @@ ENGINE MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDa
In the example, we set partitioning by month.
We also set an expression for sampling as a hash by the user ID. This allows you to pseudorandomize the data in the table for each `CounterID` and `EventDate`. If you define a [SAMPLE](../../../sql-reference/statements/select/sample.md#select-sample-clause) clause when selecting the data, ClickHouse will return an evenly pseudorandom data sample for a subset of users.
We also set an expression for sampling as a hash by the user ID. This allows you to pseudorandomize the data in the table for each `CounterID` and `EventDate`. If you define a [SAMPLE](/docs/en/sql-reference/statements/select/sample.md/#select-sample-clause) clause when selecting the data, ClickHouse will return an evenly pseudorandom data sample for a subset of users.
The `index_granularity` setting can be omitted because 8192 is the default value.
@ -207,9 +207,9 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
**MergeTree() Parameters**
- `date-column` — The name of a column of the [Date](../../../sql-reference/data-types/date.md) type. ClickHouse automatically creates partitions by month based on this column. The partition names are in the `"YYYYMM"` format.
- `date-column` — The name of a column of the [Date](/docs/en/sql-reference/data-types/date.md) type. ClickHouse automatically creates partitions by month based on this column. The partition names are in the `"YYYYMM"` format.
- `sampling_expression` — An expression for sampling.
- `(primary, key)` — Primary key. Type: [Tuple()](../../../sql-reference/data-types/tuple.md)
- `(primary, key)` — Primary key. Type: [Tuple()](/docs/en/sql-reference/data-types/tuple.md)
- `index_granularity` — The granularity of an index. The number of data rows between the “marks” of an index. The value 8192 is appropriate for most tasks.
**Example**
@ -262,7 +262,7 @@ Sparse indexes allow you to work with a very large number of table rows, because
ClickHouse does not require a unique primary key. You can insert multiple rows with the same primary key.
You can use `Nullable`-typed expressions in the `PRIMARY KEY` and `ORDER BY` clauses but it is strongly discouraged. To allow this feature, turn on the [allow_nullable_key](../../../operations/settings/settings.md#allow-nullable-key) setting. The [NULLS_LAST](../../../sql-reference/statements/select/order-by.md#sorting-of-special-values) principle applies for `NULL` values in the `ORDER BY` clause.
You can use `Nullable`-typed expressions in the `PRIMARY KEY` and `ORDER BY` clauses but it is strongly discouraged. To allow this feature, turn on the [allow_nullable_key](/docs/en/operations/settings/settings.md/#allow-nullable-key) setting. The [NULLS_LAST](/docs/en/sql-reference/statements/select/order-by.md/#sorting-of-special-values) principle applies for `NULL` values in the `ORDER BY` clause.
### Selecting the Primary Key {#selecting-the-primary-key}
@ -279,26 +279,26 @@ The number of columns in the primary key is not explicitly limited. Depending on
ClickHouse sorts data by primary key, so the higher the consistency, the better the compression.
- Provide additional logic when merging data parts in the [CollapsingMergeTree](../../../engines/table-engines/mergetree-family/collapsingmergetree.md#table_engine-collapsingmergetree) and [SummingMergeTree](../../../engines/table-engines/mergetree-family/summingmergetree.md) engines.
- Provide additional logic when merging data parts in the [CollapsingMergeTree](/docs/en/engines/table-engines/mergetree-family/collapsingmergetree.md/#table_engine-collapsingmergetree) and [SummingMergeTree](/docs/en/engines/table-engines/mergetree-family/summingmergetree.md) engines.
In this case it makes sense to specify the *sorting key* that is different from the primary key.
A long primary key will negatively affect the insert performance and memory consumption, but extra columns in the primary key do not affect ClickHouse performance during `SELECT` queries.
You can create a table without a primary key using the `ORDER BY tuple()` syntax. In this case, ClickHouse stores data in the order of inserting. If you want to save data order when inserting data by `INSERT ... SELECT` queries, set [max_insert_threads = 1](../../../operations/settings/settings.md#settings-max-insert-threads).
You can create a table without a primary key using the `ORDER BY tuple()` syntax. In this case, ClickHouse stores data in the order of inserting. If you want to save data order when inserting data by `INSERT ... SELECT` queries, set [max_insert_threads = 1](/docs/en/operations/settings/settings.md/#settings-max-insert-threads).
To select data in the initial order, use [single-threaded](../../../operations/settings/settings.md#settings-max_threads) `SELECT` queries.
To select data in the initial order, use [single-threaded](/docs/en/operations/settings/settings.md/#settings-max_threads) `SELECT` queries.
### Choosing a Primary Key that Differs from the Sorting Key {#choosing-a-primary-key-that-differs-from-the-sorting-key}
It is possible to specify a primary key (an expression with values that are written in the index file for each mark) that is different from the sorting key (an expression for sorting the rows in data parts). In this case the primary key expression tuple must be a prefix of the sorting key expression tuple.
This feature is helpful when using the [SummingMergeTree](../../../engines/table-engines/mergetree-family/summingmergetree.md) and
[AggregatingMergeTree](../../../engines/table-engines/mergetree-family/aggregatingmergetree.md) table engines. In a common case when using these engines, the table has two types of columns: *dimensions* and *measures*. Typical queries aggregate values of measure columns with arbitrary `GROUP BY` and filtering by dimensions. Because SummingMergeTree and AggregatingMergeTree aggregate rows with the same value of the sorting key, it is natural to add all dimensions to it. As a result, the key expression consists of a long list of columns and this list must be frequently updated with newly added dimensions.
This feature is helpful when using the [SummingMergeTree](/docs/en/engines/table-engines/mergetree-family/summingmergetree.md) and
[AggregatingMergeTree](/docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md) table engines. In a common case when using these engines, the table has two types of columns: *dimensions* and *measures*. Typical queries aggregate values of measure columns with arbitrary `GROUP BY` and filtering by dimensions. Because SummingMergeTree and AggregatingMergeTree aggregate rows with the same value of the sorting key, it is natural to add all dimensions to it. As a result, the key expression consists of a long list of columns and this list must be frequently updated with newly added dimensions.
In this case it makes sense to leave only a few columns in the primary key that will provide efficient range scans and add the remaining dimension columns to the sorting key tuple.
[ALTER](../../../sql-reference/statements/alter/index.md) of the sorting key is a lightweight operation because when a new column is simultaneously added to the table and to the sorting key, existing data parts do not need to be changed. Since the old sorting key is a prefix of the new sorting key and there is no data in the newly added column, the data is sorted by both the old and new sorting keys at the moment of table modification.
[ALTER](/docs/en/sql-reference/statements/alter/index.md) of the sorting key is a lightweight operation because when a new column is simultaneously added to the table and to the sorting key, existing data parts do not need to be changed. Since the old sorting key is a prefix of the new sorting key and there is no data in the newly added column, the data is sorted by both the old and new sorting keys at the moment of table modification.
### Use of Indexes and Partitions in Queries {#use-of-indexes-and-partitions-in-queries}
@ -342,7 +342,7 @@ In the example below, the index can’t be used.
SELECT count() FROM table WHERE CounterID = 34 OR URL LIKE '%upyachka%'
```
To check whether ClickHouse can use the index when running a query, use the settings [force_index_by_date](../../../operations/settings/settings.md#settings-force_index_by_date) and [force_primary_key](../../../operations/settings/settings.md#force-primary-key).
To check whether ClickHouse can use the index when running a query, use the settings [force_index_by_date](/docs/en/operations/settings/settings.md/#settings-force_index_by_date) and [force_primary_key](/docs/en/operations/settings/settings.md/#force-primary-key).
The key for partitioning by month allows reading only those data blocks which contain dates from the proper range. In this case, the data block may contain data for many dates (up to an entire month). Within a block, data is sorted by primary key, which might not contain the date as the first column. Because of this, using a query with only a date condition that does not specify the primary key prefix will cause more data to be read than for a single date.
@ -400,7 +400,7 @@ Stores unique values of the specified expression (no more than `max_rows` rows,
#### `ngrambf_v1(n, size_of_bloom_filter_in_bytes, number_of_hash_functions, random_seed)`
Stores a [Bloom filter](https://en.wikipedia.org/wiki/Bloom_filter) that contains all ngrams from a block of data. Works only with datatypes: [String](../../../sql-reference/data-types/string.md), [FixedString](../../../sql-reference/data-types/fixedstring.md) and [Map](../../../sql-reference/data-types/map.md). Can be used for optimization of `EQUALS`, `LIKE` and `IN` expressions.
Stores a [Bloom filter](https://en.wikipedia.org/wiki/Bloom_filter) that contains all ngrams from a block of data. Works only with datatypes: [String](/docs/en/sql-reference/data-types/string.md), [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) and [Map](/docs/en/sql-reference/data-types/map.md). Can be used for optimization of `EQUALS`, `LIKE` and `IN` expressions.
- `n` — ngram size,
- `size_of_bloom_filter_in_bytes` — Bloom filter size in bytes (you can use large values here, for example, 256 or 512, because it can be compressed well).
@ -417,11 +417,11 @@ The optional `false_positive` parameter is the probability of receiving a false
Supported data types: `Int*`, `UInt*`, `Float*`, `Enum`, `Date`, `DateTime`, `String`, `FixedString`, `Array`, `LowCardinality`, `Nullable`, `UUID`, `Map`.
For `Map` data type client can specify if index should be created for keys or values using [mapKeys](../../../sql-reference/functions/tuple-map-functions.md#mapkeys) or [mapValues](../../../sql-reference/functions/tuple-map-functions.md#mapvalues) function.
For `Map` data type client can specify if index should be created for keys or values using [mapKeys](/docs/en/sql-reference/functions/tuple-map-functions.md/#mapkeys) or [mapValues](/docs/en/sql-reference/functions/tuple-map-functions.md/#mapvalues) function.
There are also special-purpose and experimental indexes to support approximate nearest neighbor (ANN) queries. See [here](annindexes.md) for details.
The following functions can use the filter: [equals](../../../sql-reference/functions/comparison-functions.md), [notEquals](../../../sql-reference/functions/comparison-functions.md), [in](../../../sql-reference/functions/in-functions), [notIn](../../../sql-reference/functions/in-functions), [has](../../../sql-reference/functions/array-functions#hasarr-elem), [hasAny](../../../sql-reference/functions/array-functions#hasany), [hasAll](../../../sql-reference/functions/array-functions#hasall).
The following functions can use the filter: [equals](/docs/en/sql-reference/functions/comparison-functions.md), [notEquals](/docs/en/sql-reference/functions/comparison-functions.md), [in](/docs/en/sql-reference/functions/in-functions), [notIn](/docs/en/sql-reference/functions/in-functions), [has](/docs/en/sql-reference/functions/array-functions#hasarr-elem), [hasAny](/docs/en/sql-reference/functions/array-functions#hasany), [hasAll](/docs/en/sql-reference/functions/array-functions#hasall).
Example of index creation for `Map` data type
@ -445,21 +445,21 @@ The `set` index can be used with all functions. Function subsets for other index
| Function (operator) / Index | primary key | minmax | ngrambf_v1 | tokenbf_v1 | bloom_filter |
|------------------------------------------------------------------------------------------------------------|-------------|--------|-------------|-------------|---------------|
| [equals (=, ==)](../../../sql-reference/functions/comparison-functions.md#function-equals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notEquals(!=, &lt;&gt;)](../../../sql-reference/functions/comparison-functions.md#function-notequals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [like](../../../sql-reference/functions/string-search-functions.md#function-like) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [notLike](../../../sql-reference/functions/string-search-functions.md#function-notlike) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [startsWith](../../../sql-reference/functions/string-functions.md#startswith) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [endsWith](../../../sql-reference/functions/string-functions.md#endswith) | ✗ | ✗ | ✔ | ✔ | ✗ |
| [multiSearchAny](../../../sql-reference/functions/string-search-functions.md#function-multisearchany) | ✗ | ✗ | ✔ | ✗ | ✗ |
| [in](../../../sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notIn](../../../sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [less (<)](../../../sql-reference/functions/comparison-functions.md#function-less) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greater (>)](../../../sql-reference/functions/comparison-functions.md#function-greater) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [lessOrEquals (<=)](../../../sql-reference/functions/comparison-functions.md#function-lessorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greaterOrEquals (>=)](../../../sql-reference/functions/comparison-functions.md#function-greaterorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [empty](../../../sql-reference/functions/array-functions#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [notEmpty](../../../sql-reference/functions/array-functions#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [equals (=, ==)](/docs/en/sql-reference/functions/comparison-functions.md/#function-equals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notEquals(!=, &lt;&gt;)](/docs/en/sql-reference/functions/comparison-functions.md/#function-notequals) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [like](/docs/en/sql-reference/functions/string-search-functions.md/#function-like) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [notLike](/docs/en/sql-reference/functions/string-search-functions.md/#function-notlike) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [startsWith](/docs/en/sql-reference/functions/string-functions.md/#startswith) | ✔ | ✔ | ✔ | ✔ | ✗ |
| [endsWith](/docs/en/sql-reference/functions/string-functions.md/#endswith) | ✗ | ✗ | ✔ | ✔ | ✗ |
| [multiSearchAny](/docs/en/sql-reference/functions/string-search-functions.md/#function-multisearchany) | ✗ | ✗ | ✔ | ✗ | ✗ |
| [in](/docs/en/sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [notIn](/docs/en/sql-reference/functions/in-functions#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ |
| [less (<)](/docs/en/sql-reference/functions/comparison-functions.md/#function-less) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greater (>)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greater) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [lessOrEquals (<=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-lessorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [greaterOrEquals (>=)](/docs/en/sql-reference/functions/comparison-functions.md/#function-greaterorequals) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [empty](/docs/en/sql-reference/functions/array-functions#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| [notEmpty](/docs/en/sql-reference/functions/array-functions#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ |
| hasToken | ✗ | ✗ | ✗ | ✔ | ✗ |
Functions with a constant argument that is less than ngram size can’t be used by `ngrambf_v1` for query optimization.
@ -485,16 +485,16 @@ For example:
## Approximate Nearest Neighbor Search Indexes [experimental] {#table_engines-ANNIndex}
In addition to skip indices, there are also [Approximate Nearest Neighbor Search Indexes](../../../engines/table-engines/mergetree-family/annindexes.md).
In addition to skip indices, there are also [Approximate Nearest Neighbor Search Indexes](/docs/en/engines/table-engines/mergetree-family/annindexes.md).
## Projections {#projections}
Projections are like [materialized views](../../../sql-reference/statements/create/view.md#materialized) but defined in part-level. It provides consistency guarantees along with automatic usage in queries.
Projections are like [materialized views](/docs/en/sql-reference/statements/create/view.md/#materialized) but defined in part-level. It provides consistency guarantees along with automatic usage in queries.
:::note
When you are implementing projections you should also consider the [force_optimize_projection](../../../operations/settings/settings.md#force-optimize-projection) setting.
When you are implementing projections you should also consider the [force_optimize_projection](/docs/en/operations/settings/settings.md/#force-optimize-projection) setting.
:::
Projections are not supported in the `SELECT` statements with the [FINAL](../../../sql-reference/statements/select/from.md#select-from-final) modifier.
Projections are not supported in the `SELECT` statements with the [FINAL](/docs/en/sql-reference/statements/select/from.md/#select-from-final) modifier.
### Projection Query {#projection-query}
A projection query is what defines a projection. It implicitly selects data from the parent table.
@ -504,7 +504,7 @@ A projection query is what defines a projection. It implicitly selects data from
SELECT <column list expr> [GROUP BY] <group keys expr> [ORDER BY] <expr>
```
Projections can be modified or dropped with the [ALTER](../../../sql-reference/statements/alter/projection.md) statement.
Projections can be modified or dropped with the [ALTER](/docs/en/sql-reference/statements/alter/projection.md) statement.
### Projection Storage {#projection-storage}
Projections are stored inside the part directory. It's similar to an index but contains a subdirectory that stores an anonymous `MergeTree` table's part. The table is induced by the definition query of the projection. If there is a `GROUP BY` clause, the underlying storage engine becomes [AggregatingMergeTree](aggregatingmergetree.md), and all aggregate functions are converted to `AggregateFunction`. If there is an `ORDER BY` clause, the `MergeTree` table uses it as its primary key expression. During the merge process the projection part is merged via its storage's merge routine. The checksum of the parent table's part is combined with the projection's part. Other maintenance jobs are similar to skip indices.
@ -526,7 +526,7 @@ Determines the lifetime of values.
The `TTL` clause can be set for the whole table and for each individual column. Table-level `TTL` can also specify the logic of automatic moving data between disks and volumes, or recompressing parts where all the data has been expired.
Expressions must evaluate to [Date](../../../sql-reference/data-types/date.md) or [DateTime](../../../sql-reference/data-types/datetime.md) data type.
Expressions must evaluate to [Date](/docs/en/sql-reference/data-types/date.md) or [DateTime](/docs/en/sql-reference/data-types/datetime.md) data type.
**Syntax**
@ -537,7 +537,7 @@ TTL time_column
TTL time_column + interval
```
To define `interval`, use [time interval](../../../sql-reference/operators/index.md#operators-datetime) operators, for example:
To define `interval`, use [time interval](/docs/en/sql-reference/operators/index.md/#operators-datetime) operators, for example:
``` sql
TTL date_time + INTERVAL 1 MONTH
@ -684,11 +684,11 @@ Data with an expired `TTL` is removed when ClickHouse merges data parts.
When ClickHouse detects that data is expired, it performs an off-schedule merge. To control the frequency of such merges, you can set `merge_with_ttl_timeout`. If the value is too low, it will perform many off-schedule merges that may consume a lot of resources.
If you perform the `SELECT` query between merges, you may get expired data. To avoid it, use the [OPTIMIZE](../../../sql-reference/statements/optimize.md) query before `SELECT`.
If you perform the `SELECT` query between merges, you may get expired data. To avoid it, use the [OPTIMIZE](/docs/en/sql-reference/statements/optimize.md) query before `SELECT`.
**See Also**
- [ttl_only_drop_parts](../../../operations/settings/settings.md#ttl_only_drop_parts) setting
- [ttl_only_drop_parts](/docs/en/operations/settings/settings.md/#ttl_only_drop_parts) setting
## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
@ -697,16 +697,16 @@ If you perform the `SELECT` query between merges, you may get expired data. To a
`MergeTree` family table engines can store data on multiple block devices. For example, it can be useful when the data of a certain table are implicitly split into “hot” and “cold”. The most recent data is regularly requested but requires only a small amount of space. On the contrary, the fat-tailed historical data is requested rarely. If several disks are available, the “hot” data may be located on fast disks (for example, NVMe SSDs or in memory), while the “cold” data - on relatively slow ones (for example, HDD).
Data part is the minimum movable unit for `MergeTree`-engine tables. The data belonging to one part are stored on one disk. Data parts can be moved between disks in the background (according to user settings) as well as by means of the [ALTER](../../../sql-reference/statements/alter/partition.md#alter_move-partition) queries.
Data part is the minimum movable unit for `MergeTree`-engine tables. The data belonging to one part are stored on one disk. Data parts can be moved between disks in the background (according to user settings) as well as by means of the [ALTER](/docs/en/sql-reference/statements/alter/partition.md/#alter_move-partition) queries.
### Terms {#terms}
- Disk — Block device mounted to the filesystem.
- Default disk — Disk that stores the path specified in the [path](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-path) server setting.
- Default disk — Disk that stores the path specified in the [path](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-path) server setting.
- Volume — Ordered set of equal disks (similar to [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures)).
- Storage policy — Set of volumes and the rules for moving data between them.
The names given to the described entities can be found in the system tables, [system.storage_policies](../../../operations/system-tables/storage_policies.md#system_tables-storage_policies) and [system.disks](../../../operations/system-tables/disks.md#system_tables-disks). To apply one of the configured storage policies for a table, use the `storage_policy` setting of `MergeTree`-engine family tables.
The names given to the described entities can be found in the system tables, [system.storage_policies](/docs/en/operations/system-tables/storage_policies.md/#system_tables-storage_policies) and [system.disks](/docs/en/operations/system-tables/disks.md/#system_tables-disks). To apply one of the configured storage policies for a table, use the `storage_policy` setting of `MergeTree`-engine family tables.
### Configuration {#table_engine-mergetree-multiple-volumes_configure}
@ -853,16 +853,16 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd'
The `default` storage policy implies using only one volume, which consists of only one disk given in `<path>`.
You could change storage policy after table creation with [ALTER TABLE ... MODIFY SETTING] query, new policy should include all old disks and volumes with same names.
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.
The number of threads performing background moves of data parts can be changed by [background_move_pool_size](/docs/en/operations/settings/settings.md/#background_move_pool_size) setting.
### Details {#details}
In the case of `MergeTree` tables, data is getting to disk in different ways:
- As a result of an insert (`INSERT` query).
- During background merges and [mutations](../../../sql-reference/statements/alter/index.md#alter-mutations).
- During background merges and [mutations](/docs/en/sql-reference/statements/alter/index.md/#alter-mutations).
- When downloading from another replica.
- As a result of partition freezing [ALTER TABLE … FREEZE PARTITION](../../../sql-reference/statements/alter/partition.md#alter_freeze-partition).
- As a result of partition freezing [ALTER TABLE … FREEZE PARTITION](/docs/en/sql-reference/statements/alter/partition.md/#alter_freeze-partition).
In all these cases except for mutations and partition freezing, a part is stored on a volume and a disk according to the given storage policy:
@ -872,16 +872,16 @@ In all these cases except for mutations and partition freezing, a part is stored
Under the hood, mutations and partition freezing make use of [hard links](https://en.wikipedia.org/wiki/Hard_link). Hard links between different disks are not supported, therefore in such cases the resulting parts are stored on the same disks as the initial ones.
In the background, parts are moved between volumes on the basis of the amount of free space (`move_factor` parameter) according to the order the volumes are declared in the configuration file.
Data is never transferred from the last one and into the first one. One may use system tables [system.part_log](../../../operations/system-tables/part_log.md#system_tables-part-log) (field `type = MOVE_PART`) and [system.parts](../../../operations/system-tables/parts.md#system_tables-parts) (fields `path` and `disk`) to monitor background moves. Also, the detailed information can be found in server logs.
Data is never transferred from the last one and into the first one. One may use system tables [system.part_log](/docs/en/operations/system-tables/part_log.md/#system_tables-part-log) (field `type = MOVE_PART`) and [system.parts](/docs/en/operations/system-tables/parts.md/#system_tables-parts) (fields `path` and `disk`) to monitor background moves. Also, the detailed information can be found in server logs.
User can force moving a part or a partition from one volume to another using the query [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](../../../sql-reference/statements/alter/partition.md#alter_move-partition), all the restrictions for background operations are taken into account. The query initiates a move on its own and does not wait for background operations to be completed. User will get an error message if not enough free space is available or if any of the required conditions are not met.
User can force moving a part or a partition from one volume to another using the query [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](/docs/en/sql-reference/statements/alter/partition.md/#alter_move-partition), all the restrictions for background operations are taken into account. The query initiates a move on its own and does not wait for background operations to be completed. User will get an error message if not enough free space is available or if any of the required conditions are not met.
Moving data does not interfere with data replication. Therefore, different storage policies can be specified for the same table on different replicas.
After the completion of background merges and mutations, old parts are removed only after a certain amount of time (`old_parts_lifetime`).
During this time, they are not moved to other volumes or disks. Therefore, until the parts are finally removed, they are still taken into account for evaluation of the occupied disk space.
User can assign new big parts to different disks of a [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures) volume in a balanced way using the [min_bytes_to_rebalance_partition_over_jbod](../../../operations/settings/merge-tree-settings.md#min-bytes-to-rebalance-partition-over-jbod) setting.
User can assign new big parts to different disks of a [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures) volume in a balanced way using the [min_bytes_to_rebalance_partition_over_jbod](/docs/en/operations/settings/merge-tree-settings.md/#min-bytes-to-rebalance-partition-over-jbod) setting.
## Using S3 for Data Storage {#table_engine-mergetree-s3}

26
docs/en/engines/table-engines/mergetree-family/replication.md
View File

@ -20,7 +20,7 @@ Replication works at the level of an individual table, not the entire server. A
Replication does not depend on sharding. Each shard has its own independent replication.
Compressed data for `INSERT` and `ALTER` queries is replicated (for more information, see the documentation for [ALTER](../../../sql-reference/statements/alter/index.md#query_language_queries_alter)).
Compressed data for `INSERT` and `ALTER` queries is replicated (for more information, see the documentation for [ALTER](/docs/en/sql-reference/statements/alter/index.md/#query_language_queries_alter)).
`CREATE`, `DROP`, `ATTACH`, `DETACH` and `RENAME` queries are executed on a single server and are not replicated:
@ -28,9 +28,9 @@ Compressed data for `INSERT` and `ALTER` queries is replicated (for more informa
- The `DROP TABLE` query deletes the replica located on the server where the query is run.
- The `RENAME` query renames the table on one of the replicas. In other words, replicated tables can have different names on different replicas.
ClickHouse uses [ClickHouse Keeper](../../../guides/sre/keeper/clickhouse-keeper.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
ClickHouse uses [ClickHouse Keeper](/docs/en/guides/sre/keeper/clickhouse-keeper.md) for storing replicas meta information. It is possible to use ZooKeeper version 3.4.5 or newer, but ClickHouse Keeper is recommended.
To use replication, set parameters in the [zookeeper](../../../operations/server-configuration-parameters/settings.md#server-settings_zookeeper) server configuration section.
To use replication, set parameters in the [zookeeper](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings_zookeeper) server configuration section.
:::warning
Don’t neglect the security setting. ClickHouse supports the `digest` [ACL scheme](https://zookeeper.apache.org/doc/current/zookeeperProgrammers.html#sc_ZooKeeperAccessControl) of the ZooKeeper security subsystem.
@ -95,21 +95,21 @@ You can specify any existing ZooKeeper cluster and the system will use a directo
If ZooKeeper isn’t set in the config file, you can’t create replicated tables, and any existing replicated tables will be read-only.
ZooKeeper is not used in `SELECT` queries because replication does not affect the performance of `SELECT` and queries run just as fast as they do for non-replicated tables. When querying distributed replicated tables, ClickHouse behavior is controlled by the settings [max_replica_delay_for_distributed_queries](../../../operations/settings/settings.md#settings-max_replica_delay_for_distributed_queries) and [fallback_to_stale_replicas_for_distributed_queries](../../../operations/settings/settings.md#settings-fallback_to_stale_replicas_for_distributed_queries).
ZooKeeper is not used in `SELECT` queries because replication does not affect the performance of `SELECT` and queries run just as fast as they do for non-replicated tables. When querying distributed replicated tables, ClickHouse behavior is controlled by the settings [max_replica_delay_for_distributed_queries](/docs/en/operations/settings/settings.md/#settings-max_replica_delay_for_distributed_queries) and [fallback_to_stale_replicas_for_distributed_queries](/docs/en/operations/settings/settings.md/#settings-fallback_to_stale_replicas_for_distributed_queries).
For each `INSERT` query, approximately ten entries are added to ZooKeeper through several transactions. (To be more precise, this is for each inserted block of data; an INSERT query contains one block or one block per `max_insert_block_size = 1048576` rows.) This leads to slightly longer latencies for `INSERT` compared to non-replicated tables. But if you follow the recommendations to insert data in batches of no more than one `INSERT` per second, it does not create any problems. The entire ClickHouse cluster used for coordinating one ZooKeeper cluster has a total of several hundred `INSERTs` per second. The throughput on data inserts (the number of rows per second) is just as high as for non-replicated data.
For very large clusters, you can use different ZooKeeper clusters for different shards. However, from our experience this has not proven necessary based on production clusters with approximately 300 servers.
Replication is asynchronous and multi-master. `INSERT` queries (as well as `ALTER`) can be sent to any available server. Data is inserted on the server where the query is run, and then it is copied to the other servers. Because it is asynchronous, recently inserted data appears on the other replicas with some latency. If part of the replicas are not available, the data is written when they become available. If a replica is available, the latency is the amount of time it takes to transfer the block of compressed data over the network. The number of threads performing background tasks for replicated tables can be set by [background_schedule_pool_size](../../../operations/settings/settings.md#background_schedule_pool_size) setting.
Replication is asynchronous and multi-master. `INSERT` queries (as well as `ALTER`) can be sent to any available server. Data is inserted on the server where the query is run, and then it is copied to the other servers. Because it is asynchronous, recently inserted data appears on the other replicas with some latency. If part of the replicas are not available, the data is written when they become available. If a replica is available, the latency is the amount of time it takes to transfer the block of compressed data over the network. The number of threads performing background tasks for replicated tables can be set by [background_schedule_pool_size](/docs/en/operations/settings/settings.md/#background_schedule_pool_size) setting.
`ReplicatedMergeTree` engine uses a separate thread pool for replicated fetches. Size of the pool is limited by the [background_fetches_pool_size](../../../operations/settings/settings.md#background_fetches_pool_size) setting which can be tuned with a server restart.
`ReplicatedMergeTree` engine uses a separate thread pool for replicated fetches. Size of the pool is limited by the [background_fetches_pool_size](/docs/en/operations/settings/settings.md/#background_fetches_pool_size) setting which can be tuned with a server restart.
By default, an INSERT query waits for confirmation of writing the data from only one replica. If the data was successfully written to only one replica and the server with this replica ceases to exist, the stored data will be lost. To enable getting confirmation of data writes from multiple replicas, use the `insert_quorum` option.
Each block of data is written atomically. The INSERT query is divided into blocks up to `max_insert_block_size = 1048576` rows. In other words, if the `INSERT` query has less than 1048576 rows, it is made atomically.
Data blocks are deduplicated. For multiple writes of the same data block (data blocks of the same size containing the same rows in the same order), the block is only written once. The reason for this is in case of network failures when the client application does not know if the data was written to the DB, so the `INSERT` query can simply be repeated. It does not matter which replica INSERTs were sent to with identical data. `INSERTs` are idempotent. Deduplication parameters are controlled by [merge_tree](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-merge_tree) server settings.
Data blocks are deduplicated. For multiple writes of the same data block (data blocks of the same size containing the same rows in the same order), the block is only written once. The reason for this is in case of network failures when the client application does not know if the data was written to the DB, so the `INSERT` query can simply be repeated. It does not matter which replica INSERTs were sent to with identical data. `INSERTs` are idempotent. Deduplication parameters are controlled by [merge_tree](/docs/en/operations/server-configuration-parameters/settings.md/#server_configuration_parameters-merge_tree) server settings.
During replication, only the source data to insert is transferred over the network. Further data transformation (merging) is coordinated and performed on all the replicas in the same way. This minimizes network usage, which means that replication works well when replicas reside in different datacenters. (Note that duplicating data in different datacenters is the main goal of replication.)
@ -165,7 +165,7 @@ CREATE TABLE table_name
</details>
As the example shows, these parameters can contain substitutions in curly brackets. The substituted values are taken from the [macros](../../../operations/server-configuration-parameters/settings.md#macros) section of the configuration file.
As the example shows, these parameters can contain substitutions in curly brackets. The substituted values are taken from the [macros](/docs/en/operations/server-configuration-parameters/settings.md/#macros) section of the configuration file.
Example:
@ -295,10 +295,10 @@ If the data in ClickHouse Keeper was lost or damaged, you can save data by movin
**See Also**
- [background_schedule_pool_size](../../../operations/settings/settings.md#background_schedule_pool_size)
- [background_fetches_pool_size](../../../operations/settings/settings.md#background_fetches_pool_size)
- [execute_merges_on_single_replica_time_threshold](../../../operations/settings/settings.md#execute-merges-on-single-replica-time-threshold)
- [max_replicated_fetches_network_bandwidth](../../../operations/settings/merge-tree-settings.md#max_replicated_fetches_network_bandwidth)
- [max_replicated_sends_network_bandwidth](../../../operations/settings/merge-tree-settings.md#max_replicated_sends_network_bandwidth)
- [background_schedule_pool_size](/docs/en/operations/settings/settings.md/#background_schedule_pool_size)
- [background_fetches_pool_size](/docs/en/operations/settings/settings.md/#background_fetches_pool_size)
- [execute_merges_on_single_replica_time_threshold](/docs/en/operations/settings/settings.md/#execute-merges-on-single-replica-time-threshold)
- [max_replicated_fetches_network_bandwidth](/docs/en/operations/settings/merge-tree-settings.md/#max_replicated_fetches_network_bandwidth)
- [max_replicated_sends_network_bandwidth](/docs/en/operations/settings/merge-tree-settings.md/#max_replicated_sends_network_bandwidth)
[Original article](https://clickhouse.com/docs/en/operations/table_engines/replication/) <!--hide-->

28
docs/en/engines/table-engines/special/join.md
View File

@ -6,10 +6,10 @@ sidebar_label: Join
# Join Table Engine
Optional prepared data structure for usage in [JOIN](../../../sql-reference/statements/select/join.md#select-join) operations.
Optional prepared data structure for usage in [JOIN](/docs/en/sql-reference/statements/select/join.md/#select-join) operations.
:::note
This is not an article about the [JOIN clause](../../../sql-reference/statements/select/join.md#select-join) itself.
This is not an article about the [JOIN clause](/docs/en/sql-reference/statements/select/join.md/#select-join) itself.
:::
## Creating a Table {#creating-a-table}
@ -22,17 +22,17 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
) ENGINE = Join(join_strictness, join_type, k1[, k2, ...])
```
See the detailed description of the [CREATE TABLE](../../../sql-reference/statements/create/table.md#create-table-query) query.
See the detailed description of the [CREATE TABLE](/docs/en/sql-reference/statements/create/table.md/#create-table-query) query.
## Engine Parameters
### join_strictness
`join_strictness` – [JOIN strictness](../../../sql-reference/statements/select/join.md#select-join-types).
`join_strictness` – [JOIN strictness](/docs/en/sql-reference/statements/select/join.md/#select-join-types).
### join_type
`join_type` – [JOIN type](../../../sql-reference/statements/select/join.md#select-join-types).
`join_type` – [JOIN type](/docs/en/sql-reference/statements/select/join.md/#select-join-types).
### Key columns
@ -55,11 +55,11 @@ You can use `INSERT` queries to add data to the `Join`-engine tables. If the tab
Main use-cases for `Join`-engine tables are following:
- Place the table to the right side in a `JOIN` clause.
- Call the [joinGet](../../../sql-reference/functions/other-functions.md#joinget) function, which lets you extract data from the table the same way as from a dictionary.
- Call the [joinGet](/docs/en/sql-reference/functions/other-functions.md/#joinget) function, which lets you extract data from the table the same way as from a dictionary.
### Deleting Data {#deleting-data}
`ALTER DELETE` queries for `Join`-engine tables are implemented as [mutations](../../../sql-reference/statements/alter/index.md#mutations). `DELETE` mutation reads filtered data and overwrites data of memory and disk.
`ALTER DELETE` queries for `Join`-engine tables are implemented as [mutations](/docs/en/sql-reference/statements/alter/index.md/#mutations). `DELETE` mutation reads filtered data and overwrites data of memory and disk.
### Limitations and Settings {#join-limitations-and-settings}
@ -67,30 +67,30 @@ When creating a table, the following settings are applied:
#### join_use_nulls
[join_use_nulls](../../../operations/settings/settings.md#join_use_nulls)
[join_use_nulls](/docs/en/operations/settings/settings.md/#join_use_nulls)
#### max_rows_in_join
[max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join)
[max_rows_in_join](/docs/en/operations/settings/query-complexity.md/#settings-max_rows_in_join)
#### max_bytes_in_join
[max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join)
[max_bytes_in_join](/docs/en/operations/settings/query-complexity.md/#settings-max_bytes_in_join)
#### join_overflow_mode
[join_overflow_mode](../../../operations/settings/query-complexity.md#settings-join_overflow_mode)
[join_overflow_mode](/docs/en/operations/settings/query-complexity.md/#settings-join_overflow_mode)
#### join_any_take_last_row
[join_any_take_last_row](../../../operations/settings/settings.md#settings-join_any_take_last_row)
[join_any_take_last_row](/docs/en/operations/settings/settings.md/#settings-join_any_take_last_row)
#### join_use_nulls
[persistent](../../../operations/settings/settings.md#persistent)
[persistent](/docs/en/operations/settings/settings.md/#persistent)
The `Join`-engine tables can’t be used in `GLOBAL JOIN` operations.
The `Join`-engine allows to specify [join_use_nulls](../../../operations/settings/settings.md#join_use_nulls) setting in the `CREATE TABLE` statement. [SELECT](../../../sql-reference/statements/select/index.md) query should have the same `join_use_nulls` value.
The `Join`-engine allows to specify [join_use_nulls](/docs/en/operations/settings/settings.md/#join_use_nulls) setting in the `CREATE TABLE` statement. [SELECT](/docs/en/sql-reference/statements/select/index.md) query should have the same `join_use_nulls` value.
## Usage Examples {#example}

2289
docs/en/getting-started/example-datasets/github.md Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
docs/en/getting-started/example-datasets/images/superset-commits-authors.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 246 KiB

BIN
docs/en/getting-started/example-datasets/images/superset-github-lines-added-deleted.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 69 KiB

8
docs/en/operations/troubleshooting.md → docs/en/operations/_troubleshooting.md
View File

@ -1,9 +1,5 @@
---
slug: /en/operations/troubleshooting
sidebar_position: 46
sidebar_label: Troubleshooting
title: Troubleshooting
---
[//]: # (This file is included in FAQ > Troubleshooting)
- [Installation](#troubleshooting-installation-errors)
- [Connecting to the server](#troubleshooting-accepts-no-connections)

304
docs/en/operations/settings/settings.md
View File

@ -70,7 +70,7 @@ Another use case of `prefer_global_in_and_join` is accessing tables created by
**See also:**
- [Distributed subqueries](../../sql-reference/operators/in.md#select-distributed-subqueries) for more information on how to use `GLOBAL IN`/`GLOBAL JOIN`
- [Distributed subqueries](../../sql-reference/operators/in.md/#select-distributed-subqueries) for more information on how to use `GLOBAL IN`/`GLOBAL JOIN`
## enable_optimize_predicate_expression {#enable-optimize-predicate-expression}
@ -170,7 +170,7 @@ It makes sense to disable it if the server has millions of tiny tables that are
## function_range_max_elements_in_block {#settings-function_range_max_elements_in_block}
Sets the safety threshold for data volume generated by function [range](../../sql-reference/functions/array-functions.md#range). Defines the maximum number of values generated by function per block of data (sum of array sizes for every row in a block).
Sets the safety threshold for data volume generated by function [range](../../sql-reference/functions/array-functions.md/#range). Defines the maximum number of values generated by function per block of data (sum of array sizes for every row in a block).
Possible values:
@ -273,10 +273,10 @@ Default value: 0.
## insert_null_as_default {#insert_null_as_default}
Enables or disables the insertion of [default values](../../sql-reference/statements/create/table.md#create-default-values) instead of [NULL](../../sql-reference/syntax.md#null-literal) into columns with not [nullable](../../sql-reference/data-types/nullable.md#data_type-nullable) data type.
Enables or disables the insertion of [default values](../../sql-reference/statements/create/table.md/#create-default-values) instead of [NULL](../../sql-reference/syntax.md/#null-literal) into columns with not [nullable](../../sql-reference/data-types/nullable.md/#data_type-nullable) data type.
If column type is not nullable and this setting is disabled, then inserting `NULL` causes an exception. If column type is nullable, then `NULL` values are inserted as is, regardless of this setting.
This setting is applicable to [INSERT ... SELECT](../../sql-reference/statements/insert-into.md#insert_query_insert-select) queries. Note that `SELECT` subqueries may be concatenated with `UNION ALL` clause.
This setting is applicable to [INSERT ... SELECT](../../sql-reference/statements/insert-into.md/#insert_query_insert-select) queries. Note that `SELECT` subqueries may be concatenated with `UNION ALL` clause.
Possible values:
@ -287,7 +287,7 @@ Default value: `1`.
## join_default_strictness {#settings-join_default_strictness}
Sets default strictness for [JOIN clauses](../../sql-reference/statements/select/join.md#select-join).
Sets default strictness for [JOIN clauses](../../sql-reference/statements/select/join.md/#select-join).
Possible values:
@ -322,7 +322,7 @@ When using `partial_merge` algorithm, ClickHouse sorts the data and dumps it to
- `direct` - can be applied when the right storage supports key-value requests.
The `direct` algorithm performs a lookup in the right table using rows from the left table as keys. It's supported only by special storage such as [Dictionary](../../engines/table-engines/special/dictionary.md#dictionary) or [EmbeddedRocksDB](../../engines/table-engines/integrations/embedded-rocksdb.md) and only the `LEFT` and `INNER` JOINs.
The `direct` algorithm performs a lookup in the right table using rows from the left table as keys. It's supported only by special storage such as [Dictionary](../../engines/table-engines/special/dictionary.md/#dictionary) or [EmbeddedRocksDB](../../engines/table-engines/integrations/embedded-rocksdb.md) and only the `LEFT` and `INNER` JOINs.
- `auto` — try `hash` join and switch on the fly to another algorithm if the memory limit is violated.
@ -348,7 +348,7 @@ Default value: 0.
See also:
- [JOIN clause](../../sql-reference/statements/select/join.md#select-join)
- [JOIN clause](../../sql-reference/statements/select/join.md/#select-join)
- [Join table engine](../../engines/table-engines/special/join.md)
- [join_default_strictness](#settings-join_default_strictness)
@ -359,7 +359,7 @@ Sets the type of [JOIN](../../sql-reference/statements/select/join.md) behaviour
Possible values:
- 0 — The empty cells are filled with the default value of the corresponding field type.
- 1 — `JOIN` behaves the same way as in standard SQL. The type of the corresponding field is converted to [Nullable](../../sql-reference/data-types/nullable.md#data_type-nullable), and empty cells are filled with [NULL](../../sql-reference/syntax.md).
- 1 — `JOIN` behaves the same way as in standard SQL. The type of the corresponding field is converted to [Nullable](../../sql-reference/data-types/nullable.md/#data_type-nullable), and empty cells are filled with [NULL](../../sql-reference/syntax.md).
Default value: 0.
@ -431,7 +431,7 @@ Default value: 0.
See also:
- [JOIN strictness](../../sql-reference/statements/select/join.md#join-settings)
- [JOIN strictness](../../sql-reference/statements/select/join.md/#join-settings)
## temporary_files_codec {#temporary_files_codec}
@ -532,7 +532,7 @@ Default value: 8.
If ClickHouse should read more than `merge_tree_max_rows_to_use_cache` rows in one query, it does not use the cache of uncompressed blocks.
The cache of uncompressed blocks stores data extracted for queries. ClickHouse uses this cache to speed up responses to repeated small queries. This setting protects the cache from trashing by queries that read a large amount of data. The [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md#server-settings-uncompressed_cache_size) server setting defines the size of the cache of uncompressed blocks.
The cache of uncompressed blocks stores data extracted for queries. ClickHouse uses this cache to speed up responses to repeated small queries. This setting protects the cache from trashing by queries that read a large amount of data. The [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md/#server-settings-uncompressed_cache_size) server setting defines the size of the cache of uncompressed blocks.
Possible values:
@ -544,7 +544,7 @@ Default value: 128 ✕ 8192.
If ClickHouse should read more than `merge_tree_max_bytes_to_use_cache` bytes in one query, it does not use the cache of uncompressed blocks.
The cache of uncompressed blocks stores data extracted for queries. ClickHouse uses this cache to speed up responses to repeated small queries. This setting protects the cache from trashing by queries that read a large amount of data. The [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md#server-settings-uncompressed_cache_size) server setting defines the size of the cache of uncompressed blocks.
The cache of uncompressed blocks stores data extracted for queries. ClickHouse uses this cache to speed up responses to repeated small queries. This setting protects the cache from trashing by queries that read a large amount of data. The [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md/#server-settings-uncompressed_cache_size) server setting defines the size of the cache of uncompressed blocks.
Possible values:
@ -594,7 +594,7 @@ Default value: `1`.
Setting up query logging.
Queries sent to ClickHouse with this setup are logged according to the rules in the [query_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server configuration parameter.
Queries sent to ClickHouse with this setup are logged according to the rules in the [query_log](../../operations/server-configuration-parameters/settings.md/#server_configuration_parameters-query-log) server configuration parameter.
Example:
@ -639,7 +639,7 @@ log_queries_min_type='EXCEPTION_WHILE_PROCESSING'
Setting up query threads logging.
Query threads log into [system.query_thread_log](../../operations/system-tables/query_thread_log.md) table. This setting have effect only when [log_queries](#settings-log-queries) is true. Queries’ threads run by ClickHouse with this setup are logged according to the rules in the [query_thread_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server configuration parameter.
Query threads log into [system.query_thread_log](../../operations/system-tables/query_thread_log.md) table. This setting have effect only when [log_queries](#settings-log-queries) is true. Queries’ threads run by ClickHouse with this setup are logged according to the rules in the [query_thread_log](../../operations/server-configuration-parameters/settings.md/#server_configuration_parameters-query_thread_log) server configuration parameter.
Possible values:
@ -658,7 +658,7 @@ log_query_threads=1
Setting up query views logging.
When a query run by ClickHouse with this setup on has associated views (materialized or live views), they are logged in the [query_views_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_views_log) server configuration parameter.
When a query run by ClickHouse with this setup on has associated views (materialized or live views), they are logged in the [query_views_log](../../operations/server-configuration-parameters/settings.md/#server_configuration_parameters-query_views_log) server configuration parameter.
Example:
@ -884,7 +884,7 @@ Default value: `5`.
## max_replicated_fetches_network_bandwidth_for_server {#max_replicated_fetches_network_bandwidth_for_server}
Limits the maximum speed of data exchange over the network in bytes per second for [replicated](../../engines/table-engines/mergetree-family/replication.md) fetches for the server. Only has meaning at server startup. You can also limit the speed for a particular table with [max_replicated_fetches_network_bandwidth](../../operations/settings/merge-tree-settings.md#max_replicated_fetches_network_bandwidth) setting.
Limits the maximum speed of data exchange over the network in bytes per second for [replicated](../../engines/table-engines/mergetree-family/replication.md) fetches for the server. Only has meaning at server startup. You can also limit the speed for a particular table with [max_replicated_fetches_network_bandwidth](../../operations/settings/merge-tree-settings.md/#max_replicated_fetches_network_bandwidth) setting.
The setting isn't followed perfectly accurately.
@ -905,7 +905,7 @@ Could be used for throttling speed when replicating the data to add or replace n
## max_replicated_sends_network_bandwidth_for_server {#max_replicated_sends_network_bandwidth_for_server}
Limits the maximum speed of data exchange over the network in bytes per second for [replicated](../../engines/table-engines/mergetree-family/replication.md) sends for the server. Only has meaning at server startup. You can also limit the speed for a particular table with [max_replicated_sends_network_bandwidth](../../operations/settings/merge-tree-settings.md#max_replicated_sends_network_bandwidth) setting.
Limits the maximum speed of data exchange over the network in bytes per second for [replicated](../../engines/table-engines/mergetree-family/replication.md) sends for the server. Only has meaning at server startup. You can also limit the speed for a particular table with [max_replicated_sends_network_bandwidth](../../operations/settings/merge-tree-settings.md/#max_replicated_sends_network_bandwidth) setting.
The setting isn't followed perfectly accurately.
@ -955,7 +955,7 @@ For more information, see the section “Extreme values”.
## kafka_max_wait_ms {#kafka-max-wait-ms}
The wait time in milliseconds for reading messages from [Kafka](../../engines/table-engines/integrations/kafka.md#kafka) before retry.
The wait time in milliseconds for reading messages from [Kafka](../../engines/table-engines/integrations/kafka.md/#kafka) before retry.
Possible values:
@ -977,7 +977,7 @@ Default value: false.
## use_uncompressed_cache {#setting-use_uncompressed_cache}
Whether to use a cache of uncompressed blocks. Accepts 0 or 1. By default, 0 (disabled).
Using the uncompressed cache (only for tables in the MergeTree family) can significantly reduce latency and increase throughput when working with a large number of short queries. Enable this setting for users who send frequent short requests. Also pay attention to the [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md#server-settings-uncompressed_cache_size) configuration parameter (only set in the config file) – the size of uncompressed cache blocks. By default, it is 8 GiB. The uncompressed cache is filled in as needed and the least-used data is automatically deleted.
Using the uncompressed cache (only for tables in the MergeTree family) can significantly reduce latency and increase throughput when working with a large number of short queries. Enable this setting for users who send frequent short requests. Also pay attention to the [uncompressed_cache_size](../../operations/server-configuration-parameters/settings.md/#server-settings-uncompressed_cache_size) configuration parameter (only set in the config file) – the size of uncompressed cache blocks. By default, it is 8 GiB. The uncompressed cache is filled in as needed and the least-used data is automatically deleted.
For queries that read at least a somewhat large volume of data (one million rows or more), the uncompressed cache is disabled automatically to save space for truly small queries. This means that you can keep the ‘use_uncompressed_cache’ setting always set to 1.
@ -1124,7 +1124,7 @@ This setting is useful for replicated tables with a sampling key. A query may be
- The cluster latency distribution has a long tail, so that querying more servers increases the query overall latency.
:::warning
This setting will produce incorrect results when joins or subqueries are involved, and all tables don't meet certain requirements. See [Distributed Subqueries and max_parallel_replicas](../../sql-reference/operators/in.md#max_parallel_replica-subqueries) for more details.
This setting will produce incorrect results when joins or subqueries are involved, and all tables don't meet certain requirements. See [Distributed Subqueries and max_parallel_replicas](../../sql-reference/operators/in.md/#max_parallel_replica-subqueries) for more details.
:::
## compile_expressions {#compile-expressions}
@ -1261,7 +1261,7 @@ Possible values:
Default value: 1.
By default, blocks inserted into replicated tables by the `INSERT` statement are deduplicated (see [Data Replication](../../engines/table-engines/mergetree-family/replication.md)).
For the replicated tables by default the only 100 of the most recent blocks for each partition are deduplicated (see [replicated_deduplication_window](merge-tree-settings.md#replicated-deduplication-window), [replicated_deduplication_window_seconds](merge-tree-settings.md/#replicated-deduplication-window-seconds)).
For the replicated tables by default the only 100 of the most recent blocks for each partition are deduplicated (see [replicated_deduplication_window](merge-tree-settings.md/#replicated-deduplication-window), [replicated_deduplication_window_seconds](merge-tree-settings.md/#replicated-deduplication-window-seconds)).
For not replicated tables see [non_replicated_deduplication_window](merge-tree-settings.md/#non-replicated-deduplication-window).
## deduplicate_blocks_in_dependent_materialized_views {#settings-deduplicate-blocks-in-dependent-materialized-views}
@ -1296,7 +1296,7 @@ Default value: empty string (disabled)
`insert_deduplication_token` is used for deduplication _only_ when not empty.
For the replicated tables by default the only 100 of the most recent inserts for each partition are deduplicated (see [replicated_deduplication_window](merge-tree-settings.md#replicated-deduplication-window), [replicated_deduplication_window_seconds](merge-tree-settings.md/#replicated-deduplication-window-seconds)).
For the replicated tables by default the only 100 of the most recent inserts for each partition are deduplicated (see [replicated_deduplication_window](merge-tree-settings.md/#replicated-deduplication-window), [replicated_deduplication_window_seconds](merge-tree-settings.md/#replicated-deduplication-window-seconds)).
For not replicated tables see [non_replicated_deduplication_window](merge-tree-settings.md/#non-replicated-deduplication-window).
Example:
@ -1373,15 +1373,15 @@ Default value: 0.
## count_distinct_implementation {#settings-count_distinct_implementation}
Specifies which of the `uniq*` functions should be used to perform the [COUNT(DISTINCT …)](../../sql-reference/aggregate-functions/reference/count.md#agg_function-count) construction.
Specifies which of the `uniq*` functions should be used to perform the [COUNT(DISTINCT …)](../../sql-reference/aggregate-functions/reference/count.md/#agg_function-count) construction.
Possible values:
- [uniq](../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq)
- [uniqCombined](../../sql-reference/aggregate-functions/reference/uniqcombined.md#agg_function-uniqcombined)
- [uniqCombined64](../../sql-reference/aggregate-functions/reference/uniqcombined64.md#agg_function-uniqcombined64)
- [uniqHLL12](../../sql-reference/aggregate-functions/reference/uniqhll12.md#agg_function-uniqhll12)
- [uniqExact](../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact)
- [uniq](../../sql-reference/aggregate-functions/reference/uniq.md/#agg_function-uniq)
- [uniqCombined](../../sql-reference/aggregate-functions/reference/uniqcombined.md/#agg_function-uniqcombined)
- [uniqCombined64](../../sql-reference/aggregate-functions/reference/uniqcombined64.md/#agg_function-uniqcombined64)
- [uniqHLL12](../../sql-reference/aggregate-functions/reference/uniqhll12.md/#agg_function-uniqhll12)
- [uniqExact](../../sql-reference/aggregate-functions/reference/uniqexact.md/#agg_function-uniqexact)
Default value: `uniqExact`.
@ -1616,14 +1616,14 @@ Enables or disables optimization by transforming some functions to reading subco
These functions can be transformed:
- [length](../../sql-reference/functions/array-functions.md#array_functions-length) to read the [size0](../../sql-reference/data-types/array.md#array-size) subcolumn.
- [empty](../../sql-reference/functions/array-functions.md#function-empty) to read the [size0](../../sql-reference/data-types/array.md#array-size) subcolumn.
- [notEmpty](../../sql-reference/functions/array-functions.md#function-notempty) to read the [size0](../../sql-reference/data-types/array.md#array-size) subcolumn.
- [isNull](../../sql-reference/operators/index.md#operator-is-null) to read the [null](../../sql-reference/data-types/nullable.md#finding-null) subcolumn.
- [isNotNull](../../sql-reference/operators/index.md#is-not-null) to read the [null](../../sql-reference/data-types/nullable.md#finding-null) subcolumn.
- [count](../../sql-reference/aggregate-functions/reference/count.md) to read the [null](../../sql-reference/data-types/nullable.md#finding-null) subcolumn.
- [mapKeys](../../sql-reference/functions/tuple-map-functions.md#mapkeys) to read the [keys](../../sql-reference/data-types/map.md#map-subcolumns) subcolumn.
- [mapValues](../../sql-reference/functions/tuple-map-functions.md#mapvalues) to read the [values](../../sql-reference/data-types/map.md#map-subcolumns) subcolumn.
- [length](../../sql-reference/functions/array-functions.md/#array_functions-length) to read the [size0](../../sql-reference/data-types/array.md/#array-size) subcolumn.
- [empty](../../sql-reference/functions/array-functions.md/#function-empty) to read the [size0](../../sql-reference/data-types/array.md/#array-size) subcolumn.
- [notEmpty](../../sql-reference/functions/array-functions.md/#function-notempty) to read the [size0](../../sql-reference/data-types/array.md/#array-size) subcolumn.
- [isNull](../../sql-reference/operators/index.md/#operator-is-null) to read the [null](../../sql-reference/data-types/nullable.md/#finding-null) subcolumn.
- [isNotNull](../../sql-reference/operators/index.md/#is-not-null) to read the [null](../../sql-reference/data-types/nullable.md/#finding-null) subcolumn.
- [count](../../sql-reference/aggregate-functions/reference/count.md) to read the [null](../../sql-reference/data-types/nullable.md/#finding-null) subcolumn.
- [mapKeys](../../sql-reference/functions/tuple-map-functions.md/#mapkeys) to read the [keys](../../sql-reference/data-types/map.md/#map-subcolumns) subcolumn.
- [mapValues](../../sql-reference/functions/tuple-map-functions.md/#mapvalues) to read the [values](../../sql-reference/data-types/map.md/#map-subcolumns) subcolumn.
Possible values:
@ -1782,7 +1782,7 @@ Default value: 1000000000 nanoseconds (once a second).
See also:
- System table [trace_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
- System table [trace_log](../../operations/system-tables/trace_log.md/#system_tables-trace_log)
## query_profiler_cpu_time_period_ns {#query_profiler_cpu_time_period_ns}
@ -1805,7 +1805,7 @@ Default value: 1000000000 nanoseconds.
See also:
- System table [trace_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
- System table [trace_log](../../operations/system-tables/trace_log.md/#system_tables-trace_log)
## allow_introspection_functions {#settings-allow_introspection_functions}
@ -1821,11 +1821,11 @@ Default value: 0.
**See Also**
- [Sampling Query Profiler](../../operations/optimizing-performance/sampling-query-profiler.md)
- System table [trace_log](../../operations/system-tables/trace_log.md#system_tables-trace_log)
- System table [trace_log](../../operations/system-tables/trace_log.md/#system_tables-trace_log)
## input_format_parallel_parsing {#input-format-parallel-parsing}
Enables or disables order-preserving parallel parsing of data formats. Supported only for [TSV](../../interfaces/formats.md#tabseparated), [TKSV](../../interfaces/formats.md#tskv), [CSV](../../interfaces/formats.md#csv) and [JSONEachRow](../../interfaces/formats.md#jsoneachrow) formats.
Enables or disables order-preserving parallel parsing of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TKSV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Possible values:
@ -1836,7 +1836,7 @@ Default value: `1`.
## output_format_parallel_formatting {#output-format-parallel-formatting}
Enables or disables parallel formatting of data formats. Supported only for [TSV](../../interfaces/formats.md#tabseparated), [TKSV](../../interfaces/formats.md#tskv), [CSV](../../interfaces/formats.md#csv) and [JSONEachRow](../../interfaces/formats.md#jsoneachrow) formats.
Enables or disables parallel formatting of data formats. Supported only for [TSV](../../interfaces/formats.md/#tabseparated), [TKSV](../../interfaces/formats.md/#tskv), [CSV](../../interfaces/formats.md/#csv) and [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) formats.
Possible values:
@ -1878,7 +1878,7 @@ Default value: 0.
## insert_distributed_sync {#insert_distributed_sync}
Enables or disables synchronous data insertion into a [Distributed](../../engines/table-engines/special/distributed.md#distributed) table.
Enables or disables synchronous data insertion into a [Distributed](../../engines/table-engines/special/distributed.md/#distributed) table.
By default, when inserting data into a `Distributed` table, the ClickHouse server sends data to cluster nodes in asynchronous mode. When `insert_distributed_sync=1`, the data is processed synchronously, and the `INSERT` operation succeeds only after all the data is saved on all shards (at least one replica for each shard if `internal_replication` is true).
@ -1891,12 +1891,12 @@ Default value: `0`.
**See Also**
- [Distributed Table Engine](../../engines/table-engines/special/distributed.md#distributed)
- [Managing Distributed Tables](../../sql-reference/statements/system.md#query-language-system-distributed)
- [Distributed Table Engine](../../engines/table-engines/special/distributed.md/#distributed)
- [Managing Distributed Tables](../../sql-reference/statements/system.md/#query-language-system-distributed)
## insert_shard_id {#insert_shard_id}
If not `0`, specifies the shard of [Distributed](../../engines/table-engines/special/distributed.md#distributed) table into which the data will be inserted synchronously.
If not `0`, specifies the shard of [Distributed](../../engines/table-engines/special/distributed.md/#distributed) table into which the data will be inserted synchronously.
If `insert_shard_id` value is incorrect, the server will throw an exception.
@ -1909,7 +1909,7 @@ SELECT uniq(shard_num) FROM system.clusters WHERE cluster = 'requested_cluster';
Possible values:
- 0 — Disabled.
- Any number from `1` to `shards_num` of corresponding [Distributed](../../engines/table-engines/special/distributed.md#distributed) table.
- Any number from `1` to `shards_num` of corresponding [Distributed](../../engines/table-engines/special/distributed.md/#distributed) table.
Default value: `0`.
@ -1969,7 +1969,7 @@ Default value: 16.
## background_move_pool_size {#background_move_pool_size}
Sets the number of threads performing background moves of data parts for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes)-engine tables. This setting is applied at the ClickHouse server start and can’t be changed in a user session.
Sets the number of threads performing background moves of data parts for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-multiple-volumes)-engine tables. This setting is applied at the ClickHouse server start and can’t be changed in a user session.
Possible values:
@ -1979,7 +1979,7 @@ Default value: 8.
## background_schedule_pool_size {#background_schedule_pool_size}
Sets the number of threads performing background tasks for [replicated](../../engines/table-engines/mergetree-family/replication.md) tables, [Kafka](../../engines/table-engines/integrations/kafka.md) streaming, [DNS cache updates](../../operations/server-configuration-parameters/settings.md#server-settings-dns-cache-update-period). This setting is applied at ClickHouse server start and can’t be changed in a user session.
Sets the number of threads performing background tasks for [replicated](../../engines/table-engines/mergetree-family/replication.md) tables, [Kafka](../../engines/table-engines/integrations/kafka.md) streaming, [DNS cache updates](../../operations/server-configuration-parameters/settings.md/#server-settings-dns-cache-update-period). This setting is applied at ClickHouse server start and can’t be changed in a user session.
Possible values:
@ -2036,12 +2036,12 @@ Default value: 16.
**See Also**
- [Kafka](../../engines/table-engines/integrations/kafka.md#kafka) engine.
- [RabbitMQ](../../engines/table-engines/integrations/rabbitmq.md#rabbitmq-engine) engine.
- [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.
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.
Possible values:
@ -2052,7 +2052,7 @@ Default value: 1.
## transform_null_in {#transform_null_in}
Enables equality of [NULL](../../sql-reference/syntax.md#null-literal) values for [IN](../../sql-reference/operators/in.md) operator.
Enables equality of [NULL](../../sql-reference/syntax.md/#null-literal) values for [IN](../../sql-reference/operators/in.md) operator.
By default, `NULL` values can’t be compared because `NULL` means undefined value. Thus, comparison `expr = NULL` must always return `false`. With this setting `NULL = NULL` returns `true` for `IN` operator.
@ -2106,7 +2106,7 @@ Result:
**See Also**
- [NULL Processing in IN Operators](../../sql-reference/operators/in.md#in-null-processing)
- [NULL Processing in IN Operators](../../sql-reference/operators/in.md/#in-null-processing)
## low_cardinality_max_dictionary_size {#low_cardinality_max_dictionary_size}
@ -2133,7 +2133,7 @@ Default value: 0.
## low_cardinality_allow_in_native_format {#low_cardinality_allow_in_native_format}
Allows or restricts using the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) data type with the [Native](../../interfaces/formats.md#native) format.
Allows or restricts using the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) data type with the [Native](../../interfaces/formats.md/#native) format.
If usage of `LowCardinality` is restricted, ClickHouse server converts `LowCardinality`-columns to ordinary ones for `SELECT` queries, and convert ordinary columns to `LowCardinality`-columns for `INSERT` queries.
@ -2197,7 +2197,7 @@ Default value: 268435456.
## optimize_read_in_order {#optimize_read_in_order}
Enables [ORDER BY](../../sql-reference/statements/select/order-by.md#optimize_read_in_order) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries for reading data from [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) tables.
Enables [ORDER BY](../../sql-reference/statements/select/order-by.md/#optimize_read_in_order) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries for reading data from [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) tables.
Possible values:
@ -2208,7 +2208,7 @@ Default value: `1`.
**See Also**
- [ORDER BY Clause](../../sql-reference/statements/select/order-by.md#optimize_read_in_order)
- [ORDER BY Clause](../../sql-reference/statements/select/order-by.md/#optimize_read_in_order)
## optimize_aggregation_in_order {#optimize_aggregation_in_order}
@ -2223,11 +2223,11 @@ Default value: `0`.
**See Also**
- [GROUP BY optimization](../../sql-reference/statements/select/group-by.md#aggregation-in-order)
- [GROUP BY optimization](../../sql-reference/statements/select/group-by.md/#aggregation-in-order)
## mutations_sync {#mutations_sync}
Allows to execute `ALTER TABLE ... UPDATE|DELETE` queries ([mutations](../../sql-reference/statements/alter/index.md#mutations)) synchronously.
Allows to execute `ALTER TABLE ... UPDATE|DELETE` queries ([mutations](../../sql-reference/statements/alter/index.md/#mutations)) synchronously.
Possible values:
@ -2239,8 +2239,8 @@ Default value: `0`.
**See Also**
- [Synchronicity of ALTER Queries](../../sql-reference/statements/alter/index.md#synchronicity-of-alter-queries)
- [Mutations](../../sql-reference/statements/alter/index.md#mutations)
- [Synchronicity of ALTER Queries](../../sql-reference/statements/alter/index.md/#synchronicity-of-alter-queries)
- [Mutations](../../sql-reference/statements/alter/index.md/#mutations)
## ttl_only_drop_parts {#ttl_only_drop_parts}
@ -2261,8 +2261,8 @@ Default value: `0`.
**See Also**
- [CREATE TABLE query clauses and settings](../../engines/table-engines/mergetree-family/mergetree.md#mergetree-query-clauses) (`merge_with_ttl_timeout` setting)
- [Table TTL](../../engines/table-engines/mergetree-family/mergetree.md#mergetree-table-ttl)
- [CREATE TABLE query clauses and settings](../../engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses) (`merge_with_ttl_timeout` setting)
- [Table TTL](../../engines/table-engines/mergetree-family/mergetree.md/#mergetree-table-ttl)
## lock_acquire_timeout {#lock_acquire_timeout}
@ -2279,7 +2279,7 @@ Default value: `120` seconds.
## cast_keep_nullable {#cast_keep_nullable}
Enables or disables keeping of the `Nullable` data type in [CAST](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) operations.
Enables or disables keeping of the `Nullable` data type in [CAST](../../sql-reference/functions/type-conversion-functions.md/#type_conversion_function-cast) operations.
When the setting is enabled and the argument of `CAST` function is `Nullable`, the result is also transformed to `Nullable` type. When the setting is disabled, the result always has the destination type exactly.
@ -2324,7 +2324,7 @@ Result:
**See Also**
- [CAST](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) function
- [CAST](../../sql-reference/functions/type-conversion-functions.md/#type_conversion_function-cast) function
## system_events_show_zero_values {#system_events_show_zero_values}
@ -2369,7 +2369,7 @@ Result
## persistent {#persistent}
Disables persistency for the [Set](../../engines/table-engines/special/set.md#set) and [Join](../../engines/table-engines/special/join.md#join) table engines.
Disables persistency for the [Set](../../engines/table-engines/special/set.md/#set) and [Join](../../engines/table-engines/special/join.md/#join) table engines.
Reduces the I/O overhead. Suitable for scenarios that pursue performance and do not require persistence.
@ -2382,7 +2382,7 @@ Default value: `1`.
## allow_nullable_key {#allow-nullable-key}
Allows using of the [Nullable](../../sql-reference/data-types/nullable.md#data_type-nullable)-typed values in a sorting and a primary key for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md#table_engines-mergetree) tables.
Allows using of the [Nullable](../../sql-reference/data-types/nullable.md/#data_type-nullable)-typed values in a sorting and a primary key for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md/#table_engines-mergetree) tables.
Possible values:
@ -2401,7 +2401,7 @@ Do not enable this feature in version `<= 21.8`. It's not properly implemented a
## 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.
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.
It is implemented via query rewrite (similar to [count_distinct_implementation](#settings-count_distinct_implementation) setting) to get consistent results for distributed queries.
Possible values:
@ -2448,7 +2448,7 @@ 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).
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).
Possible values:
@ -2478,7 +2478,7 @@ It can be useful when merges are CPU bounded not IO bounded (performing heavy da
## 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.
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:
@ -2551,7 +2551,7 @@ Result:
└─────────────┘
```
Note that this setting influences [Materialized view](../../sql-reference/statements/create/view.md#materialized) and [MaterializedMySQL](../../engines/database-engines/materialized-mysql.md) behaviour.
Note that this setting influences [Materialized view](../../sql-reference/statements/create/view.md/#materialized) and [MaterializedMySQL](../../engines/database-engines/materialized-mysql.md) behaviour.
## engine_file_empty_if_not_exists {#engine-file-empty_if-not-exists}
@ -2608,7 +2608,7 @@ Default value: `0`.
## allow_experimental_live_view {#allow-experimental-live-view}
Allows creation of experimental [live views](../../sql-reference/statements/create/view.md#live-view).
Allows creation of experimental [live views](../../sql-reference/statements/create/view.md/#live-view).
Possible values:
@ -2619,19 +2619,19 @@ Default value: `0`.
## live_view_heartbeat_interval {#live-view-heartbeat-interval}
Sets the heartbeat interval in seconds to indicate [live view](../../sql-reference/statements/create/view.md#live-view) is alive .
Sets the heartbeat interval in seconds to indicate [live view](../../sql-reference/statements/create/view.md/#live-view) is alive .
Default value: `15`.
## max_live_view_insert_blocks_before_refresh {#max-live-view-insert-blocks-before-refresh}
Sets the maximum number of inserted blocks after which mergeable blocks are dropped and query for [live view](../../sql-reference/statements/create/view.md#live-view) is re-executed.
Sets the maximum number of inserted blocks after which mergeable blocks are dropped and query for [live view](../../sql-reference/statements/create/view.md/#live-view) is re-executed.
Default value: `64`.
## periodic_live_view_refresh {#periodic-live-view-refresh}
Sets the interval in seconds after which periodically refreshed [live view](../../sql-reference/statements/create/view.md#live-view) is forced to refresh.
Sets the interval in seconds after which periodically refreshed [live view](../../sql-reference/statements/create/view.md/#live-view) is forced to refresh.
Default value: `60`.
@ -2670,7 +2670,7 @@ Default value: 180.
## check_query_single_value_result {#check_query_single_value_result}
Defines the level of detail for the [CHECK TABLE](../../sql-reference/statements/check-table.md#checking-mergetree-tables) query result for `MergeTree` family engines .
Defines the level of detail for the [CHECK TABLE](../../sql-reference/statements/check-table.md/#checking-mergetree-tables) query result for `MergeTree` family engines .
Possible values:
@ -2681,7 +2681,7 @@ Default value: `0`.
## prefer_column_name_to_alias {#prefer-column-name-to-alias}
Enables or disables using the original column names instead of aliases in query expressions and clauses. It especially matters when alias is the same as the column name, see [Expression Aliases](../../sql-reference/syntax.md#notes-on-usage). Enable this setting to make aliases syntax rules in ClickHouse more compatible with most other database engines.
Enables or disables using the original column names instead of aliases in query expressions and clauses. It especially matters when alias is the same as the column name, see [Expression Aliases](../../sql-reference/syntax.md/#notes-on-usage). Enable this setting to make aliases syntax rules in ClickHouse more compatible with most other database engines.
Possible values:
@ -2725,7 +2725,7 @@ Result:
## limit {#limit}
Sets the maximum number of rows to get from the query result. It adjusts the value set by the [LIMIT](../../sql-reference/statements/select/limit.md#limit-clause) clause, so that the limit, specified in the query, cannot exceed the limit, set by this setting.
Sets the maximum number of rows to get from the query result. It adjusts the value set by the [LIMIT](../../sql-reference/statements/select/limit.md/#limit-clause) clause, so that the limit, specified in the query, cannot exceed the limit, set by this setting.
Possible values:
@ -2736,7 +2736,7 @@ Default value: `0`.
## offset {#offset}
Sets the number of rows to skip before starting to return rows from the query. It adjusts the offset set by the [OFFSET](../../sql-reference/statements/select/offset.md#offset-fetch) clause, so that these two values are summarized.
Sets the number of rows to skip before starting to return rows from the query. It adjusts the offset set by the [OFFSET](../../sql-reference/statements/select/offset.md/#offset-fetch) clause, so that these two values are summarized.
Possible values:
@ -2773,7 +2773,7 @@ Result:
## optimize_syntax_fuse_functions {#optimize_syntax_fuse_functions}
Enables to fuse aggregate functions with identical argument. It rewrites query contains at least two aggregate functions from [sum](../../sql-reference/aggregate-functions/reference/sum.md#agg_function-sum), [count](../../sql-reference/aggregate-functions/reference/count.md#agg_function-count) or [avg](../../sql-reference/aggregate-functions/reference/avg.md#agg_function-avg) with identical argument to [sumCount](../../sql-reference/aggregate-functions/reference/sumcount.md#agg_function-sumCount).
Enables to fuse aggregate functions with identical argument. It rewrites query contains at least two aggregate functions from [sum](../../sql-reference/aggregate-functions/reference/sum.md/#agg_function-sum), [count](../../sql-reference/aggregate-functions/reference/count.md/#agg_function-count) or [avg](../../sql-reference/aggregate-functions/reference/avg.md/#agg_function-avg) with identical argument to [sumCount](../../sql-reference/aggregate-functions/reference/sumcount.md/#agg_function-sumCount).
Possible values:
@ -2932,7 +2932,7 @@ If the setting is set to `0`, the table function does not make Nullable columns
## allow_experimental_projection_optimization {#allow-experimental-projection-optimization}
Enables or disables [projection](../../engines/table-engines/mergetree-family/mergetree.md#projections) optimization when processing `SELECT` queries.
Enables or disables [projection](../../engines/table-engines/mergetree-family/mergetree.md/#projections) optimization when processing `SELECT` queries.
Possible values:
@ -2943,7 +2943,7 @@ Default value: `1`.
## force_optimize_projection {#force-optimize-projection}
Enables or disables the obligatory use of [projections](../../engines/table-engines/mergetree-family/mergetree.md#projections) in `SELECT` queries, when projection optimization is enabled (see [allow_experimental_projection_optimization](#allow-experimental-projection-optimization) setting).
Enables or disables the obligatory use of [projections](../../engines/table-engines/mergetree-family/mergetree.md/#projections) in `SELECT` queries, when projection optimization is enabled (see [allow_experimental_projection_optimization](#allow-experimental-projection-optimization) setting).
Possible values:
@ -2978,7 +2978,7 @@ Default value: `120` seconds.
## regexp_max_matches_per_row {#regexp-max-matches-per-row}
Sets the maximum number of matches for a single regular expression per row. Use it to protect against memory overload when using greedy regular expression in the [extractAllGroupsHorizontal](../../sql-reference/functions/string-search-functions.md#extractallgroups-horizontal) function.
Sets the maximum number of matches for a single regular expression per row. Use it to protect against memory overload when using greedy regular expression in the [extractAllGroupsHorizontal](../../sql-reference/functions/string-search-functions.md/#extractallgroups-horizontal) function.
Possible values:
@ -3010,7 +3010,7 @@ Default value: `1`.
## short_circuit_function_evaluation {#short-circuit-function-evaluation}
Allows calculating the [if](../../sql-reference/functions/conditional-functions.md#if), [multiIf](../../sql-reference/functions/conditional-functions.md#multiif), [and](../../sql-reference/functions/logical-functions.md#logical-and-function), and [or](../../sql-reference/functions/logical-functions.md#logical-or-function) functions according to a [short scheme](https://en.wikipedia.org/wiki/Short-circuit_evaluation). This helps optimize the execution of complex expressions in these functions and prevent possible exceptions (such as division by zero when it is not expected).
Allows calculating the [if](../../sql-reference/functions/conditional-functions.md/#if), [multiIf](../../sql-reference/functions/conditional-functions.md/#multiif), [and](../../sql-reference/functions/logical-functions.md/#logical-and-function), and [or](../../sql-reference/functions/logical-functions.md/#logical-or-function) functions according to a [short scheme](https://en.wikipedia.org/wiki/Short-circuit_evaluation). This helps optimize the execution of complex expressions in these functions and prevent possible exceptions (such as division by zero when it is not expected).
Possible values:
@ -3022,7 +3022,7 @@ Default value: `enable`.
## max_hyperscan_regexp_length {#max-hyperscan-regexp-length}
Defines the maximum length for each regular expression in the [hyperscan multi-match functions](../../sql-reference/functions/string-search-functions.md#multimatchanyhaystack-pattern1-pattern2-patternn).
Defines the maximum length for each regular expression in the [hyperscan multi-match functions](../../sql-reference/functions/string-search-functions.md/#multimatchanyhaystack-pattern1-pattern2-patternn).
Possible values:
@ -3065,7 +3065,7 @@ Exception: Regexp length too large.
## max_hyperscan_regexp_total_length {#max-hyperscan-regexp-total-length}
Sets the maximum length total of all regular expressions in each [hyperscan multi-match function](../../sql-reference/functions/string-search-functions.md#multimatchanyhaystack-pattern1-pattern2-patternn).
Sets the maximum length total of all regular expressions in each [hyperscan multi-match function](../../sql-reference/functions/string-search-functions.md/#multimatchanyhaystack-pattern1-pattern2-patternn).
Possible values:
@ -3142,8 +3142,8 @@ Result:
## enable_extended_results_for_datetime_functions {#enable-extended-results-for-datetime-functions}
Enables or disables returning results of type:
- `Date32` with extended range (compared to type `Date`) for functions [toStartOfYear](../../sql-reference/functions/date-time-functions.md#tostartofyear), [toStartOfISOYear](../../sql-reference/functions/date-time-functions.md#tostartofisoyear), [toStartOfQuarter](../../sql-reference/functions/date-time-functions.md#tostartofquarter), [toStartOfMonth](../../sql-reference/functions/date-time-functions.md#tostartofmonth), [toStartOfWeek](../../sql-reference/functions/date-time-functions.md#tostartofweek), [toMonday](../../sql-reference/functions/date-time-functions.md#tomonday) and [toLastDayOfMonth](../../sql-reference/functions/date-time-functions.md#tolastdayofmonth).
- `DateTime64` with extended range (compared to type `DateTime`) for functions [toStartOfDay](../../sql-reference/functions/date-time-functions.md#tostartofday), [toStartOfHour](../../sql-reference/functions/date-time-functions.md#tostartofhour), [toStartOfMinute](../../sql-reference/functions/date-time-functions.md#tostartofminute), [toStartOfFiveMinutes](../../sql-reference/functions/date-time-functions.md#tostartoffiveminutes), [toStartOfTenMinutes](../../sql-reference/functions/date-time-functions.md#tostartoftenminutes), [toStartOfFifteenMinutes](../../sql-reference/functions/date-time-functions.md#tostartoffifteenminutes) and [timeSlot](../../sql-reference/functions/date-time-functions.md#timeslot).
- `Date32` with extended range (compared to type `Date`) for functions [toStartOfYear](../../sql-reference/functions/date-time-functions.md/#tostartofyear), [toStartOfISOYear](../../sql-reference/functions/date-time-functions.md/#tostartofisoyear), [toStartOfQuarter](../../sql-reference/functions/date-time-functions.md/#tostartofquarter), [toStartOfMonth](../../sql-reference/functions/date-time-functions.md/#tostartofmonth), [toStartOfWeek](../../sql-reference/functions/date-time-functions.md/#tostartofweek), [toMonday](../../sql-reference/functions/date-time-functions.md/#tomonday) and [toLastDayOfMonth](../../sql-reference/functions/date-time-functions.md/#tolastdayofmonth).
- `DateTime64` with extended range (compared to type `DateTime`) for functions [toStartOfDay](../../sql-reference/functions/date-time-functions.md/#tostartofday), [toStartOfHour](../../sql-reference/functions/date-time-functions.md/#tostartofhour), [toStartOfMinute](../../sql-reference/functions/date-time-functions.md/#tostartofminute), [toStartOfFiveMinutes](../../sql-reference/functions/date-time-functions.md/#tostartoffiveminutes), [toStartOfTenMinutes](../../sql-reference/functions/date-time-functions.md/#tostartoftenminutes), [toStartOfFifteenMinutes](../../sql-reference/functions/date-time-functions.md/#tostartoffifteenminutes) and [timeSlot](../../sql-reference/functions/date-time-functions.md/#timeslot).
Possible values:
@ -3167,7 +3167,7 @@ Default value: `1`.
## optimize_move_to_prewhere_if_final {#optimize_move_to_prewhere_if_final}
Enables or disables automatic [PREWHERE](../../sql-reference/statements/select/prewhere.md) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries with [FINAL](../../sql-reference/statements/select/from.md#select-from-final) modifier.
Enables or disables automatic [PREWHERE](../../sql-reference/statements/select/prewhere.md) optimization in [SELECT](../../sql-reference/statements/select/index.md) queries with [FINAL](../../sql-reference/statements/select/from.md/#select-from-final) modifier.
Works only for [*MergeTree](../../engines/table-engines/mergetree-family/index.md) tables.
@ -3184,7 +3184,7 @@ Default value: `0`.
## describe_include_subcolumns {#describe_include_subcolumns}
Enables describing subcolumns for a [DESCRIBE](../../sql-reference/statements/describe-table.md) query. For example, members of a [Tuple](../../sql-reference/data-types/tuple.md) or subcolumns of a [Map](../../sql-reference/data-types/map.md#map-subcolumns), [Nullable](../../sql-reference/data-types/nullable.md#finding-null) or an [Array](../../sql-reference/data-types/array.md#array-size) data type.
Enables describing subcolumns for a [DESCRIBE](../../sql-reference/statements/describe-table.md) query. For example, members of a [Tuple](../../sql-reference/data-types/tuple.md) or subcolumns of a [Map](../../sql-reference/data-types/map.md/#map-subcolumns), [Nullable](../../sql-reference/data-types/nullable.md/#finding-null) or an [Array](../../sql-reference/data-types/array.md/#array-size) data type.
Possible values:
@ -3283,7 +3283,7 @@ Default value: `0`.
## alter_partition_verbose_result {#alter-partition-verbose-result}
Enables or disables the display of information about the parts to which the manipulation operations with partitions and parts have been successfully applied.
Applicable to [ATTACH PARTITION|PART](../../sql-reference/statements/alter/partition.md#alter_attach-partition) and to [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md#alter_freeze-partition).
Applicable to [ATTACH PARTITION|PART](../../sql-reference/statements/alter/partition.md/#alter_attach-partition) and to [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md/#alter_freeze-partition).
Possible values:
@ -3418,11 +3418,11 @@ When writing data, ClickHouse throws an exception if input data contain columns
Supported formats:
- [JSONEachRow](../../interfaces/formats.md#jsoneachrow)
- [TSKV](../../interfaces/formats.md#tskv)
- [JSONEachRow](../../interfaces/formats.md/#jsoneachrow)
- [TSKV](../../interfaces/formats.md/#tskv)
- All formats with suffixes WithNames/WithNamesAndTypes
- [JSONColumns](../../interfaces/formats.md#jsoncolumns)
- [MySQLDump](../../interfaces/formats.md#mysqldump)
- [JSONColumns](../../interfaces/formats.md/#jsoncolumns)
- [MySQLDump](../../interfaces/formats.md/#mysqldump)
Possible values:
@ -3439,18 +3439,18 @@ To improve insert performance, we recommend disabling this check if you are sure
Supported formats:
- [CSVWithNames](../../interfaces/formats.md#csvwithnames)
- [CSVWithNamesAndTypes](../../interfaces/formats.md#csvwithnamesandtypes)
- [TabSeparatedWithNames](../../interfaces/formats.md#tabseparatedwithnames)
- [TabSeparatedWithNamesAndTypes](../../interfaces/formats.md#tabseparatedwithnamesandtypes)
- [JSONCompactEachRowWithNames](../../interfaces/formats.md#jsoncompacteachrowwithnames)
- [JSONCompactEachRowWithNamesAndTypes](../../interfaces/formats.md#jsoncompacteachrowwithnamesandtypes)
- [JSONCompactStringsEachRowWithNames](../../interfaces/formats.md#jsoncompactstringseachrowwithnames)
- [JSONCompactStringsEachRowWithNamesAndTypes](../../interfaces/formats.md#jsoncompactstringseachrowwithnamesandtypes)
- [RowBinaryWithNames](../../interfaces/formats.md#rowbinarywithnames)
- [RowBinaryWithNamesAndTypes](../../interfaces/formats.md#rowbinarywithnamesandtypes)
- [CustomSeparatedWithNames](../../interfaces/formats.md#customseparatedwithnames)
- [CustomSeparatedWithNamesAndTypes](../../interfaces/formats.md#customseparatedwithnamesandtypes)
- [CSVWithNames](../../interfaces/formats.md/#csvwithnames)
- [CSVWithNamesAndTypes](../../interfaces/formats.md/#csvwithnamesandtypes)
- [TabSeparatedWithNames](../../interfaces/formats.md/#tabseparatedwithnames)
- [TabSeparatedWithNamesAndTypes](../../interfaces/formats.md/#tabseparatedwithnamesandtypes)
- [JSONCompactEachRowWithNames](../../interfaces/formats.md/#jsoncompacteachrowwithnames)
- [JSONCompactEachRowWithNamesAndTypes](../../interfaces/formats.md/#jsoncompacteachrowwithnamesandtypes)
- [JSONCompactStringsEachRowWithNames](../../interfaces/formats.md/#jsoncompactstringseachrowwithnames)
- [JSONCompactStringsEachRowWithNamesAndTypes](../../interfaces/formats.md/#jsoncompactstringseachrowwithnamesandtypes)
- [RowBinaryWithNames](../../interfaces/formats.md/#rowbinarywithnames)
- [RowBinaryWithNamesAndTypes](../../interfaces/formats.md/#rowbinarywithnamesandtypes)
- [CustomSeparatedWithNames](../../interfaces/formats.md/#customseparatedwithnames)
- [CustomSeparatedWithNamesAndTypes](../../interfaces/formats.md/#customseparatedwithnamesandtypes)
Possible values:
@ -3465,12 +3465,12 @@ Controls whether format parser should check if data types from the input data ma
Supported formats:
- [CSVWithNamesAndTypes](../../interfaces/formats.md#csvwithnamesandtypes)
- [TabSeparatedWithNamesAndTypes](../../interfaces/formats.md#tabseparatedwithnamesandtypes)
- [JSONCompactEachRowWithNamesAndTypes](../../interfaces/formats.md#jsoncompacteachrowwithnamesandtypes)
- [JSONCompactStringsEachRowWithNamesAndTypes](../../interfaces/formats.md#jsoncompactstringseachrowwithnamesandtypes)
- [RowBinaryWithNamesAndTypes](../../interfaces/formats.md#rowbinarywithnamesandtypes-rowbinarywithnamesandtypes)
- [CustomSeparatedWithNamesAndTypes](../../interfaces/formats.md#customseparatedwithnamesandtypes)
- [CSVWithNamesAndTypes](../../interfaces/formats.md/#csvwithnamesandtypes)
- [TabSeparatedWithNamesAndTypes](../../interfaces/formats.md/#tabseparatedwithnamesandtypes)
- [JSONCompactEachRowWithNamesAndTypes](../../interfaces/formats.md/#jsoncompacteachrowwithnamesandtypes)
- [JSONCompactStringsEachRowWithNamesAndTypes](../../interfaces/formats.md/#jsoncompactstringseachrowwithnamesandtypes)
- [RowBinaryWithNamesAndTypes](../../interfaces/formats.md/#rowbinarywithnamesandtypes-rowbinarywithnamesandtypes)
- [CustomSeparatedWithNamesAndTypes](../../interfaces/formats.md/#customseparatedwithnamesandtypes)
Possible values:
@ -3481,7 +3481,7 @@ Default value: 1.
## input_format_defaults_for_omitted_fields {#input_format_defaults_for_omitted_fields}
When performing `INSERT` queries, replace omitted input column values with default values of the respective columns. This option only applies to [JSONEachRow](../../interfaces/formats.md#jsoneachrow), [CSV](../../interfaces/formats.md#csv), [TabSeparated](../../interfaces/formats.md#tabseparated) formats and formats with `WithNames`/`WithNamesAndTypes` suffixes.
When performing `INSERT` queries, replace omitted input column values with default values of the respective columns. This option only applies to [JSONEachRow](../../interfaces/formats.md/#jsoneachrow), [CSV](../../interfaces/formats.md/#csv), [TabSeparated](../../interfaces/formats.md/#tabseparated) formats and formats with `WithNames`/`WithNamesAndTypes` suffixes.
:::note
When this option is enabled, extended table metadata are sent from server to client. It consumes additional computing resources on the server and can reduce performance.
@ -3496,7 +3496,7 @@ Default value: 1.
## input_format_null_as_default {#input_format_null_as_default}
Enables or disables the initialization of [NULL](../../sql-reference/syntax.md#null-literal) fields with [default values](../../sql-reference/statements/create/table.md#create-default-values), if data type of these fields is not [nullable](../../sql-reference/data-types/nullable.md#data_type-nullable).
Enables or disables the initialization of [NULL](../../sql-reference/syntax.md/#null-literal) fields with [default values](../../sql-reference/statements/create/table.md/#create-default-values), if data type of these fields is not [nullable](../../sql-reference/data-types/nullable.md/#data_type-nullable).
If column type is not nullable and this setting is disabled, then inserting `NULL` causes an exception. If column type is nullable, then `NULL` values are inserted as is, regardless of this setting.
This setting is applicable to [INSERT ... VALUES](../../sql-reference/statements/insert-into.md) queries for text input formats.
@ -3663,7 +3663,7 @@ Enabled by default
## insert_distributed_one_random_shard {#insert_distributed_one_random_shard}
Enables or disables random shard insertion into a [Distributed](../../engines/table-engines/special/distributed.md#distributed) table when there is no distributed key.
Enables or disables random shard insertion into a [Distributed](../../engines/table-engines/special/distributed.md/#distributed) table when there is no distributed key.
By default, when inserting data into a `Distributed` table with more than one shard, the ClickHouse server will reject any insertion request if there is no distributed key. When `insert_distributed_one_random_shard = 1`, insertions are allowed and data is forwarded randomly among all shards.
@ -3682,7 +3682,7 @@ Enables or disables the insertion of JSON data with nested objects.
Supported formats:
- [JSONEachRow](../../interfaces/formats.md#jsoneachrow)
- [JSONEachRow](../../interfaces/formats.md/#jsoneachrow)
Possible values:
@ -3693,7 +3693,7 @@ Default value: 0.
See also:
- [Usage of Nested Structures](../../interfaces/formats.md#jsoneachrow-nested) with the `JSONEachRow` format.
- [Usage of Nested Structures](../../interfaces/formats.md/#jsoneachrow-nested) with the `JSONEachRow` format.
### input_format_json_read_bools_as_numbers {#input_format_json_read_bools_as_numbers}
@ -3716,7 +3716,7 @@ Enabled by default.
### output_format_json_quote_64bit_integers {#output_format_json_quote_64bit_integers}
Controls quoting of 64-bit or bigger [integers](../../sql-reference/data-types/int-uint.md) (like `UInt64` or `Int128`) when they are output in a [JSON](../../interfaces/formats.md#json) format.
Controls quoting of 64-bit or bigger [integers](../../sql-reference/data-types/int-uint.md) (like `UInt64` or `Int128`) when they are output in a [JSON](../../interfaces/formats.md/#json) format.
Such integers are enclosed in quotes by default. This behavior is compatible with most JavaScript implementations.
Possible values:
@ -3734,7 +3734,7 @@ Disabled by default.
### output_format_json_quote_denormals {#output_format_json_quote_denormals}
Enables `+nan`, `-nan`, `+inf`, `-inf` outputs in [JSON](../../interfaces/formats.md#json) output format.
Enables `+nan`, `-nan`, `+inf`, `-inf` outputs in [JSON](../../interfaces/formats.md/#json) output format.
Possible values:
@ -3851,7 +3851,7 @@ Disabled by default.
### output_format_json_array_of_rows {#output_format_json_array_of_rows}
Enables the ability to output all rows as a JSON array in the [JSONEachRow](../../interfaces/formats.md#jsoneachrow) format.
Enables the ability to output all rows as a JSON array in the [JSONEachRow](../../interfaces/formats.md/#jsoneachrow) format.
Possible values:
@ -3904,7 +3904,7 @@ Disabled by default.
### format_json_object_each_row_column_for_object_name {#format_json_object_each_row_column_for_object_name}
The name of column that will be used for storing/writing object names in [JSONObjectEachRow](../../interfaces/formats.md#jsonobjecteachrow) format.
The name of column that will be used for storing/writing object names in [JSONObjectEachRow](../../interfaces/formats.md/#jsonobjecteachrow) format.
Column type should be String. If value is empty, default names `row_{i}`will be used for object names.
Default value: ''.
@ -4005,7 +4005,7 @@ Disabled by default.
### format_tsv_null_representation {#format_tsv_null_representation}
Defines the representation of `NULL` for [TSV](../../interfaces/formats.md#tabseparated) output and input formats. User can set any string as a value, for example, `My NULL`.
Defines the representation of `NULL` for [TSV](../../interfaces/formats.md/#tabseparated) output and input formats. User can set any string as a value, for example, `My NULL`.
Default value: `\N`.
@ -4159,7 +4159,7 @@ Default value: `0`.
### format_csv_null_representation {#format_csv_null_representation}
Defines the representation of `NULL` for [CSV](../../interfaces/formats.md#csv) output and input formats. User can set any string as a value, for example, `My NULL`.
Defines the representation of `NULL` for [CSV](../../interfaces/formats.md/#csv) output and input formats. User can set any string as a value, for example, `My NULL`.
Default value: `\N`.
@ -4198,7 +4198,7 @@ My NULL
### input_format_values_interpret_expressions {#input_format_values_interpret_expressions}
Enables or disables the full SQL parser if the fast stream parser can’t parse the data. This setting is used only for the [Values](../../interfaces/formats.md#data-format-values) format at the data insertion. For more information about syntax parsing, see the [Syntax](../../sql-reference/syntax.md) section.
Enables or disables the full SQL parser if the fast stream parser can’t parse the data. This setting is used only for the [Values](../../interfaces/formats.md/#data-format-values) format at the data insertion. For more information about syntax parsing, see the [Syntax](../../sql-reference/syntax.md) section.
Possible values:
@ -4248,7 +4248,7 @@ Ok.
### input_format_values_deduce_templates_of_expressions {#input_format_values_deduce_templates_of_expressions}
Enables or disables template deduction for SQL expressions in [Values](../../interfaces/formats.md#data-format-values) format. It allows parsing and interpreting expressions in `Values` much faster if expressions in consecutive rows have the same structure. ClickHouse tries to deduce the template of an expression, parse the following rows using this template and evaluate the expression on a batch of successfully parsed rows.
Enables or disables template deduction for SQL expressions in [Values](../../interfaces/formats.md/#data-format-values) format. It allows parsing and interpreting expressions in `Values` much faster if expressions in consecutive rows have the same structure. ClickHouse tries to deduce the template of an expression, parse the following rows using this template and evaluate the expression on a batch of successfully parsed rows.
Possible values:
@ -4293,7 +4293,7 @@ Default value: 1.
### input_format_arrow_import_nested {#input_format_arrow_import_nested}
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [Arrow](../../interfaces/formats.md#data_types-matching-arrow) input format.
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [Arrow](../../interfaces/formats.md/#data_types-matching-arrow) input format.
Possible values:
@ -4322,7 +4322,7 @@ Disabled by default.
### output_format_arrow_low_cardinality_as_dictionary {#output_format_arrow_low_cardinality_as_dictionary}
Allows to convert the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) type to the `DICTIONARY` type of the [Arrow](../../interfaces/formats.md#data-format-arrow) format for `SELECT` queries.
Allows to convert the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) type to the `DICTIONARY` type of the [Arrow](../../interfaces/formats.md/#data-format-arrow) format for `SELECT` queries.
Possible values:
@ -4341,7 +4341,7 @@ Disabled by default.
### input_format_orc_import_nested {#input_format_orc_import_nested}
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [ORC](../../interfaces/formats.md#data-format-orc) input format.
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [ORC](../../interfaces/formats.md/#data-format-orc) input format.
Possible values:
@ -4384,7 +4384,7 @@ Disabled by default.
## input_format_parquet_import_nested {#input_format_parquet_import_nested}
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [Parquet](../../interfaces/formats.md#data-format-parquet) input format.
Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns as an array of structs in [Parquet](../../interfaces/formats.md/#data-format-parquet) input format.
Possible values:
@ -4481,7 +4481,7 @@ Disabled by default.
### input_format_avro_allow_missing_fields {#input_format_avro_allow_missing_fields}
Enables using fields that are not specified in [Avro](../../interfaces/formats.md#data-format-avro) or [AvroConfluent](../../interfaces/formats.md#data-format-avro-confluent) format schema. When a field is not found in the schema, ClickHouse uses the default value instead of throwing an exception.
Enables using fields that are not specified in [Avro](../../interfaces/formats.md/#data-format-avro) or [AvroConfluent](../../interfaces/formats.md/#data-format-avro-confluent) format schema. When a field is not found in the schema, ClickHouse uses the default value instead of throwing an exception.
Possible values:
@ -4492,7 +4492,7 @@ Default value: 0.
### format_avro_schema_registry_url {#format_avro_schema_registry_url}
Sets [Confluent Schema Registry](https://docs.confluent.io/current/schema-registry/index.html) URL to use with [AvroConfluent](../../interfaces/formats.md#data-format-avro-confluent) format.
Sets [Confluent Schema Registry](https://docs.confluent.io/current/schema-registry/index.html) URL to use with [AvroConfluent](../../interfaces/formats.md/#data-format-avro-confluent) format.
Default value: `Empty`.
@ -4549,7 +4549,7 @@ Default value: `250`.
### output_format_pretty_max_value_width {#output_format_pretty_max_value_width}
Limits the width of value displayed in [Pretty](../../interfaces/formats.md#pretty) formats. If the value width exceeds the limit, the value is cut.
Limits the width of value displayed in [Pretty](../../interfaces/formats.md/#pretty) formats. If the value width exceeds the limit, the value is cut.
Possible values:
@ -4625,7 +4625,7 @@ SELECT * FROM a;
### output_format_pretty_row_numbers {#output_format_pretty_row_numbers}
Adds row numbers to output in the [Pretty](../../interfaces/formats.md#pretty) format.
Adds row numbers to output in the [Pretty](../../interfaces/formats.md/#pretty) format.
Possible values:
@ -4670,52 +4670,52 @@ Delimiter between rows (for Template format).
### format_custom_escaping_rule {#format_custom_escaping_rule}
Sets the field escaping rule for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the field escaping rule for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Possible values:
- `'Escaped'` — Similarly to [TSV](../../interfaces/formats.md#tabseparated).
- `'Quoted'` — Similarly to [Values](../../interfaces/formats.md#data-format-values).
- `'CSV'` — Similarly to [CSV](../../interfaces/formats.md#csv).
- `'JSON'` — Similarly to [JSONEachRow](../../interfaces/formats.md#jsoneachrow).
- `'XML'` — Similarly to [XML](../../interfaces/formats.md#xml).
- `'Raw'` — Extracts subpatterns as a whole, no escaping rules, similarly to [TSVRaw](../../interfaces/formats.md#tabseparatedraw).
- `'Escaped'` — Similarly to [TSV](../../interfaces/formats.md/#tabseparated).
- `'Quoted'` — Similarly to [Values](../../interfaces/formats.md/#data-format-values).
- `'CSV'` — Similarly to [CSV](../../interfaces/formats.md/#csv).
- `'JSON'` — Similarly to [JSONEachRow](../../interfaces/formats.md/#jsoneachrow).
- `'XML'` — Similarly to [XML](../../interfaces/formats.md/#xml).
- `'Raw'` — Extracts subpatterns as a whole, no escaping rules, similarly to [TSVRaw](../../interfaces/formats.md/#tabseparatedraw).
Default value: `'Escaped'`.
### format_custom_field_delimiter {#format_custom_field_delimiter}
Sets the character that is interpreted as a delimiter between the fields for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a delimiter between the fields for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `'\t'`.
### format_custom_row_before_delimiter {#format_custom_row_before_delimiter}
Sets the character that is interpreted as a delimiter before the field of the first column for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a delimiter before the field of the first column for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `''`.
### format_custom_row_after_delimiter {#format_custom_row_after_delimiter}
Sets the character that is interpreted as a delimiter after the field of the last column for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a delimiter after the field of the last column for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `'\n'`.
### format_custom_row_between_delimiter {#format_custom_row_between_delimiter}
Sets the character that is interpreted as a delimiter between the rows for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a delimiter between the rows for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `''`.
### format_custom_result_before_delimiter {#format_custom_result_before_delimiter}
Sets the character that is interpreted as a prefix before the result set for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a prefix before the result set for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `''`.
### format_custom_result_after_delimiter {#format_custom_result_after_delimiter}
Sets the character that is interpreted as a suffix after the result set for [CustomSeparated](../../interfaces/formats.md#format-customseparated) data format.
Sets the character that is interpreted as a suffix after the result set for [CustomSeparated](../../interfaces/formats.md/#format-customseparated) data format.
Default value: `''`.
@ -4727,12 +4727,12 @@ Field escaping rule.
Possible values:
- `'Escaped'` — Similarly to [TSV](../../interfaces/formats.md#tabseparated).
- `'Quoted'` — Similarly to [Values](../../interfaces/formats.md#data-format-values).
- `'CSV'` — Similarly to [CSV](../../interfaces/formats.md#csv).
- `'JSON'` — Similarly to [JSONEachRow](../../interfaces/formats.md#jsoneachrow).
- `'XML'` — Similarly to [XML](../../interfaces/formats.md#xml).
- `'Raw'` — Extracts subpatterns as a whole, no escaping rules, similarly to [TSVRaw](../../interfaces/formats.md#tabseparatedraw).
- `'Escaped'` — Similarly to [TSV](../../interfaces/formats.md/#tabseparated).
- `'Quoted'` — Similarly to [Values](../../interfaces/formats.md/#data-format-values).
- `'CSV'` — Similarly to [CSV](../../interfaces/formats.md/#csv).
- `'JSON'` — Similarly to [JSONEachRow](../../interfaces/formats.md/#jsoneachrow).
- `'XML'` — Similarly to [XML](../../interfaces/formats.md/#xml).
- `'Raw'` — Extracts subpatterns as a whole, no escaping rules, similarly to [TSVRaw](../../interfaces/formats.md/#tabseparatedraw).
Default value: `Raw`.
@ -4746,7 +4746,7 @@ Disabled by default.
### format_capn_proto_enum_comparising_mode {#format_capn_proto_enum_comparising_mode}
Determines how to map ClickHouse `Enum` data type and [CapnProto](../../interfaces/formats.md#capnproto) `Enum` data type from schema.
Determines how to map ClickHouse `Enum` data type and [CapnProto](../../interfaces/formats.md/#capnproto) `Enum` data type from schema.
Possible values:

18
docs/en/operations/storing-data.md
View File

@ -7,13 +7,13 @@ title: "External Disks for Storing Data"
Data, processed in ClickHouse, is usually stored in the local file system — on the same machine with the ClickHouse server. That requires large-capacity disks, which can be expensive enough. To avoid that you can store the data remotely — on [Amazon S3](https://aws.amazon.com/s3/) disks or in the Hadoop Distributed File System ([HDFS](https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html)).
To work with data stored on `Amazon S3` disks use [S3](../engines/table-engines/integrations/s3.md) table engine, and to work with data in the Hadoop Distributed File System — [HDFS](../engines/table-engines/integrations/hdfs.md) table engine.
To work with data stored on `Amazon S3` disks use [S3](/docs/en/engines/table-engines/integrations/s3.md) table engine, and to work with data in the Hadoop Distributed File System — [HDFS](/docs/en/engines/table-engines/integrations/hdfs.md) table engine.
To load data from a web server with static files use a disk with type [web](#storing-data-on-webserver).
## Configuring HDFS {#configuring-hdfs}
[MergeTree](../engines/table-engines/mergetree-family/mergetree.md) and [Log](../engines/table-engines/log-family/log.md) family table engines can store data to HDFS using a disk with type `HDFS`.
[MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) and [Log](/docs/en/engines/table-engines/log-family/log.md) family table engines can store data to HDFS using a disk with type `HDFS`.
Configuration markup:
@ -53,7 +53,7 @@ Optional parameters:
## Using Virtual File System for Data Encryption {#encrypted-virtual-file-system}
You can encrypt the data stored on [S3](../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-s3), or [HDFS](#configuring-hdfs) external disks, or on a local disk. To turn on the encryption mode, in the configuration file you must define a disk with the type `encrypted` and choose a disk on which the data will be saved. An `encrypted` disk ciphers all written files on the fly, and when you read files from an `encrypted` disk it deciphers them automatically. So you can work with an `encrypted` disk like with a normal one.
You can encrypt the data stored on [S3](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3), or [HDFS](#configuring-hdfs) external disks, or on a local disk. To turn on the encryption mode, in the configuration file you must define a disk with the type `encrypted` and choose a disk on which the data will be saved. An `encrypted` disk ciphers all written files on the fly, and when you read files from an `encrypted` disk it deciphers them automatically. So you can work with an `encrypted` disk like with a normal one.
Example of disk configuration:
@ -80,14 +80,14 @@ Required parameters:
- `type` — `encrypted`. Otherwise the encrypted disk is not created.
- `disk` — Type of disk for data storage.
- `key` — The key for encryption and decryption. Type: [Uint64](../sql-reference/data-types/int-uint.md). You can use `key_hex` parameter to encrypt in hexadecimal form.
- `key` — The key for encryption and decryption. Type: [Uint64](/docs/en/sql-reference/data-types/int-uint.md). You can use `key_hex` parameter to encrypt in hexadecimal form.
You can specify multiple keys using the `id` attribute (see example above).
Optional parameters:
- `path` — Path to the location on the disk where the data will be saved. If not specified, the data will be saved in the root directory.
- `current_key_id` — The key used for encryption. All the specified keys can be used for decryption, and you can always switch to another key while maintaining access to previously encrypted data.
- `algorithm` — [Algorithm](../sql-reference/statements/create/table.md#create-query-encryption-codecs) for encryption. Possible values: `AES_128_CTR`, `AES_192_CTR` or `AES_256_CTR`. Default value: `AES_128_CTR`. The key length depends on the algorithm: `AES_128_CTR` — 16 bytes, `AES_192_CTR` — 24 bytes, `AES_256_CTR` — 32 bytes.
- `algorithm` — [Algorithm](/docs/en/sql-reference/statements/create/table.md/#create-query-encryption-codecs) for encryption. Possible values: `AES_128_CTR`, `AES_192_CTR` or `AES_256_CTR`. Default value: `AES_128_CTR`. The key length depends on the algorithm: `AES_128_CTR` — 16 bytes, `AES_192_CTR` — 24 bytes, `AES_256_CTR` — 32 bytes.
Example of disk configuration:
@ -265,9 +265,9 @@ Cache profile events:
There is a tool `clickhouse-static-files-uploader`, which prepares a data directory for a given table (`SELECT data_paths FROM system.tables WHERE name = 'table_name'`). For each table you need, you get a directory of files. These files can be uploaded to, for example, a web server with static files. After this preparation, you can load this table into any ClickHouse server via `DiskWeb`.
This is a read-only disk. Its data is only read and never modified. A new table is loaded to this disk via `ATTACH TABLE` query (see example below). Local disk is not actually used, each `SELECT` query will result in a `http` request to fetch required data. All modification of the table data will result in an exception, i.e. the following types of queries are not allowed: [CREATE TABLE](../sql-reference/statements/create/table.md), [ALTER TABLE](../sql-reference/statements/alter/index.md), [RENAME TABLE](../sql-reference/statements/rename.md#misc_operations-rename_table), [DETACH TABLE](../sql-reference/statements/detach.md) and [TRUNCATE TABLE](../sql-reference/statements/truncate.md).
This is a read-only disk. Its data is only read and never modified. A new table is loaded to this disk via `ATTACH TABLE` query (see example below). Local disk is not actually used, each `SELECT` query will result in a `http` request to fetch required data. All modification of the table data will result in an exception, i.e. the following types of queries are not allowed: [CREATE TABLE](/docs/en/sql-reference/statements/create/table.md), [ALTER TABLE](/docs/en/sql-reference/statements/alter/index.md), [RENAME TABLE](/docs/en/sql-reference/statements/rename.md/#misc_operations-rename_table), [DETACH TABLE](/docs/en/sql-reference/statements/detach.md) and [TRUNCATE TABLE](/docs/en/sql-reference/statements/truncate.md).
Web server storage is supported only for the [MergeTree](../engines/table-engines/mergetree-family/mergetree.md) and [Log](../engines/table-engines/log-family/log.md) engine families. To access the data stored on a `web` disk, use the [storage_policy](../engines/table-engines/mergetree-family/mergetree.md#terms) setting when executing the query. For example, `ATTACH TABLE table_web UUID '{}' (id Int32) ENGINE = MergeTree() ORDER BY id SETTINGS storage_policy = 'web'`.
Web server storage is supported only for the [MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) and [Log](/docs/en/engines/table-engines/log-family/log.md) engine families. To access the data stored on a `web` disk, use the [storage_policy](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#terms) setting when executing the query. For example, `ATTACH TABLE table_web UUID '{}' (id Int32) ENGINE = MergeTree() ORDER BY id SETTINGS storage_policy = 'web'`.
A ready test case. You need to add this configuration to config:
@ -451,7 +451,7 @@ Optional parameters:
- `remote_fs_read_backoff_threashold` — The maximum wait time when trying to read data for remote disk. Default value: `10000` seconds.
- `remote_fs_read_backoff_max_tries` — The maximum number of attempts to read with backoff. Default value: `5`.
If a query fails with an exception `DB:Exception Unreachable URL`, then you can try to adjust the settings: [http_connection_timeout](../operations/settings/settings.md#http_connection_timeout), [http_receive_timeout](../operations/settings/settings.md#http_receive_timeout), [keep_alive_timeout](../operations/server-configuration-parameters/settings.md#keep-alive-timeout).
If a query fails with an exception `DB:Exception Unreachable URL`, then you can try to adjust the settings: [http_connection_timeout](/docs/en/operations/settings/settings.md/#http_connection_timeout), [http_receive_timeout](/docs/en/operations/settings/settings.md/#http_receive_timeout), [keep_alive_timeout](/docs/en/operations/server-configuration-parameters/settings.md/#keep-alive-timeout).
To get files for upload run:
`clickhouse static-files-disk-uploader --metadata-path <path> --output-dir <dir>` (`--metadata-path` can be found in query `SELECT data_paths FROM system.tables WHERE name = 'table_name'`).
@ -460,7 +460,7 @@ When loading files by `endpoint`, they must be loaded into `<endpoint>/store/` p
If URL is not reachable on disk load when the server is starting up tables, then all errors are caught. If in this case there were errors, tables can be reloaded (become visible) via `DETACH TABLE table_name` -> `ATTACH TABLE table_name`. If metadata was successfully loaded at server startup, then tables are available straight away.
Use [http_max_single_read_retries](../operations/settings/settings.md#http-max-single-read-retries) setting to limit the maximum number of retries during a single HTTP read.
Use [http_max_single_read_retries](/docs/en/operations/settings/settings.md/#http-max-single-read-retries) setting to limit the maximum number of retries during a single HTTP read.
## Zero-copy Replication (not ready for production) {#zero-copy}

4
docs/en/operations/system-tables/index.md
View File

@ -1,7 +1,8 @@
---
slug: /en/operations/system-tables/
sidebar_position: 52
sidebar_label: System Tables
sidebar_label: Overview
pagination_next: 'en/operations/system-tables/asynchronous_metric_log'
---
# System Tables
@ -72,4 +73,3 @@ If procfs is supported and enabled on the system, ClickHouse server collects the
- `OSReadBytes`
- `OSWriteBytes`
[Original article](https://clickhouse.com/docs/en/operations/system-tables/) <!--hide-->

34
docs/en/operations/system-tables/mutations.md
View File

@ -3,31 +3,31 @@ slug: /en/operations/system-tables/mutations
---
# mutations
The table contains information about [mutations](../../sql-reference/statements/alter/index.md#mutations) of [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) tables and their progress. Each mutation command is represented by a single row.
The table contains information about [mutations](/docs/en/sql-reference/statements/alter/index.md/#mutations) of [MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) tables and their progress. Each mutation command is represented by a single row.
Columns:
- `database` ([String](../../sql-reference/data-types/string.md)) — The name of the database to which the mutation was applied.
- `database` ([String](/docs/en/sql-reference/data-types/string.md)) — The name of the database to which the mutation was applied.
- `table` ([String](../../sql-reference/data-types/string.md)) — The name of the table to which the mutation was applied.
- `table` ([String](/docs/en/sql-reference/data-types/string.md)) — The name of the table to which the mutation was applied.
- `mutation_id` ([String](../../sql-reference/data-types/string.md)) — The ID of the mutation. For replicated tables these IDs correspond to znode names in the `<table_path_in_clickhouse_keeper>/mutations/` directory in ClickHouse Keeper. For non-replicated tables the IDs correspond to file names in the data directory of the table.
- `mutation_id` ([String](/docs/en/sql-reference/data-types/string.md)) — The ID of the mutation. For replicated tables these IDs correspond to znode names in the `<table_path_in_clickhouse_keeper>/mutations/` directory in ClickHouse Keeper. For non-replicated tables the IDs correspond to file names in the data directory of the table.
- `command` ([String](../../sql-reference/data-types/string.md)) — The mutation command string (the part of the query after `ALTER TABLE [db.]table`).
- `command` ([String](/docs/en/sql-reference/data-types/string.md)) — The mutation command string (the part of the query after `ALTER TABLE [db.]table`).
- `create_time` ([Datetime](../../sql-reference/data-types/datetime.md)) — Date and time when the mutation command was submitted for execution.
- `create_time` ([Datetime](/docs/en/sql-reference/data-types/datetime.md)) — Date and time when the mutation command was submitted for execution.
- `block_numbers.partition_id` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — For mutations of replicated tables, the array contains the partitions' IDs (one record for each partition). For mutations of non-replicated tables the array is empty.
- `block_numbers.partition_id` ([Array](/docs/en/sql-reference/data-types/array.md)([String](/docs/en/sql-reference/data-types/string.md))) — For mutations of replicated tables, the array contains the partitions' IDs (one record for each partition). For mutations of non-replicated tables the array is empty.
- `block_numbers.number` ([Array](../../sql-reference/data-types/array.md)([Int64](../../sql-reference/data-types/int-uint.md))) — For mutations of replicated tables, the array contains one record for each partition, with the block number that was acquired by the mutation. Only parts that contain blocks with numbers less than this number will be mutated in the partition.
- `block_numbers.number` ([Array](/docs/en/sql-reference/data-types/array.md)([Int64](/docs/en/sql-reference/data-types/int-uint.md))) — For mutations of replicated tables, the array contains one record for each partition, with the block number that was acquired by the mutation. Only parts that contain blocks with numbers less than this number will be mutated in the partition.
In non-replicated tables, block numbers in all partitions form a single sequence. This means that for mutations of non-replicated tables, the column will contain one record with a single block number acquired by the mutation.
- `parts_to_do_names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — An array of names of data parts that need to be mutated for the mutation to complete.
- `parts_to_do_names` ([Array](/docs/en/sql-reference/data-types/array.md)([String](/docs/en/sql-reference/data-types/string.md))) — An array of names of data parts that need to be mutated for the mutation to complete.
- `parts_to_do` ([Int64](../../sql-reference/data-types/int-uint.md)) — The number of data parts that need to be mutated for the mutation to complete.
- `parts_to_do` ([Int64](/docs/en/sql-reference/data-types/int-uint.md)) — The number of data parts that need to be mutated for the mutation to complete.
- `is_done` ([UInt8](../../sql-reference/data-types/int-uint.md)) — The flag whether the mutation is done or not. Possible values:
- `is_done` ([UInt8](/docs/en/sql-reference/data-types/int-uint.md)) — The flag whether the mutation is done or not. Possible values:
- `1` if the mutation is completed,
- `0` if the mutation is still in process.
@ -37,16 +37,16 @@ Even if `parts_to_do = 0` it is possible that a mutation of a replicated table i
If there were problems with mutating some data parts, the following columns contain additional information:
- `latest_failed_part` ([String](../../sql-reference/data-types/string.md)) — The name of the most recent part that could not be mutated.
- `latest_failed_part` ([String](/docs/en/sql-reference/data-types/string.md)) — The name of the most recent part that could not be mutated.
- `latest_fail_time` ([Datetime](../../sql-reference/data-types/datetime.md)) — The date and time of the most recent part mutation failure.
- `latest_fail_time` ([Datetime](/docs/en/sql-reference/data-types/datetime.md)) — The date and time of the most recent part mutation failure.
- `latest_fail_reason` ([String](../../sql-reference/data-types/string.md)) — The exception message that caused the most recent part mutation failure.
- `latest_fail_reason` ([String](/docs/en/sql-reference/data-types/string.md)) — The exception message that caused the most recent part mutation failure.
**See Also**
- [Mutations](../../sql-reference/statements/alter/index.md#mutations)
- [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) table engine
- [ReplicatedMergeTree](../../engines/table-engines/mergetree-family/replication.md) family
- [Mutations](/docs/en/sql-reference/statements/alter/index.md/#mutations)
- [MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) table engine
- [ReplicatedMergeTree](/docs/en/engines/table-engines/mergetree-family/replication.md) family
[Original article](https://clickhouse.com/docs/en/operations/system-tables/mutations) <!--hide-->

22
docs/en/operations/system-tables/parts.md
View File

@ -9,7 +9,7 @@ Each row describes one data part.
Columns:
- `partition` ([String](../../sql-reference/data-types/string.md)) – The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter/index.md#query_language_queries_alter) query.
- `partition` ([String](../../sql-reference/data-types/string.md)) – The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter/index.md/#query_language_queries_alter) query.
Formats:
@ -75,7 +75,7 @@ Columns:
- `primary_key_bytes_in_memory_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md)) – The amount of memory (in bytes) reserved for primary key values.
- `is_frozen` ([UInt8](../../sql-reference/data-types/int-uint.md)) – Flag that shows that a partition data backup exists. 1, the backup exists. 0, the backup does not exist. For more details, see [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md#alter_freeze-partition)
- `is_frozen` ([UInt8](../../sql-reference/data-types/int-uint.md)) – Flag that shows that a partition data backup exists. 1, the backup exists. 0, the backup does not exist. For more details, see [FREEZE PARTITION](../../sql-reference/statements/alter/partition.md/#alter_freeze-partition)
- `database` ([String](../../sql-reference/data-types/string.md)) – Name of the database.
@ -87,25 +87,25 @@ Columns:
- `disk_name` ([String](../../sql-reference/data-types/string.md)) – Name of a disk that stores the data part.
- `hash_of_all_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) of compressed files.
- `hash_of_all_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md/#hash_functions-siphash128) of compressed files.
- `hash_of_uncompressed_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) of uncompressed files (files with marks, index file etc.).
- `hash_of_uncompressed_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md/#hash_functions-siphash128) of uncompressed files (files with marks, index file etc.).
- `uncompressed_hash_of_compressed_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md#hash_functions-siphash128) of data in the compressed files as if they were uncompressed.
- `uncompressed_hash_of_compressed_files` ([String](../../sql-reference/data-types/string.md)) – [sipHash128](../../sql-reference/functions/hash-functions.md/#hash_functions-siphash128) of data in the compressed files as if they were uncompressed.
- `delete_ttl_info_min` ([DateTime](../../sql-reference/data-types/datetime.md)) — The minimum value of the date and time key for [TTL DELETE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `delete_ttl_info_min` ([DateTime](../../sql-reference/data-types/datetime.md)) — The minimum value of the date and time key for [TTL DELETE rule](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl).
- `delete_ttl_info_max` ([DateTime](../../sql-reference/data-types/datetime.md)) — The maximum value of the date and time key for [TTL DELETE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `delete_ttl_info_max` ([DateTime](../../sql-reference/data-types/datetime.md)) — The maximum value of the date and time key for [TTL DELETE rule](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl).
- `move_ttl_info.expression` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of expressions. Each expression defines a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `move_ttl_info.expression` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Array of expressions. Each expression defines a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl).
:::warning
The `move_ttl_info.expression` array is kept mostly for backward compatibility, now the simpliest way to check `TTL MOVE` rule is to use the `move_ttl_info.min` and `move_ttl_info.max` fields.
:::
- `move_ttl_info.min` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — Array of date and time values. Each element describes the minimum key value for a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `move_ttl_info.min` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — Array of date and time values. Each element describes the minimum key value for a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl).
- `move_ttl_info.max` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — Array of date and time values. Each element describes the maximum key value for a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl).
- `move_ttl_info.max` ([Array](../../sql-reference/data-types/array.md)([DateTime](../../sql-reference/data-types/datetime.md))) — Array of date and time values. Each element describes the maximum key value for a [TTL MOVE rule](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl).
- `bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) – Alias for `bytes_on_disk`.
@ -166,6 +166,6 @@ move_ttl_info.max: []
**See Also**
- [MergeTree family](../../engines/table-engines/mergetree-family/mergetree.md)
- [TTL for Columns and Tables](../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-ttl)
- [TTL for Columns and Tables](../../engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-ttl)
[Original article](https://clickhouse.com/docs/en/operations/system-tables/parts) <!--hide-->

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

@ -9,7 +9,7 @@ Each row describes one data part.
Columns:
- `partition` ([String](../../sql-reference/data-types/string.md)) — The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter/index.md#query_language_queries_alter) query.
- `partition` ([String](../../sql-reference/data-types/string.md)) — The partition name. To learn what a partition is, see the description of the [ALTER](../../sql-reference/statements/alter/index.md/#query_language_queries_alter) query.
Formats:

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

@ -24,6 +24,7 @@ Columns:
- `DOUBLE_SHA1_PASSWORD`
- `LDAP`
- `KERBEROS`
- `SSL_CERTIFICATE`
- `profiles` ([Array](../../sql-reference/data-types/array.md)([LowCardinality(String)](../../sql-reference/data-types/lowcardinality.md))) — The list of profiles set for all roles and/or users.
- `roles` ([Array](../../sql-reference/data-types/array.md)([LowCardinality(String)](../../sql-reference/data-types/lowcardinality.md))) — The list of roles to which the profile is applied.
- `settings` ([Array](../../sql-reference/data-types/array.md)([Tuple](../../sql-reference/data-types/tuple.md)([LowCardinality(String)](../../sql-reference/data-types/lowcardinality.md), [String](../../sql-reference/data-types/string.md)))) — Settings that were changed when the client logged in/out.

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

@ -12,7 +12,7 @@ Columns:
- `storage` ([String](../../sql-reference/data-types/string.md)) — Path to the storage of users. Configured in the `access_control_path` parameter.
- `auth_type` ([Enum8](../../sql-reference/data-types/enum.md)('no_password' = 0,'plaintext_password' = 1, 'sha256_password' = 2, 'double_sha1_password' = 3)) — Shows the authentication type. There are multiple ways of user identification: with no password, with plain text password, with [SHA256](https://ru.wikipedia.org/wiki/SHA-2)-encoded password or with [double SHA-1](https://ru.wikipedia.org/wiki/SHA-1)-encoded password.
- `auth_type` ([Enum8](../../sql-reference/data-types/enum.md)('no_password' = 0,'plaintext_password' = 1, 'sha256_password' = 2, 'double_sha1_password' = 3, 'ldap' = 4, 'kerberos' = 5, 'ssl_certificate' = 6)) — Shows the authentication type. There are multiple ways of user identification: with no password, with plain text password, with [SHA256](https://ru.wikipedia.org/wiki/SHA-2)-encoded password or with [double SHA-1](https://ru.wikipedia.org/wiki/SHA-1)-encoded password.
- `auth_params` ([String](../../sql-reference/data-types/string.md)) — Authentication parameters in the JSON format depending on the `auth_type`.

58
docs/en/operations/utilities/clickhouse-benchmark.md
View File

@ -109,56 +109,38 @@ In the report you can find:
`clickhouse-benchmark` can compare performances for two running ClickHouse servers.
To use the comparison mode, specify endpoints of both servers by two pairs of `--host`, `--port` keys. Keys matched together by position in arguments list, the first `--host` is matched with the first `--port` and so on. `clickhouse-benchmark` establishes connections to both servers, then sends queries. Each query addressed to a randomly selected server. The results are shown for each server separately.
To use the comparison mode, specify endpoints of both servers by two pairs of `--host`, `--port` keys. Keys matched together by position in arguments list, the first `--host` is matched with the first `--port` and so on. `clickhouse-benchmark` establishes connections to both servers, then sends queries. Each query addressed to a randomly selected server. The results are shown in a table.
## Example {#clickhouse-benchmark-example}
``` bash
$ echo "SELECT * FROM system.numbers LIMIT 10000000 OFFSET 10000000" | clickhouse-benchmark -i 10
$ echo "SELECT * FROM system.numbers LIMIT 10000000 OFFSET 10000000" | clickhouse-benchmark --host=localhost --port=9001 --host=localhost --port=9000 -i 10
```
``` text
Loaded 1 queries.
Queries executed: 6.
Queries executed: 5.
localhost:9000, queries 6, QPS: 6.153, RPS: 123398340.957, MiB/s: 941.455, result RPS: 61532982.200, result MiB/s: 469.459.
localhost:9001, queries 2, QPS: 3.764, RPS: 75446929.370, MiB/s: 575.614, result RPS: 37639659.982, result MiB/s: 287.168.
localhost:9000, queries 3, QPS: 3.815, RPS: 76466659.385, MiB/s: 583.394, result RPS: 38148392.297, result MiB/s: 291.049.
0.000% 0.159 sec.
10.000% 0.159 sec.
20.000% 0.159 sec.
30.000% 0.160 sec.
40.000% 0.160 sec.
50.000% 0.162 sec.
60.000% 0.164 sec.
70.000% 0.165 sec.
80.000% 0.166 sec.
90.000% 0.166 sec.
95.000% 0.167 sec.
99.000% 0.167 sec.
99.900% 0.167 sec.
99.990% 0.167 sec.
0.000% 0.258 sec. 0.250 sec.
10.000% 0.258 sec. 0.250 sec.
20.000% 0.258 sec. 0.250 sec.
30.000% 0.258 sec. 0.267 sec.
40.000% 0.258 sec. 0.267 sec.
50.000% 0.273 sec. 0.267 sec.
60.000% 0.273 sec. 0.267 sec.
70.000% 0.273 sec. 0.267 sec.
80.000% 0.273 sec. 0.269 sec.
90.000% 0.273 sec. 0.269 sec.
95.000% 0.273 sec. 0.269 sec.
99.000% 0.273 sec. 0.269 sec.
99.900% 0.273 sec. 0.269 sec.
99.990% 0.273 sec. 0.269 sec.
Queries executed: 10.
localhost:9000, queries 10, QPS: 6.082, RPS: 121959604.568, MiB/s: 930.478, result RPS: 60815551.642, result MiB/s: 463.986.
0.000% 0.159 sec.
10.000% 0.159 sec.
20.000% 0.160 sec.
30.000% 0.163 sec.
40.000% 0.164 sec.
50.000% 0.165 sec.
60.000% 0.166 sec.
70.000% 0.166 sec.
80.000% 0.167 sec.
90.000% 0.167 sec.
95.000% 0.170 sec.
99.000% 0.172 sec.
99.900% 0.172 sec.
99.990% 0.172 sec.
No difference proven at 99.5% confidence
```
[Original article](https://clickhouse.com/docs/en/operations/utilities/clickhouse-benchmark.md) <!--hide-->

5
docs/en/operations/utilities/index.md
View File

@ -1,10 +1,11 @@
---
slug: /en/operations/utilities/
sidebar_position: 56
sidebar_label: Utilities
sidebar_label: Overview
pagination_next: 'en/operations/utilities/clickhouse-copier'
---
# ClickHouse Utility
# ClickHouse Utilities
- [clickhouse-local](../../operations/utilities/clickhouse-local.md) — Allows running SQL queries on data without starting the ClickHouse server, similar to how `awk` does this.
- [clickhouse-copier](../../operations/utilities/clickhouse-copier.md) — Copies (and reshards) data from one cluster to another cluster.

22
docs/en/sql-reference/statements/alter/column.md
View File

@ -35,11 +35,11 @@ These actions are described in detail below.
ADD COLUMN [IF NOT EXISTS] name [type] [default_expr] [codec] [AFTER name_after | FIRST]
```
Adds a new column to the table with the specified `name`, `type`, [`codec`](../create/table.md#codecs) and `default_expr` (see the section [Default expressions](../../../sql-reference/statements/create/table.md#create-default-values)).
Adds a new column to the table with the specified `name`, `type`, [`codec`](../create/table.md/#codecs) and `default_expr` (see the section [Default expressions](/docs/en/sql-reference/statements/create/table.md/#create-default-values)).
If the `IF NOT EXISTS` clause is included, the query won’t return an error if the column already exists. If you specify `AFTER name_after` (the name of another column), the column is added after the specified one in the list of table columns. If you want to add a column to the beginning of the table use the `FIRST` clause. Otherwise, the column is added to the end of the table. For a chain of actions, `name_after` can be the name of a column that is added in one of the previous actions.
Adding a column just changes the table structure, without performing any actions with data. The data does not appear on the disk after `ALTER`. If the data is missing for a column when reading from the table, it is filled in with default values (by performing the default expression if there is one, or using zeros or empty strings). The column appears on the disk after merging data parts (see [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md)).
Adding a column just changes the table structure, without performing any actions with data. The data does not appear on the disk after `ALTER`. If the data is missing for a column when reading from the table, it is filled in with default values (by performing the default expression if there is one, or using zeros or empty strings). The column appears on the disk after merging data parts (see [MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md)).
This approach allows us to complete the `ALTER` query instantly, without increasing the volume of old data.
@ -76,7 +76,7 @@ Deletes the column with the name `name`. If the `IF EXISTS` clause is specified,
Deletes data from the file system. Since this deletes entire files, the query is completed almost instantly.
:::warning
You can’t delete a column if it is referenced by [materialized view](../../../sql-reference/statements/create/view.md#materialized). Otherwise, it returns an error.
You can’t delete a column if it is referenced by [materialized view](/docs/en/sql-reference/statements/create/view.md/#materialized). Otherwise, it returns an error.
:::
Example:
@ -107,7 +107,7 @@ ALTER TABLE visits RENAME COLUMN webBrowser TO browser
CLEAR COLUMN [IF EXISTS] name IN PARTITION partition_name
```
Resets all data in a column for a specified partition. Read more about setting the partition name in the section [How to set the partition expression](partition.md#how-to-set-partition-expression).
Resets all data in a column for a specified partition. Read more about setting the partition name in the section [How to set the partition expression](partition.md/#how-to-set-partition-expression).
If the `IF EXISTS` clause is specified, the query won’t return an error if the column does not exist.
@ -127,7 +127,7 @@ Adds a comment to the column. If the `IF EXISTS` clause is specified, the query
Each column can have one comment. If a comment already exists for the column, a new comment overwrites the previous comment.
Comments are stored in the `comment_expression` column returned by the [DESCRIBE TABLE](../../../sql-reference/statements/describe-table.md) query.
Comments are stored in the `comment_expression` column returned by the [DESCRIBE TABLE](/docs/en/sql-reference/statements/describe-table.md) query.
Example:
@ -152,15 +152,15 @@ This query changes the `name` column properties:
- TTL
For examples of columns compression CODECS modifying, see [Column Compression Codecs](../create/table.md#codecs).
For examples of columns compression CODECS modifying, see [Column Compression Codecs](../create/table.md/#codecs).
For examples of columns TTL modifying, see [Column TTL](../../../engines/table-engines/mergetree-family/mergetree.md#mergetree-column-ttl).
For examples of columns TTL modifying, see [Column TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-column-ttl).
If the `IF EXISTS` clause is specified, the query won’t return an error if the column does not exist.
The query also can change the order of the columns using `FIRST | AFTER` clause, see [ADD COLUMN](#alter_add-column) description.
When changing the type, values are converted as if the [toType](../../../sql-reference/functions/type-conversion-functions.md) functions were applied to them. If only the default expression is changed, the query does not do anything complex, and is completed almost instantly.
When changing the type, values are converted as if the [toType](/docs/en/sql-reference/functions/type-conversion-functions.md) functions were applied to them. If only the default expression is changed, the query does not do anything complex, and is completed almost instantly.
Example:
@ -246,7 +246,7 @@ SELECT groupArray(x), groupArray(s) FROM tmp;
**See Also**
- [MATERIALIZED](../../statements/create/table.md#materialized).
- [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized).
## Limitations
@ -254,8 +254,8 @@ The `ALTER` query lets you create and delete separate elements (columns) in nest
There is no support for deleting columns in the primary key or the sampling key (columns that are used in the `ENGINE` expression). Changing the type for columns that are included in the primary key is only possible if this change does not cause the data to be modified (for example, you are allowed to add values to an Enum or to change a type from `DateTime` to `UInt32`).
If the `ALTER` query is not sufficient to make the table changes you need, you can create a new table, copy the data to it using the [INSERT SELECT](../../../sql-reference/statements/insert-into.md#insert_query_insert-select) query, then switch the tables using the [RENAME](../../../sql-reference/statements/rename.md#rename-table) query and delete the old table. You can use the [clickhouse-copier](../../../operations/utilities/clickhouse-copier.md) as an alternative to the `INSERT SELECT` query.
If the `ALTER` query is not sufficient to make the table changes you need, you can create a new table, copy the data to it using the [INSERT SELECT](/docs/en/sql-reference/statements/insert-into.md/#insert_query_insert-select) query, then switch the tables using the [RENAME](/docs/en/sql-reference/statements/rename.md/#rename-table) query and delete the old table. You can use the [clickhouse-copier](/docs/en/operations/utilities/clickhouse-copier.md) as an alternative to the `INSERT SELECT` query.
The `ALTER` query blocks all reads and writes for the table. In other words, if a long `SELECT` is running at the time of the `ALTER` query, the `ALTER` query will wait for it to complete. At the same time, all new queries to the same table will wait while this `ALTER` is running.
For tables that do not store data themselves (such as [Merge](../../../sql-reference/statements/alter/index.md) and [Distributed](../../../sql-reference/statements/alter/index.md)), `ALTER` just changes the table structure, and does not change the structure of subordinate tables. For example, when running ALTER for a `Distributed` table, you will also need to run `ALTER` for the tables on all remote servers.
For tables that do not store data themselves (such as [Merge](/docs/en/sql-reference/statements/alter/index.md) and [Distributed](/docs/en/sql-reference/statements/alter/index.md)), `ALTER` just changes the table structure, and does not change the structure of subordinate tables. For example, when running ALTER for a `Distributed` table, you will also need to run `ALTER` for the tables on all remote servers.

12
docs/en/sql-reference/statements/alter/delete.md
View File

@ -10,21 +10,21 @@ sidebar_label: DELETE
ALTER TABLE [db.]table [ON CLUSTER cluster] DELETE WHERE filter_expr
```
Deletes data matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
Deletes data matching the specified filtering expression. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
:::note
The `ALTER TABLE` prefix makes this syntax different from most other systems supporting SQL. It is intended to signify that unlike similar queries in OLTP databases this is a heavy operation not designed for frequent use. `ALTER TABLE` is considered a heavyweight operation that requires the underlying data to be merged before it is deleted. For MergeTree tables, consider using the [`DELETE FROM` query](../delete.md), which performs a lightweight delete and can be considerably faster.
The `ALTER TABLE` prefix makes this syntax different from most other systems supporting SQL. It is intended to signify that unlike similar queries in OLTP databases this is a heavy operation not designed for frequent use. `ALTER TABLE` is considered a heavyweight operation that requires the underlying data to be merged before it is deleted. For MergeTree tables, consider using the [`DELETE FROM` query](/docs/en/sql-reference/statements/delete.md), which performs a lightweight delete and can be considerably faster.
:::
The `filter_expr` must be of type `UInt8`. The query deletes rows in the table for which this expression takes a non-zero value.
One query can contain several commands separated by commas.
The synchronicity of the query processing is defined by the [mutations_sync](../../../operations/settings/settings.md#mutations_sync) setting. By default, it is asynchronous.
The synchronicity of the query processing is defined by the [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting. By default, it is asynchronous.
**See also**
- [Mutations](../../../sql-reference/statements/alter/index.md#mutations)
- [Synchronicity of ALTER Queries](../../../sql-reference/statements/alter/index.md#synchronicity-of-alter-queries)
- [mutations_sync](../../../operations/settings/settings.md#mutations_sync) setting
- [Mutations](/docs/en/sql-reference/statements/alter/index.md/#mutations)
- [Synchronicity of ALTER Queries](/docs/en/sql-reference/statements/alter/index.md/#synchronicity-of-alter-queries)
- [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting

44
docs/en/sql-reference/statements/alter/index.md
View File

@ -8,43 +8,43 @@ sidebar_label: ALTER
Most `ALTER TABLE` queries modify table settings or data:
- [COLUMN](../../../sql-reference/statements/alter/column.md)
- [PARTITION](../../../sql-reference/statements/alter/partition.md)
- [DELETE](../../../sql-reference/statements/alter/delete.md)
- [UPDATE](../../../sql-reference/statements/alter/update.md)
- [ORDER BY](../../../sql-reference/statements/alter/order-by.md)
- [INDEX](../../../sql-reference/statements/alter/index/index.md)
- [CONSTRAINT](../../../sql-reference/statements/alter/constraint.md)
- [TTL](../../../sql-reference/statements/alter/ttl.md)
- [COLUMN](/docs/en/sql-reference/statements/alter/column.md)
- [PARTITION](/docs/en/sql-reference/statements/alter/partition.md)
- [DELETE](/docs/en/sql-reference/statements/alter/delete.md)
- [UPDATE](/docs/en/sql-reference/statements/alter/update.md)
- [ORDER BY](/docs/en/sql-reference/statements/alter/order-by.md)
- [INDEX](/docs/en/sql-reference/statements/alter/skipping-index.md)
- [CONSTRAINT](/docs/en/sql-reference/statements/alter/constraint.md)
- [TTL](/docs/en/sql-reference/statements/alter/ttl.md)
:::note
Most `ALTER TABLE` queries are supported only for [\*MergeTree](../../../engines/table-engines/mergetree-family/index.md) tables, as well as [Merge](../../../engines/table-engines/special/merge.md) and [Distributed](../../../engines/table-engines/special/distributed.md).
Most `ALTER TABLE` queries are supported only for [\*MergeTree](/docs/en/engines/table-engines/mergetree-family/index.md) tables, as well as [Merge](/docs/en/engines/table-engines/special/merge.md) and [Distributed](/docs/en/engines/table-engines/special/distributed.md).
:::
These `ALTER` statements manipulate views:
- [ALTER TABLE ... MODIFY QUERY](../../../sql-reference/statements/alter/view.md) — Modifies a [Materialized view](../create/view.md#materialized) structure.
- [ALTER LIVE VIEW](../../../sql-reference/statements/alter/view.md#alter-live-view) — Refreshes a [Live view](../create/view.md#live-view).
- [ALTER TABLE ... MODIFY QUERY](/docs/en/sql-reference/statements/alter/view.md) — Modifies a [Materialized view](/docs/en/sql-reference/statements/create/view.md/#materialized) structure.
- [ALTER LIVE VIEW](/docs/en/sql-reference/statements/alter/view.md/#alter-live-view) — Refreshes a [Live view](/docs/en/sql-reference/statements/create/view.md/#live-view).
These `ALTER` statements modify entities related to role-based access control:
- [USER](../../../sql-reference/statements/alter/user.md)
- [ROLE](../../../sql-reference/statements/alter/role.md)
- [QUOTA](../../../sql-reference/statements/alter/quota.md)
- [ROW POLICY](../../../sql-reference/statements/alter/row-policy.md)
- [SETTINGS PROFILE](../../../sql-reference/statements/alter/settings-profile.md)
- [USER](/docs/en/sql-reference/statements/alter/user.md)
- [ROLE](/docs/en/sql-reference/statements/alter/role.md)
- [QUOTA](/docs/en/sql-reference/statements/alter/quota.md)
- [ROW POLICY](/docs/en/sql-reference/statements/alter/row-policy.md)
- [SETTINGS PROFILE](/docs/en/sql-reference/statements/alter/settings-profile.md)
[ALTER TABLE ... MODIFY COMMENT](../../../sql-reference/statements/alter/comment.md) statement adds, modifies, or removes comments to the table, regardless if it was set before or not.
[ALTER TABLE ... MODIFY COMMENT](/docs/en/sql-reference/statements/alter/comment.md) statement adds, modifies, or removes comments to the table, regardless if it was set before or not.
## Mutations
`ALTER` queries that are intended to manipulate table data are implemented with a mechanism called “mutations”, most notably [ALTER TABLE … DELETE](../../../sql-reference/statements/alter/delete.md) and [ALTER TABLE … UPDATE](../../../sql-reference/statements/alter/update.md). They are asynchronous background processes similar to merges in [MergeTree](../../../engines/table-engines/mergetree-family/index.md) tables that to produce new “mutated” versions of parts.
`ALTER` queries that are intended to manipulate table data are implemented with a mechanism called “mutations”, most notably [ALTER TABLE … DELETE](/docs/en/sql-reference/statements/alter/delete.md) and [ALTER TABLE … UPDATE](/docs/en/sql-reference/statements/alter/update.md). They are asynchronous background processes similar to merges in [MergeTree](/docs/en/engines/table-engines/mergetree-family/index.md) tables that to produce new “mutated” versions of parts.
For `*MergeTree` tables mutations execute by **rewriting whole data parts**. There is no atomicity - parts are substituted for mutated parts as soon as they are ready and a `SELECT` query that started executing during a mutation will see data from parts that have already been mutated along with data from parts that have not been mutated yet.
Mutations are totally ordered by their creation order and are applied to each part in that order. Mutations are also partially ordered with `INSERT INTO` queries: data that was inserted into the table before the mutation was submitted will be mutated and data that was inserted after that will not be mutated. Note that mutations do not block inserts in any way.
A mutation query returns immediately after the mutation entry is added (in case of replicated tables to ZooKeeper, for non-replicated tables - to the filesystem). The mutation itself executes asynchronously using the system profile settings. To track the progress of mutations you can use the [`system.mutations`](../../../operations/system-tables/mutations.md#system_tables-mutations) table. A mutation that was successfully submitted will continue to execute even if ClickHouse servers are restarted. There is no way to roll back the mutation once it is submitted, but if the mutation is stuck for some reason it can be cancelled with the [`KILL MUTATION`](../../../sql-reference/statements/kill.md#kill-mutation) query.
A mutation query returns immediately after the mutation entry is added (in case of replicated tables to ZooKeeper, for non-replicated tables - to the filesystem). The mutation itself executes asynchronously using the system profile settings. To track the progress of mutations you can use the [`system.mutations`](/docs/en/operations/system-tables/mutations.md/#system_tables-mutations) table. A mutation that was successfully submitted will continue to execute even if ClickHouse servers are restarted. There is no way to roll back the mutation once it is submitted, but if the mutation is stuck for some reason it can be cancelled with the [`KILL MUTATION`](/docs/en/sql-reference/statements/kill.md/#kill-mutation) query.
Entries for finished mutations are not deleted right away (the number of preserved entries is determined by the `finished_mutations_to_keep` storage engine parameter). Older mutation entries are deleted.
@ -52,12 +52,12 @@ Entries for finished mutations are not deleted right away (the number of preserv
For non-replicated tables, all `ALTER` queries are performed synchronously. For replicated tables, the query just adds instructions for the appropriate actions to `ZooKeeper`, and the actions themselves are performed as soon as possible. However, the query can wait for these actions to be completed on all the replicas.
For all `ALTER` queries, you can use the [replication_alter_partitions_sync](../../../operations/settings/settings.md#replication-alter-partitions-sync) setting to set up waiting.
For all `ALTER` queries, you can use the [replication_alter_partitions_sync](/docs/en/operations/settings/settings.md/#replication-alter-partitions-sync) setting to set up waiting.
You can specify how long (in seconds) to wait for inactive replicas to execute all `ALTER` queries with the [replication_wait_for_inactive_replica_timeout](../../../operations/settings/settings.md#replication-wait-for-inactive-replica-timeout) setting.
You can specify how long (in seconds) to wait for inactive replicas to execute all `ALTER` queries with the [replication_wait_for_inactive_replica_timeout](/docs/en/operations/settings/settings.md/#replication-wait-for-inactive-replica-timeout) setting.
:::note
For all `ALTER` queries, if `replication_alter_partitions_sync = 2` and some replicas are not active for more than the time, specified in the `replication_wait_for_inactive_replica_timeout` setting, then an exception `UNFINISHED` is thrown.
:::
For `ALTER TABLE ... UPDATE|DELETE` queries the synchronicity is defined by the [mutations_sync](../../../operations/settings/settings.md#mutations_sync) setting.
For `ALTER TABLE ... UPDATE|DELETE` queries the synchronicity is defined by the [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting.

22
docs/en/sql-reference/statements/alter/partition.md
View File

@ -5,7 +5,7 @@ sidebar_label: PARTITION
title: "Manipulating Partitions and Parts"
---
The following operations with [partitions](../../../engines/table-engines/mergetree-family/custom-partitioning-key.md) are available:
The following operations with [partitions](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md) are available:
- [DETACH PARTITION\|PART](#detach-partitionpart) — Moves a partition or part to the `detached` directory and forget it.
- [DROP PARTITION\|PART](#drop-partitionpart) — Deletes a partition or part.
@ -43,7 +43,7 @@ Read about setting the partition expression in a section [How to set the partiti
After the query is executed, you can do whatever you want with the data in the `detached` directory — delete it from the file system, or just leave it.
This query is replicated – it moves the data to the `detached` directory on all replicas. Note that you can execute this query only on a leader replica. To find out if a replica is a leader, perform the `SELECT` query to the [system.replicas](../../../operations/system-tables/replicas.md#system_tables-replicas) table. Alternatively, it is easier to make a `DETACH` query on all replicas - all the replicas throw an exception, except the leader replicas (as multiple leaders are allowed).
This query is replicated – it moves the data to the `detached` directory on all replicas. Note that you can execute this query only on a leader replica. To find out if a replica is a leader, perform the `SELECT` query to the [system.replicas](/docs/en/operations/system-tables/replicas.md/#system_tables-replicas) table. Alternatively, it is easier to make a `DETACH` query on all replicas - all the replicas throw an exception, except the leader replicas (as multiple leaders are allowed).
## DROP PARTITION\|PART
@ -175,7 +175,7 @@ At the time of execution, for a data snapshot, the query creates hardlinks to a
- if the `WITH NAME` parameter is specified, then the value of the `'backup_name'` parameter is used instead of the incremental number.
:::note
If you use [a set of disks for data storage in a table](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes), the `shadow/N` directory appears on every disk, storing data parts that matched by the `PARTITION` expression.
If you use [a set of disks for data storage in a table](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-multiple-volumes), the `shadow/N` directory appears on every disk, storing data parts that matched by the `PARTITION` expression.
:::
The same structure of directories is created inside the backup as inside `/var/lib/clickhouse/`. The query performs `chmod` for all files, forbidding writing into them.
@ -249,7 +249,7 @@ Although the query is called `ALTER TABLE`, it does not change the table structu
## MOVE PARTITION\|PART
Moves partitions or data parts to another volume or disk for `MergeTree`-engine tables. See [Using Multiple Block Devices for Data Storage](../../../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes).
Moves partitions or data parts to another volume or disk for `MergeTree`-engine tables. See [Using Multiple Block Devices for Data Storage](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-multiple-volumes).
``` sql
ALTER TABLE table_name [ON CLUSTER cluster] MOVE PARTITION|PART partition_expr TO DISK|VOLUME 'disk_name'
@ -270,7 +270,7 @@ ALTER TABLE hits MOVE PARTITION '2019-09-01' TO DISK 'fast_ssd'
## UPDATE IN PARTITION
Manipulates data in the specifies partition matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
Manipulates data in the specifies partition matching the specified filtering expression. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
Syntax:
@ -286,11 +286,11 @@ ALTER TABLE mt UPDATE x = x + 1 IN PARTITION 2 WHERE p = 2;
### See Also
- [UPDATE](../../../sql-reference/statements/alter/update.md#alter-table-update-statements)
- [UPDATE](/docs/en/sql-reference/statements/alter/update.md/#alter-table-update-statements)
## DELETE IN PARTITION
Deletes data in the specifies partition matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
Deletes data in the specifies partition matching the specified filtering expression. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
Syntax:
@ -306,7 +306,7 @@ ALTER TABLE mt DELETE IN PARTITION 2 WHERE p = 2;
### See Also
- [DELETE](../../../sql-reference/statements/alter/delete.md#alter-mutations)
- [DELETE](/docs/en/sql-reference/statements/alter/delete.md/#alter-mutations)
## How to Set Partition Expression
@ -315,16 +315,16 @@ You can specify the partition expression in `ALTER ... PARTITION` queries in dif
- As a value from the `partition` column of the `system.parts` table. For example, `ALTER TABLE visits DETACH PARTITION 201901`.
- As a tuple of expressions or constants that matches (in types) the table partitioning keys tuple. In the case of a single element partitioning key, the expression should be wrapped in the `tuple (...)` function. For example, `ALTER TABLE visits DETACH PARTITION tuple(toYYYYMM(toDate('2019-01-25')))`.
- Using the partition ID. Partition ID is a string identifier of the partition (human-readable, if possible) that is used as the names of partitions in the file system and in ZooKeeper. The partition ID must be specified in the `PARTITION ID` clause, in a single quotes. For example, `ALTER TABLE visits DETACH PARTITION ID '201901'`.
- In the [ALTER ATTACH PART](#alter_attach-partition) and [DROP DETACHED PART](#alter_drop-detached) query, to specify the name of a part, use string literal with a value from the `name` column of the [system.detached_parts](../../../operations/system-tables/detached_parts.md#system_tables-detached_parts) table. For example, `ALTER TABLE visits ATTACH PART '201901_1_1_0'`.
- In the [ALTER ATTACH PART](#alter_attach-partition) and [DROP DETACHED PART](#alter_drop-detached) query, to specify the name of a part, use string literal with a value from the `name` column of the [system.detached_parts](/docs/en/operations/system-tables/detached_parts.md/#system_tables-detached_parts) table. For example, `ALTER TABLE visits ATTACH PART '201901_1_1_0'`.
Usage of quotes when specifying the partition depends on the type of partition expression. For example, for the `String` type, you have to specify its name in quotes (`'`). For the `Date` and `Int*` types no quotes are needed.
All the rules above are also true for the [OPTIMIZE](../../../sql-reference/statements/optimize.md) query. If you need to specify the only partition when optimizing a non-partitioned table, set the expression `PARTITION tuple()`. For example:
All the rules above are also true for the [OPTIMIZE](/docs/en/sql-reference/statements/optimize.md) query. If you need to specify the only partition when optimizing a non-partitioned table, set the expression `PARTITION tuple()`. For example:
``` sql
OPTIMIZE TABLE table_not_partitioned PARTITION tuple() FINAL;
```
`IN PARTITION` specifies the partition to which the [UPDATE](../../../sql-reference/statements/alter/update.md#alter-table-update-statements) or [DELETE](../../../sql-reference/statements/alter/delete.md#alter-mutations) expressions are applied as a result of the `ALTER TABLE` query. New parts are created only from the specified partition. In this way, `IN PARTITION` helps to reduce the load when the table is divided into many partitions, and you only need to update the data point-by-point.
`IN PARTITION` specifies the partition to which the [UPDATE](/docs/en/sql-reference/statements/alter/update.md/#alter-table-update-statements) or [DELETE](/docs/en/sql-reference/statements/alter/delete.md/#alter-mutations) expressions are applied as a result of the `ALTER TABLE` query. New parts are created only from the specified partition. In this way, `IN PARTITION` helps to reduce the load when the table is divided into many partitions, and you only need to update the data point-by-point.
The examples of `ALTER ... PARTITION` queries are demonstrated in the tests [`00502_custom_partitioning_local`](https://github.com/ClickHouse/ClickHouse/blob/master/tests/queries/0_stateless/00502_custom_partitioning_local.sql) and [`00502_custom_partitioning_replicated_zookeeper`](https://github.com/ClickHouse/ClickHouse/blob/master/tests/queries/0_stateless/00502_custom_partitioning_replicated_zookeeper.sql).

10
docs/en/sql-reference/statements/alter/projection.md
View File

@ -5,7 +5,7 @@ sidebar_label: PROJECTION
title: "Manipulating Projections"
---
The following operations with [projections](../../../engines/table-engines/mergetree-family/mergetree.md#projections) are available:
The following operations with [projections](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#projections) are available:
## ADD PROJECTION
@ -13,15 +13,15 @@ The following operations with [projections](../../../engines/table-engines/merge
## DROP PROJECTION
`ALTER TABLE [db].name DROP PROJECTION name` - Removes projection description from tables metadata and deletes projection files from disk. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
`ALTER TABLE [db].name DROP PROJECTION name` - Removes projection description from tables metadata and deletes projection files from disk. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
## MATERIALIZE PROJECTION
`ALTER TABLE [db.]table MATERIALIZE PROJECTION name IN PARTITION partition_name` - The query rebuilds the projection `name` in the partition `partition_name`. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
`ALTER TABLE [db.]table MATERIALIZE PROJECTION name IN PARTITION partition_name` - The query rebuilds the projection `name` in the partition `partition_name`. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
## CLEAR PROJECTION
`ALTER TABLE [db.]table CLEAR PROJECTION name IN PARTITION partition_name` - Deletes projection files from disk without removing description. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
`ALTER TABLE [db.]table CLEAR PROJECTION name IN PARTITION partition_name` - Deletes projection files from disk without removing description. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
The commands `ADD`, `DROP` and `CLEAR` are lightweight in a sense that they only change metadata or remove files.
@ -29,5 +29,5 @@ The commands `ADD`, `DROP` and `CLEAR` are lightweight in a sense that they only
Also, they are replicated, syncing projections metadata via ClickHouse Keeper or ZooKeeper.
:::note
Projection manipulation is supported only for tables with [`*MergeTree`](../../../engines/table-engines/mergetree-family/mergetree.md) engine (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) variants).
Projection manipulation is supported only for tables with [`*MergeTree`](/docs/en/engines/table-engines/mergetree-family/mergetree.md) engine (including [replicated](/docs/en/engines/table-engines/mergetree-family/replication.md) variants).
:::

7
docs/en/sql-reference/statements/alter/index/index.md → docs/en/sql-reference/statements/alter/skipping-index.md
View File

@ -1,5 +1,6 @@
---
slug: /en/sql-reference/statements/alter/index
slug: /en/sql-reference/statements/alter/skipping-index
toc_hidden_folder: true
sidebar_position: 42
sidebar_label: INDEX
@ -13,12 +14,12 @@ The following operations are available:
- `ALTER TABLE [db].table_name [ON CLUSTER cluster] DROP INDEX name` - Removes index description from tables metadata and deletes index files from disk.
- `ALTER TABLE [db.]table_name [ON CLUSTER cluster] MATERIALIZE INDEX name [IN PARTITION partition_name]` - Rebuilds the secondary index `name` for the specified `partition_name`. Implemented as a [mutation](../../../../sql-reference/statements/alter/index.md#mutations). If `IN PARTITION` part is omitted then it rebuilds the index for the whole table data.
- `ALTER TABLE [db.]table_name [ON CLUSTER cluster] MATERIALIZE INDEX name [IN PARTITION partition_name]` - Rebuilds the secondary index `name` for the specified `partition_name`. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations). If `IN PARTITION` part is omitted then it rebuilds the index for the whole table data.
The first two commands are lightweight in a sense that they only change metadata or remove files.
Also, they are replicated, syncing indices metadata via ZooKeeper.
:::note
Index manipulation is supported only for tables with [`*MergeTree`](../../../../engines/table-engines/mergetree-family/mergetree.md) engine (including [replicated](../../../../engines/table-engines/mergetree-family/replication.md) variants).
Index manipulation is supported only for tables with [`*MergeTree`](/docs/en/engines/table-engines/mergetree-family/mergetree.md) engine (including [replicated](/docs/en/engines/table-engines/mergetree-family/replication.md) variants).
:::

10
docs/en/sql-reference/statements/alter/update.md
View File

@ -10,7 +10,7 @@ sidebar_label: UPDATE
ALTER TABLE [db.]table [ON CLUSTER cluster] UPDATE column1 = expr1 [, ...] WHERE filter_expr
```
Manipulates data matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
Manipulates data matching the specified filtering expression. Implemented as a [mutation](/docs/en/sql-reference/statements/alter/index.md/#mutations).
:::note
The `ALTER TABLE` prefix makes this syntax different from most other systems supporting SQL. It is intended to signify that unlike similar queries in OLTP databases this is a heavy operation not designed for frequent use.
@ -20,11 +20,11 @@ The `filter_expr` must be of type `UInt8`. This query updates values of specifie
One query can contain several commands separated by commas.
The synchronicity of the query processing is defined by the [mutations_sync](../../../operations/settings/settings.md#mutations_sync) setting. By default, it is asynchronous.
The synchronicity of the query processing is defined by the [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting. By default, it is asynchronous.
**See also**
- [Mutations](../../../sql-reference/statements/alter/index.md#mutations)
- [Synchronicity of ALTER Queries](../../../sql-reference/statements/alter/index.md#synchronicity-of-alter-queries)
- [mutations_sync](../../../operations/settings/settings.md#mutations_sync) setting
- [Mutations](/docs/en/sql-reference/statements/alter/index.md/#mutations)
- [Synchronicity of ALTER Queries](/docs/en/sql-reference/statements/alter/index.md/#synchronicity-of-alter-queries)
- [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting

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

@ -12,7 +12,7 @@ Syntax:
``` sql
ALTER USER [IF EXISTS] name1 [ON CLUSTER cluster_name1] [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] [RENAME TO new_name2] ...]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']}]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name'}]
[[ADD | DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[DEFAULT ROLE role [,...] | ALL | ALL EXCEPT role [,...] ]
[GRANTEES {user | role | ANY | NONE} [,...] [EXCEPT {user | role} [,...]]]

2
docs/en/sql-reference/statements/check-table.md
View File

@ -8,7 +8,7 @@ title: "CHECK TABLE Statement"
Checks if the data in the table is corrupted.
``` sql
CHECK TABLE [db.]name
CHECK TABLE [db.]name [PARTITION partition_expr]
```
The `CHECK TABLE` query compares actual file sizes with the expected values which are stored on the server. If the file sizes do not match the stored values, it means the data is corrupted. This can be caused, for example, by a system crash during query execution.

5
docs/en/sql-reference/statements/create/user.md
View File

@ -12,7 +12,7 @@ Syntax:
``` sql
CREATE USER [IF NOT EXISTS | OR REPLACE] name1 [ON CLUSTER cluster_name1]
[, name2 [ON CLUSTER cluster_name2] ...]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']}]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name'}]
[HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[DEFAULT ROLE role [,...]]
[DEFAULT DATABASE database | NONE]
@ -34,6 +34,7 @@ There are multiple ways of user identification:
- `IDENTIFIED WITH double_sha1_hash BY 'hash'`
- `IDENTIFIED WITH ldap SERVER 'server_name'`
- `IDENTIFIED WITH kerberos` or `IDENTIFIED WITH kerberos REALM 'realm'`
- `IDENTIFIED WITH ssl_certificate CN 'mysite.com:user'`
For identification with sha256_hash using `SALT` - hash must be calculated from concatination of 'password' and 'salt'.
@ -54,7 +55,7 @@ Another way of specifying host is to use `@` syntax following the username. Exam
- `CREATE USER mira@'localhost'` — Equivalent to the `HOST LOCAL` syntax.
- `CREATE USER mira@'192.168.%.%'` — Equivalent to the `HOST LIKE` syntax.
:::warning
:::warning
ClickHouse treats `user_name@'address'` as a username as a whole. Thus, technically you can create multiple users with the same `user_name` and different constructions after `@`. However, we do not recommend to do so.
:::

44
docs/en/sql-reference/statements/index.md
View File

@ -8,25 +8,25 @@ sidebar_label: Statements
Statements represent various kinds of action you can perform using SQL queries. Each kind of statement has it’s own syntax and usage details that are described separately:
- [SELECT](../../sql-reference/statements/select/index.md)
- [INSERT INTO](../../sql-reference/statements/insert-into.md)
- [CREATE](../../sql-reference/statements/create/index.md)
- [ALTER](../../sql-reference/statements/alter/index.md)
- [SYSTEM](../../sql-reference/statements/system.md)
- [SHOW](../../sql-reference/statements/show.md)
- [GRANT](../../sql-reference/statements/grant.md)
- [REVOKE](../../sql-reference/statements/revoke.md)
- [ATTACH](../../sql-reference/statements/attach.md)
- [CHECK TABLE](../../sql-reference/statements/check-table.md)
- [DESCRIBE TABLE](../../sql-reference/statements/describe-table.md)
- [DETACH](../../sql-reference/statements/detach.md)
- [DROP](../../sql-reference/statements/drop.md)
- [EXISTS](../../sql-reference/statements/exists.md)
- [KILL](../../sql-reference/statements/kill.md)
- [OPTIMIZE](../../sql-reference/statements/optimize.md)
- [RENAME](../../sql-reference/statements/rename.md)
- [SET](../../sql-reference/statements/set.md)
- [SET ROLE](../../sql-reference/statements/set-role.md)
- [TRUNCATE](../../sql-reference/statements/truncate.md)
- [USE](../../sql-reference/statements/use.md)
- [EXPLAIN](../../sql-reference/statements/explain.md)
- [SELECT](/docs/en/sql-reference/statements/select/index.md)
- [INSERT INTO](/docs/en/sql-reference/statements/insert-into.md)
- [CREATE](/docs/en/sql-reference/statements/create/index.md)
- [ALTER](/docs/en/sql-reference/statements/alter/index.md)
- [SYSTEM](/docs/en/sql-reference/statements/system.md)
- [SHOW](/docs/en/sql-reference/statements/show.md)
- [GRANT](/docs/en/sql-reference/statements/grant.md)
- [REVOKE](/docs/en/sql-reference/statements/revoke.md)
- [ATTACH](/docs/en/sql-reference/statements/attach.md)
- [CHECK TABLE](/docs/en/sql-reference/statements/check-table.md)
- [DESCRIBE TABLE](/docs/en/sql-reference/statements/describe-table.md)
- [DETACH](/docs/en/sql-reference/statements/detach.md)
- [DROP](/docs/en/sql-reference/statements/drop.md)
- [EXISTS](/docs/en/sql-reference/statements/exists.md)
- [KILL](/docs/en/sql-reference/statements/kill.md)
- [OPTIMIZE](/docs/en/sql-reference/statements/optimize.md)
- [RENAME](/docs/en/sql-reference/statements/rename.md)
- [SET](/docs/en/sql-reference/statements/set.md)
- [SET ROLE](/docs/en/sql-reference/statements/set-role.md)
- [TRUNCATE](/docs/en/sql-reference/statements/truncate.md)
- [USE](/docs/en/sql-reference/statements/use.md)
- [EXPLAIN](/docs/en/sql-reference/statements/explain.md)

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

@ -281,8 +281,8 @@ After running this statement the `[db.]replicated_merge_tree_family_table_name`
### RESTART REPLICA
Provides possibility to reinitialize Zookeeper sessions state for `ReplicatedMergeTree` table, will compare current state with Zookeeper as source of true and add tasks to Zookeeper queue if needed.
Initialization replication queue based on ZooKeeper date happens in the same way as `ATTACH TABLE` statement. For a short time the table will be unavailable for any operations.
Provides possibility to reinitialize Zookeeper session's state for `ReplicatedMergeTree` table, will compare current state with Zookeeper as source of truth and add tasks to Zookeeper queue if needed.
Initialization of replication queue based on ZooKeeper data happens in the same way as for `ATTACH TABLE` statement. For a short time, the table will be unavailable for any operations.
``` sql
SYSTEM RESTART REPLICA [db.]replicated_merge_tree_family_table_name

4
docs/en/sql-reference/table-functions/index.md
View File

@ -39,3 +39,7 @@ You can’t use table functions if the [allow_ddl](../../operations/settings/per
| [s3](../../sql-reference/table-functions/s3.md) | Creates a [S3](../../engines/table-engines/integrations/s3.md)-engine table. |
| [sqlite](../../sql-reference/table-functions/sqlite.md) | Creates a [sqlite](../../engines/table-engines/integrations/sqlite.md)-engine table. |
:::note
Only these table functions are enabled in readonly mode :
null, view, viewIfPermitted, numbers, numbers_mt, generateRandom, values, cluster, clusterAllReplicas
:::

3
programs/library-bridge/ExternalDictionaryLibraryHandler.cpp
View File

@ -1,7 +1,6 @@
#include "ExternalDictionaryLibraryHandler.h"
#include <base/scope_guard.h>
#include <base/bit_cast.h>
#include <base/find_symbols.h>
#include <IO/ReadHelpers.h>
@ -113,7 +112,7 @@ Block ExternalDictionaryLibraryHandler::loadAll()
Block ExternalDictionaryLibraryHandler::loadIds(const std::vector<uint64_t> & ids)
{
const ExternalDictionaryLibraryAPI::VectorUInt64 ids_data{bit_cast<decltype(ExternalDictionaryLibraryAPI::VectorUInt64::data)>(ids.data()), ids.size()};
const ExternalDictionaryLibraryAPI::VectorUInt64 ids_data{std::bit_cast<decltype(ExternalDictionaryLibraryAPI::VectorUInt64::data)>(ids.data()), ids.size()};
auto columns_holder = std::make_unique<ExternalDictionaryLibraryAPI::CString[]>(attributes_names.size());
ExternalDictionaryLibraryAPI::CStrings columns_pass{static_cast<decltype(ExternalDictionaryLibraryAPI::CStrings::data)>(columns_holder.get()), attributes_names.size()};

1
programs/library-bridge/ExternalDictionaryLibraryUtils.h
View File

@ -2,7 +2,6 @@
#include <Common/StringUtils/StringUtils.h>
#include <Core/Block.h>
#include <base/bit_cast.h>
#include <base/range.h>
#include "ExternalDictionaryLibraryAPI.h"

5
programs/obfuscator/Obfuscator.cpp
View File

@ -32,7 +32,6 @@
#include <Core/Block.h>
#include <base/StringRef.h>
#include <Common/DateLUT.h>
#include <base/bit_cast.h>
#include <IO/ReadBufferFromFileDescriptor.h>
#include <IO/WriteBufferFromFileDescriptor.h>
#include <IO/ReadBufferFromFile.h>
@ -278,9 +277,9 @@ Float transformFloatMantissa(Float x, UInt64 seed)
using UInt = std::conditional_t<std::is_same_v<Float, Float32>, UInt32, UInt64>;
constexpr size_t mantissa_num_bits = std::is_same_v<Float, Float32> ? 23 : 52;
UInt x_uint = bit_cast<UInt>(x);
UInt x_uint = std::bit_cast<UInt>(x);
x_uint = static_cast<UInt>(feistelNetwork(x_uint, mantissa_num_bits, seed));
return bit_cast<Float>(x_uint);
return std::bit_cast<Float>(x_uint);
}

46
programs/server/dashboard.html
View File

@ -152,7 +152,7 @@
filter: contrast(125%);
}
#add {
#add, #reload {
font-weight: bold;
user-select: none;
cursor: pointer;
@ -166,7 +166,7 @@
margin-bottom: 1rem;
}
#add:hover {
#add:hover, #reload:hover {
background: var(--button-background-color);
}
@ -286,6 +286,7 @@
<input spellcheck="false" id="password" type="password" placeholder="password" />
</div>
<div>
<input id="reload" type="button" value="Reload" style="display: none;">
<input id="add" type="button" value="Add chart">
<span class="nowrap themes"><span id="toggle-dark">🌚</span><span id="toggle-light">🌞</span></span>
<div id="chart-params"></div>
@ -672,15 +673,39 @@ function insertChart(i) {
chart.addEventListener('mouseleave', e => { edit_buttons.style.display = 'none'; });
charts.appendChild(chart);
return {chart: chart, textarea: query_editor_textarea};
};
document.getElementById('add').addEventListener('click', e => {
queries.push({ title: '', query: '' });
insertChart(plots.length);
const {chart, textarea} = insertChart(plots.length);
chart.scrollIntoView();
textarea.focus();
plots.push(null);
resize();
});
document.getElementById('reload').addEventListener('click', e => {
reloadAll();
});
function showReloadIfNeeded() {
const is_any_field_changed = (host != document.getElementById('url').value
|| user != document.getElementById('user').value
|| password != document.getElementById('password').value);
if (is_any_field_changed) {
document.getElementById('reload').style.display = '';
} else {
document.getElementById('reload').style.display = 'none';
}
}
document.getElementById('password').addEventListener('input', e => { showReloadIfNeeded(); })
document.getElementById('user').addEventListener('input', e => { showReloadIfNeeded(); })
document.getElementById('url').addEventListener('input', e => { showReloadIfNeeded(); })
function legendAsTooltipPlugin({ className, style = { background: "var(--legend-background)" } } = {}) {
let legendEl;
@ -731,6 +756,8 @@ function legendAsTooltipPlugin({ className, style = { background: "var(--legend-
};
}
let add_http_cors_header = false;
async function draw(idx, chart, url_params, query) {
if (plots[idx]) {
plots[idx].destroy();
@ -742,6 +769,12 @@ async function draw(idx, chart, url_params, query) {
password = document.getElementById('password').value;
let url = `${host}?default_format=JSONCompactColumns`
if (add_http_cors_header) {
// For debug purposes, you may set add_http_cors_header from a browser console
url += '&add_http_cors_header=1';
}
if (user) {
url += `&user=${encodeURIComponent(user)}`;
}
@ -843,10 +876,15 @@ function resize() {
new ResizeObserver(resize).observe(document.body);
document.getElementById('params').onsubmit = function(event) {
function reloadAll() {
updateParams();
drawAll();
saveState();
document.getElementById('reload').style.display = 'none';
}
document.getElementById('params').onsubmit = function(event) {
reloadAll();
event.preventDefault();
}

6
src/Access/ContextAccess.cpp
View File

@ -379,12 +379,12 @@ std::shared_ptr<const EnabledRowPolicies> ContextAccess::getEnabledRowPolicies()
return no_row_policies;
}
ASTPtr ContextAccess::getRowPolicyFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, const ASTPtr & combine_with_expr) const
RowPolicyFilterPtr ContextAccess::getRowPolicyFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, RowPolicyFilterPtr combine_with_filter) const
{
std::lock_guard lock{mutex};
if (enabled_row_policies)
return enabled_row_policies->getFilter(database, table_name, filter_type, combine_with_expr);
return nullptr;
return enabled_row_policies->getFilter(database, table_name, filter_type, combine_with_filter);
return combine_with_filter;
}
std::shared_ptr<const EnabledQuota> ContextAccess::getQuota() const

4
src/Access/ContextAccess.h
View File

@ -1,7 +1,7 @@
#pragma once
#include <Access/AccessRights.h>
#include <Access/Common/RowPolicyDefs.h>
#include <Access/EnabledRowPolicies.h>
#include <Interpreters/ClientInfo.h>
#include <Core/UUID.h>
#include <base/scope_guard.h>
@ -87,7 +87,7 @@ public:
/// Returns the row policy filter for a specified table.
/// The function returns nullptr if there is no filter to apply.
ASTPtr getRowPolicyFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, const ASTPtr & combine_with_expr = nullptr) const;
RowPolicyFilterPtr getRowPolicyFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, RowPolicyFilterPtr combine_with_filter = {}) const;
/// Returns the quota to track resource consumption.
std::shared_ptr<const EnabledQuota> getQuota() const;

52
src/Access/EnabledRowPolicies.cpp
View File

@ -6,12 +6,18 @@
namespace DB
{
bool RowPolicyFilter::empty() const
{
bool value;
return !expression || (tryGetLiteralBool(expression.get(), value) && value);
}
size_t EnabledRowPolicies::Hash::operator()(const MixedFiltersKey & key) const
{
return std::hash<std::string_view>{}(key.database) - std::hash<std::string_view>{}(key.table_name) + static_cast<size_t>(key.filter_type);
}
EnabledRowPolicies::EnabledRowPolicies() : params()
{
}
@ -23,7 +29,7 @@ EnabledRowPolicies::EnabledRowPolicies(const Params & params_) : params(params_)
EnabledRowPolicies::~EnabledRowPolicies() = default;
ASTPtr EnabledRowPolicies::getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type) const
RowPolicyFilterPtr EnabledRowPolicies::getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type) const
{
/// We don't lock `mutex` here.
auto loaded = mixed_filters.load();
@ -31,26 +37,36 @@ ASTPtr EnabledRowPolicies::getFilter(const String & database, const String & tab
if (it == loaded->end())
return {};
auto filter = it->second.ast;
bool value;
if (tryGetLiteralBool(filter.get(), value) && value)
return nullptr; /// The condition is always true, no need to check it.
return filter;
return it->second;
}
ASTPtr EnabledRowPolicies::getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, const ASTPtr & combine_with_expr) const
RowPolicyFilterPtr EnabledRowPolicies::getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, RowPolicyFilterPtr combine_with_filter) const
{
ASTPtr filter = getFilter(database, table_name, filter_type);
if (filter && combine_with_expr)
filter = makeASTForLogicalAnd({filter, combine_with_expr});
else if (!filter)
filter = combine_with_expr;
RowPolicyFilterPtr filter = getFilter(database, table_name, filter_type);
if (filter && combine_with_filter)
{
auto new_filter = std::make_shared<RowPolicyFilter>(*filter);
bool value;
if (tryGetLiteralBool(filter.get(), value) && value)
return nullptr; /// The condition is always true, no need to check it.
if (filter->empty())
{
new_filter->expression = combine_with_filter->expression;
}
else if (combine_with_filter->empty())
{
new_filter->expression = filter->expression;
}
else
{
new_filter->expression = makeASTForLogicalAnd({filter->expression, combine_with_filter->expression});
}
std::copy(combine_with_filter->policies.begin(), combine_with_filter->policies.end(), std::back_inserter(new_filter->policies));
filter = new_filter;
}
else if (!filter)
{
filter = combine_with_filter;
}
return filter;
}

31
src/Access/EnabledRowPolicies.h
View File

@ -1,12 +1,16 @@
#pragma once
#include <Access/Common/RowPolicyDefs.h>
#include <Access/RowPolicy.h>
#include <base/types.h>
#include <Core/UUID.h>
#include <boost/container/flat_set.hpp>
#include <boost/smart_ptr/atomic_shared_ptr.hpp>
#include <unordered_map>
#include <memory>
#include <unordered_map>
#include <vector>
namespace DB
@ -14,6 +18,19 @@ namespace DB
class IAST;
using ASTPtr = std::shared_ptr<IAST>;
struct RowPolicyFilter;
using RowPolicyFilterPtr = std::shared_ptr<const RowPolicyFilter>;
struct RowPolicyFilter
{
ASTPtr expression;
std::shared_ptr<const std::pair<String, String>> database_and_table_name;
std::vector<RowPolicyPtr> policies;
bool empty() const;
};
/// Provides fast access to row policies' conditions for a specific user and tables.
class EnabledRowPolicies
@ -39,8 +56,8 @@ public:
/// Returns prepared filter for a specific table and operations.
/// The function can return nullptr, that means there is no filters applied.
/// The returned filter can be a combination of the filters defined by multiple row policies.
ASTPtr getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type) const;
ASTPtr getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, const ASTPtr & combine_with_expr) const;
RowPolicyFilterPtr getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type) const;
RowPolicyFilterPtr getFilter(const String & database, const String & table_name, RowPolicyFilterType filter_type, RowPolicyFilterPtr combine_with_filter) const;
private:
friend class RowPolicyCache;
@ -57,18 +74,12 @@ private:
friend bool operator!=(const MixedFiltersKey & left, const MixedFiltersKey & right) { return left.toTuple() != right.toTuple(); }
};
struct MixedFiltersResult
{
ASTPtr ast;
std::shared_ptr<const std::pair<String, String>> database_and_table_name;
};
struct Hash
{
size_t operator()(const MixedFiltersKey & key) const;
};
using MixedFiltersMap = std::unordered_map<MixedFiltersKey, MixedFiltersResult, Hash>;
using MixedFiltersMap = std::unordered_map<MixedFiltersKey, RowPolicyFilterPtr, Hash>;
const Params params;
mutable boost::atomic_shared_ptr<const MixedFiltersMap> mixed_filters;

12
src/Access/RowPolicyCache.cpp
View File

@ -212,6 +212,7 @@ void RowPolicyCache::mixFiltersFor(EnabledRowPolicies & enabled)
{
FiltersMixer mixer;
std::shared_ptr<const std::pair<String, String>> database_and_table_name;
std::vector<RowPolicyPtr> policies;
};
std::unordered_map<MixedFiltersKey, MixerWithNames, Hash> mixers;
@ -232,7 +233,10 @@ void RowPolicyCache::mixFiltersFor(EnabledRowPolicies & enabled)
auto & mixer = mixers[key];
mixer.database_and_table_name = info.database_and_table_name;
if (match)
{
mixer.mixer.add(info.parsed_filters[filter_type_i], policy.isRestrictive());
mixer.policies.push_back(info.policy);
}
}
}
}
@ -240,9 +244,11 @@ void RowPolicyCache::mixFiltersFor(EnabledRowPolicies & enabled)
auto mixed_filters = boost::make_shared<MixedFiltersMap>();
for (auto & [key, mixer] : mixers)
{
auto & mixed_filter = (*mixed_filters)[key];
mixed_filter.database_and_table_name = mixer.database_and_table_name;
mixed_filter.ast = std::move(mixer.mixer).getResult(access_control.isEnabledUsersWithoutRowPoliciesCanReadRows());
auto mixed_filter = std::make_shared<RowPolicyFilter>();
mixed_filter->database_and_table_name = std::move(mixer.database_and_table_name);
mixed_filter->expression = std::move(mixer.mixer).getResult(access_control.isEnabledUsersWithoutRowPoliciesCanReadRows());
mixed_filter->policies = std::move(mixer.policies);
mixed_filters->emplace(key, std::move(mixed_filter));
}
enabled.mixed_filters.store(mixed_filters);

2
src/Access/SettingsConstraints.cpp
View File

@ -147,7 +147,7 @@ bool SettingsConstraints::checkImpl(const Settings & current_settings, SettingCh
{
if (const auto hints = current_settings.getHints(change.name); !hints.empty())
{
e.addMessage(fmt::format("Maybe you meant {}", toString(hints)));
e.addMessage(fmt::format("Maybe you meant {}", toString(hints)));
}
}
throw;

2
src/AggregateFunctions/AggregateFunctionAggThrow.cpp
View File

@ -76,6 +76,8 @@ public:
data(place).~Data();
}
bool hasTrivialDestructor() const override { return std::is_trivially_destructible_v<Data>; }
void add(AggregateDataPtr __restrict, const IColumn **, size_t, Arena *) const override
{
}

5
src/AggregateFunctions/AggregateFunctionDistinct.h
View File

@ -239,6 +239,11 @@ public:
nested_func->destroy(getNestedPlace(place));
}
bool hasTrivialDestructor() const override
{
return std::is_trivially_destructible_v<Data> && nested_func->hasTrivialDestructor();
}
void destroyUpToState(AggregateDataPtr __restrict place) const noexcept override
{
this->data(place).~Data();

2
src/AggregateFunctions/AggregateFunctionForEach.h
View File

@ -174,7 +174,7 @@ public:
bool hasTrivialDestructor() const override
{
return nested_func->hasTrivialDestructor();
return std::is_trivially_destructible_v<AggregateFunctionForEachData> && nested_func->hasTrivialDestructor();
}
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override

5
src/AggregateFunctions/AggregateFunctionMap.h
View File

@ -228,6 +228,11 @@ public:
destroyImpl<false>(place);
}
bool hasTrivialDestructor() const override
{
return std::is_trivially_destructible_v<Data> && nested_func->hasTrivialDestructor();
}
void destroyUpToState(AggregateDataPtr __restrict place) const noexcept override
{
destroyImpl<true>(place);

11
src/AggregateFunctions/IAggregateFunction.h
View File

@ -685,7 +685,16 @@ public:
static constexpr bool DateTime64Supported = true;
IAggregateFunctionDataHelper(const DataTypes & argument_types_, const Array & parameters_)
: IAggregateFunctionHelper<Derived>(argument_types_, parameters_) {}
: IAggregateFunctionHelper<Derived>(argument_types_, parameters_)
{
/// To prevent derived classes changing the destroy() without updating hasTrivialDestructor() to match it
/// Enforce that either both of them are changed or none are
constexpr bool declares_destroy_and_hasTrivialDestructor =
std::is_same_v<decltype(&IAggregateFunctionDataHelper::destroy), decltype(&Derived::destroy)> ==
std::is_same_v<decltype(&IAggregateFunctionDataHelper::hasTrivialDestructor), decltype(&Derived::hasTrivialDestructor)>;
static_assert(declares_destroy_and_hasTrivialDestructor,
"destroy() and hasTrivialDestructor() methods of an aggregate function must be either both overridden or not");
}
void create(AggregateDataPtr __restrict place) const override /// NOLINT
{

5
src/AggregateFunctions/QuantileBFloat16Histogram.h
View File

@ -1,7 +1,6 @@
#pragma once
#include <base/types.h>
#include <base/bit_cast.h>
#include <base/sort.h>
#include <Common/HashTable/HashMap.h>
@ -104,13 +103,13 @@ private:
/// Take the most significant 16 bits of the floating point number.
BFloat16 toBFloat16(const Value & x) const
{
return bit_cast<UInt32>(static_cast<Float32>(x)) >> 16;
return std::bit_cast<UInt32>(static_cast<Float32>(x)) >> 16;
}
/// Put the bits into most significant 16 bits of the floating point number and fill other bits with zeros.
Float32 toFloat32(const BFloat16 & x) const
{
return bit_cast<Float32>(x << 16);
return std::bit_cast<Float32>(x << 16);
}
using Pair = PairNoInit<Float32, Weight>;

2
src/Analyzer/IQueryTreePass.h
View File

@ -16,7 +16,7 @@ namespace DB
* Dependencies between passes must be avoided.
*/
class IQueryTreePass;
using QueryTreePassPtr = std::shared_ptr<IQueryTreePass>;
using QueryTreePassPtr = std::unique_ptr<IQueryTreePass>;
using QueryTreePasses = std::vector<QueryTreePassPtr>;
class IQueryTreePass

37
src/Analyzer/Identifier.h
View File

@ -152,6 +152,11 @@ public:
return popFirst(1);
}
void pop_front() /// NOLINT
{
return popFirst();
}
void popLast(size_t parts_to_remove_size)
{
assert(parts_to_remove_size <= parts.size());
@ -177,23 +182,21 @@ public:
void push_back(std::string && part) /// NOLINT
{
parts.push_back(std::move(part));
full_name += '.';
full_name += parts.back();
emplace_back(std::move(part));
}
void push_back(const std::string & part) /// NOLINT
{
parts.push_back(part);
full_name += '.';
full_name += parts.back();
emplace_back(part);
}
template <typename ...Args>
void emplace_back(Args&&... args) /// NOLINT
{
parts.emplace_back(std::forward<Args>(args)...);
full_name += '.';
bool was_not_empty = parts.size() != 1;
if (was_not_empty)
full_name += '.';
full_name += parts.back();
}
private:
@ -365,6 +368,26 @@ inline std::ostream & operator<<(std::ostream & stream, const IdentifierView & i
}
template <>
struct std::hash<DB::Identifier>
{
size_t operator()(const DB::Identifier & identifier) const
{
std::hash<std::string> hash;
return hash(identifier.getFullName());
}
};
template <>
struct std::hash<DB::IdentifierView>
{
size_t operator()(const DB::IdentifierView & identifier) const
{
std::hash<std::string_view> hash;
return hash(identifier.getFullName());
}
};
/// See https://fmt.dev/latest/api.html#formatting-user-defined-types
template <>

231
src/Analyzer/Passes/FuseFunctionsPass.cpp Normal file
View File

@ -0,0 +1,231 @@
#include <Analyzer/Passes/FuseFunctionsPass.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <Functions/FunctionFactory.h>
#include <AggregateFunctions/IAggregateFunction.h>
#include <Analyzer/InDepthQueryTreeVisitor.h>
#include <Analyzer/FunctionNode.h>
#include <Analyzer/ConstantNode.h>
#include <DataTypes/DataTypesNumber.h>
#include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeTuple.h>
namespace DB
{
namespace ErrorCodes
{
extern const int BAD_ARGUMENTS;
extern const int LOGICAL_ERROR;
}
namespace
{
class FuseFunctionsVisitor : public InDepthQueryTreeVisitor<FuseFunctionsVisitor>
{
public:
explicit FuseFunctionsVisitor(const std::unordered_set<String> names_to_collect_)
: names_to_collect(names_to_collect_)
{}
void visitImpl(QueryTreeNodePtr & node)
{
auto * function_node = node->as<FunctionNode>();
if (!function_node || !function_node->isAggregateFunction() || !names_to_collect.contains(function_node->getFunctionName()))
return;
if (function_node->getResultType()->isNullable())
/// Do not apply to functions with Nullable result type, because `sumCount` handles it different from `sum` and `avg`.
return;
const auto & argument_nodes = function_node->getArguments().getNodes();
if (argument_nodes.size() != 1)
/// Do not apply for `count()` with without arguments or `count(*)`, only `count(x)` is supported.
return;
mapping[QueryTreeNodeWithHash(argument_nodes[0])].push_back(&node);
}
struct QueryTreeNodeWithHash
{
const QueryTreeNodePtr & node;
IQueryTreeNode::Hash hash;
explicit QueryTreeNodeWithHash(const QueryTreeNodePtr & node_)
: node(node_)
, hash(node->getTreeHash())
{}
bool operator==(const QueryTreeNodeWithHash & rhs) const
{
return hash == rhs.hash && node->isEqual(*rhs.node);
}
struct Hash
{
size_t operator() (const QueryTreeNodeWithHash & key) const { return key.hash.first ^ key.hash.second; }
};
};
/// argument -> list of sum/count/avg functions with this argument
std::unordered_map<QueryTreeNodeWithHash, std::vector<QueryTreeNodePtr *>, QueryTreeNodeWithHash::Hash> mapping;
private:
std::unordered_set<String> names_to_collect;
};
QueryTreeNodePtr createResolvedFunction(ContextPtr context, const String & name, DataTypePtr result_type, QueryTreeNodes arguments)
{
auto function_node = std::make_shared<FunctionNode>(name);
auto function = FunctionFactory::instance().get(name, context);
function_node->resolveAsFunction(std::move(function), result_type);
function_node->getArguments().getNodes() = std::move(arguments);
return function_node;
}
FunctionNodePtr createResolvedAggregateFunction(const String & name, const QueryTreeNodePtr & argument, const Array & parameters = {})
{
auto function_node = std::make_shared<FunctionNode>(name);
AggregateFunctionProperties properties;
auto aggregate_function = AggregateFunctionFactory::instance().get(name, {argument->getResultType()}, parameters, properties);
function_node->resolveAsAggregateFunction(aggregate_function, aggregate_function->getReturnType());
function_node->getArgumentsNode() = std::make_shared<ListNode>(QueryTreeNodes{argument});
return function_node;
}
QueryTreeNodePtr createTupleElementFunction(ContextPtr context, DataTypePtr result_type, QueryTreeNodePtr argument, UInt64 index)
{
return createResolvedFunction(context, "tupleElement", result_type, {argument, std::make_shared<ConstantNode>(index)});
}
QueryTreeNodePtr createArrayElementFunction(ContextPtr context, DataTypePtr result_type, QueryTreeNodePtr argument, UInt64 index)
{
return createResolvedFunction(context, "arrayElement", result_type, {argument, std::make_shared<ConstantNode>(index)});
}
void replaceWithSumCount(QueryTreeNodePtr & node, const FunctionNodePtr & sum_count_node, ContextPtr context)
{
auto sum_count_result_type = std::dynamic_pointer_cast<const DataTypeTuple>(sum_count_node->getResultType());
if (!sum_count_result_type || sum_count_result_type->getElements().size() != 2)
{
throw Exception(ErrorCodes::LOGICAL_ERROR,
"Unexpected return type '{}' of function '{}', should be tuple of two elements",
sum_count_node->getResultType(), sum_count_node->getFunctionName());
}
String function_name = node->as<const FunctionNode &>().getFunctionName();
if (function_name == "sum")
{
assert(node->getResultType()->equals(*sum_count_result_type->getElement(0)));
node = createTupleElementFunction(context, node->getResultType(), sum_count_node, 1);
}
else if (function_name == "count")
{
assert(node->getResultType()->equals(*sum_count_result_type->getElement(1)));
node = createTupleElementFunction(context, node->getResultType(), sum_count_node, 2);
}
else if (function_name == "avg")
{
auto sum_result = createTupleElementFunction(context, sum_count_result_type->getElement(0), sum_count_node, 1);
auto count_result = createTupleElementFunction(context, sum_count_result_type->getElement(1), sum_count_node, 2);
/// To avoid integer division by zero
auto count_float_result = createResolvedFunction(context, "toFloat64", std::make_shared<DataTypeFloat64>(), {count_result});
node = createResolvedFunction(context, "divide", node->getResultType(), {sum_result, count_float_result});
}
else
{
throw Exception(ErrorCodes::LOGICAL_ERROR, "Unsupported function '{}'", function_name);
}
}
FunctionNodePtr createFusedQuantilesNode(const std::vector<QueryTreeNodePtr *> nodes, const QueryTreeNodePtr & argument)
{
Array parameters;
parameters.reserve(nodes.size());
for (const auto * node : nodes)
{
const FunctionNode & function_node = (*node)->as<const FunctionNode &>();
const auto & function_name = function_node.getFunctionName();
const auto & parameter_nodes = function_node.getParameters().getNodes();
if (parameter_nodes.empty())
{
parameters.push_back(Float64(0.5)); /// default value
continue;
}
if (parameter_nodes.size() != 1)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Function '{}' should have exactly one parameter", function_name);
const auto & constant_value = parameter_nodes.front()->getConstantValueOrNull();
if (!constant_value)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Function '{}' should have constant parameter", function_name);
parameters.push_back(constant_value->getValue());
}
return createResolvedAggregateFunction("quantiles", argument, parameters);
}
void tryFuseSumCountAvg(QueryTreeNodePtr query_tree_node, ContextPtr context)
{
FuseFunctionsVisitor visitor({"sum", "count", "avg"});
visitor.visit(query_tree_node);
for (auto & [argument, nodes] : visitor.mapping)
{
if (nodes.size() < 2)
continue;
auto sum_count_node = createResolvedAggregateFunction("sumCount", argument.node);
for (auto * node : nodes)
{
assert(node);
replaceWithSumCount(*node, sum_count_node, context);
}
}
}
void tryFuseQuantiles(QueryTreeNodePtr query_tree_node, ContextPtr context)
{
FuseFunctionsVisitor visitor_quantile({"quantile"});
visitor_quantile.visit(query_tree_node);
for (auto & [argument, nodes] : visitor_quantile.mapping)
{
if (nodes.size() < 2)
continue;
auto quantiles_node = createFusedQuantilesNode(nodes, argument.node);
auto result_array_type = std::dynamic_pointer_cast<const DataTypeArray>(quantiles_node->getResultType());
if (!result_array_type)
{
throw Exception(ErrorCodes::LOGICAL_ERROR,
"Unexpected return type '{}' of function '{}', should be array",
quantiles_node->getResultType(), quantiles_node->getFunctionName());
}
for (size_t i = 0; i < nodes.size(); ++i)
{
*nodes[i] = createArrayElementFunction(context, result_array_type->getNestedType(), quantiles_node, i + 1);
}
}
}
}
void FuseFunctionsPass::run(QueryTreeNodePtr query_tree_node, ContextPtr context)
{
tryFuseSumCountAvg(query_tree_node, context);
tryFuseQuantiles(query_tree_node, context);
}
}

27
src/Analyzer/Passes/FuseFunctionsPass.h Normal file
View File

@ -0,0 +1,27 @@
#pragma once
#include <Analyzer/IQueryTreePass.h>
namespace DB
{
/*
* This pass replaces several calls of aggregate functions of the same family into one call.
* Result will be calculated only once because of CSE.
*
* Replaces:
* `sum(x), count(x), avg(x)` with `sumCount(x).1, sumCount(x).2, sumCount(x).1 / toFloat64(sumCount(x).2)`
* `quantile(0.5)(x), quantile(0.9)(x)` with `quantiles(0.5, 0.9)(x)[1], quantiles(0.5, 0.9)(x)[2]`
*/
class FuseFunctionsPass final : public IQueryTreePass
{
public:
String getName() override { return "FuseFunctionsPass"; }
String getDescription() override { return "Replaces several calls of aggregate functions of the same family into one call"; }
void run(QueryTreeNodePtr query_tree_node, ContextPtr context) override;
};
}

766
src/Analyzer/Passes/QueryAnalysisPass.cpp
View File

File diff suppressed because it is too large Load Diff

77
src/Analyzer/QueryTreePassManager.cpp
View File

@ -13,11 +13,15 @@
#include <Analyzer/Passes/AggregateFunctionsArithmericOperationsPass.h>
#include <Analyzer/Passes/UniqInjectiveFunctionsEliminationPass.h>
#include <Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.h>
#include <Analyzer/Passes/FuseFunctionsPass.h>
#include <IO/WriteHelpers.h>
#include <IO/Operators.h>
#include <Interpreters/Context.h>
#include <Analyzer/ColumnNode.h>
#include <Analyzer/InDepthQueryTreeVisitor.h>
#include <Common/Exception.h>
namespace DB
{
@ -25,13 +29,44 @@ namespace DB
namespace ErrorCodes
{
extern const int BAD_ARGUMENTS;
extern const int LOGICAL_ERROR;
}
namespace
{
#ifndef NDEBUG
/** This visitor checks if Query Tree structure is valid after each pass
* in debug build.
*/
class ValidationChecker : public InDepthQueryTreeVisitor<ValidationChecker>
{
String pass_name;
public:
explicit ValidationChecker(String pass_name_)
: pass_name(std::move(pass_name_))
{}
void visitImpl(QueryTreeNodePtr & node) const
{
auto * column = node->as<ColumnNode>();
if (!column)
return;
if (column->getColumnSourceOrNull() == nullptr)
throw Exception(ErrorCodes::LOGICAL_ERROR,
"Column {} {} query tree node does not have valid source node after running {} pass",
column->getColumnName(), column->getColumnType(), pass_name);
}
};
#endif
}
/** ClickHouse query tree pass manager.
*
* TODO: Support _shard_num into shardNum() rewriting.
* TODO: Support logical expressions optimizer.
* TODO: Support fuse sum count optimize_fuse_sum_count_avg, optimize_syntax_fuse_functions.
* TODO: Support setting convert_query_to_cnf.
* TODO: Support setting optimize_using_constraints.
* TODO: Support setting optimize_substitute_columns.
@ -43,7 +78,6 @@ namespace ErrorCodes
* TODO: Support setting optimize_redundant_functions_in_order_by.
* TODO: Support setting optimize_monotonous_functions_in_order_by.
* TODO: Support setting optimize_if_transform_strings_to_enum.
* TODO: Support settings.optimize_syntax_fuse_functions.
* TODO: Support settings.optimize_or_like_chain.
* TODO: Add optimizations based on function semantics. Example: SELECT * FROM test_table WHERE id != id. (id is not nullable column).
*/
@ -61,7 +95,12 @@ void QueryTreePassManager::run(QueryTreeNodePtr query_tree_node)
size_t passes_size = passes.size();
for (size_t i = 0; i < passes_size; ++i)
{
passes[i]->run(query_tree_node, current_context);
#ifndef NDEBUG
ValidationChecker(passes[i]->getName()).visit(query_tree_node);
#endif
}
}
void QueryTreePassManager::run(QueryTreeNodePtr query_tree_node, size_t up_to_pass_index)
@ -75,7 +114,12 @@ void QueryTreePassManager::run(QueryTreeNodePtr query_tree_node, size_t up_to_pa
auto current_context = getContext();
for (size_t i = 0; i < up_to_pass_index; ++i)
{
passes[i]->run(query_tree_node, current_context);
#ifndef NDEBUG
ValidationChecker(passes[i]->getName()).visit(query_tree_node);
#endif
}
}
void QueryTreePassManager::dump(WriteBuffer & buffer)
@ -114,38 +158,41 @@ void addQueryTreePasses(QueryTreePassManager & manager)
auto context = manager.getContext();
const auto & settings = context->getSettingsRef();
manager.addPass(std::make_shared<QueryAnalysisPass>());
manager.addPass(std::make_unique<QueryAnalysisPass>());
if (settings.optimize_functions_to_subcolumns)
manager.addPass(std::make_shared<FunctionToSubcolumnsPass>());
manager.addPass(std::make_unique<FunctionToSubcolumnsPass>());
if (settings.count_distinct_optimization)
manager.addPass(std::make_shared<CountDistinctPass>());
manager.addPass(std::make_unique<CountDistinctPass>());
if (settings.optimize_rewrite_sum_if_to_count_if)
manager.addPass(std::make_shared<SumIfToCountIfPass>());
manager.addPass(std::make_unique<SumIfToCountIfPass>());
if (settings.optimize_normalize_count_variants)
manager.addPass(std::make_shared<NormalizeCountVariantsPass>());
manager.addPass(std::make_unique<NormalizeCountVariantsPass>());
manager.addPass(std::make_shared<CustomizeFunctionsPass>());
manager.addPass(std::make_unique<CustomizeFunctionsPass>());
if (settings.optimize_arithmetic_operations_in_aggregate_functions)
manager.addPass(std::make_shared<AggregateFunctionsArithmericOperationsPass>());
manager.addPass(std::make_unique<AggregateFunctionsArithmericOperationsPass>());
if (settings.optimize_injective_functions_inside_uniq)
manager.addPass(std::make_shared<UniqInjectiveFunctionsEliminationPass>());
manager.addPass(std::make_unique<UniqInjectiveFunctionsEliminationPass>());
if (settings.optimize_multiif_to_if)
manager.addPass(std::make_shared<MultiIfToIfPass>());
manager.addPass(std::make_unique<MultiIfToIfPass>());
manager.addPass(std::make_shared<IfConstantConditionPass>());
manager.addPass(std::make_unique<IfConstantConditionPass>());
if (settings.optimize_if_chain_to_multiif)
manager.addPass(std::make_shared<IfChainToMultiIfPass>());
manager.addPass(std::make_unique<IfChainToMultiIfPass>());
manager.addPass(std::make_shared<OrderByTupleEliminationPass>());
manager.addPass(std::make_shared<OrderByLimitByDuplicateEliminationPass>());
manager.addPass(std::make_unique<OrderByTupleEliminationPass>());
manager.addPass(std::make_unique<OrderByLimitByDuplicateEliminationPass>());
if (settings.optimize_syntax_fuse_functions)
manager.addPass(std::make_unique<FuseFunctionsPass>());
}
}

52
src/Analyzer/Utils.cpp
View File

@ -5,6 +5,11 @@
#include <Parsers/ASTSubquery.h>
#include <Parsers/ASTFunction.h>
#include <DataTypes/DataTypeTuple.h>
#include <DataTypes/DataTypeArray.h>
#include <Functions/FunctionHelpers.h>
#include <Analyzer/IdentifierNode.h>
#include <Analyzer/JoinNode.h>
#include <Analyzer/ArrayJoinNode.h>
@ -289,41 +294,28 @@ QueryTreeNodes buildTableExpressionsStack(const QueryTreeNodePtr & join_tree_nod
return result;
}
QueryTreeNodePtr getColumnSourceForJoinNodeWithUsing(const QueryTreeNodePtr & join_node)
bool nestedIdentifierCanBeResolved(const DataTypePtr & compound_type, IdentifierView nested_identifier)
{
QueryTreeNodePtr column_source_node = join_node;
const IDataType * current_type = compound_type.get();
while (true)
for (const auto & identifier_part : nested_identifier)
{
auto column_source_node_type = column_source_node->getNodeType();
if (column_source_node_type == QueryTreeNodeType::TABLE ||
column_source_node_type == QueryTreeNodeType::TABLE_FUNCTION ||
column_source_node_type == QueryTreeNodeType::QUERY ||
column_source_node_type == QueryTreeNodeType::UNION)
{
break;
}
else if (column_source_node_type == QueryTreeNodeType::ARRAY_JOIN)
{
auto & array_join_node = column_source_node->as<ArrayJoinNode &>();
column_source_node = array_join_node.getTableExpression();
continue;
}
else if (column_source_node_type == QueryTreeNodeType::JOIN)
{
auto & join_node_typed = column_source_node->as<JoinNode &>();
column_source_node = isRight(join_node_typed.getKind()) ? join_node_typed.getRightTableExpression() : join_node_typed.getLeftTableExpression();
continue;
}
else
{
throw Exception(ErrorCodes::LOGICAL_ERROR,
"Unexpected node type for table expression. Expected table, table function, query, union, join or array join. Actual {}",
column_source_node->getNodeTypeName());
}
while (const DataTypeArray * array = checkAndGetDataType<DataTypeArray>(current_type))
current_type = array->getNestedType().get();
const DataTypeTuple * tuple = checkAndGetDataType<DataTypeTuple>(current_type);
if (!tuple)
return false;
auto position = tuple->tryGetPositionByName(identifier_part);
if (!position)
return false;
current_type = tuple->getElements()[*position].get();
}
return column_source_node;
return true;
}
}

9
src/Analyzer/Utils.h
View File

@ -31,9 +31,12 @@ QueryTreeNodes extractTableExpressions(const QueryTreeNodePtr & join_tree_node);
*/
QueryTreeNodes buildTableExpressionsStack(const QueryTreeNodePtr & join_tree_node);
/** Get column source for JOIN node with USING.
* Example: SELECT id FROM test_table_1 AS t1 INNER JOIN test_table_2 AS t2 USING (id);
/** Returns true if nested identifier can be resolved from compound type.
* Compound type can be tuple or array of tuples.
*
* Example: Compound type: Tuple(nested_path Tuple(nested_path_2 UInt64)). Nested identifier: nested_path_1.nested_path_2.
* Result: true.
*/
QueryTreeNodePtr getColumnSourceForJoinNodeWithUsing(const QueryTreeNodePtr & join_node);
bool nestedIdentifierCanBeResolved(const DataTypePtr & compound_type, IdentifierView nested_identifier);
}

16
src/Analyzer/tests/gtest_identifier.cpp
View File

@ -70,6 +70,22 @@ TEST(Identifier, IdentifierBasics)
}
}
TEST(Identifier, IdentifierPushParts)
{
{
Identifier identifier;
identifier.push_back("value1");
ASSERT_EQ(identifier.getFullName(), "value1");
identifier.push_back("value2");
ASSERT_EQ(identifier.getFullName(), "value1.value2");
identifier.push_back("value3");
ASSERT_EQ(identifier.getFullName(), "value1.value2.value3");
ASSERT_FALSE(identifier.isEmpty());
}
}
TEST(Identifier, IdentifierPopParts)
{
{

2
src/Client/ClientBase.cpp
View File

@ -1247,7 +1247,7 @@ void ClientBase::sendData(Block & sample, const ColumnsDescription & columns_des
bool have_data_in_stdin = !is_interactive && !stdin_is_a_tty && !std_in.eof();
if (need_render_progress && have_data_in_stdin)
if (need_render_progress)
{
/// Set total_bytes_to_read for current fd.
FileProgress file_progress(0, std_in.getFileSize());

2
src/Common/DateLUTImpl.h
View File

@ -1336,7 +1336,7 @@ public:
}
template <typename DateOrTime>
inline auto addQuarters(DateOrTime d, Int64 delta) const
inline auto NO_SANITIZE_UNDEFINED addQuarters(DateOrTime d, Int64 delta) const
{
return addMonths(d, delta * 3);
}

33
src/Common/HashTable/Hash.h
View File

@ -161,14 +161,9 @@ template <typename T>
requires (sizeof(T) <= sizeof(UInt64))
inline size_t DefaultHash64(T key)
{
union
{
T in;
DB::UInt64 out;
} u;
u.out = 0;
u.in = key;
return intHash64(u.out);
DB::UInt64 out {0};
std::memcpy(&out, &key, sizeof(T));
return intHash64(out);
}
@ -224,14 +219,9 @@ template <typename T>
requires (sizeof(T) <= sizeof(UInt64))
inline size_t hashCRC32(T key, DB::UInt64 updated_value = -1)
{
union
{
T in;
DB::UInt64 out;
} u;
u.out = 0;
u.in = key;
return intHashCRC32(u.out, updated_value);
DB::UInt64 out {0};
std::memcpy(&out, &key, sizeof(T));
return intHashCRC32(out, updated_value);
}
template <typename T>
@ -446,14 +436,9 @@ struct IntHash32
}
else if constexpr (sizeof(T) <= sizeof(UInt64))
{
union
{
T in;
DB::UInt64 out;
} u;
u.out = 0;
u.in = key;
return intHash32<salt>(u.out);
DB::UInt64 out {0};
std::memcpy(&out, &key, sizeof(T));
return intHash32<salt>(out);
}
UNREACHABLE();

17
src/Common/NamePrompter.cpp
View File

@ -1,15 +1,20 @@
#include <IO/WriteHelpers.h>
#include <Common/NamePrompter.h>
namespace DB::detail
namespace DB
{
void appendHintsMessageImpl(String & message, const std::vector<String> & hints)
String getHintsErrorMessageSuffix(const std::vector<String> & hints)
{
if (hints.empty())
{
return;
}
return {};
message += ". Maybe you meant: " + toString(hints);
return ". Maybe you meant: " + toString(hints);
}
void appendHintsMessage(String & message, const std::vector<String> & hints)
{
message += getHintsErrorMessageSuffix(hints);
}
}

12
src/Common/NamePrompter.h
View File

@ -12,6 +12,7 @@
namespace DB
{
template <size_t MaxNumHints>
class NamePrompter
{
@ -90,10 +91,9 @@ private:
}
};
namespace detail
{
void appendHintsMessageImpl(String & message, const std::vector<String> & hints);
}
String getHintsErrorMessageSuffix(const std::vector<String> & hints);
void appendHintsMessage(String & error_message, const std::vector<String> & hints);
template <size_t MaxNumHints, typename Self>
class IHints
@ -106,10 +106,10 @@ public:
return prompter.getHints(name, getAllRegisteredNames());
}
void appendHintsMessage(String & message, const String & name) const
void appendHintsMessage(String & error_message, const String & name) const
{
auto hints = getHints(name);
detail::appendHintsMessageImpl(message, hints);
DB::appendHintsMessage(error_message, hints);
}
IHints() = default;

10
src/Common/ThreadFuzzer.cpp
View File

@ -243,15 +243,17 @@ static void injection(
}
}
void ThreadFuzzer::maybeInjectSleep()
{
auto & fuzzer = ThreadFuzzer::instance();
injection(fuzzer.yield_probability, fuzzer.migrate_probability, fuzzer.sleep_probability, fuzzer.sleep_time_us);
}
void ThreadFuzzer::signalHandler(int)
{
DENY_ALLOCATIONS_IN_SCOPE;
auto saved_errno = errno;
auto & fuzzer = ThreadFuzzer::instance();
injection(fuzzer.yield_probability, fuzzer.migrate_probability, fuzzer.sleep_probability, fuzzer.sleep_time_us);
maybeInjectSleep();
errno = saved_errno;
}

1
src/Common/ThreadFuzzer.h
View File

@ -58,6 +58,7 @@ public:
static void start();
static bool isStarted();
static void maybeInjectSleep();
private:
uint64_t cpu_time_period_us = 0;
double yield_probability = 0;

39
src/Common/ZooKeeper/ZooKeeper.h
View File

@ -76,7 +76,7 @@ using GetPriorityForLoadBalancing = DB::GetPriorityForLoadBalancing;
template <typename T>
concept ZooKeeperResponse = std::derived_from<T, Coordination::Response>;
template <ZooKeeperResponse ResponseType>
template <ZooKeeperResponse ResponseType, bool try_multi>
struct MultiReadResponses
{
template <typename TResponses>
@ -96,7 +96,17 @@ struct MultiReadResponses
if constexpr (std::same_as<TResponses, RegularResponses>)
return dynamic_cast<ResponseType &>(*resp[index]);
else
{
if constexpr (try_multi)
{
/// We should not ignore errors except ZNONODE
/// for consistency with exists, tryGet and tryGetChildren
const auto & error = resp[index].error;
if (error != Coordination::Error::ZOK && error != Coordination::Error::ZNONODE)
throw KeeperException(error);
}
return resp[index];
}
},
responses);
}
@ -144,6 +154,7 @@ class ZooKeeper
public:
using Ptr = std::shared_ptr<ZooKeeper>;
using ErrorsList = std::initializer_list<Coordination::Error>;
ZooKeeper(const ZooKeeperArgs & args_, std::shared_ptr<DB::ZooKeeperLog> zk_log_ = nullptr);
@ -217,7 +228,7 @@ public:
bool exists(const std::string & path, Coordination::Stat * stat = nullptr, const EventPtr & watch = nullptr);
bool existsWatch(const std::string & path, Coordination::Stat * stat, Coordination::WatchCallback watch_callback);
using MultiExistsResponse = MultiReadResponses<Coordination::ExistsResponse>;
using MultiExistsResponse = MultiReadResponses<Coordination::ExistsResponse, true>;
template <typename TIter>
MultiExistsResponse exists(TIter start, TIter end)
{
@ -233,7 +244,8 @@ public:
std::string get(const std::string & path, Coordination::Stat * stat = nullptr, const EventPtr & watch = nullptr);
std::string getWatch(const std::string & path, Coordination::Stat * stat, Coordination::WatchCallback watch_callback);
using MultiGetResponse = MultiReadResponses<Coordination::GetResponse>;
using MultiGetResponse = MultiReadResponses<Coordination::GetResponse, false>;
using MultiTryGetResponse = MultiReadResponses<Coordination::GetResponse, true>;
template <typename TIter>
MultiGetResponse get(TIter start, TIter end)
@ -264,13 +276,13 @@ public:
Coordination::Error * code = nullptr);
template <typename TIter>
MultiGetResponse tryGet(TIter start, TIter end)
MultiTryGetResponse tryGet(TIter start, TIter end)
{
return multiRead<Coordination::GetResponse, true>(
start, end, zkutil::makeGetRequest, [&](const auto & path) { return asyncTryGet(path); });
}
MultiGetResponse tryGet(const std::vector<std::string> & paths)
MultiTryGetResponse tryGet(const std::vector<std::string> & paths)
{
return tryGet(paths.begin(), paths.end());
}
@ -297,7 +309,8 @@ public:
Coordination::WatchCallback watch_callback,
Coordination::ListRequestType list_request_type = Coordination::ListRequestType::ALL);
using MultiGetChildrenResponse = MultiReadResponses<Coordination::ListResponse>;
using MultiGetChildrenResponse = MultiReadResponses<Coordination::ListResponse, false>;
using MultiTryGetChildrenResponse = MultiReadResponses<Coordination::ListResponse, true>;
template <typename TIter>
MultiGetChildrenResponse
@ -333,7 +346,7 @@ public:
Coordination::ListRequestType list_request_type = Coordination::ListRequestType::ALL);
template <typename TIter>
MultiGetChildrenResponse
MultiTryGetChildrenResponse
tryGetChildren(TIter start, TIter end, Coordination::ListRequestType list_request_type = Coordination::ListRequestType::ALL)
{
return multiRead<Coordination::ListResponse, true>(
@ -343,7 +356,7 @@ public:
[&](const auto & path) { return asyncTryGetChildren(path, list_request_type); });
}
MultiGetChildrenResponse
MultiTryGetChildrenResponse
tryGetChildren(const std::vector<std::string> & paths, Coordination::ListRequestType list_request_type = Coordination::ListRequestType::ALL)
{
return tryGetChildren(paths.begin(), paths.end(), list_request_type);
@ -511,7 +524,7 @@ private:
using AsyncFunction = std::function<std::future<TResponse>(const std::string &)>;
template <typename TResponse, bool try_multi, typename TIter>
MultiReadResponses<TResponse> multiRead(TIter start, TIter end, RequestFactory request_factory, AsyncFunction<TResponse> async_fun)
MultiReadResponses<TResponse, try_multi> multiRead(TIter start, TIter end, RequestFactory request_factory, AsyncFunction<TResponse> async_fun)
{
if (getApiVersion() >= DB::KeeperApiVersion::WITH_MULTI_READ)
{
@ -523,12 +536,12 @@ private:
{
Coordination::Responses responses;
tryMulti(requests, responses);
return MultiReadResponses<TResponse>{std::move(responses)};
return MultiReadResponses<TResponse, try_multi>{std::move(responses)};
}
else
{
auto responses = multi(requests);
return MultiReadResponses<TResponse>{std::move(responses)};
return MultiReadResponses<TResponse, try_multi>{std::move(responses)};
}
}
@ -536,14 +549,14 @@ private:
std::vector<std::future<TResponse>> future_responses;
if (responses_size == 0)
return MultiReadResponses<TResponse>(std::move(future_responses));
return MultiReadResponses<TResponse, try_multi>(std::move(future_responses));
future_responses.reserve(responses_size);
for (auto it = start; it != end; ++it)
future_responses.push_back(async_fun(*it));
return MultiReadResponses<TResponse>{std::move(future_responses)};
return MultiReadResponses<TResponse, try_multi>{std::move(future_responses)};
}
std::unique_ptr<Coordination::IKeeper> impl;

2
src/Core/Settings.h
View File

@ -523,7 +523,7 @@ static constexpr UInt64 operator""_GiB(unsigned long long value)
M(Bool, enable_global_with_statement, true, "Propagate WITH statements to UNION queries and all subqueries", 0) \
M(Bool, aggregate_functions_null_for_empty, false, "Rewrite all aggregate functions in a query, adding -OrNull suffix to them", 0) \
M(Bool, optimize_syntax_fuse_functions, false, "Not ready for production, do not use. Allow apply syntax optimisation: fuse aggregate functions", 0) \
M(Bool, optimize_fuse_sum_count_avg, false, "Not ready for production, do not use. Fuse functions `sum, avg, count` with identical arguments into one `sumCount` (`optimize_syntax_fuse_functions should be enabled)", 0) \
M(Bool, optimize_fuse_sum_count_avg, false, "Replace calls of functions `sum`, `avg`, `count` with identical arguments into one `sumCount`", 0) \
M(Bool, flatten_nested, true, "If true, columns of type Nested will be flatten to separate array columns instead of one array of tuples", 0) \
M(Bool, asterisk_include_materialized_columns, false, "Include MATERIALIZED columns for wildcard query", 0) \
M(Bool, asterisk_include_alias_columns, false, "Include ALIAS columns for wildcard query", 0) \

1
src/DataTypes/IDataType.h
View File

@ -411,6 +411,7 @@ inline bool isDecimal(const DataTypePtr & data_type) { return WhichDataType(data
inline bool isTuple(const DataTypePtr & data_type) { return WhichDataType(data_type).isTuple(); }
inline bool isArray(const DataTypePtr & data_type) { return WhichDataType(data_type).isArray(); }
inline bool isMap(const DataTypePtr & data_type) {return WhichDataType(data_type).isMap(); }
inline bool isInterval(const DataTypePtr & data_type) {return WhichDataType(data_type).isInterval(); }
inline bool isNothing(const DataTypePtr & data_type) { return WhichDataType(data_type).isNothing(); }
inline bool isUUID(const DataTypePtr & data_type) { return WhichDataType(data_type).isUUID(); }

1
src/Databases/MySQL/MaterializedMySQLSyncThread.cpp
View File

@ -24,7 +24,6 @@
#include <Common/quoteString.h>
#include <Common/setThreadName.h>
#include <base/sleep.h>
#include <base/bit_cast.h>
#include <boost/algorithm/string/split.hpp>
#include <boost/algorithm/string/trim.hpp>
#include <Parsers/CommonParsers.h>

3
src/Disks/DiskType.h
View File

@ -11,6 +11,7 @@ enum class DataSourceType
Local,
RAM,
S3,
S3_Plain,
HDFS,
WebServer,
AzureBlobStorage,
@ -26,6 +27,8 @@ inline String toString(DataSourceType data_source_type)
return "memory";
case DataSourceType::S3:
return "s3";
case DataSourceType::S3_Plain:
return "s3_plain";
case DataSourceType::HDFS:
return "hdfs";
case DataSourceType::WebServer:

4
src/Disks/ObjectStorages/S3/S3ObjectStorage.h
View File

@ -213,7 +213,9 @@ public:
template <class ...Args>
S3PlainObjectStorage(Args && ...args)
: S3ObjectStorage("S3PlainObjectStorage", std::forward<Args>(args)...)
{}
{
data_source_description.type = DataSourceType::S3_Plain;
}
};
}

159
src/Functions/FunctionBinaryArithmetic.h
View File

@ -22,6 +22,7 @@
#include <DataTypes/DataTypeFactory.h>
#include <DataTypes/DataTypeFixedString.h>
#include <DataTypes/DataTypeInterval.h>
#include <DataTypes/DataTypeTuple.h>
#include <DataTypes/DataTypeString.h>
#include <DataTypes/DataTypesDecimal.h>
#include <DataTypes/DataTypesNumber.h>
@ -642,7 +643,8 @@ class FunctionBinaryArithmetic : public IFunction
DataTypeInt8, DataTypeInt16, DataTypeInt32, DataTypeInt64, DataTypeInt128, DataTypeInt256,
DataTypeDecimal32, DataTypeDecimal64, DataTypeDecimal128, DataTypeDecimal256,
DataTypeDate, DataTypeDateTime,
DataTypeFixedString, DataTypeString>;
DataTypeFixedString, DataTypeString,
DataTypeInterval>;
using Floats = TypeList<DataTypeFloat32, DataTypeFloat64>;
@ -717,6 +719,82 @@ class FunctionBinaryArithmetic : public IFunction
return FunctionFactory::instance().get(function_name, context);
}
static FunctionOverloadResolverPtr
getFunctionForDateTupleOfIntervalsArithmetic(const DataTypePtr & type0, const DataTypePtr & type1, ContextPtr context)
{
bool first_is_date_or_datetime = isDateOrDate32(type0) || isDateTime(type0) || isDateTime64(type0);
bool second_is_date_or_datetime = isDateOrDate32(type1) || isDateTime(type1) || isDateTime64(type1);
/// Exactly one argument must be Date or DateTime
if (first_is_date_or_datetime == second_is_date_or_datetime)
return {};
if (!isTuple(type0) && !isTuple(type1))
return {};
/// Special case when the function is plus or minus, one of arguments is Date/DateTime and another is Tuple.
/// We construct another function and call it.
if constexpr (!is_plus && !is_minus)
return {};
if (isTuple(type0) && second_is_date_or_datetime && is_minus)
throw Exception("Wrong order of arguments for function " + String(name) + ": argument of Tuple type cannot be first",
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
std::string function_name;
if (is_plus)
{
function_name = "addTupleOfIntervals";
}
else
{
function_name = "subtractTupleOfIntervals";
}
return FunctionFactory::instance().get(function_name, context);
}
static FunctionOverloadResolverPtr
getFunctionForMergeIntervalsArithmetic(const DataTypePtr & type0, const DataTypePtr & type1, ContextPtr context)
{
/// Special case when the function is plus or minus, first argument is Interval or Tuple of Intervals
/// and the second argument is the Interval of a different kind.
/// We construct another function (example: addIntervals) and call it
if constexpr (!is_plus && !is_minus)
return {};
const auto * tuple_data_type_0 = checkAndGetDataType<DataTypeTuple>(type0.get());
const auto * interval_data_type_0 = checkAndGetDataType<DataTypeInterval>(type0.get());
const auto * interval_data_type_1 = checkAndGetDataType<DataTypeInterval>(type1.get());
if ((!tuple_data_type_0 && !interval_data_type_0) || !interval_data_type_1)
return {};
if (interval_data_type_0 && interval_data_type_0->equals(*interval_data_type_1))
return {};
if (tuple_data_type_0)
{
auto & tuple_types = tuple_data_type_0->getElements();
for (auto & type : tuple_types)
if (!isInterval(type))
return {};
}
std::string function_name;
if (is_plus)
{
function_name = "addInterval";
}
else
{
function_name = "subtractInterval";
}
return FunctionFactory::instance().get(function_name, context);
}
static FunctionOverloadResolverPtr
getFunctionForTupleArithmetic(const DataTypePtr & type0, const DataTypePtr & type1, ContextPtr context)
{
@ -915,6 +993,30 @@ class FunctionBinaryArithmetic : public IFunction
return function->execute(new_arguments, result_type, input_rows_count);
}
ColumnPtr executeDateTimeTupleOfIntervalsPlusMinus(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type,
size_t input_rows_count, const FunctionOverloadResolverPtr & function_builder) const
{
ColumnsWithTypeAndName new_arguments = arguments;
/// Tuple argument must be second.
if (isTuple(arguments[0].type))
std::swap(new_arguments[0], new_arguments[1]);
auto function = function_builder->build(new_arguments);
return function->execute(new_arguments, result_type, input_rows_count);
}
ColumnPtr executeIntervalTupleOfIntervalsPlusMinus(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type,
size_t input_rows_count, const FunctionOverloadResolverPtr & function_builder) const
{
ColumnsWithTypeAndName new_arguments = arguments;
auto function = function_builder->build(new_arguments);
return function->execute(new_arguments, result_type, input_rows_count);
}
ColumnPtr executeTupleNumberOperator(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type,
size_t input_rows_count, const FunctionOverloadResolverPtr & function_builder) const
{
@ -1134,6 +1236,34 @@ public:
return function->getResultType();
}
/// Special case when the function is plus or minus, one of arguments is Date/DateTime and another is Tuple.
if (auto function_builder = getFunctionForDateTupleOfIntervalsArithmetic(arguments[0], arguments[1], context))
{
ColumnsWithTypeAndName new_arguments(2);
for (size_t i = 0; i < 2; ++i)
new_arguments[i].type = arguments[i];
/// Tuple argument must be second.
if (isTuple(new_arguments[0].type))
std::swap(new_arguments[0], new_arguments[1]);
auto function = function_builder->build(new_arguments);
return function->getResultType();
}
/// Special case when the function is plus or minus, one of arguments is Interval/Tuple of Intervals and another is Interval.
if (auto function_builder = getFunctionForMergeIntervalsArithmetic(arguments[0], arguments[1], context))
{
ColumnsWithTypeAndName new_arguments(2);
for (size_t i = 0; i < 2; ++i)
new_arguments[i].type = arguments[i];
auto function = function_builder->build(new_arguments);
return function->getResultType();
}
/// Special case when the function is multiply or divide, one of arguments is Tuple and another is Number.
if (auto function_builder = getFunctionForTupleAndNumberArithmetic(arguments[0], arguments[1], context))
{
@ -1185,6 +1315,21 @@ public:
type_res = std::make_shared<DataTypeString>();
return true;
}
else if constexpr (std::is_same_v<LeftDataType, DataTypeInterval> || std::is_same_v<RightDataType, DataTypeInterval>)
{
if constexpr (std::is_same_v<LeftDataType, DataTypeInterval> &&
std::is_same_v<RightDataType, DataTypeInterval>)
{
if constexpr (is_plus || is_minus)
{
if (left.getKind() == right.getKind())
{
type_res = std::make_shared<LeftDataType>(left.getKind());
return true;
}
}
}
}
else
{
using ResultDataType = typename BinaryOperationTraits<Op, LeftDataType, RightDataType>::ResultDataType;
@ -1566,6 +1711,18 @@ public:
return executeDateTimeIntervalPlusMinus(arguments, result_type, input_rows_count, function_builder);
}
/// Special case when the function is plus or minus, one of arguments is Date/DateTime and another is Tuple.
if (auto function_builder = getFunctionForDateTupleOfIntervalsArithmetic(arguments[0].type, arguments[1].type, context))
{
return executeDateTimeTupleOfIntervalsPlusMinus(arguments, result_type, input_rows_count, function_builder);
}
/// Special case when the function is plus or minus, one of arguments is Interval/Tuple of Intervals and another is Interval.
if (auto function_builder = getFunctionForMergeIntervalsArithmetic(arguments[0].type, arguments[1].type, context))
{
return executeIntervalTupleOfIntervalsPlusMinus(arguments, result_type, input_rows_count, function_builder);
}
/// Special case when the function is plus, minus or multiply, both arguments are tuples.
if (auto function_builder = getFunctionForTupleArithmetic(arguments[0].type, arguments[1].type, context))
{

10
src/Functions/FunctionUnaryArithmetic.h
View File

@ -3,6 +3,7 @@
#include <DataTypes/DataTypesNumber.h>
#include <DataTypes/DataTypesDecimal.h>
#include <DataTypes/DataTypeFixedString.h>
#include <DataTypes/DataTypeInterval.h>
#include <DataTypes/Native.h>
#include <Columns/ColumnVector.h>
#include <Columns/ColumnDecimal.h>
@ -145,7 +146,8 @@ class FunctionUnaryArithmetic : public IFunction
DataTypeDecimal<Decimal64>,
DataTypeDecimal<Decimal128>,
DataTypeDecimal<Decimal256>,
DataTypeFixedString
DataTypeFixedString,
DataTypeInterval
>(type, std::forward<F>(f));
}
@ -211,6 +213,12 @@ public:
return false;
result = std::make_shared<DataType>(type.getN());
}
else if constexpr (std::is_same_v<DataTypeInterval, DataType>)
{
if constexpr (!IsUnaryOperation<Op>::negate)
return false;
result = std::make_shared<DataTypeInterval>(type.getKind());
}
else
{
using T0 = typename DataType::FieldType;

1
src/Functions/FunctionsRound.h
View File

@ -16,7 +16,6 @@
#include <cmath>
#include <type_traits>
#include <array>
#include <base/bit_cast.h>
#include <base/sort.h>
#include <algorithm>

27
src/Functions/FunctionsStringSearch.h
View File

@ -91,23 +91,30 @@ public:
DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
{
if (arguments.size() < 2 || 3 < arguments.size())
throw Exception("Number of arguments for function " + getName() + " doesn't match: passed "
+ toString(arguments.size()) + ", should be 2 or 3.",
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
throw Exception(
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
"Number of arguments for function {} doesn't match: passed {}, should be 2 or 3",
getName(), arguments.size());
if (!isStringOrFixedString(arguments[0]))
throw Exception(
"Illegal type " + arguments[0]->getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of argument of function {}",
arguments[0]->getName(), getName());
if (!isString(arguments[1]))
throw Exception(
"Illegal type " + arguments[1]->getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of argument of function {}",
arguments[1]->getName(), getName());
if (arguments.size() >= 3)
{
if (!isUnsignedInteger(arguments[2]))
throw Exception(
"Illegal type " + arguments[2]->getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of argument of function {}",
arguments[2]->getName(), getName());
}
return std::make_shared<DataTypeNumber<typename Impl::ResultType>>();
@ -196,9 +203,11 @@ public:
vec_res);
else
throw Exception(
"Illegal columns " + arguments[0].column->getName() + " and "
+ arguments[1].column->getName() + " of arguments of function " + getName(),
ErrorCodes::ILLEGAL_COLUMN);
ErrorCodes::ILLEGAL_COLUMN,
"Illegal columns {} and {} of arguments of function {}",
arguments[0].column->getName(),
arguments[1].column->getName(),
getName());
return col_res;
}

353
src/Functions/MatchImpl.h
View File

@ -25,7 +25,7 @@ namespace impl
/// Is the [I]LIKE expression reduced to finding a substring in a string?
inline bool likePatternIsSubstring(std::string_view pattern, String & res)
{
if (pattern.size() < 2 || pattern.front() != '%' || pattern.back() != '%')
if (pattern.size() < 2 || !pattern.starts_with('%') || !pattern.ends_with('%'))
return false;
res.clear();
@ -101,9 +101,7 @@ struct MatchImpl
static constexpr bool case_insensitive = (case_ == MatchTraits::Case::Insensitive);
static constexpr bool negate = (result_ == MatchTraits::Result::Negate);
using Searcher = std::conditional_t<case_insensitive,
VolnitskyCaseInsensitiveUTF8,
VolnitskyUTF8>;
using Searcher = std::conditional_t<case_insensitive, VolnitskyCaseInsensitiveUTF8, VolnitskyUTF8>;
static void vectorConstant(
const ColumnString::Chars & haystack_data,
@ -115,13 +113,12 @@ struct MatchImpl
const size_t haystack_size = haystack_offsets.size();
assert(haystack_size == res.size());
assert(start_pos_ == nullptr);
if (haystack_offsets.empty())
return;
/// A simple case where the [I]LIKE expression reduces to finding a substring in a string
/// Special case that the [I]LIKE expression reduces to finding a substring in a string
String strstr_pattern;
if (is_like && impl::likePatternIsSubstring(needle, strstr_pattern))
{
@ -158,105 +155,101 @@ struct MatchImpl
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
return;
}
const auto & regexp = Regexps::Regexp(Regexps::createRegexp<is_like, /*no_capture*/ true, case_insensitive>(needle));
String required_substring;
bool is_trivial;
bool required_substring_is_prefix; /// for `anchored` execution of the regexp.
regexp.getAnalyzeResult(required_substring, is_trivial, required_substring_is_prefix);
if (required_substring.empty())
{
if (!regexp.getRE2()) /// An empty regexp. Always matches.
memset(res.data(), !negate, haystack_size * sizeof(res[0]));
else
{
size_t prev_offset = 0;
for (size_t i = 0; i < haystack_size; ++i)
{
const bool match = regexp.getRE2()->Match(
{reinterpret_cast<const char *>(&haystack_data[prev_offset]), haystack_offsets[i] - prev_offset - 1},
0,
haystack_offsets[i] - prev_offset - 1,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
prev_offset = haystack_offsets[i];
}
}
}
else
{
const auto & regexp = Regexps::Regexp(Regexps::createRegexp<is_like, /*no_capture*/ true, case_insensitive>(needle));
/// NOTE This almost matches with the case of impl::likePatternIsSubstring.
String required_substring;
bool is_trivial;
bool required_substring_is_prefix; /// for `anchored` execution of the regexp.
const UInt8 * const begin = haystack_data.data();
const UInt8 * const end = haystack_data.begin() + haystack_data.size();
const UInt8 * pos = begin;
regexp.getAnalyzeResult(required_substring, is_trivial, required_substring_is_prefix);
/// The current index in the array of strings.
size_t i = 0;
if (required_substring.empty())
Searcher searcher(required_substring.data(), required_substring.size(), end - pos);
/// We will search for the next occurrence in all rows at once.
while (pos < end && end != (pos = searcher.search(pos, end - pos)))
{
if (!regexp.getRE2()) /// An empty regexp. Always matches.
/// Determine which index it refers to.
while (begin + haystack_offsets[i] <= pos)
{
if (haystack_size)
memset(res.data(), !negate, haystack_size * sizeof(res[0]));
res[i] = negate;
++i;
}
else
/// We check that the entry does not pass through the boundaries of strings.
if (pos + required_substring.size() < begin + haystack_offsets[i])
{
size_t prev_offset = 0;
for (size_t i = 0; i < haystack_size; ++i)
/// And if it does not, if necessary, we check the regexp.
if (is_trivial)
res[i] = !negate;
else
{
const char * str_data = reinterpret_cast<const char *>(&haystack_data[haystack_offsets[i - 1]]);
size_t str_size = haystack_offsets[i] - haystack_offsets[i - 1] - 1;
/** Even in the case of `required_substring_is_prefix` use UNANCHORED check for regexp,
* so that it can match when `required_substring` occurs into the string several times,
* and at the first occurrence, the regexp is not a match.
*/
const size_t start_pos = (required_substring_is_prefix) ? (reinterpret_cast<const char *>(pos) - str_data) : 0;
const size_t end_pos = str_size;
const bool match = regexp.getRE2()->Match(
{reinterpret_cast<const char *>(&haystack_data[prev_offset]), haystack_offsets[i] - prev_offset - 1},
0,
haystack_offsets[i] - prev_offset - 1,
{str_data, str_size},
start_pos,
end_pos,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
prev_offset = haystack_offsets[i];
}
}
else
res[i] = negate;
pos = begin + haystack_offsets[i];
++i;
}
else
{
/// NOTE This almost matches with the case of impl::likePatternIsSubstring.
const UInt8 * const begin = haystack_data.data();
const UInt8 * const end = haystack_data.begin() + haystack_data.size();
const UInt8 * pos = begin;
/// The current index in the array of strings.
size_t i = 0;
Searcher searcher(required_substring.data(), required_substring.size(), end - pos);
/// We will search for the next occurrence in all rows at once.
while (pos < end && end != (pos = searcher.search(pos, end - pos)))
{
/// Determine which index it refers to.
while (begin + haystack_offsets[i] <= pos)
{
res[i] = negate;
++i;
}
/// We check that the entry does not pass through the boundaries of strings.
if (pos + required_substring.size() < begin + haystack_offsets[i])
{
/// And if it does not, if necessary, we check the regexp.
if (is_trivial)
res[i] = !negate;
else
{
const char * str_data = reinterpret_cast<const char *>(&haystack_data[haystack_offsets[i - 1]]);
size_t str_size = haystack_offsets[i] - haystack_offsets[i - 1] - 1;
/** Even in the case of `required_substring_is_prefix` use UNANCHORED check for regexp,
* so that it can match when `required_substring` occurs into the string several times,
* and at the first occurrence, the regexp is not a match.
*/
const size_t start_pos = (required_substring_is_prefix) ? (reinterpret_cast<const char *>(pos) - str_data) : 0;
const size_t end_pos = str_size;
const bool match = regexp.getRE2()->Match(
{str_data, str_size},
start_pos,
end_pos,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
}
}
else
res[i] = negate;
pos = begin + haystack_offsets[i];
++i;
}
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
}
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
}
}
@ -274,7 +267,7 @@ struct MatchImpl
if (haystack.empty())
return;
/// A simple case where the LIKE expression reduces to finding a substring in a string
/// Special case that the [I]LIKE expression reduces to finding a substring in a string
String strstr_pattern;
if (is_like && impl::likePatternIsSubstring(needle, strstr_pattern))
{
@ -316,109 +309,105 @@ struct MatchImpl
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
return;
}
const auto & regexp = Regexps::Regexp(Regexps::createRegexp<is_like, /*no_capture*/ true, case_insensitive>(needle));
String required_substring;
bool is_trivial;
bool required_substring_is_prefix; /// for `anchored` execution of the regexp.
regexp.getAnalyzeResult(required_substring, is_trivial, required_substring_is_prefix);
if (required_substring.empty())
{
if (!regexp.getRE2()) /// An empty regexp. Always matches.
memset(res.data(), !negate, haystack_size * sizeof(res[0]));
else
{
size_t offset = 0;
for (size_t i = 0; i < haystack_size; ++i)
{
const bool match = regexp.getRE2()->Match(
{reinterpret_cast<const char *>(&haystack[offset]), N},
0,
N,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
offset += N;
}
}
}
else
{
const auto & regexp = Regexps::Regexp(Regexps::createRegexp<is_like, /*no_capture*/ true, case_insensitive>(needle));
/// NOTE This almost matches with the case of likePatternIsSubstring.
String required_substring;
bool is_trivial;
bool required_substring_is_prefix; /// for `anchored` execution of the regexp.
const UInt8 * const begin = haystack.data();
const UInt8 * const end = haystack.data() + haystack.size();
const UInt8 * pos = begin;
regexp.getAnalyzeResult(required_substring, is_trivial, required_substring_is_prefix);
size_t i = 0;
const UInt8 * next_pos = begin;
if (required_substring.empty())
/// If required substring is larger than string size - it cannot be found.
if (required_substring.size() <= N)
{
if (!regexp.getRE2()) /// An empty regexp. Always matches.
Searcher searcher(required_substring.data(), required_substring.size(), end - pos);
/// We will search for the next occurrence in all rows at once.
while (pos < end && end != (pos = searcher.search(pos, end - pos)))
{
if (haystack_size)
memset(res.data(), !negate, haystack_size * sizeof(res[0]));
}
else
{
size_t offset = 0;
for (size_t i = 0; i < haystack_size; ++i)
/// Let's determine which index it refers to.
while (next_pos + N <= pos)
{
const bool match = regexp.getRE2()->Match(
{reinterpret_cast<const char *>(&haystack[offset]), N},
0,
N,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
offset += N;
}
}
}
else
{
/// NOTE This almost matches with the case of likePatternIsSubstring.
const UInt8 * const begin = haystack.data();
const UInt8 * const end = haystack.data() + haystack.size();
const UInt8 * pos = begin;
size_t i = 0;
const UInt8 * next_pos = begin;
/// If required substring is larger than string size - it cannot be found.
if (required_substring.size() <= N)
{
Searcher searcher(required_substring.data(), required_substring.size(), end - pos);
/// We will search for the next occurrence in all rows at once.
while (pos < end && end != (pos = searcher.search(pos, end - pos)))
{
/// Let's determine which index it refers to.
while (next_pos + N <= pos)
{
res[i] = negate;
next_pos += N;
++i;
}
res[i] = negate;
next_pos += N;
if (pos + required_substring.size() <= next_pos)
{
/// And if it does not, if necessary, we check the regexp.
if (is_trivial)
res[i] = !negate;
else
{
const char * str_data = reinterpret_cast<const char *>(next_pos - N);
/** Even in the case of `required_substring_is_prefix` use UNANCHORED check for regexp,
* so that it can match when `required_substring` occurs into the string several times,
* and at the first occurrence, the regexp is not a match.
*/
const size_t start_pos = (required_substring_is_prefix) ? (reinterpret_cast<const char *>(pos) - str_data) : 0;
const size_t end_pos = N;
const bool match = regexp.getRE2()->Match(
{str_data, N},
start_pos,
end_pos,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
}
}
else
res[i] = negate;
pos = next_pos;
++i;
}
}
next_pos += N;
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
if (pos + required_substring.size() <= next_pos)
{
/// And if it does not, if necessary, we check the regexp.
if (is_trivial)
res[i] = !negate;
else
{
const char * str_data = reinterpret_cast<const char *>(next_pos - N);
/** Even in the case of `required_substring_is_prefix` use UNANCHORED check for regexp,
* so that it can match when `required_substring` occurs into the string several times,
* and at the first occurrence, the regexp is not a match.
*/
const size_t start_pos = (required_substring_is_prefix) ? (reinterpret_cast<const char *>(pos) - str_data) : 0;
const size_t end_pos = N;
const bool match = regexp.getRE2()->Match(
{str_data, N},
start_pos,
end_pos,
re2_st::RE2::UNANCHORED,
nullptr,
0);
res[i] = negate ^ match;
}
}
else
res[i] = negate;
pos = next_pos;
++i;
}
}
/// Tail, in which there can be no substring.
if (i < res.size())
memset(&res[i], negate, (res.size() - i) * sizeof(res[0]));
}
}
@ -434,7 +423,6 @@ struct MatchImpl
assert(haystack_size == needle_offset.size());
assert(haystack_size == res.size());
assert(start_pos_ == nullptr);
if (haystack_offsets.empty())
@ -481,9 +469,7 @@ struct MatchImpl
if (required_substr.empty())
{
if (!regexp->getRE2()) /// An empty regexp. Always matches.
{
res[i] = !negate;
}
else
{
const bool match = regexp->getRE2()->Match(
@ -502,15 +488,11 @@ struct MatchImpl
const auto * match = searcher.search(cur_haystack_data, cur_haystack_length);
if (match == cur_haystack_data + cur_haystack_length)
{
res[i] = negate; // no match
}
else
{
if (is_trivial)
{
res[i] = !negate; // no wildcards in pattern
}
else
{
const size_t start_pos = (required_substring_is_prefix) ? (match - cur_haystack_data) : 0;
@ -546,7 +528,6 @@ struct MatchImpl
assert(haystack_size == needle_offset.size());
assert(haystack_size == res.size());
assert(start_pos_ == nullptr);
if (haystack.empty())
@ -593,9 +574,7 @@ struct MatchImpl
if (required_substr.empty())
{
if (!regexp->getRE2()) /// An empty regexp. Always matches.
{
res[i] = !negate;
}
else
{
const bool match = regexp->getRE2()->Match(
@ -614,15 +593,11 @@ struct MatchImpl
const auto * match = searcher.search(cur_haystack_data, cur_haystack_length);
if (match == cur_haystack_data + cur_haystack_length)
{
res[i] = negate; // no match
}
else
{
if (is_trivial)
{
res[i] = !negate; // no wildcards in pattern
}
else
{
const size_t start_pos = (required_substring_is_prefix) ? (match - cur_haystack_data) : 0;

5
src/Functions/isFinite.cpp
View File

@ -1,6 +1,5 @@
#include <Functions/FunctionNumericPredicate.h>
#include <Functions/FunctionFactory.h>
#include <base/bit_cast.h>
#include <type_traits>
@ -20,11 +19,11 @@ struct IsFiniteImpl
static bool execute(const T t)
{
if constexpr (std::is_same_v<T, float>)
return (bit_cast<uint32_t>(t)
return (std::bit_cast<uint32_t>(t)
& 0b01111111100000000000000000000000)
!= 0b01111111100000000000000000000000;
else if constexpr (std::is_same_v<T, double>)
return (bit_cast<uint64_t>(t)
return (std::bit_cast<uint64_t>(t)
& 0b0111111111110000000000000000000000000000000000000000000000000000)
!= 0b0111111111110000000000000000000000000000000000000000000000000000;
else

5
src/Functions/isInfinite.cpp
View File

@ -1,6 +1,5 @@
#include <Functions/FunctionNumericPredicate.h>
#include <Functions/FunctionFactory.h>
#include <base/bit_cast.h>
#include <type_traits>
@ -16,11 +15,11 @@ struct IsInfiniteImpl
static bool execute(const T t)
{
if constexpr (std::is_same_v<T, float>)
return (bit_cast<uint32_t>(t)
return (std::bit_cast<uint32_t>(t)
& 0b01111111111111111111111111111111)
== 0b01111111100000000000000000000000;
else if constexpr (std::is_same_v<T, double>)
return (bit_cast<uint64_t>(t)
return (std::bit_cast<uint64_t>(t)
& 0b0111111111111111111111111111111111111111111111111111111111111111)
== 0b0111111111110000000000000000000000000000000000000000000000000000;
else

3
src/Functions/notLike.cpp
View File

@ -12,7 +12,8 @@ struct NameNotLike
static constexpr auto name = "notLike";
};
using FunctionNotLike = FunctionsStringSearch<MatchImpl<NameNotLike, MatchTraits::Syntax::Like, MatchTraits::Case::Sensitive, MatchTraits::Result::Negate>>;
using NotLikeImpl = MatchImpl<NameNotLike, MatchTraits::Syntax::Like, MatchTraits::Case::Sensitive, MatchTraits::Result::Negate>;
using FunctionNotLike = FunctionsStringSearch<NotLikeImpl>;
}

5
src/Functions/padString.cpp
View File

@ -5,7 +5,6 @@
#include <Functions/GatherUtils/Algorithms.h>
#include <Functions/GatherUtils/Sinks.h>
#include <Functions/GatherUtils/Sources.h>
#include <base/bit_cast.h>
namespace DB
{
@ -59,10 +58,10 @@ namespace
{
if (num_chars <= step)
{
writeSlice(StringSource::Slice{bit_cast<const UInt8 *>(pad_string.data()), numCharsToNumBytes(num_chars)}, res_sink);
writeSlice(StringSource::Slice{std::bit_cast<const UInt8 *>(pad_string.data()), numCharsToNumBytes(num_chars)}, res_sink);
break;
}
writeSlice(StringSource::Slice{bit_cast<const UInt8 *>(pad_string.data()), numCharsToNumBytes(step)}, res_sink);
writeSlice(StringSource::Slice{std::bit_cast<const UInt8 *>(pad_string.data()), numCharsToNumBytes(step)}, res_sink);
num_chars -= step;
}
}

25
src/Functions/serverConstants.cpp
View File

@ -1,4 +1,6 @@
#include <Functions/FunctionConstantBase.h>
#include <base/getFQDNOrHostName.h>
#include <Poco/Util/AbstractConfiguration.h>
#include <DataTypes/DataTypesNumber.h>
#include <DataTypes/DataTypeString.h>
#include <DataTypes/DataTypeUUID.h>
@ -115,6 +117,13 @@ namespace
static FunctionPtr create(ContextPtr context) { return std::make_shared<FunctionGetOSKernelVersion>(context); }
};
class FunctionDisplayName : public FunctionConstantBase<FunctionDisplayName, String, DataTypeString>
{
public:
static constexpr auto name = "displayName";
explicit FunctionDisplayName(ContextPtr context) : FunctionConstantBase(context->getConfigRef().getString("display_name", getFQDNOrHostName()), context->isDistributed()) {}
static FunctionPtr create(ContextPtr context) {return std::make_shared<FunctionDisplayName>(context); }
};
}
#if defined(__ELF__) && !defined(OS_FREEBSD)
@ -173,4 +182,20 @@ REGISTER_FUNCTION(GetOSKernelVersion)
}
REGISTER_FUNCTION(DisplayName)
{
factory.registerFunction<FunctionDisplayName>(
{
R"(
Returns the value of `display_name` from config or server FQDN if not set.
[example:displayName]
)",
Documentation::Examples{{"displayName", "SELECT displayName();"}},
Documentation::Categories{"Constant", "Miscellaneous"}
},
FunctionFactory::CaseSensitive);
}
}

328
src/Functions/vectorFunctions.cpp
View File

@ -1,5 +1,6 @@
#include <Columns/ColumnTuple.h>
#include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeInterval.h>
#include <DataTypes/DataTypeTuple.h>
#include <DataTypes/DataTypesNumber.h>
#include <DataTypes/DataTypeNothing.h>
@ -415,6 +416,274 @@ public:
}
};
template <typename Impl>
class FunctionDateOrDateTimeOperationTupleOfIntervals : public ITupleFunction
{
public:
static constexpr auto name = Impl::name;
explicit FunctionDateOrDateTimeOperationTupleOfIntervals(ContextPtr context_) : ITupleFunction(context_) {}
static FunctionPtr create(ContextPtr context_)
{
return std::make_shared<FunctionDateOrDateTimeOperationTupleOfIntervals>(context_);
}
String getName() const override { return name; }
size_t getNumberOfArguments() const override { return 2; }
DataTypePtr getReturnTypeImpl(const ColumnsWithTypeAndName & arguments) const override
{
if (!isDateOrDate32(arguments[0].type) && !isDateTime(arguments[0].type) && !isDateTime64(arguments[0].type))
throw Exception{ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of first argument of function {}. Should be a date or a date with time",
arguments[0].type->getName(), getName()};
const auto * cur_tuple = checkAndGetDataType<DataTypeTuple>(arguments[1].type.get());
if (!cur_tuple)
throw Exception{ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of second argument of function {}. Should be a tuple",
arguments[0].type->getName(), getName()};
const auto & cur_types = cur_tuple->getElements();
Columns cur_elements;
if (arguments[1].column)
cur_elements = getTupleElements(*arguments[1].column);
size_t tuple_size = cur_types.size();
if (tuple_size == 0)
return arguments[0].type;
auto plus = FunctionFactory::instance().get(Impl::func_name, context);
DataTypePtr res_type = arguments[0].type;
for (size_t i = 0; i < tuple_size; ++i)
{
try
{
ColumnWithTypeAndName left{res_type, {}};
ColumnWithTypeAndName right{cur_elements.empty() ? nullptr : cur_elements[i], cur_types[i], {}};
auto plus_elem = plus->build({left, right});
res_type = plus_elem->getResultType();
}
catch (DB::Exception & e)
{
e.addMessage("While executing function {} for tuple element {}", getName(), i);
throw;
}
}
return res_type;
}
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
{
const auto * cur_tuple = checkAndGetDataType<DataTypeTuple>(arguments[1].type.get());
const auto & cur_types = cur_tuple->getElements();
auto cur_elements = getTupleElements(*arguments[1].column);
size_t tuple_size = cur_elements.size();
if (tuple_size == 0)
return arguments[0].column;
auto plus = FunctionFactory::instance().get(Impl::func_name, context);
ColumnWithTypeAndName res;
for (size_t i = 0; i < tuple_size; ++i)
{
ColumnWithTypeAndName column{cur_elements[i], cur_types[i], {}};
auto elem_plus = plus->build(ColumnsWithTypeAndName{i == 0 ? arguments[0] : res, column});
auto res_type = elem_plus->getResultType();
res.column = elem_plus->execute({i == 0 ? arguments[0] : res, column}, res_type, input_rows_count);
res.type = res_type;
}
return res.column;
}
};
struct AddTupleOfIntervalsImpl
{
static constexpr auto name = "addTupleOfIntervals";
static constexpr auto func_name = "plus";
};
struct SubtractTupleOfIntervalsImpl
{
static constexpr auto name = "subtractTupleOfIntervals";
static constexpr auto func_name = "minus";
};
using FunctionAddTupleOfIntervals = FunctionDateOrDateTimeOperationTupleOfIntervals<AddTupleOfIntervalsImpl>;
using FunctionSubtractTupleOfIntervals = FunctionDateOrDateTimeOperationTupleOfIntervals<SubtractTupleOfIntervalsImpl>;
template <bool is_minus>
struct FunctionTupleOperationInterval : public ITupleFunction
{
public:
static constexpr auto name = is_minus ? "subtractInterval" : "addInterval";
explicit FunctionTupleOperationInterval(ContextPtr context_) : ITupleFunction(context_) {}
static FunctionPtr create(ContextPtr context_)
{
return std::make_shared<FunctionTupleOperationInterval>(context_);
}
String getName() const override { return name; }
size_t getNumberOfArguments() const override { return 2; }
DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
{
if (!isTuple(arguments[0]) && !isInterval(arguments[0]))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of first argument of function {}, must be Tuple or Interval",
arguments[0]->getName(), getName());
if (!isInterval(arguments[1]))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of second argument of function {}, must be Interval",
arguments[1]->getName(), getName());
DataTypes types;
const auto * tuple = checkAndGetDataType<DataTypeTuple>(arguments[0].get());
if (tuple)
{
const auto & cur_types = tuple->getElements();
for (const auto & type : cur_types)
if (!isInterval(type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of Tuple element of first argument of function {}, must be Interval",
type->getName(), getName());
types = cur_types;
}
else
{
types = {arguments[0]};
}
const auto * interval_last = checkAndGetDataType<DataTypeInterval>(types.back().get());
const auto * interval_new = checkAndGetDataType<DataTypeInterval>(arguments[1].get());
if (!interval_last->equals(*interval_new))
types.push_back(arguments[1]);
return std::make_shared<DataTypeTuple>(types);
}
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
{
if (!isInterval(arguments[1].type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of second argument of function {}, must be Interval",
arguments[1].type->getName(), getName());
Columns tuple_columns;
const auto * first_tuple = checkAndGetDataType<DataTypeTuple>(arguments[0].type.get());
const auto * first_interval = checkAndGetDataType<DataTypeInterval>(arguments[0].type.get());
const auto * second_interval = checkAndGetDataType<DataTypeInterval>(arguments[1].type.get());
bool can_be_merged;
if (first_interval)
{
can_be_merged = first_interval->equals(*second_interval);
if (can_be_merged)
tuple_columns.resize(1);
else
tuple_columns.resize(2);
tuple_columns[0] = arguments[0].column->convertToFullColumnIfConst();
}
else if (first_tuple)
{
const auto & cur_types = first_tuple->getElements();
for (const auto & type : cur_types)
if (!isInterval(type))
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of Tuple element of first argument of function {}, must be Interval",
type->getName(), getName());
auto cur_elements = getTupleElements(*arguments[0].column);
size_t tuple_size = cur_elements.size();
if (tuple_size == 0)
{
can_be_merged = false;
}
else
{
const auto * tuple_last_interval = checkAndGetDataType<DataTypeInterval>(cur_types.back().get());
can_be_merged = tuple_last_interval->equals(*second_interval);
}
if (can_be_merged)
tuple_columns.resize(tuple_size);
else
tuple_columns.resize(tuple_size + 1);
for (size_t i = 0; i < tuple_size; ++i)
tuple_columns[i] = cur_elements[i];
}
else
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
"Illegal type {} of first argument of function {}, must be Tuple or Interval",
arguments[0].type->getName(), getName());
ColumnPtr & last_column = tuple_columns.back();
if (can_be_merged)
{
ColumnWithTypeAndName left{last_column, arguments[1].type, {}};
if constexpr (is_minus)
{
auto minus = FunctionFactory::instance().get("minus", context);
auto elem_minus = minus->build({left, arguments[1]});
last_column = elem_minus->execute({left, arguments[1]}, arguments[1].type, input_rows_count)
->convertToFullColumnIfConst();
}
else
{
auto plus = FunctionFactory::instance().get("plus", context);
auto elem_plus = plus->build({left, arguments[1]});
last_column = elem_plus->execute({left, arguments[1]}, arguments[1].type, input_rows_count)
->convertToFullColumnIfConst();
}
}
else
{
if constexpr (is_minus)
{
auto negate = FunctionFactory::instance().get("negate", context);
auto elem_negate = negate->build({arguments[1]});
last_column = elem_negate->execute({arguments[1]}, arguments[1].type, input_rows_count);
}
else
{
last_column = arguments[1].column;
}
}
return ColumnTuple::create(tuple_columns);
}
};
using FunctionTupleAddInterval = FunctionTupleOperationInterval<false>;
using FunctionTupleSubtractInterval = FunctionTupleOperationInterval<true>;
/// this is for convenient usage in LNormalize
template <class FuncLabel>
class FunctionLNorm : public ITupleFunction {};
@ -1282,6 +1551,65 @@ REGISTER_FUNCTION(VectorFunctions)
factory.registerFunction<FunctionTupleDivide>();
factory.registerFunction<FunctionTupleNegate>();
factory.registerFunction<FunctionAddTupleOfIntervals>(
{
R"(
Consecutively adds a tuple of intervals to a Date or a DateTime.
[example:tuple]
)",
Documentation::Examples{
{"tuple", "WITH toDate('2018-01-01') AS date SELECT addTupleOfIntervals(date, (INTERVAL 1 DAY, INTERVAL 1 YEAR))"},
},
Documentation::Categories{"Tuple", "Interval", "Date", "DateTime"}
});
factory.registerFunction<FunctionSubtractTupleOfIntervals>(
{
R"(
Consecutively subtracts a tuple of intervals from a Date or a DateTime.
[example:tuple]
)",
Documentation::Examples{
{"tuple", "WITH toDate('2018-01-01') AS date SELECT subtractTupleOfIntervals(date, (INTERVAL 1 DAY, INTERVAL 1 YEAR))"},
},
Documentation::Categories{"Tuple", "Interval", "Date", "DateTime"}
});
factory.registerFunction<FunctionTupleAddInterval>(
{
R"(
Adds an interval to another interval or tuple of intervals. The returned value is tuple of intervals.
[example:tuple]
[example:interval1]
If the types of the first interval (or the interval in the tuple) and the second interval are the same they will be merged into one interval.
[example:interval2]
)",
Documentation::Examples{
{"tuple", "SELECT addInterval((INTERVAL 1 DAY, INTERVAL 1 YEAR), INTERVAL 1 MONTH)"},
{"interval1", "SELECT addInterval(INTERVAL 1 DAY, INTERVAL 1 MONTH)"},
{"interval2", "SELECT addInterval(INTERVAL 1 DAY, INTERVAL 1 DAY)"},
},
Documentation::Categories{"Tuple", "Interval"}
});
factory.registerFunction<FunctionTupleSubtractInterval>(
{
R"(
Adds an negated interval to another interval or tuple of intervals. The returned value is tuple of intervals.
[example:tuple]
[example:interval1]
If the types of the first interval (or the interval in the tuple) and the second interval are the same they will be merged into one interval.
[example:interval2]
)",
Documentation::Examples{
{"tuple", "SELECT subtractInterval((INTERVAL 1 DAY, INTERVAL 1 YEAR), INTERVAL 1 MONTH)"},
{"interval1", "SELECT subtractInterval(INTERVAL 1 DAY, INTERVAL 1 MONTH)"},
{"interval2", "SELECT subtractInterval(INTERVAL 2 DAY, INTERVAL 1 DAY)"},
},
Documentation::Categories{"Tuple", "Interval"}
});
factory.registerFunction<FunctionTupleMultiplyByNumber>();
factory.registerFunction<FunctionTupleDivideByNumber>();

1
src/Interpreters/BloomFilterHash.h
View File

@ -1,6 +1,5 @@
#pragma once
#include <base/bit_cast.h>
#include <Common/HashTable/Hash.h>
#include <Columns/IColumn.h>
#include <Columns/ColumnArray.h>

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