mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-26 01:22:04 +00:00
Merge branch 'master' into feature/adaptive_merged_block_size
This commit is contained in:
LiuNeng
GitHub
commit
4f9dba8535
37
.github/workflows/master.yml
vendored
37
.github/workflows/master.yml
vendored
@ -59,16 +59,17 @@ jobs:
|
||||
uses: ./.github/workflows/reusable_docker.yml
|
||||
with:
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
StyleCheck:
|
||||
needs: [RunConfig, BuildDockers]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: Style check
|
||||
runner_type: style-checker
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
run_command: |
|
||||
python3 style_check.py --no-push
|
||||
# Tested in MQ
|
||||
# StyleCheck:
|
||||
# needs: [RunConfig, BuildDockers]
|
||||
# if: ${{ !failure() && !cancelled() }}
|
||||
# uses: ./.github/workflows/reusable_test.yml
|
||||
# with:
|
||||
# test_name: Style check
|
||||
# runner_type: style-checker
|
||||
# data: ${{ needs.RunConfig.outputs.data }}
|
||||
# run_command: |
|
||||
# python3 style_check.py --no-push
|
||||
CompatibilityCheckX86:
|
||||
needs: [RunConfig, BuilderDebRelease]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
@ -447,6 +448,14 @@ jobs:
|
||||
test_name: Stateless tests (debug)
|
||||
runner_type: func-tester
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
FunctionalStatelessTestAsanAzure:
|
||||
needs: [RunConfig, BuilderDebAsan]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: Stateless tests (azure, asan)
|
||||
runner_type: func-tester
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
##############################################################################################
|
||||
############################ FUNCTIONAl STATEFUL TESTS #######################################
|
||||
##############################################################################################
|
||||
@ -597,6 +606,14 @@ jobs:
|
||||
test_name: Stress test (tsan)
|
||||
runner_type: stress-tester
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
StressTestTsanAzure:
|
||||
needs: [RunConfig, BuilderDebTsan]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: Stress test (azure, tsan)
|
||||
runner_type: stress-tester
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
StressTestMsan:
|
||||
needs: [RunConfig, BuilderDebMsan]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
|
||||
4
.github/workflows/pull_request.yml
vendored
4
.github/workflows/pull_request.yml
vendored
@ -158,7 +158,7 @@ jobs:
|
||||
#
|
||||
FinishCheck:
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
needs: [Tests_1, Tests_2, Builds_1_Report, Builds_2_Report]
|
||||
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2]
|
||||
runs-on: [self-hosted, style-checker]
|
||||
steps:
|
||||
- name: Check out repository code
|
||||
@ -171,7 +171,7 @@ jobs:
|
||||
- name: Finish label
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
python3 finish_check.py
|
||||
python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}
|
||||
- name: Auto merge if approved
|
||||
if: ${{ github.event_name != 'merge_group' }}
|
||||
run: |
|
||||
|
||||
@ -16,7 +16,7 @@
|
||||
#ci_set_reduced
|
||||
#ci_set_arm
|
||||
#ci_set_integration
|
||||
#ci_set_analyzer
|
||||
#ci_set_old_analyzer
|
||||
|
||||
## To run specified job in CI:
|
||||
#job_<JOB NAME>
|
||||
|
||||
@ -38,9 +38,9 @@
|
||||
* Optimized function `dotProduct` to omit unnecessary and expensive memory copies. [#60928](https://github.com/ClickHouse/ClickHouse/pull/60928) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* 30x faster printing for 256-bit integers. [#61100](https://github.com/ClickHouse/ClickHouse/pull/61100) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* If the table's primary key contains mostly useless columns, don't keep them in memory. This is controlled by a new setting `primary_key_ratio_of_unique_prefix_values_to_skip_suffix_columns` with the value `0.9` by default, which means: for a composite primary key, if a column changes its value for at least 0.9 of all the times, the next columns after it will be not loaded. [#60255](https://github.com/ClickHouse/ClickHouse/pull/60255) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Improve the performance of serialized aggregation method when involving multiple `Nullable` columns. [#55809](https://github.com/ClickHouse/ClickHouse/pull/55809) ([Amos Bird](https://github.com/amosbird)).
|
||||
* Lazy build JSON's output to improve performance of ALL JOIN. [#58278](https://github.com/ClickHouse/ClickHouse/pull/58278) ([LiuNeng](https://github.com/liuneng1994)).
|
||||
* Make HTTP/HTTPs connections with external services, such as AWS S3 reusable for all uses cases. Even when response is 3xx or 4xx. [#58845](https://github.com/ClickHouse/ClickHouse/pull/58845) ([Sema Checherinda](https://github.com/CheSema)).
|
||||
* Improve the performance of serialized aggregation methods when involving multiple `Nullable` columns. [#55809](https://github.com/ClickHouse/ClickHouse/pull/55809) ([Amos Bird](https://github.com/amosbird)).
|
||||
* Lazy builds JSON's output to improve performance of ALL JOIN. [#58278](https://github.com/ClickHouse/ClickHouse/pull/58278) ([LiuNeng](https://github.com/liuneng1994)).
|
||||
* Make HTTP/HTTPs connections with external services, such as AWS S3 reusable for all use cases. Even when the response is 3xx or 4xx. [#58845](https://github.com/ClickHouse/ClickHouse/pull/58845) ([Sema Checherinda](https://github.com/CheSema)).
|
||||
* Improvements to aggregate functions `argMin` / `argMax` / `any` / `anyLast` / `anyHeavy`, as well as `ORDER BY {u8/u16/u32/u64/i8/i16/u32/i64) LIMIT 1` queries. [#58640](https://github.com/ClickHouse/ClickHouse/pull/58640) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Trivial optimization for column's filter. Peak memory can be reduced to 44% of the original in some cases. [#59698](https://github.com/ClickHouse/ClickHouse/pull/59698) ([李扬](https://github.com/taiyang-li)).
|
||||
* Execute `multiIf` function in a columnar fashion when the result type's underlying type is a number. [#60384](https://github.com/ClickHouse/ClickHouse/pull/60384) ([李扬](https://github.com/taiyang-li)).
|
||||
@ -49,7 +49,7 @@
|
||||
* Optimize data movement between columns of a Nullable number or a Nullable string, which improves some micro-benchmarks. [#60846](https://github.com/ClickHouse/ClickHouse/pull/60846) ([李扬](https://github.com/taiyang-li)).
|
||||
* Operations with the filesystem cache will suffer less from the lock contention. [#61066](https://github.com/ClickHouse/ClickHouse/pull/61066) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Optimize array join and other JOINs by preventing a wrong compiler's optimization. Close [#61074](https://github.com/ClickHouse/ClickHouse/issues/61074). [#61075](https://github.com/ClickHouse/ClickHouse/pull/61075) ([李扬](https://github.com/taiyang-li)).
|
||||
* If a query with a syntax error contained `COLUMNS` matcher with a regular expression, the regular expression was compiled each time during the parser's backtracking, instead of being compiled once. This was a fundamental error. The compiled regexp was put to AST. But the letter A in AST means "abstract" which means it should not contain heavyweight objects. Parts of AST can be created and discarded during parsing, including a large number of backtracking. This leads to slowness on the parsing side and consequently allows DoS by a readonly user. But the main problem is that it prevents progress in fuzzers. [#61543](https://github.com/ClickHouse/ClickHouse/pull/61543) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* If a query with a syntax error contained the `COLUMNS` matcher with a regular expression, the regular expression was compiled each time during the parser's backtracking, instead of being compiled once. This was a fundamental error. The compiled regexp was put to AST. But the letter A in AST means "abstract" which means it should not contain heavyweight objects. Parts of AST can be created and discarded during parsing, including a large number of backtracking. This leads to slowness on the parsing side and consequently allows DoS by a readonly user. But the main problem is that it prevents progress in fuzzers. [#61543](https://github.com/ClickHouse/ClickHouse/pull/61543) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Add a new analyzer pass to optimize the IN operator for a single value. [#61564](https://github.com/ClickHouse/ClickHouse/pull/61564) ([LiuNeng](https://github.com/liuneng1994)).
|
||||
* DNSResolver shuffles set of resolved IPs which is needed to uniformly utilize multiple endpoints of AWS S3. [#60965](https://github.com/ClickHouse/ClickHouse/pull/60965) ([Sema Checherinda](https://github.com/CheSema)).
|
||||
|
||||
|
||||
@ -8,9 +8,6 @@ option (SANITIZE "Enable one of the code sanitizers" "")
|
||||
|
||||
set (SAN_FLAGS "${SAN_FLAGS} -g -fno-omit-frame-pointer -DSANITIZER")
|
||||
|
||||
# It's possible to pass an ignore list to sanitizers (-fsanitize-ignorelist). Intentionally not doing this because
|
||||
# 1. out-of-source suppressions are awkward 2. it seems ignore lists don't work after the Clang v16 upgrade (#49829)
|
||||
|
||||
if (SANITIZE)
|
||||
if (SANITIZE STREQUAL "address")
|
||||
set (ASAN_FLAGS "-fsanitize=address -fsanitize-address-use-after-scope")
|
||||
|
||||
2
contrib/curl
vendored
2
contrib/curl
vendored
@ -1 +1 @@
|
||||
Subproject commit 1a05e833f8f7140628b27882b10525fd9ec4b873
|
||||
Subproject commit de7b3e89218467159a7af72d58cea8425946e97d
|
||||
@ -33,14 +33,15 @@ set (SRCS
|
||||
"${LIBRARY_DIR}/lib/curl_memrchr.c"
|
||||
"${LIBRARY_DIR}/lib/curl_multibyte.c"
|
||||
"${LIBRARY_DIR}/lib/curl_ntlm_core.c"
|
||||
"${LIBRARY_DIR}/lib/curl_ntlm_wb.c"
|
||||
"${LIBRARY_DIR}/lib/curl_path.c"
|
||||
"${LIBRARY_DIR}/lib/curl_range.c"
|
||||
"${LIBRARY_DIR}/lib/curl_rtmp.c"
|
||||
"${LIBRARY_DIR}/lib/curl_sasl.c"
|
||||
"${LIBRARY_DIR}/lib/curl_sha512_256.c"
|
||||
"${LIBRARY_DIR}/lib/curl_sspi.c"
|
||||
"${LIBRARY_DIR}/lib/curl_threads.c"
|
||||
"${LIBRARY_DIR}/lib/curl_trc.c"
|
||||
"${LIBRARY_DIR}/lib/cw-out.c"
|
||||
"${LIBRARY_DIR}/lib/dict.c"
|
||||
"${LIBRARY_DIR}/lib/doh.c"
|
||||
"${LIBRARY_DIR}/lib/dynbuf.c"
|
||||
@ -98,6 +99,7 @@ set (SRCS
|
||||
"${LIBRARY_DIR}/lib/psl.c"
|
||||
"${LIBRARY_DIR}/lib/rand.c"
|
||||
"${LIBRARY_DIR}/lib/rename.c"
|
||||
"${LIBRARY_DIR}/lib/request.c"
|
||||
"${LIBRARY_DIR}/lib/rtsp.c"
|
||||
"${LIBRARY_DIR}/lib/select.c"
|
||||
"${LIBRARY_DIR}/lib/sendf.c"
|
||||
|
||||
@ -38,6 +38,7 @@
|
||||
|
||||
#define HAVE_ARPA_INET_H
|
||||
#define HAVE_ERRNO_H
|
||||
#define HAVE_GETSOCKNAME
|
||||
#define HAVE_FCNTL_H
|
||||
#define HAVE_NETDB_H
|
||||
#define HAVE_NETINET_IN_H
|
||||
|
||||
@ -14,11 +14,14 @@ RUN curl -o krb5-libs-1.10.3-65.el6.x86_64.rpm ftp://ftp.pbone.net/mirror/vault.
|
||||
rpm -Uvh libkadm5-1.10.3-65.el6.x86_64.rpm libss-1.41.12-24.el6.x86_64.rpm krb5-libs-1.10.3-65.el6.x86_64.rpm krb5-workstation-1.10.3-65.el6.x86_64.rpm libcom_err-1.41.12-24.el6.x86_64.rpm && \
|
||||
rm -fr *.rpm
|
||||
|
||||
ADD https://archive.apache.org/dist/commons/daemon/source/commons-daemon-1.0.15-src.tar.gz /tmp/commons-daemon-1.0.15-src.tar.gz
|
||||
|
||||
RUN cd /tmp && \
|
||||
curl http://archive.apache.org/dist/commons/daemon/source/commons-daemon-1.0.15-src.tar.gz -o commons-daemon-1.0.15-src.tar.gz && \
|
||||
tar xzf commons-daemon-1.0.15-src.tar.gz && \
|
||||
cd commons-daemon-1.0.15-src/src/native/unix && \
|
||||
./configure && \
|
||||
make && \
|
||||
cp ./jsvc /usr/local/hadoop-2.7.0/sbin && \
|
||||
[ -e /usr/local/hadoop ] || ln -s ./hadoop-2.7.0 /usr/local/hadoop
|
||||
cd /tmp && \
|
||||
rm -rf commons-daemon-1.0.15-src* && \
|
||||
{ [ -e /usr/local/hadoop ] || ln -s ./hadoop-2.7.0 /usr/local/hadoop; }
|
||||
|
||||
@ -19,7 +19,7 @@ ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
|
||||
# install test configs
|
||||
/usr/share/clickhouse-test/config/install.sh
|
||||
|
||||
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
|
||||
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --silent --inMemoryPersistence &
|
||||
./setup_minio.sh stateful
|
||||
|
||||
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
|
||||
@ -87,7 +87,7 @@ function start()
|
||||
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
|
||||
break
|
||||
fi
|
||||
timeout 120 service clickhouse-server start
|
||||
timeout 120 sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
|
||||
sleep 0.5
|
||||
counter=$((counter + 1))
|
||||
done
|
||||
|
||||
@ -42,12 +42,6 @@ source /utils.lib
|
||||
# install test configs
|
||||
/usr/share/clickhouse-test/config/install.sh
|
||||
|
||||
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
|
||||
echo "Azure is disabled"
|
||||
else
|
||||
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
|
||||
fi
|
||||
|
||||
./setup_minio.sh stateless
|
||||
./setup_hdfs_minicluster.sh
|
||||
|
||||
@ -97,12 +91,11 @@ if [ "$NUM_TRIES" -gt "1" ]; then
|
||||
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_TIME_US_MAX=10000
|
||||
|
||||
mkdir -p /var/run/clickhouse-server
|
||||
# simplest way to forward env variables to server
|
||||
sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
|
||||
else
|
||||
sudo clickhouse start
|
||||
fi
|
||||
|
||||
# simplest way to forward env variables to server
|
||||
sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
|
||||
|
||||
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
|
||||
sudo sed -i "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" /etc/clickhouse-server1/config.d/filesystem_caches_path.xml
|
||||
|
||||
@ -212,6 +205,14 @@ function run_tests()
|
||||
ADDITIONAL_OPTIONS+=('--s3-storage')
|
||||
fi
|
||||
|
||||
if [[ -n "$USE_AZURE_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_AZURE_STORAGE_FOR_MERGE_TREE" -eq 1 ]]; then
|
||||
# to disable the same tests
|
||||
ADDITIONAL_OPTIONS+=('--s3-storage')
|
||||
# azurite is slow, but with these two settings it can be super slow
|
||||
ADDITIONAL_OPTIONS+=('--no-random-settings')
|
||||
ADDITIONAL_OPTIONS+=('--no-random-merge-tree-settings')
|
||||
fi
|
||||
|
||||
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
|
||||
ADDITIONAL_OPTIONS+=('--shared-catalog')
|
||||
fi
|
||||
@ -286,7 +287,7 @@ stop_logs_replication
|
||||
failed_to_save_logs=0
|
||||
for table in query_log zookeeper_log trace_log transactions_info_log metric_log
|
||||
do
|
||||
err=$( { clickhouse-client -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst; } 2>&1 )
|
||||
err=$(clickhouse-client -q "select * from system.$table into outfile '/test_output/$table.tsv.gz' format TSVWithNamesAndTypes")
|
||||
echo "$err"
|
||||
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
|
||||
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
|
||||
|
||||
@ -279,7 +279,7 @@ function check_logs_for_critical_errors()
|
||||
|
||||
function collect_query_and_trace_logs()
|
||||
{
|
||||
for table in query_log trace_log
|
||||
for table in query_log trace_log metric_log
|
||||
do
|
||||
clickhouse-local --config-file=/etc/clickhouse-server/config.xml --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst ||:
|
||||
done
|
||||
|
||||
@ -52,7 +52,6 @@ export ZOOKEEPER_FAULT_INJECTION=1
|
||||
# available for dump via clickhouse-local
|
||||
configure
|
||||
|
||||
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
|
||||
./setup_minio.sh stateless # to have a proper environment
|
||||
|
||||
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
|
||||
|
||||
37
docs/changelogs/v23.8.13.25-lts.md
Normal file
37
docs/changelogs/v23.8.13.25-lts.md
Normal file
@ -0,0 +1,37 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v23.8.13.25-lts (37e034f903e) FIXME as compared to v23.8.12.13-lts (bdbd0d87e5d)
|
||||
|
||||
#### Improvement
|
||||
* Backported in [#61930](https://github.com/ClickHouse/ClickHouse/issues/61930): Fixed accounting of memory allocated before attaching thread to a query or a user. [#56089](https://github.com/ClickHouse/ClickHouse/pull/56089) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
|
||||
#### Build/Testing/Packaging Improvement
|
||||
* Backported in [#62007](https://github.com/ClickHouse/ClickHouse/issues/62007): Remove from the Keeper Docker image the volumes at /etc/clickhouse-keeper and /var/log/clickhouse-keeper. [#61683](https://github.com/ClickHouse/ClickHouse/pull/61683) ([Tristan](https://github.com/Tristan971)).
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
|
||||
* Fix REPLACE/MOVE PARTITION with zero-copy replication [#54193](https://github.com/ClickHouse/ClickHouse/pull/54193) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Fix ATTACH query with external ON CLUSTER [#61365](https://github.com/ClickHouse/ClickHouse/pull/61365) ([Nikolay Degterinsky](https://github.com/evillique)).
|
||||
* Cancel merges before removing moved parts [#61610](https://github.com/ClickHouse/ClickHouse/pull/61610) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Mark CANNOT_PARSE_ESCAPE_SEQUENCE error as parse error to be able to skip it in row input formats [#61883](https://github.com/ClickHouse/ClickHouse/pull/61883) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Try to fix segfault in Hive engine [#62578](https://github.com/ClickHouse/ClickHouse/pull/62578) ([Nikolay Degterinsky](https://github.com/evillique)).
|
||||
|
||||
#### CI Fix or Improvement (changelog entry is not required)
|
||||
|
||||
* Backported in [#62201](https://github.com/ClickHouse/ClickHouse/issues/62201):. [#62190](https://github.com/ClickHouse/ClickHouse/pull/62190) ([Konstantin Bogdanov](https://github.com/thevar1able)).
|
||||
* Backported in [#62796](https://github.com/ClickHouse/ClickHouse/issues/62796): We won't fail the job when GH fails to retrieve the job ID and URLs. [#62651](https://github.com/ClickHouse/ClickHouse/pull/62651) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
|
||||
* Backported in [#62968](https://github.com/ClickHouse/ClickHouse/issues/62968):. [#62932](https://github.com/ClickHouse/ClickHouse/pull/62932) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NO CL CATEGORY
|
||||
|
||||
* Backported in [#62585](https://github.com/ClickHouse/ClickHouse/issues/62585):. [#60078](https://github.com/ClickHouse/ClickHouse/pull/60078) ([Maksim Kita](https://github.com/kitaisreal)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Throw on query timeout in ZooKeeperRetries [#60922](https://github.com/ClickHouse/ClickHouse/pull/60922) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
|
||||
@ -4,7 +4,7 @@ sidebar_position: 30
|
||||
sidebar_label: Replicated
|
||||
---
|
||||
|
||||
# [experimental] Replicated
|
||||
# Replicated
|
||||
|
||||
The engine is based on the [Atomic](../../engines/database-engines/atomic.md) engine. It supports replication of metadata via DDL log being written to ZooKeeper and executed on all of the replicas for a given database.
|
||||
|
||||
|
||||
@ -8,6 +8,8 @@ sidebar_label: HDFS
|
||||
|
||||
This engine provides integration with the [Apache Hadoop](https://en.wikipedia.org/wiki/Apache_Hadoop) ecosystem by allowing to manage data on [HDFS](https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html) via ClickHouse. This engine is similar to the [File](../../../engines/table-engines/special/file.md#table_engines-file) and [URL](../../../engines/table-engines/special/url.md#table_engines-url) engines, but provides Hadoop-specific features.
|
||||
|
||||
This feature is not supported by ClickHouse engineers, and it is known to have a sketchy quality. In case of any problems, fix them yourself and submit a pull request.
|
||||
|
||||
## Usage {#usage}
|
||||
|
||||
``` sql
|
||||
|
||||
@ -10,7 +10,8 @@ The RecipeNLG dataset is available for download [here](https://recipenlg.cs.put.
|
||||
|
||||
1. Go to the download page [https://recipenlg.cs.put.poznan.pl/dataset](https://recipenlg.cs.put.poznan.pl/dataset).
|
||||
1. Accept Terms and Conditions and download zip file.
|
||||
1. Unpack the zip file with `unzip`. You will get the `full_dataset.csv` file.
|
||||
1. Option: Using the `md5sum dataset.zip` to validate the zip file and it should be equal to `3a168dfd0912bb034225619b3586ce76`.
|
||||
1. Unpack the zip file with `unzip dataset.zip`. You will get the `full_dataset.csv` file in the `dataset` directory.
|
||||
|
||||
## Create a Table
|
||||
|
||||
@ -72,7 +73,7 @@ Result:
|
||||
|
||||
``` text
|
||||
┌─count()─┐
|
||||
│ 2231141 │
|
||||
│ 2231142 │
|
||||
└─────────┘
|
||||
```
|
||||
|
||||
@ -115,7 +116,7 @@ Result:
|
||||
│ egg │ 160507 │
|
||||
│ baking powder │ 148277 │
|
||||
│ lemon juice │ 146414 │
|
||||
│ Salt │ 122557 │
|
||||
│ Salt │ 122558 │
|
||||
│ cinnamon │ 117927 │
|
||||
│ sour cream │ 116682 │
|
||||
│ cream cheese │ 114423 │
|
||||
|
||||
@ -327,7 +327,9 @@ Use buffering to avoid situations where a query processing error occurred after
|
||||
|
||||
## Setting a role with query parameters {#setting-role-with-query-parameters}
|
||||
|
||||
In certain scenarios, it might be required to set the granted role first, before executing the statement itself.
|
||||
This is a new feature added in ClickHouse 24.4.
|
||||
|
||||
In specific scenarios, setting the granted role first might be required before executing the statement itself.
|
||||
However, it is not possible to send `SET ROLE` and the statement together, as multi-statements are not allowed:
|
||||
|
||||
```
|
||||
@ -346,7 +348,7 @@ To overcome this limitation, you could use the `role` query parameter instead:
|
||||
curl -sS "http://localhost:8123?role=my_role" --data-binary "SELECT * FROM my_table;"
|
||||
```
|
||||
|
||||
This will be an equivalent of executing `SET ROLE my_role` before the statement.
|
||||
This will be the equivalent of executing `SET ROLE my_role` before the statement.
|
||||
|
||||
Additionally, it is possible to specify multiple `role` query parameters:
|
||||
|
||||
|
||||
@ -7,6 +7,8 @@ toc_max_heading_level: 2
|
||||
|
||||
# Core Settings
|
||||
|
||||
All below settings are also available in table [system.settings](/docs/en/operations/system-tables/settings).
|
||||
|
||||
## additional_table_filters
|
||||
|
||||
An additional filter expression that is applied after reading
|
||||
@ -3931,19 +3933,6 @@ For example, `avg(if(cond, col, null))` can be rewritten to `avgOrNullIf(cond, c
|
||||
Supported only with experimental analyzer (`allow_experimental_analyzer = 1`).
|
||||
:::
|
||||
|
||||
## allow_experimental_database_replicated {#allow_experimental_database_replicated}
|
||||
|
||||
Enables to create databases with [Replicated](../../engines/database-engines/replicated.md) engine.
|
||||
|
||||
Possible values:
|
||||
|
||||
- 0 — Disabled.
|
||||
- 1 — Enabled.
|
||||
|
||||
Default value: `0`.
|
||||
|
||||
Cloud default value: `1`.
|
||||
|
||||
## database_replicated_initial_query_timeout_sec {#database_replicated_initial_query_timeout_sec}
|
||||
|
||||
Sets how long initial DDL query should wait for Replicated database to process previous DDL queue entries in seconds.
|
||||
|
||||
@ -111,7 +111,7 @@ On newer Linux kernels transparent huge pages are alright.
|
||||
$ echo 'madvise' | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
|
||||
```
|
||||
|
||||
If you want to modify the transparent huge pages setting permanently, editing the `/etc/default/grub` to add the `transparent_hugepage=never` to the `GRUB_CMDLINE_LINUX_DEFAULT` option:
|
||||
If you want to modify the transparent huge pages setting permanently, editing the `/etc/default/grub` to add the `transparent_hugepage=madvise` to the `GRUB_CMDLINE_LINUX_DEFAULT` option:
|
||||
|
||||
```bash
|
||||
$ GRUB_CMDLINE_LINUX_DEFAULT="transparent_hugepage=madvise ..."
|
||||
|
||||
@ -3213,6 +3213,74 @@ Result:
|
||||
└───────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## connectionId
|
||||
|
||||
Retrieves the connection ID of the client that submitted the current query and returns it as a UInt64 integer.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
connectionId()
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
None.
|
||||
|
||||
**Returned value**
|
||||
|
||||
Returns an integer of type UInt64.
|
||||
|
||||
**Implementation details**
|
||||
|
||||
This function is most useful in debugging scenarios or for internal purposes within the MySQL handler. It was created for compatibility with [MySQL's `CONNECTION_ID` function](https://dev.mysql.com/doc/refman/8.0/en/information-functions.html#function_connection-id) It is not typically used in production queries.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT connectionId();
|
||||
```
|
||||
|
||||
```response
|
||||
0
|
||||
```
|
||||
|
||||
## connection_id
|
||||
|
||||
An alias of `connectionId`. Retrieves the connection ID of the client that submitted the current query and returns it as a UInt64 integer.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
connection_id()
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
None.
|
||||
|
||||
**Returned value**
|
||||
|
||||
Returns an integer of type UInt64.
|
||||
|
||||
**Implementation details**
|
||||
|
||||
This function is most useful in debugging scenarios or for internal purposes within the MySQL handler. It was created for compatibility with [MySQL's `CONNECTION_ID` function](https://dev.mysql.com/doc/refman/8.0/en/information-functions.html#function_connection-id) It is not typically used in production queries.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT connection_id();
|
||||
```
|
||||
|
||||
```response
|
||||
0
|
||||
```
|
||||
|
||||
## getClientHTTPHeader
|
||||
|
||||
Get the value of an HTTP header.
|
||||
|
||||
@ -79,9 +79,9 @@ round(expression [, decimal_places])
|
||||
|
||||
The rounded number of the same type as the input number.
|
||||
|
||||
### Examples
|
||||
**Examples**
|
||||
|
||||
**Example of use with Float**
|
||||
Example of usage with Float:
|
||||
|
||||
``` sql
|
||||
SELECT number / 2 AS x, round(x) FROM system.numbers LIMIT 3;
|
||||
@ -95,7 +95,7 @@ SELECT number / 2 AS x, round(x) FROM system.numbers LIMIT 3;
|
||||
└─────┴──────────────────────────┘
|
||||
```
|
||||
|
||||
**Example of use with Decimal**
|
||||
Example of usage with Decimal:
|
||||
|
||||
``` sql
|
||||
SELECT cast(number / 2 AS Decimal(10,4)) AS x, round(x) FROM system.numbers LIMIT 3;
|
||||
@ -124,9 +124,7 @@ SELECT cast(number / 2 AS Decimal(10,4)) AS x, round(x) FROM system.numbers LIM
|
||||
└────────┴──────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Examples of rounding**
|
||||
|
||||
Rounding to the nearest number.
|
||||
Examples of rounding to the nearest number:
|
||||
|
||||
``` text
|
||||
round(3.2, 0) = 3
|
||||
@ -183,9 +181,7 @@ roundBankers(expression [, decimal_places])
|
||||
|
||||
A value rounded by the banker’s rounding method.
|
||||
|
||||
### Examples
|
||||
|
||||
**Example of use**
|
||||
**Examples**
|
||||
|
||||
Query:
|
||||
|
||||
@ -210,7 +206,7 @@ Result:
|
||||
└─────┴───┘
|
||||
```
|
||||
|
||||
**Examples of Banker’s rounding**
|
||||
Examples of Banker’s rounding:
|
||||
|
||||
``` text
|
||||
roundBankers(0.4) = 0
|
||||
@ -226,25 +222,180 @@ roundBankers(10.755, 2) = 10.76
|
||||
|
||||
- [round](#rounding_functions-round)
|
||||
|
||||
## roundToExp2(num)
|
||||
## roundToExp2
|
||||
|
||||
Accepts a number. If the number is less than one, it returns 0. Otherwise, it rounds the number down to the nearest (whole non-negative) degree of two.
|
||||
Accepts a number. If the number is less than one, it returns `0`. Otherwise, it rounds the number down to the nearest (whole non-negative) degree of two.
|
||||
|
||||
## roundDuration(num)
|
||||
**Syntax**
|
||||
|
||||
Accepts a number. If the number is less than one, it returns 0. Otherwise, it rounds the number down to numbers from the set: 1, 10, 30, 60, 120, 180, 240, 300, 600, 1200, 1800, 3600, 7200, 18000, 36000.
|
||||
```sql
|
||||
roundToExp2(num)
|
||||
```
|
||||
|
||||
## roundAge(num)
|
||||
**Parameters**
|
||||
|
||||
Accepts a number. If the number is
|
||||
- smaller than 1, it returns 0,
|
||||
- between 1 and 17, it returns 17,
|
||||
- between 18 and 24, it returns 18,
|
||||
- between 25 and 34, it returns 25,
|
||||
- between 35 and 44, it returns 35,
|
||||
- between 45 and 54, it returns 45,
|
||||
- larger than 55, it returns 55.
|
||||
- `num`: A number representing an age in years. [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md).
|
||||
|
||||
## roundDown(num, arr)
|
||||
**Returned value**
|
||||
|
||||
- `0`, for `num` $\lt 1$. [UInt8](../data-types/int-uint.md).
|
||||
- `num` rounded down to the nearest (whole non-negative) degree of two. [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md) equivalent to the input type.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT *, roundToExp2(*) FROM system.numbers WHERE number IN (0, 2, 5, 10, 19, 50)
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─number─┬─roundToExp2(number)─┐
|
||||
│ 0 │ 0 │
|
||||
│ 2 │ 2 │
|
||||
│ 5 │ 4 │
|
||||
│ 10 │ 8 │
|
||||
│ 19 │ 16 │
|
||||
│ 50 │ 32 │
|
||||
└────────┴─────────────────────┘
|
||||
```
|
||||
|
||||
## roundDuration
|
||||
|
||||
Accepts a number. If the number is less than one, it returns `0`. Otherwise, it rounds the number down to numbers from the set of commonly used durations: `1, 10, 30, 60, 120, 180, 240, 300, 600, 1200, 1800, 3600, 7200, 18000, 36000`.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
roundDuration(num)
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `num`: A number to round to one of the numbers in the set of common durations. [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md).
|
||||
|
||||
**Returned value**
|
||||
|
||||
- `0`, for `num` $\lt 1$.
|
||||
- Otherwise, one of: `1, 10, 30, 60, 120, 180, 240, 300, 600, 1200, 1800, 3600, 7200, 18000, 36000`. [UInt16](../data-types/int-uint.md).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT *, roundDuration(*) FROM system.numbers WHERE number IN (0, 9, 19, 47, 101, 149, 205, 271, 421, 789, 1423, 2345, 4567, 9876, 24680, 42573)
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─number─┬─roundDuration(number)─┐
|
||||
│ 0 │ 0 │
|
||||
│ 9 │ 1 │
|
||||
│ 19 │ 10 │
|
||||
│ 47 │ 30 │
|
||||
│ 101 │ 60 │
|
||||
│ 149 │ 120 │
|
||||
│ 205 │ 180 │
|
||||
│ 271 │ 240 │
|
||||
│ 421 │ 300 │
|
||||
│ 789 │ 600 │
|
||||
│ 1423 │ 1200 │
|
||||
│ 2345 │ 1800 │
|
||||
│ 4567 │ 3600 │
|
||||
│ 9876 │ 7200 │
|
||||
│ 24680 │ 18000 │
|
||||
│ 42573 │ 36000 │
|
||||
└────────┴───────────────────────┘
|
||||
```
|
||||
|
||||
## roundAge
|
||||
|
||||
Accepts a number within various commonly used ranges of human age and returns either a maximum or a minimum within that range.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
roundAge(num)
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `age`: A number representing an age in years. [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md).
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Returns `0`, for $age \lt 1$.
|
||||
- Returns `17`, for $1 \leq age \leq 17$.
|
||||
- Returns `18`, for $18 \leq age \leq 24$.
|
||||
- Returns `25`, for $25 \leq age \leq 34$.
|
||||
- Returns `35`, for $35 \leq age \leq 44$.
|
||||
- Returns `45`, for $45 \leq age \leq 54$.
|
||||
- Returns `55`, for $age \geq 55$.
|
||||
|
||||
Type: [UInt8](../data-types/int-uint.md).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT *, roundAge(*) FROM system.numbers WHERE number IN (0, 5, 20, 31, 37, 54, 72);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─number─┬─roundAge(number)─┐
|
||||
│ 0 │ 0 │
|
||||
│ 5 │ 17 │
|
||||
│ 20 │ 18 │
|
||||
│ 31 │ 25 │
|
||||
│ 37 │ 35 │
|
||||
│ 54 │ 45 │
|
||||
│ 72 │ 55 │
|
||||
└────────┴──────────────────┘
|
||||
```
|
||||
|
||||
## roundDown
|
||||
|
||||
Accepts a number and rounds it down to an element in the specified array. If the value is less than the lowest bound, the lowest bound is returned.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
roundDown(num, arr)
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `num`: A number to round down. [Numeric](../data-types/int-uint.md).
|
||||
- `arr`: Array of elements to round `age` down to. [Array](../data-types/array.md) of [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md) type.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Number rounded down to an element in `arr`. If the value is less than the lowest bound, the lowest bound is returned. [UInt](../data-types/int-uint.md)/[Float](../data-types/float.md) type deduced from the type of `arr`.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT *, roundDown(*, [3, 4, 5]) FROM system.numbers WHERE number IN (0, 1, 2, 3, 4, 5)
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─number─┬─roundDown(number, [3, 4, 5])─┐
|
||||
│ 0 │ 3 │
|
||||
│ 1 │ 3 │
|
||||
│ 2 │ 3 │
|
||||
│ 3 │ 3 │
|
||||
│ 4 │ 4 │
|
||||
│ 5 │ 5 │
|
||||
└────────┴──────────────────────────────┘
|
||||
```
|
||||
|
||||
@ -6,24 +6,29 @@ sidebar_label: Embedded Dictionaries
|
||||
|
||||
# Functions for Working with Embedded Dictionaries
|
||||
|
||||
:::note
|
||||
In order for the functions below to work, the server config must specify the paths and addresses for getting all the embedded dictionaries. The dictionaries are loaded at the first call of any of these functions. If the reference lists can’t be loaded, an exception is thrown.
|
||||
|
||||
For information about creating reference lists, see the section “Dictionaries”.
|
||||
As such, the examples shown in this section will throw an exception in [ClickHouse Fiddle](https://fiddle.clickhouse.com/) and in quick release and production deployments by default, unless first configured.
|
||||
:::
|
||||
|
||||
For information about creating reference lists, see the section [“Dictionaries”](../dictionaries#embedded-dictionaries).
|
||||
|
||||
## Multiple Geobases
|
||||
|
||||
ClickHouse supports working with multiple alternative geobases (regional hierarchies) simultaneously, in order to support various perspectives on which countries certain regions belong to.
|
||||
|
||||
The ‘clickhouse-server’ config specifies the file with the regional hierarchy::`<path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file>`
|
||||
The ‘clickhouse-server’ config specifies the file with the regional hierarchy:
|
||||
|
||||
Besides this file, it also searches for files nearby that have the _ symbol and any suffix appended to the name (before the file extension).
|
||||
For example, it will also find the file `/opt/geo/regions_hierarchy_ua.txt`, if present.
|
||||
```<path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file>```
|
||||
|
||||
`ua` is called the dictionary key. For a dictionary without a suffix, the key is an empty string.
|
||||
Besides this file, it also searches for files nearby that have the `_` symbol and any suffix appended to the name (before the file extension).
|
||||
For example, it will also find the file `/opt/geo/regions_hierarchy_ua.txt`, if present. Here `ua` is called the dictionary key. For a dictionary without a suffix, the key is an empty string.
|
||||
|
||||
All the dictionaries are re-loaded in runtime (once every certain number of seconds, as defined in the builtin_dictionaries_reload_interval config parameter, or once an hour by default). However, the list of available dictionaries is defined one time, when the server starts.
|
||||
All the dictionaries are re-loaded during runtime (once every certain number of seconds, as defined in the [`builtin_dictionaries_reload_interval`](../../operations/server-configuration-parameters/settings#builtin-dictionaries-reload-interval) config parameter, or once an hour by default). However, the list of available dictionaries is defined once, when the server starts.
|
||||
|
||||
All functions for working with regions have an optional argument at the end – the dictionary key. It is referred to as the geobase.
|
||||
|
||||
Example:
|
||||
|
||||
``` sql
|
||||
@ -32,13 +37,116 @@ regionToCountry(RegionID, '') – Uses the default dictionary: /opt/geo/regions_
|
||||
regionToCountry(RegionID, 'ua') – Uses the dictionary for the 'ua' key: /opt/geo/regions_hierarchy_ua.txt
|
||||
```
|
||||
|
||||
### regionToCity(id\[, geobase\])
|
||||
### regionToName
|
||||
|
||||
Accepts a UInt32 number – the region ID from the geobase. If this region is a city or part of a city, it returns the region ID for the appropriate city. Otherwise, returns 0.
|
||||
Accepts a region ID and geobase and returns a string of the name of the region in the corresponding language. If the region with the specified ID does not exist, an empty string is returned.
|
||||
|
||||
### regionToArea(id\[, geobase\])
|
||||
**Syntax**
|
||||
|
||||
Converts a region to an area (type 5 in the geobase). In every other way, this function is the same as ‘regionToCity’.
|
||||
``` sql
|
||||
regionToName(id\[, lang\])
|
||||
```
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Name of the region in the corresponding language specified by `geobase`. [String](../data-types/string).
|
||||
- Otherwise, an empty string.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionToName(number::UInt32,'en') FROM numbers(0,5);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┐
|
||||
│ │
|
||||
│ World │
|
||||
│ USA │
|
||||
│ Colorado │
|
||||
│ Boulder County │
|
||||
└────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToCity
|
||||
|
||||
Accepts a region ID from the geobase. If this region is a city or part of a city, it returns the region ID for the appropriate city. Otherwise, returns 0.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
regionToCity(id [, geobase])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Region ID for the appropriate city, if it exists. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT regionToName(number::UInt32, 'en'), regionToCity(number::UInt32) AS id, regionToName(id, 'en') FROM numbers(13);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┬─id─┬─regionToName(regionToCity(CAST(number, 'UInt32')), 'en')─┐
|
||||
│ │ 0 │ │
|
||||
│ World │ 0 │ │
|
||||
│ USA │ 0 │ │
|
||||
│ Colorado │ 0 │ │
|
||||
│ Boulder County │ 0 │ │
|
||||
│ Boulder │ 5 │ Boulder │
|
||||
│ China │ 0 │ │
|
||||
│ Sichuan │ 0 │ │
|
||||
│ Chengdu │ 8 │ Chengdu │
|
||||
│ America │ 0 │ │
|
||||
│ North America │ 0 │ │
|
||||
│ Eurasia │ 0 │ │
|
||||
│ Asia │ 0 │ │
|
||||
└────────────────────────────────────────────┴────┴──────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToArea
|
||||
|
||||
Converts a region to an area (type 5 in the geobase). In every other way, this function is the same as [‘regionToCity’](#regiontocity).
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
regionToArea(id [, geobase])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Region ID for the appropriate area, if it exists. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT DISTINCT regionToName(regionToArea(toUInt32(number), 'ua'))
|
||||
@ -46,6 +154,8 @@ FROM system.numbers
|
||||
LIMIT 15
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(regionToArea(toUInt32(number), \'ua\'))─┐
|
||||
│ │
|
||||
@ -66,16 +176,38 @@ LIMIT 15
|
||||
└──────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToDistrict(id\[, geobase\])
|
||||
### regionToDistrict
|
||||
|
||||
Converts a region to a federal district (type 4 in the geobase). In every other way, this function is the same as ‘regionToCity’.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
regionToDistrict(id [, geobase])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Region ID for the appropriate city, if it exists. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT DISTINCT regionToName(regionToDistrict(toUInt32(number), 'ua'))
|
||||
FROM system.numbers
|
||||
LIMIT 15
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(regionToDistrict(toUInt32(number), \'ua\'))─┐
|
||||
│ │
|
||||
@ -96,17 +228,103 @@ LIMIT 15
|
||||
└──────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToCountry(id\[, geobase\])
|
||||
### regionToCountry
|
||||
|
||||
Converts a region to a country. In every other way, this function is the same as ‘regionToCity’.
|
||||
Example: `regionToCountry(toUInt32(213)) = 225` converts Moscow (213) to Russia (225).
|
||||
Converts a region to a country (type 3 in the geobase). In every other way, this function is the same as ‘regionToCity’.
|
||||
|
||||
### regionToContinent(id\[, geobase\])
|
||||
**Syntax**
|
||||
|
||||
Converts a region to a continent. In every other way, this function is the same as ‘regionToCity’.
|
||||
Example: `regionToContinent(toUInt32(213)) = 10001` converts Moscow (213) to Eurasia (10001).
|
||||
```sql
|
||||
regionToCountry(id [, geobase])
|
||||
```
|
||||
|
||||
### regionToTopContinent(id\[, geobase\])
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Region ID for the appropriate country, if it exists. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionToName(number::UInt32, 'en'), regionToCountry(number::UInt32) AS id, regionToName(id, 'en') FROM numbers(13);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┬─id─┬─regionToName(regionToCountry(CAST(number, 'UInt32')), 'en')─┐
|
||||
│ │ 0 │ │
|
||||
│ World │ 0 │ │
|
||||
│ USA │ 2 │ USA │
|
||||
│ Colorado │ 2 │ USA │
|
||||
│ Boulder County │ 2 │ USA │
|
||||
│ Boulder │ 2 │ USA │
|
||||
│ China │ 6 │ China │
|
||||
│ Sichuan │ 6 │ China │
|
||||
│ Chengdu │ 6 │ China │
|
||||
│ America │ 0 │ │
|
||||
│ North America │ 0 │ │
|
||||
│ Eurasia │ 0 │ │
|
||||
│ Asia │ 0 │ │
|
||||
└────────────────────────────────────────────┴────┴─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToContinent
|
||||
|
||||
Converts a region to a continent (type 1 in the geobase). In every other way, this function is the same as ‘regionToCity’.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
regionToContinent(id [, geobase])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Region ID for the appropriate continent, if it exists. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionToName(number::UInt32, 'en'), regionToContinent(number::UInt32) AS id, regionToName(id, 'en') FROM numbers(13);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┬─id─┬─regionToName(regionToContinent(CAST(number, 'UInt32')), 'en')─┐
|
||||
│ │ 0 │ │
|
||||
│ World │ 0 │ │
|
||||
│ USA │ 10 │ North America │
|
||||
│ Colorado │ 10 │ North America │
|
||||
│ Boulder County │ 10 │ North America │
|
||||
│ Boulder │ 10 │ North America │
|
||||
│ China │ 12 │ Asia │
|
||||
│ Sichuan │ 12 │ Asia │
|
||||
│ Chengdu │ 12 │ Asia │
|
||||
│ America │ 9 │ America │
|
||||
│ North America │ 10 │ North America │
|
||||
│ Eurasia │ 11 │ Eurasia │
|
||||
│ Asia │ 12 │ Asia │
|
||||
└────────────────────────────────────────────┴────┴───────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToTopContinent
|
||||
|
||||
Finds the highest continent in the hierarchy for the region.
|
||||
|
||||
@ -116,37 +334,175 @@ Finds the highest continent in the hierarchy for the region.
|
||||
regionToTopContinent(id[, geobase])
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../../sql-reference/data-types/int-uint.md).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../../sql-reference/data-types/string.md). Optional.
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Identifier of the top level continent (the latter when you climb the hierarchy of regions).
|
||||
- Identifier of the top level continent (the latter when you climb the hierarchy of regions).[UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
Type: `UInt32`.
|
||||
**Example**
|
||||
|
||||
### regionToPopulation(id\[, geobase\])
|
||||
Query:
|
||||
|
||||
Gets the population for a region.
|
||||
The population can be recorded in files with the geobase. See the section “Dictionaries”.
|
||||
If the population is not recorded for the region, it returns 0.
|
||||
In the geobase, the population might be recorded for child regions, but not for parent regions.
|
||||
``` sql
|
||||
SELECT regionToName(number::UInt32, 'en'), regionToTopContinent(number::UInt32) AS id, regionToName(id, 'en') FROM numbers(13);
|
||||
```
|
||||
|
||||
### regionIn(lhs, rhs\[, geobase\])
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┬─id─┬─regionToName(regionToTopContinent(CAST(number, 'UInt32')), 'en')─┐
|
||||
│ │ 0 │ │
|
||||
│ World │ 0 │ │
|
||||
│ USA │ 9 │ America │
|
||||
│ Colorado │ 9 │ America │
|
||||
│ Boulder County │ 9 │ America │
|
||||
│ Boulder │ 9 │ America │
|
||||
│ China │ 11 │ Eurasia │
|
||||
│ Sichuan │ 11 │ Eurasia │
|
||||
│ Chengdu │ 11 │ Eurasia │
|
||||
│ America │ 9 │ America │
|
||||
│ North America │ 9 │ America │
|
||||
│ Eurasia │ 11 │ Eurasia │
|
||||
│ Asia │ 11 │ Eurasia │
|
||||
└────────────────────────────────────────────┴────┴──────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### regionToPopulation
|
||||
|
||||
Gets the population for a region. The population can be recorded in files with the geobase. See the section [“Dictionaries”](../dictionaries#embedded-dictionaries). If the population is not recorded for the region, it returns 0. In the geobase, the population might be recorded for child regions, but not for parent regions.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
regionToPopulation(id[, geobase])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Population for the region. [UInt32](../data-types/int-uint).
|
||||
- 0, if there is none.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionToName(number::UInt32, 'en'), regionToPopulation(number::UInt32) AS id, regionToName(id, 'en') FROM numbers(13);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─regionToName(CAST(number, 'UInt32'), 'en')─┬─population─┐
|
||||
│ │ 0 │
|
||||
│ World │ 4294967295 │
|
||||
│ USA │ 330000000 │
|
||||
│ Colorado │ 5700000 │
|
||||
│ Boulder County │ 330000 │
|
||||
│ Boulder │ 100000 │
|
||||
│ China │ 1500000000 │
|
||||
│ Sichuan │ 83000000 │
|
||||
│ Chengdu │ 20000000 │
|
||||
│ America │ 1000000000 │
|
||||
│ North America │ 600000000 │
|
||||
│ Eurasia │ 4294967295 │
|
||||
│ Asia │ 4294967295 │
|
||||
└────────────────────────────────────────────┴────────────┘
|
||||
```
|
||||
|
||||
### regionIn
|
||||
|
||||
Checks whether a `lhs` region belongs to a `rhs` region. Returns a UInt8 number equal to 1 if it belongs, or 0 if it does not belong.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
regionIn(lhs, rhs\[, geobase\])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `lhs` — Lhs region ID from the geobase. [UInt32](../../sql-reference/data-types/int-uint).
|
||||
- `rhs` — Rhs region ID from the geobase. [UInt32](../../sql-reference/data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- 1, if it belongs. [UInt8](../../sql-reference/data-types/int-uint).
|
||||
- 0, if it doesn't belong.
|
||||
|
||||
**Implementation details**
|
||||
|
||||
Checks whether a ‘lhs’ region belongs to a ‘rhs’ region. Returns a UInt8 number equal to 1 if it belongs, or 0 if it does not belong.
|
||||
The relationship is reflexive – any region also belongs to itself.
|
||||
|
||||
### regionHierarchy(id\[, geobase\])
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionToName(n1.number::UInt32, 'en') || (regionIn(n1.number::UInt32, n2.number::UInt32) ? ' is in ' : ' is not in ') || regionToName(n2.number::UInt32, 'en') FROM numbers(1,2) AS n1 CROSS JOIN numbers(1,5) AS n2;
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
World is in World
|
||||
World is not in USA
|
||||
World is not in Colorado
|
||||
World is not in Boulder County
|
||||
World is not in Boulder
|
||||
USA is in World
|
||||
USA is in USA
|
||||
USA is not in Colorado
|
||||
USA is not in Boulder County
|
||||
USA is not in Boulder
|
||||
```
|
||||
|
||||
### regionHierarchy
|
||||
|
||||
Accepts a UInt32 number – the region ID from the geobase. Returns an array of region IDs consisting of the passed region and all parents along the chain.
|
||||
Example: `regionHierarchy(toUInt32(213)) = [213,1,3,225,10001,10000]`.
|
||||
|
||||
### regionToName(id\[, lang\])
|
||||
**Syntax**
|
||||
|
||||
Accepts a UInt32 number – the region ID from the geobase. A string with the name of the language can be passed as a second argument. Supported languages are: ru, en, ua, uk, by, kz, tr. If the second argument is omitted, the language ‘ru’ is used. If the language is not supported, an exception is thrown. Returns a string – the name of the region in the corresponding language. If the region with the specified ID does not exist, an empty string is returned.
|
||||
``` sql
|
||||
regionHierarchy(id\[, geobase\])
|
||||
```
|
||||
|
||||
`ua` and `uk` both mean Ukrainian.
|
||||
**Parameters**
|
||||
|
||||
- `id` — Region ID from the geobase. [UInt32](../data-types/int-uint).
|
||||
- `geobase` — Dictionary key. See [Multiple Geobases](#multiple-geobases). [String](../data-types/string). Optional.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Array of region IDs consisting of the passed region and all parents along the chain. [Array](../data-types/array)([UInt32](../data-types/int-uint)).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT regionHierarchy(number::UInt32) AS arr, arrayMap(id -> regionToName(id, 'en'), arr) FROM numbers(5);
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─arr────────────┬─arrayMap(lambda(tuple(id), regionToName(id, 'en')), regionHierarchy(CAST(number, 'UInt32')))─┐
|
||||
│ [] │ [] │
|
||||
│ [1] │ ['World'] │
|
||||
│ [2,10,9,1] │ ['USA','North America','America','World'] │
|
||||
│ [3,2,10,9,1] │ ['Colorado','USA','North America','America','World'] │
|
||||
│ [4,3,2,10,9,1] │ ['Boulder County','Colorado','USA','North America','America','World'] │
|
||||
└────────────────┴──────────────────────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
@ -19,25 +19,51 @@ Subquery is another `SELECT` query that may be specified in parenthesis inside `
|
||||
|
||||
## FINAL Modifier
|
||||
|
||||
When `FINAL` is specified, ClickHouse fully merges the data before returning the result and thus performs all data transformations that happen during merges for the given table engine.
|
||||
When `FINAL` is specified, ClickHouse fully merges the data before returning the result. This also performs all data transformations that happen during merges for the given table engine.
|
||||
|
||||
It is applicable when selecting data from ReplacingMergeTree, SummingMergeTree, AggregatingMergeTree, CollapsingMergeTree and VersionedCollapsingMergeTree tables.
|
||||
It is applicable when selecting data from from tables using the following table engines:
|
||||
- `ReplacingMergeTree`
|
||||
- `SummingMergeTree`
|
||||
- `AggregatingMergeTree`
|
||||
- `CollapsingMergeTree`
|
||||
- `VersionedCollapsingMergeTree`
|
||||
|
||||
`SELECT` queries with `FINAL` are executed in parallel. The [max_final_threads](../../../operations/settings/settings.md#max-final-threads) setting limits the number of threads used.
|
||||
|
||||
There are drawbacks to using `FINAL` (see below).
|
||||
|
||||
### Drawbacks
|
||||
|
||||
Queries that use `FINAL` are executed slightly slower than similar queries that do not, because:
|
||||
Queries that use `FINAL` execute slightly slower than similar queries that do not use `FINAL` because:
|
||||
|
||||
- Data is merged during query execution.
|
||||
- Queries with `FINAL` read primary key columns in addition to the columns specified in the query.
|
||||
- Queries with `FINAL` may read primary key columns in addition to the columns specified in the query.
|
||||
|
||||
`FINAL` requires additional compute and memory resources, as the processing that normally would occur at merge time must occur in memory at the time of the query. However, using FINAL is sometimes necessary in order to produce accurate results, and is less expensive than running `OPTIMIZE` to force a merge. It is also sometimes possible to use different queries that assume the background processes of the `MergeTree` engine haven’t happened yet and deal with it by applying aggregation (for example, to discard duplicates). If you need to use FINAL in your queries in order to get the required results, then it is okay to do so but be aware of the additional processing required.
|
||||
`FINAL` requires additional compute and memory resources because the processing that normally would occur at merge time must occur in memory at the time of the query. However, using FINAL is sometimes necessary in order to produce accurate results (as data may not yet be fully merged). It is less expensive than running `OPTIMIZE` to force a merge.
|
||||
|
||||
As an alternative to using `FINAL`, it is sometimes possible to use different queries that assume the background processes of the `MergeTree` engine have not yet occurred and deal with it by applying an aggregation (for example, to discard duplicates). If you need to use `FINAL` in your queries in order to get the required results, it is okay to do so but be aware of the additional processing required.
|
||||
|
||||
`FINAL` can be applied automatically using [FINAL](../../../operations/settings/settings.md#final) setting to all tables in a query using a session or a user profile.
|
||||
|
||||
### Example Usage
|
||||
|
||||
**Using the `FINAL` keyword**
|
||||
|
||||
```sql
|
||||
SELECT x, y FROM mytable FINAL WHERE x > 1;
|
||||
```
|
||||
|
||||
**Using `FINAL` as a query-level setting**
|
||||
|
||||
```sql
|
||||
SELECT x, y FROM mytable WHERE x > 1 SETTINGS final = 1;
|
||||
```
|
||||
|
||||
**Using `FINAL` as a session-level setting**
|
||||
|
||||
```sql
|
||||
SET final = 1;
|
||||
SELECT x, y FROM mytable WHERE x > 1;
|
||||
```
|
||||
|
||||
## Implementation Details
|
||||
|
||||
If the `FROM` clause is omitted, data will be read from the `system.one` table.
|
||||
|
||||
@ -3447,17 +3447,6 @@ SELECT
|
||||
FROM fuse_tbl
|
||||
```
|
||||
|
||||
## allow_experimental_database_replicated {#allow_experimental_database_replicated}
|
||||
|
||||
Позволяет создавать базы данных с движком [Replicated](../../engines/database-engines/replicated.md).
|
||||
|
||||
Возможные значения:
|
||||
|
||||
- 0 — Disabled.
|
||||
- 1 — Enabled.
|
||||
|
||||
Значение по умолчанию: `0`.
|
||||
|
||||
## database_replicated_initial_query_timeout_sec {#database_replicated_initial_query_timeout_sec}
|
||||
|
||||
Устанавливает, как долго начальный DDL-запрос должен ждать, пока реплицированная база данных прецессирует предыдущие записи очереди DDL в секундах.
|
||||
|
||||
@ -5,7 +5,7 @@ sidebar_position: 106
|
||||
|
||||
# argMax {#agg-function-argmax}
|
||||
|
||||
Вычисляет значение `arg` при максимальном значении `val`.
|
||||
Вычисляет значение `arg` при максимальном значении `val`. Если несколько строк имеют одинаковое `val`, в которых равное значение является максимальным, то возвращаемое `arg` не является детерминированным. Обе части, arg и max, ведут себя как агрегатные функции, они обе пропускают Null во время обработки и возвращают не Null значения, если не Null значения доступны.
|
||||
|
||||
**Синтаксис**
|
||||
|
||||
@ -49,3 +49,60 @@ SELECT argMax(user, salary), argMax(tuple(user, salary), salary) FROM salary;
|
||||
│ director │ ('director',5000) │
|
||||
└──────────────────────┴─────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Дополнительный пример**
|
||||
|
||||
```sql
|
||||
CREATE TABLE test
|
||||
(
|
||||
a Nullable(String),
|
||||
b Nullable(Int64)
|
||||
)
|
||||
ENGINE = Memory AS
|
||||
SELECT *
|
||||
FROM VALUES(('a', 1), ('b', 2), ('c', 2), (NULL, 3), (NULL, NULL), ('d', NULL));
|
||||
|
||||
select * from test;
|
||||
┌─a────┬────b─┐
|
||||
│ a │ 1 │
|
||||
│ b │ 2 │
|
||||
│ c │ 2 │
|
||||
│ ᴺᵁᴸᴸ │ 3 │
|
||||
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │
|
||||
│ d │ ᴺᵁᴸᴸ │
|
||||
└──────┴──────┘
|
||||
|
||||
SELECT argMax(a, b), max(b) FROM test;
|
||||
┌─argMax(a, b)─┬─max(b)─┐
|
||||
│ b │ 3 │ -- argMax = 'b' потому что это первое not Null значение, max(b) из другой строки!
|
||||
└──────────────┴────────┘
|
||||
|
||||
SELECT argMax(tuple(a), b) FROM test;
|
||||
┌─argMax(tuple(a), b)─┐
|
||||
│ (NULL) │ -- Кортеж `Tuple`, который содержит только `NULL` значения является не `NULL` кортежем, поэтому агрегатыне функции не будут пропускать эту строку с `NULL` значениями.
|
||||
└─────────────────────┘
|
||||
|
||||
SELECT (argMax((a, b), b) as t).1 argMaxA, t.2 argMaxB FROM test;
|
||||
┌─argMaxA─┬─argMaxB─┐
|
||||
│ ᴺᵁᴸᴸ │ 3 │ -- Вы можете использовать кортеж Tuple и получить оба значения для соответсвующего max(b).
|
||||
└─────────┴─────────┘
|
||||
|
||||
SELECT argMax(a, b), max(b) FROM test WHERE a IS NULL AND b IS NULL;
|
||||
┌─argMax(a, b)─┬─max(b)─┐
|
||||
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ -- Все агрегированные строки содержат хотя бы одно `NULL` значение, поэтому все строки пропускаются и результатом будет `NULL`.
|
||||
└──────────────┴────────┘
|
||||
|
||||
SELECT argMax(a, (b,a)) FROM test;
|
||||
┌─argMax(a, tuple(b, a))─┐
|
||||
│ c │ -- Есть две строки с b=2, кортеж `Tuple` в функции `Max` позволяет получить не первый `arg`.
|
||||
└────────────────────────┘
|
||||
|
||||
SELECT argMax(a, tuple(b)) FROM test;
|
||||
┌─argMax(a, tuple(b))─┐
|
||||
│ b │ -- Кортеж `Tuple` может использоваться в `Max`, чтобы не пропускать `NULL` значения в `Max`.
|
||||
└─────────────────────┘
|
||||
```
|
||||
|
||||
**Смотрите также**
|
||||
|
||||
- [Tuple](/docs/ru/sql-reference/data-types/tuple.md)
|
||||
|
||||
@ -918,11 +918,13 @@ bool Client::processWithFuzzing(const String & full_query)
|
||||
}
|
||||
|
||||
|
||||
void Client::printHelpMessage(const OptionsDescription & options_description)
|
||||
void Client::printHelpMessage(const OptionsDescription & options_description, bool verbose)
|
||||
{
|
||||
std::cout << options_description.main_description.value() << "\n";
|
||||
std::cout << options_description.external_description.value() << "\n";
|
||||
std::cout << options_description.hosts_and_ports_description.value() << "\n";
|
||||
if (verbose)
|
||||
std::cout << "All settings are documented at https://clickhouse.com/docs/en/operations/settings/settings.\n\n";
|
||||
std::cout << "In addition, --param_name=value can be specified for substitution of parameters for parametrized queries.\n";
|
||||
std::cout << "\nSee also: https://clickhouse.com/docs/en/integrations/sql-clients/cli\n";
|
||||
}
|
||||
|
||||
@ -25,7 +25,7 @@ protected:
|
||||
|
||||
String getName() const override { return "client"; }
|
||||
|
||||
void printHelpMessage(const OptionsDescription & options_description) override;
|
||||
void printHelpMessage(const OptionsDescription & options_description, bool verbose) override;
|
||||
|
||||
void addOptions(OptionsDescription & options_description) override;
|
||||
|
||||
|
||||
@ -774,10 +774,12 @@ void LocalServer::processConfig()
|
||||
}
|
||||
|
||||
|
||||
void LocalServer::printHelpMessage([[maybe_unused]] const OptionsDescription & options_description)
|
||||
void LocalServer::printHelpMessage(const OptionsDescription & options_description, bool verbose)
|
||||
{
|
||||
std::cout << getHelpHeader() << "\n";
|
||||
std::cout << options_description.main_description.value() << "\n";
|
||||
if (verbose)
|
||||
std::cout << "All settings are documented at https://clickhouse.com/docs/en/operations/settings/settings.\n\n";
|
||||
std::cout << getHelpFooter() << "\n";
|
||||
std::cout << "In addition, --param_name=value can be specified for substitution of parameters for parametrized queries.\n";
|
||||
std::cout << "\nSee also: https://clickhouse.com/docs/en/operations/utilities/clickhouse-local/\n";
|
||||
|
||||
@ -36,7 +36,7 @@ protected:
|
||||
|
||||
String getName() const override { return "local"; }
|
||||
|
||||
void printHelpMessage(const OptionsDescription & options_description) override;
|
||||
void printHelpMessage(const OptionsDescription & options_description, bool verbose) override;
|
||||
|
||||
void addOptions(OptionsDescription & options_description) override;
|
||||
|
||||
|
||||
@ -280,11 +280,11 @@ void AccessControl::setUpFromMainConfig(const Poco::Util::AbstractConfiguration
|
||||
|
||||
/// Optional improvements in access control system.
|
||||
/// The default values are false because we need to be compatible with earlier access configurations
|
||||
setEnabledUsersWithoutRowPoliciesCanReadRows(config_.getBool("access_control_improvements.users_without_row_policies_can_read_rows", false));
|
||||
setOnClusterQueriesRequireClusterGrant(config_.getBool("access_control_improvements.on_cluster_queries_require_cluster_grant", false));
|
||||
setSelectFromSystemDatabaseRequiresGrant(config_.getBool("access_control_improvements.select_from_system_db_requires_grant", false));
|
||||
setSelectFromInformationSchemaRequiresGrant(config_.getBool("access_control_improvements.select_from_information_schema_requires_grant", false));
|
||||
setSettingsConstraintsReplacePrevious(config_.getBool("access_control_improvements.settings_constraints_replace_previous", false));
|
||||
setEnabledUsersWithoutRowPoliciesCanReadRows(config_.getBool("access_control_improvements.users_without_row_policies_can_read_rows", true));
|
||||
setOnClusterQueriesRequireClusterGrant(config_.getBool("access_control_improvements.on_cluster_queries_require_cluster_grant", true));
|
||||
setSelectFromSystemDatabaseRequiresGrant(config_.getBool("access_control_improvements.select_from_system_db_requires_grant", true));
|
||||
setSelectFromInformationSchemaRequiresGrant(config_.getBool("access_control_improvements.select_from_information_schema_requires_grant", true));
|
||||
setSettingsConstraintsReplacePrevious(config_.getBool("access_control_improvements.settings_constraints_replace_previous", true));
|
||||
setTableEnginesRequireGrant(config_.getBool("access_control_improvements.table_engines_require_grant", false));
|
||||
|
||||
addStoragesFromMainConfig(config_, config_path_, get_zookeeper_function_);
|
||||
|
||||
@ -165,7 +165,6 @@ private:
|
||||
|
||||
/** ClickHouse query tree pass manager.
|
||||
*
|
||||
* TODO: Support setting optimize_monotonous_functions_in_order_by.
|
||||
* TODO: Add optimizations based on function semantics. Example: SELECT * FROM test_table WHERE id != id. (id is not nullable column).
|
||||
*/
|
||||
|
||||
|
||||
@ -221,7 +221,8 @@ std::unique_ptr<WriteBuffer> BackupWriterAzureBlobStorage::writeFile(const Strin
|
||||
key,
|
||||
DBMS_DEFAULT_BUFFER_SIZE,
|
||||
write_settings,
|
||||
settings);
|
||||
settings,
|
||||
threadPoolCallbackRunnerUnsafe<void>(getBackupsIOThreadPool().get(), "BackupWRAzure"));
|
||||
}
|
||||
|
||||
void BackupWriterAzureBlobStorage::removeFile(const String & file_name)
|
||||
|
||||
@ -109,7 +109,7 @@ RestorerFromBackup::~RestorerFromBackup()
|
||||
if (getNumFutures() > 0)
|
||||
{
|
||||
LOG_INFO(log, "Waiting for {} tasks to finish", getNumFutures());
|
||||
waitFutures();
|
||||
waitFutures(/* throw_if_error= */ false);
|
||||
}
|
||||
}
|
||||
|
||||
@ -161,7 +161,7 @@ void RestorerFromBackup::run(Mode mode)
|
||||
setStage(Stage::COMPLETED);
|
||||
}
|
||||
|
||||
void RestorerFromBackup::waitFutures()
|
||||
void RestorerFromBackup::waitFutures(bool throw_if_error)
|
||||
{
|
||||
std::exception_ptr error;
|
||||
|
||||
@ -176,11 +176,7 @@ void RestorerFromBackup::waitFutures()
|
||||
if (futures_to_wait.empty())
|
||||
break;
|
||||
|
||||
/// Wait for all tasks.
|
||||
for (auto & future : futures_to_wait)
|
||||
future.wait();
|
||||
|
||||
/// Check if there is an exception.
|
||||
/// Wait for all tasks to finish.
|
||||
for (auto & future : futures_to_wait)
|
||||
{
|
||||
try
|
||||
@ -197,7 +193,12 @@ void RestorerFromBackup::waitFutures()
|
||||
}
|
||||
|
||||
if (error)
|
||||
std::rethrow_exception(error);
|
||||
{
|
||||
if (throw_if_error)
|
||||
std::rethrow_exception(error);
|
||||
else
|
||||
tryLogException(error, log);
|
||||
}
|
||||
}
|
||||
|
||||
size_t RestorerFromBackup::getNumFutures() const
|
||||
|
||||
@ -130,7 +130,7 @@ private:
|
||||
|
||||
/// Waits until all tasks are processed (including the tasks scheduled while we're waiting).
|
||||
/// Throws an exception if any of the tasks throws an exception.
|
||||
void waitFutures();
|
||||
void waitFutures(bool throw_if_error = true);
|
||||
|
||||
/// Throws an exception if the RESTORE query was cancelled.
|
||||
void checkIsQueryCancelled() const;
|
||||
|
||||
@ -2955,7 +2955,8 @@ void ClientBase::init(int argc, char ** argv)
|
||||
|
||||
/// Common options for clickhouse-client and clickhouse-local.
|
||||
options_description.main_description->add_options()
|
||||
("help", "produce help message")
|
||||
("help", "print usage summary, combine with --verbose to display all options")
|
||||
("verbose", "print query and other debugging info")
|
||||
("version,V", "print version information and exit")
|
||||
("version-clean", "print version in machine-readable format and exit")
|
||||
|
||||
@ -2979,7 +2980,6 @@ void ClientBase::init(int argc, char ** argv)
|
||||
("time,t", "print query execution time to stderr in non-interactive mode (for benchmarks)")
|
||||
|
||||
("echo", "in batch mode, print query before execution")
|
||||
("verbose", "print query and other debugging info")
|
||||
|
||||
("log-level", po::value<std::string>(), "log level")
|
||||
("server_logs_file", po::value<std::string>(), "put server logs into specified file")
|
||||
@ -3008,6 +3008,8 @@ void ClientBase::init(int argc, char ** argv)
|
||||
|
||||
addOptions(options_description);
|
||||
|
||||
OptionsDescription options_description_non_verbose = options_description;
|
||||
|
||||
auto getter = [](const auto & op)
|
||||
{
|
||||
String op_long_name = op->long_name();
|
||||
@ -3042,11 +3044,17 @@ void ClientBase::init(int argc, char ** argv)
|
||||
exit(0); // NOLINT(concurrency-mt-unsafe)
|
||||
}
|
||||
|
||||
if (options.count("verbose"))
|
||||
config().setBool("verbose", true);
|
||||
|
||||
/// Output of help message.
|
||||
if (options.count("help")
|
||||
|| (options.count("host") && options["host"].as<std::string>() == "elp")) /// If user writes -help instead of --help.
|
||||
{
|
||||
printHelpMessage(options_description);
|
||||
if (config().getBool("verbose", false))
|
||||
printHelpMessage(options_description, true);
|
||||
else
|
||||
printHelpMessage(options_description_non_verbose, false);
|
||||
exit(0); // NOLINT(concurrency-mt-unsafe)
|
||||
}
|
||||
|
||||
@ -3113,8 +3121,6 @@ void ClientBase::init(int argc, char ** argv)
|
||||
config().setBool("highlight", options["highlight"].as<bool>());
|
||||
if (options.count("history_file"))
|
||||
config().setString("history_file", options["history_file"].as<std::string>());
|
||||
if (options.count("verbose"))
|
||||
config().setBool("verbose", true);
|
||||
if (options.count("interactive"))
|
||||
config().setBool("interactive", true);
|
||||
if (options.count("pager"))
|
||||
|
||||
@ -121,7 +121,7 @@ protected:
|
||||
};
|
||||
|
||||
virtual void updateLoggerLevel(const String &) {}
|
||||
virtual void printHelpMessage(const OptionsDescription & options_description) = 0;
|
||||
virtual void printHelpMessage(const OptionsDescription & options_description, bool verbose) = 0;
|
||||
virtual void addOptions(OptionsDescription & options_description) = 0;
|
||||
virtual void processOptions(const OptionsDescription & options_description,
|
||||
const CommandLineOptions & options,
|
||||
|
||||
@ -28,28 +28,6 @@ namespace ErrorCodes
|
||||
extern const int USER_SESSION_LIMIT_EXCEEDED;
|
||||
}
|
||||
|
||||
Suggest::Suggest()
|
||||
{
|
||||
/// Keywords may be not up to date with ClickHouse parser.
|
||||
addWords({"CREATE", "DATABASE", "IF", "NOT", "EXISTS", "TEMPORARY", "TABLE", "ON",
|
||||
"CLUSTER", "DEFAULT", "MATERIALIZED", "ALIAS", "ENGINE", "AS", "VIEW", "POPULATE",
|
||||
"SETTINGS", "ATTACH", "DETACH", "DROP", "RENAME", "TO", "ALTER", "ADD",
|
||||
"MODIFY", "CLEAR", "COLUMN", "AFTER", "COPY", "PROJECT", "PRIMARY", "KEY",
|
||||
"CHECK", "PARTITION", "PART", "FREEZE", "FETCH", "FROM", "SHOW", "INTO",
|
||||
"OUTFILE", "FORMAT", "TABLES", "DATABASES", "LIKE", "PROCESSLIST", "CASE", "WHEN",
|
||||
"THEN", "ELSE", "END", "DESCRIBE", "DESC", "USE", "SET", "OPTIMIZE",
|
||||
"FINAL", "DEDUPLICATE", "INSERT", "VALUES", "SELECT", "DISTINCT", "SAMPLE", "ARRAY",
|
||||
"JOIN", "GLOBAL", "LOCAL", "ANY", "ALL", "INNER", "LEFT", "RIGHT",
|
||||
"FULL", "OUTER", "CROSS", "USING", "PREWHERE", "WHERE", "GROUP", "BY",
|
||||
"WITH", "TOTALS", "HAVING", "ORDER", "COLLATE", "LIMIT", "UNION", "AND",
|
||||
"OR", "ASC", "IN", "KILL", "QUERY", "SYNC", "ASYNC", "TEST",
|
||||
"BETWEEN", "TRUNCATE", "USER", "ROLE", "PROFILE", "QUOTA", "POLICY", "ROW",
|
||||
"GRANT", "REVOKE", "OPTION", "ADMIN", "EXCEPT", "REPLACE", "IDENTIFIED", "HOST",
|
||||
"NAME", "READONLY", "WRITABLE", "PERMISSIVE", "FOR", "RESTRICTIVE", "RANDOMIZED", "INTERVAL",
|
||||
"LIMITS", "ONLY", "TRACKING", "IP", "REGEXP", "ILIKE", "CLEANUP", "APPEND",
|
||||
"IGNORE NULLS", "RESPECT NULLS", "OVER", "PASTE", "WINDOW", "QUALIFY"});
|
||||
}
|
||||
|
||||
static String getLoadSuggestionQuery(Int32 suggestion_limit, bool basic_suggestion)
|
||||
{
|
||||
/// NOTE: Once you will update the completion list,
|
||||
@ -82,6 +60,7 @@ static String getLoadSuggestionQuery(Int32 suggestion_limit, bool basic_suggesti
|
||||
add_column("name", "data_type_families", false, {});
|
||||
add_column("name", "merge_tree_settings", false, {});
|
||||
add_column("name", "settings", false, {});
|
||||
add_column("keyword", "keywords", false, {});
|
||||
|
||||
if (!basic_suggestion)
|
||||
{
|
||||
|
||||
@ -17,7 +17,7 @@ namespace DB
|
||||
class Suggest : public LineReader::Suggest, boost::noncopyable
|
||||
{
|
||||
public:
|
||||
Suggest();
|
||||
Suggest() = default;
|
||||
|
||||
~Suggest()
|
||||
{
|
||||
|
||||
@ -24,6 +24,7 @@ public:
|
||||
void updateHash(SipHash & hash) const override;
|
||||
|
||||
protected:
|
||||
/// 1 byte (`gcd_bytes_size` value) + 1 byte (`bytes_to_skip` value) + `bytes_to_skip` bytes (trash) + `gcd_bytes_size` bytes (gcd value) + (`source_size` - `bytes_to_skip`) bytes (data)
|
||||
UInt32 doCompressData(const char * source, UInt32 source_size, char * dest) const override;
|
||||
void doDecompressData(const char * source, UInt32 source_size, char * dest, UInt32 uncompressed_size) const override;
|
||||
UInt32 getMaxCompressedDataSize(UInt32 uncompressed_size) const override;
|
||||
@ -54,7 +55,7 @@ UInt32 CompressionCodecGCD::getMaxCompressedDataSize(UInt32 uncompressed_size) c
|
||||
{
|
||||
return uncompressed_size
|
||||
+ gcd_bytes_size // To store gcd
|
||||
+ 2; // Local header
|
||||
+ 2; // Values of `gcd_bytes_size` and `bytes_to_skip`
|
||||
}
|
||||
|
||||
uint8_t CompressionCodecGCD::getMethodByte() const
|
||||
@ -147,7 +148,7 @@ void decompressDataForType(const char * source, UInt32 source_size, char * dest,
|
||||
if (source_size - sizeof(T) != output_size)
|
||||
throw Exception(ErrorCodes::CANNOT_DECOMPRESS, "Cannot decompress GCD-encoded data");
|
||||
|
||||
memcpy(dest, source, source_size);
|
||||
memcpy(dest, source, source_size - sizeof(T));
|
||||
return;
|
||||
}
|
||||
|
||||
@ -160,6 +161,7 @@ void decompressDataForType(const char * source, UInt32 source_size, char * dest,
|
||||
source += sizeof(T);
|
||||
dest += sizeof(T);
|
||||
}
|
||||
chassert(source == source_end);
|
||||
}
|
||||
|
||||
}
|
||||
@ -209,6 +211,8 @@ void CompressionCodecGCD::doDecompressData(const char * source, UInt32 source_si
|
||||
throw Exception(ErrorCodes::CANNOT_DECOMPRESS, "Cannot decompress GCD-encoded data. File has wrong header");
|
||||
|
||||
UInt8 bytes_to_skip = uncompressed_size % bytes_size;
|
||||
chassert(bytes_to_skip == static_cast<UInt8>(source[1]));
|
||||
|
||||
UInt32 output_size = uncompressed_size - bytes_to_skip;
|
||||
|
||||
if (static_cast<UInt32>(2 + bytes_to_skip) > source_size)
|
||||
|
||||
@ -112,6 +112,7 @@ class IColumn;
|
||||
M(Bool, azure_create_new_file_on_insert, false, "Enables or disables creating a new file on each insert in azure engine tables", 0) \
|
||||
M(Bool, s3_check_objects_after_upload, false, "Check each uploaded object to s3 with head request to be sure that upload was successful", 0) \
|
||||
M(Bool, s3_allow_parallel_part_upload, true, "Use multiple threads for s3 multipart upload. It may lead to slightly higher memory usage", 0) \
|
||||
M(Bool, azure_allow_parallel_part_upload, true, "Use multiple threads for azure multipart upload.", 0) \
|
||||
M(Bool, s3_throw_on_zero_files_match, false, "Throw an error, when ListObjects request cannot match any files", 0) \
|
||||
M(Bool, s3_disable_checksum, false, "Do not calculate a checksum when sending a file to S3. This speeds up writes by avoiding excessive processing passes on a file. It is mostly safe as the data of MergeTree tables is checksummed by ClickHouse anyway, and when S3 is accessed with HTTPS, the TLS layer already provides integrity while transferring through the network. While additional checksums on S3 give defense in depth.", 0) \
|
||||
M(UInt64, s3_retry_attempts, 100, "Setting for Aws::Client::RetryStrategy, Aws::Client does retries itself, 0 means no retries", 0) \
|
||||
@ -604,7 +605,6 @@ class IColumn;
|
||||
M(Bool, optimize_if_chain_to_multiif, false, "Replace if(cond1, then1, if(cond2, ...)) chains to multiIf. Currently it's not beneficial for numeric types.", 0) \
|
||||
M(Bool, optimize_multiif_to_if, true, "Replace 'multiIf' with only one condition to 'if'.", 0) \
|
||||
M(Bool, optimize_if_transform_strings_to_enum, false, "Replaces string-type arguments in If and Transform to enum. Disabled by default cause it could make inconsistent change in distributed query that would lead to its fail.", 0) \
|
||||
M(Bool, optimize_monotonous_functions_in_order_by, false, "Replace monotonous function with its argument in ORDER BY", 0) \
|
||||
M(Bool, optimize_functions_to_subcolumns, false, "Transform functions to subcolumns, if possible, to reduce amount of read data. E.g. 'length(arr)' -> 'arr.size0', 'col IS NULL' -> 'col.null' ", 0) \
|
||||
M(Bool, optimize_using_constraints, false, "Use constraints for query optimization", 0) \
|
||||
M(Bool, optimize_substitute_columns, false, "Use constraints for column substitution", 0) \
|
||||
@ -707,7 +707,6 @@ class IColumn;
|
||||
M(Bool, engine_file_skip_empty_files, false, "Allows to skip empty files in file table engine", 0) \
|
||||
M(Bool, engine_url_skip_empty_files, false, "Allows to skip empty files in url table engine", 0) \
|
||||
M(Bool, enable_url_encoding, true, " Allows to enable/disable decoding/encoding path in uri in URL table engine", 0) \
|
||||
M(Bool, allow_experimental_database_replicated, false, "Allow to create databases with Replicated engine", 0) \
|
||||
M(UInt64, database_replicated_initial_query_timeout_sec, 300, "How long initial DDL query should wait for Replicated database to precess previous DDL queue entries", 0) \
|
||||
M(Bool, database_replicated_enforce_synchronous_settings, false, "Enforces synchronous waiting for some queries (see also database_atomic_wait_for_drop_and_detach_synchronously, mutation_sync, alter_sync). Not recommended to enable these settings.", 0) \
|
||||
M(UInt64, max_distributed_depth, 5, "Maximum distributed query depth", 0) \
|
||||
@ -934,6 +933,7 @@ class IColumn;
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_query_cache, true) \
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_alter_materialized_view_structure, true) \
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_shared_merge_tree, true) \
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_database_replicated, true) \
|
||||
\
|
||||
MAKE_OBSOLETE(M, Milliseconds, async_insert_stale_timeout_ms, 0) \
|
||||
MAKE_OBSOLETE(M, StreamingHandleErrorMode, handle_kafka_error_mode, StreamingHandleErrorMode::DEFAULT) \
|
||||
@ -978,6 +978,7 @@ class IColumn;
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_undrop_table_query, true) \
|
||||
MAKE_OBSOLETE(M, Bool, allow_experimental_s3queue, true) \
|
||||
MAKE_OBSOLETE(M, Bool, query_plan_optimize_primary_key, true) \
|
||||
MAKE_OBSOLETE(M, Bool, optimize_monotonous_functions_in_order_by, false) \
|
||||
|
||||
/** The section above is for obsolete settings. Do not add anything there. */
|
||||
|
||||
|
||||
@ -92,9 +92,11 @@ static std::map<ClickHouseVersion, SettingsChangesHistory::SettingsChanges> sett
|
||||
{"input_format_json_ignore_unnecessary_fields", false, true, "Ignore unnecessary fields and not parse them. Enabling this may not throw exceptions on json strings of invalid format or with duplicated fields"},
|
||||
{"input_format_hive_text_allow_variable_number_of_columns", false, true, "Ignore extra columns in Hive Text input (if file has more columns than expected) and treat missing fields in Hive Text input as default values."},
|
||||
{"first_day_of_week", "Monday", "Monday", "Added a setting for the first day of the week for date/time functions"},
|
||||
{"allow_experimental_database_replicated", false, true, "Database engine Replicated is now in Beta stage"},
|
||||
{"temporary_data_in_cache_reserve_space_wait_lock_timeout_milliseconds", (10 * 60 * 1000), (10 * 60 * 1000), "Wait time to lock cache for sapce reservation in temporary data in filesystem cache"},
|
||||
{"prefer_external_sort_block_bytes", 0, DEFAULT_BLOCK_SIZE * 256, "Prefer maximum block bytes for external sort, reduce the memory usage during merging."}
|
||||
}},
|
||||
{"azure_allow_parallel_part_upload", "true", "true", "Use multiple threads for azure multipart upload."},
|
||||
{"prefer_external_sort_block_bytes", 0, DEFAULT_BLOCK_SIZE * 256, "Prefer maximum block bytes for external sort, reduce the memory usage during merging."},
|
||||
}},
|
||||
{"24.3", {{"s3_connect_timeout_ms", 1000, 1000, "Introduce new dedicated setting for s3 connection timeout"},
|
||||
{"allow_experimental_shared_merge_tree", false, true, "The setting is obsolete"},
|
||||
{"use_page_cache_for_disks_without_file_cache", false, false, "Added userspace page cache"},
|
||||
|
||||
@ -1139,8 +1139,10 @@ void DatabaseReplicated::recoverLostReplica(const ZooKeeperPtr & current_zookeep
|
||||
}
|
||||
LOG_INFO(log, "All tables are created successfully");
|
||||
|
||||
chassert(max_log_ptr_at_creation || our_log_ptr);
|
||||
UInt32 first_entry_to_mark_finished = new_replica ? max_log_ptr_at_creation : our_log_ptr;
|
||||
/// NOTE first_entry_to_mark_finished can be 0 if our replica has crashed just after creating its nodes in ZK,
|
||||
/// so it's a new replica, but after restarting we don't know max_log_ptr_at_creation anymore...
|
||||
/// It's a very rare case, and it's okay if some queries throw TIMEOUT_EXCEEDED when waiting for all replicas
|
||||
if (first_entry_to_mark_finished)
|
||||
{
|
||||
/// If the replica is new and some of the queries applied during recovery
|
||||
|
||||
@ -154,6 +154,7 @@ void IDisk::copyThroughBuffers(
|
||||
/// Disable parallel write. We already copy in parallel.
|
||||
/// Avoid high memory usage. See test_s3_zero_copy_ttl/test.py::test_move_and_s3_memory_usage
|
||||
write_settings.s3_allow_parallel_part_upload = false;
|
||||
write_settings.azure_allow_parallel_part_upload = false;
|
||||
|
||||
asyncCopy(*this, from_path, *to_disk, to_path, copying_thread_pool, results, copy_root_dir, read_settings, write_settings, cancellation_hook);
|
||||
|
||||
|
||||
@ -282,12 +282,17 @@ std::unique_ptr<WriteBufferFromFileBase> AzureObjectStorage::writeObject( /// NO
|
||||
|
||||
LOG_TEST(log, "Writing file: {}", object.remote_path);
|
||||
|
||||
ThreadPoolCallbackRunnerUnsafe<void> scheduler;
|
||||
if (write_settings.azure_allow_parallel_part_upload)
|
||||
scheduler = threadPoolCallbackRunnerUnsafe<void>(getThreadPoolWriter(), "VFSWrite");
|
||||
|
||||
return std::make_unique<WriteBufferFromAzureBlobStorage>(
|
||||
client.get(),
|
||||
object.remote_path,
|
||||
buf_size,
|
||||
patchSettings(write_settings),
|
||||
settings.get());
|
||||
settings.get(),
|
||||
std::move(scheduler));
|
||||
}
|
||||
|
||||
void AzureObjectStorage::removeObjectImpl(const StoredObject & object, const SharedAzureClientPtr & client_ptr, bool if_exists)
|
||||
|
||||
@ -1169,7 +1169,10 @@ struct ToStartOfHourImpl
|
||||
struct ToYearImpl
|
||||
{
|
||||
static constexpr auto name = "toYear";
|
||||
|
||||
static UInt16 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toYear(t);
|
||||
}
|
||||
static UInt16 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toYear(t);
|
||||
@ -1217,7 +1220,10 @@ struct ToWeekYearImpl
|
||||
static constexpr auto name = "toWeekYear";
|
||||
|
||||
static constexpr Int8 week_mode = 3;
|
||||
|
||||
static UInt16 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toYearWeek(t, week_mode).first;
|
||||
}
|
||||
static UInt16 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toYearWeek(t, week_mode).first;
|
||||
@ -1241,7 +1247,10 @@ struct ToWeekYearImpl
|
||||
struct ToWeekOfWeekYearImpl
|
||||
{
|
||||
static constexpr auto name = "toWeekOfWeekYear";
|
||||
|
||||
static UInt16 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOWeek(t);
|
||||
}
|
||||
static UInt16 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOWeek(t);
|
||||
@ -1265,7 +1274,10 @@ struct ToWeekOfWeekYearImpl
|
||||
struct ToQuarterImpl
|
||||
{
|
||||
static constexpr auto name = "toQuarter";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toQuarter(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toQuarter(t);
|
||||
@ -1290,7 +1302,10 @@ struct ToQuarterImpl
|
||||
struct ToMonthImpl
|
||||
{
|
||||
static constexpr auto name = "toMonth";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toMonth(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toMonth(t);
|
||||
@ -1315,7 +1330,10 @@ struct ToMonthImpl
|
||||
struct ToDayOfMonthImpl
|
||||
{
|
||||
static constexpr auto name = "toDayOfMonth";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfMonth(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfMonth(t);
|
||||
@ -1341,7 +1359,10 @@ struct ToDayOfWeekImpl
|
||||
{
|
||||
static constexpr auto name = "toDayOfWeek";
|
||||
static constexpr bool value_may_be_string = true;
|
||||
|
||||
static UInt8 execute(UInt64 t, UInt8 mode, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfWeek(t, mode);
|
||||
}
|
||||
static UInt8 execute(Int64 t, UInt8 mode, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfWeek(t, mode);
|
||||
@ -1365,7 +1386,10 @@ struct ToDayOfWeekImpl
|
||||
struct ToDayOfYearImpl
|
||||
{
|
||||
static constexpr auto name = "toDayOfYear";
|
||||
|
||||
static UInt16 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfYear(t);
|
||||
}
|
||||
static UInt16 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toDayOfYear(t);
|
||||
@ -1421,7 +1445,10 @@ public:
|
||||
struct ToHourImpl
|
||||
{
|
||||
static constexpr auto name = "toHour";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toHour(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toHour(t);
|
||||
@ -1446,7 +1473,10 @@ struct ToHourImpl
|
||||
struct TimezoneOffsetImpl
|
||||
{
|
||||
static constexpr auto name = "timezoneOffset";
|
||||
|
||||
static time_t execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.timezoneOffset(t);
|
||||
}
|
||||
static time_t execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.timezoneOffset(t);
|
||||
@ -1474,7 +1504,10 @@ struct TimezoneOffsetImpl
|
||||
struct ToMinuteImpl
|
||||
{
|
||||
static constexpr auto name = "toMinute";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toMinute(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toMinute(t);
|
||||
@ -1499,7 +1532,10 @@ struct ToMinuteImpl
|
||||
struct ToSecondImpl
|
||||
{
|
||||
static constexpr auto name = "toSecond";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toSecond(t);
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toSecond(t);
|
||||
@ -1550,7 +1586,10 @@ struct ToMillisecondImpl
|
||||
struct ToISOYearImpl
|
||||
{
|
||||
static constexpr auto name = "toISOYear";
|
||||
|
||||
static UInt16 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOYear(time_zone.toDayNum(t));
|
||||
}
|
||||
static UInt16 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOYear(time_zone.toDayNum(t));
|
||||
@ -1607,7 +1646,10 @@ struct ToStartOfISOYearImpl
|
||||
struct ToISOWeekImpl
|
||||
{
|
||||
static constexpr auto name = "toISOWeek";
|
||||
|
||||
static UInt8 execute(UInt64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOWeek(time_zone.toDayNum(t));
|
||||
}
|
||||
static UInt8 execute(Int64 t, const DateLUTImpl & time_zone)
|
||||
{
|
||||
return time_zone.toISOWeek(time_zone.toDayNum(t));
|
||||
|
||||
@ -62,8 +62,8 @@ template <> struct InstructionValueTypeMap<DataTypeInt16> { using Instructi
|
||||
template <> struct InstructionValueTypeMap<DataTypeUInt16> { using InstructionValueType = UInt32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeInt32> { using InstructionValueType = UInt32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeUInt32> { using InstructionValueType = UInt32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeInt64> { using InstructionValueType = UInt32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeUInt64> { using InstructionValueType = UInt32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeInt64> { using InstructionValueType = Int64; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeUInt64> { using InstructionValueType = UInt64; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeDate> { using InstructionValueType = UInt16; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeDate32> { using InstructionValueType = Int32; };
|
||||
template <> struct InstructionValueTypeMap<DataTypeDateTime> { using InstructionValueType = UInt32; };
|
||||
@ -1017,7 +1017,7 @@ public:
|
||||
else
|
||||
{
|
||||
for (auto & instruction : instructions)
|
||||
instruction.perform(pos, static_cast<UInt32>(vec[i]), 0, 0, *time_zone);
|
||||
instruction.perform(pos, static_cast<T>(vec[i]), 0, 0, *time_zone);
|
||||
}
|
||||
*pos++ = '\0';
|
||||
|
||||
@ -1073,7 +1073,7 @@ public:
|
||||
{
|
||||
/// DateTime/DateTime64 --> insert instruction
|
||||
/// Other types cannot provide the requested data --> write out template
|
||||
if constexpr (is_any_of<T, UInt32, Int64>)
|
||||
if constexpr (is_any_of<T, UInt32, Int64, UInt64>)
|
||||
{
|
||||
Instruction<T> instruction;
|
||||
instruction.setMysqlFunc(std::move(func));
|
||||
@ -1539,7 +1539,7 @@ public:
|
||||
/// If the argument was DateTime, add instruction for printing. If it was date, just append default literal
|
||||
auto add_instruction = [&]([[maybe_unused]] typename Instruction<T>::FuncJoda && func, [[maybe_unused]] const String & default_literal)
|
||||
{
|
||||
if constexpr (is_any_of<T, UInt32, Int64>)
|
||||
if constexpr (is_any_of<T, UInt32, Int64, UInt64>)
|
||||
{
|
||||
Instruction<T> instruction;
|
||||
instruction.setJodaFunc(std::move(func));
|
||||
|
||||
@ -23,6 +23,7 @@ struct WriteSettings
|
||||
size_t filesystem_cache_reserve_space_wait_lock_timeout_milliseconds = 1000;
|
||||
|
||||
bool s3_allow_parallel_part_upload = true;
|
||||
bool azure_allow_parallel_part_upload = true;
|
||||
|
||||
/// Monitoring
|
||||
bool for_object_storage = false; // to choose which profile events should be incremented
|
||||
|
||||
@ -118,7 +118,7 @@ LockedKeyPtr KeyMetadata::lockNoStateCheck()
|
||||
return std::make_unique<LockedKey>(shared_from_this());
|
||||
}
|
||||
|
||||
bool KeyMetadata::createBaseDirectory()
|
||||
bool KeyMetadata::createBaseDirectory(bool throw_if_failed)
|
||||
{
|
||||
if (!created_base_directory.exchange(true))
|
||||
{
|
||||
@ -131,7 +131,7 @@ bool KeyMetadata::createBaseDirectory()
|
||||
{
|
||||
created_base_directory = false;
|
||||
|
||||
if (e.code() == std::errc::no_space_on_device)
|
||||
if (!throw_if_failed && e.code() == std::errc::no_space_on_device)
|
||||
{
|
||||
LOG_TRACE(cache_metadata->log, "Failed to create base directory for key {}, "
|
||||
"because no space left on device", key);
|
||||
|
||||
@ -113,7 +113,7 @@ struct KeyMetadata : private std::map<size_t, FileSegmentMetadataPtr>,
|
||||
|
||||
LockedKeyPtr tryLock();
|
||||
|
||||
bool createBaseDirectory();
|
||||
bool createBaseDirectory(bool throw_if_failed = false);
|
||||
|
||||
std::string getPath() const;
|
||||
|
||||
|
||||
@ -54,10 +54,18 @@ WriteBufferToFileSegment::WriteBufferToFileSegment(FileSegmentsHolderPtr segment
|
||||
void WriteBufferToFileSegment::nextImpl()
|
||||
{
|
||||
auto downloader [[maybe_unused]] = file_segment->getOrSetDownloader();
|
||||
chassert(downloader == FileSegment::getCallerId());
|
||||
if (downloader != FileSegment::getCallerId())
|
||||
{
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR,
|
||||
"Failed to set a downloader (current downloader: {}, file segment info: {})",
|
||||
downloader, file_segment->getInfoForLog());
|
||||
}
|
||||
|
||||
SCOPE_EXIT({
|
||||
file_segment->completePartAndResetDownloader();
|
||||
if (file_segment->isDownloader())
|
||||
file_segment->completePartAndResetDownloader();
|
||||
else
|
||||
chassert(false);
|
||||
});
|
||||
|
||||
size_t bytes_to_write = offset();
|
||||
|
||||
@ -245,11 +245,15 @@ void executeQuery(
|
||||
const auto & shard_info = cluster->getShardsInfo()[i];
|
||||
|
||||
auto query_for_shard = query_info.query_tree->clone();
|
||||
if (sharding_key_expr && query_info.optimized_cluster && settings.optimize_skip_unused_shards_rewrite_in && shards > 1)
|
||||
if (sharding_key_expr &&
|
||||
query_info.optimized_cluster &&
|
||||
settings.optimize_skip_unused_shards_rewrite_in &&
|
||||
shards > 1 &&
|
||||
/// TODO: support composite sharding key
|
||||
sharding_key_expr->getRequiredColumns().size() == 1)
|
||||
{
|
||||
OptimizeShardingKeyRewriteInVisitor::Data visitor_data{
|
||||
sharding_key_expr,
|
||||
sharding_key_expr->getSampleBlock().getByPosition(0).type,
|
||||
sharding_key_column_name,
|
||||
shard_info,
|
||||
not_optimized_cluster->getSlotToShard(),
|
||||
@ -282,11 +286,15 @@ void executeQuery(
|
||||
const auto & shard_info = cluster->getShardsInfo()[i];
|
||||
|
||||
ASTPtr query_ast_for_shard = query_info.query->clone();
|
||||
if (sharding_key_expr && query_info.optimized_cluster && settings.optimize_skip_unused_shards_rewrite_in && shards > 1)
|
||||
if (sharding_key_expr &&
|
||||
query_info.optimized_cluster &&
|
||||
settings.optimize_skip_unused_shards_rewrite_in &&
|
||||
shards > 1 &&
|
||||
/// TODO: support composite sharding key
|
||||
sharding_key_expr->getRequiredColumns().size() == 1)
|
||||
{
|
||||
OptimizeShardingKeyRewriteInVisitor::Data visitor_data{
|
||||
sharding_key_expr,
|
||||
sharding_key_expr->getSampleBlock().getByPosition(0).type,
|
||||
sharding_key_column_name,
|
||||
shard_info,
|
||||
not_optimized_cluster->getSlotToShard(),
|
||||
|
||||
@ -5256,6 +5256,7 @@ WriteSettings Context::getWriteSettings() const
|
||||
res.filesystem_cache_reserve_space_wait_lock_timeout_milliseconds = settings.filesystem_cache_reserve_space_wait_lock_timeout_milliseconds;
|
||||
|
||||
res.s3_allow_parallel_part_upload = settings.s3_allow_parallel_part_upload;
|
||||
res.azure_allow_parallel_part_upload = settings.azure_allow_parallel_part_upload;
|
||||
|
||||
res.remote_throttler = getRemoteWriteThrottler();
|
||||
res.local_throttler = getLocalWriteThrottler();
|
||||
|
||||
@ -258,15 +258,6 @@ BlockIO InterpreterCreateQuery::createDatabase(ASTCreateQuery & create)
|
||||
"Enable allow_experimental_database_materialized_mysql to use it");
|
||||
}
|
||||
|
||||
if (create.storage->engine->name == "Replicated"
|
||||
&& !getContext()->getSettingsRef().allow_experimental_database_replicated
|
||||
&& !internal && !create.attach)
|
||||
{
|
||||
throw Exception(ErrorCodes::UNKNOWN_DATABASE_ENGINE,
|
||||
"Replicated is an experimental database engine. "
|
||||
"Enable allow_experimental_database_replicated to use it");
|
||||
}
|
||||
|
||||
if (create.storage->engine->name == "MaterializedPostgreSQL"
|
||||
&& !getContext()->getSettingsRef().allow_experimental_database_materialized_postgresql
|
||||
&& !internal && !create.attach)
|
||||
|
||||
@ -38,25 +38,27 @@ Field executeFunctionOnField(
|
||||
return (*ret.column)[0];
|
||||
}
|
||||
|
||||
/// @param sharding_column_value - one of values from IN
|
||||
/// @param column_value - one of values from IN
|
||||
/// @param sharding_column_name - name of that column
|
||||
/// @return true if shard may contain such value (or it is unknown), otherwise false.
|
||||
bool shardContains(
|
||||
Field sharding_column_value,
|
||||
Field column_value,
|
||||
const std::string & sharding_column_name,
|
||||
const OptimizeShardingKeyRewriteInMatcher::Data & data)
|
||||
{
|
||||
/// Type of column in storage (used for implicit conversion from i.e. String to Int)
|
||||
const DataTypePtr & column_type = data.sharding_key_expr->getSampleBlock().getByName(sharding_column_name).type;
|
||||
/// Implicit conversion.
|
||||
sharding_column_value = convertFieldToType(sharding_column_value, *data.sharding_key_type);
|
||||
column_value = convertFieldToType(column_value, *column_type);
|
||||
|
||||
/// NULL is not allowed in sharding key,
|
||||
/// so it should be safe to assume that shard cannot contain it.
|
||||
if (sharding_column_value.isNull())
|
||||
if (column_value.isNull())
|
||||
return false;
|
||||
|
||||
Field sharding_value = executeFunctionOnField(
|
||||
sharding_column_value, sharding_column_name,
|
||||
data.sharding_key_expr, data.sharding_key_type,
|
||||
column_value, sharding_column_name,
|
||||
data.sharding_key_expr, column_type,
|
||||
data.sharding_key_column_name);
|
||||
/// The value from IN can be non-numeric,
|
||||
/// but in this case it should be convertible to numeric type, let's try.
|
||||
|
||||
@ -28,8 +28,6 @@ struct OptimizeShardingKeyRewriteInMatcher
|
||||
{
|
||||
/// Expression of sharding_key for the Distributed() table
|
||||
const ExpressionActionsPtr & sharding_key_expr;
|
||||
/// Type of sharding_key column.
|
||||
const DataTypePtr & sharding_key_type;
|
||||
/// Name of the column for sharding_expr
|
||||
const std::string & sharding_key_column_name;
|
||||
/// Info for the current shard (to compare shard_num with calculated)
|
||||
|
||||
@ -111,7 +111,7 @@ FileSegmentsHolderPtr TemporaryDataOnDisk::createCacheFile(size_t max_file_size)
|
||||
CreateFileSegmentSettings(FileSegmentKind::Temporary, /* unbounded */ true), FileCache::getCommonUser());
|
||||
|
||||
chassert(holder->size() == 1);
|
||||
holder->back().getKeyMetadata()->createBaseDirectory();
|
||||
holder->back().getKeyMetadata()->createBaseDirectory(/* throw_if_failed */true);
|
||||
|
||||
return holder;
|
||||
}
|
||||
|
||||
@ -368,92 +368,6 @@ std::unordered_set<String> getDistinctNames(const ASTSelectQuery & select)
|
||||
return names;
|
||||
}
|
||||
|
||||
/// Replace monotonous functions in ORDER BY if they don't participate in GROUP BY expression,
|
||||
/// has a single argument and not an aggregate functions.
|
||||
void optimizeMonotonousFunctionsInOrderBy(ASTSelectQuery * select_query, ContextPtr context,
|
||||
const TablesWithColumns & tables_with_columns,
|
||||
const TreeRewriterResult & result)
|
||||
{
|
||||
auto order_by = select_query->orderBy();
|
||||
if (!order_by)
|
||||
return;
|
||||
|
||||
/// Do not apply optimization for Distributed and Merge storages,
|
||||
/// because we can't get the sorting key of their underlying tables
|
||||
/// and we can break the matching of the sorting key for `read_in_order`
|
||||
/// optimization by removing monotonous functions from the prefix of key.
|
||||
if (result.is_remote_storage || (result.storage && result.storage->getName() == "Merge"))
|
||||
return;
|
||||
|
||||
for (const auto & child : order_by->children)
|
||||
{
|
||||
auto * order_by_element = child->as<ASTOrderByElement>();
|
||||
|
||||
if (!order_by_element || order_by_element->children.empty())
|
||||
throw Exception(ErrorCodes::UNKNOWN_TYPE_OF_AST_NODE, "Bad ORDER BY expression AST");
|
||||
|
||||
if (order_by_element->with_fill)
|
||||
return;
|
||||
}
|
||||
|
||||
std::unordered_set<String> group_by_hashes;
|
||||
if (auto group_by = select_query->groupBy())
|
||||
{
|
||||
if (select_query->group_by_with_grouping_sets)
|
||||
{
|
||||
for (auto & set : group_by->children)
|
||||
{
|
||||
for (auto & elem : set->children)
|
||||
{
|
||||
const auto hash = elem->getTreeHash(/*ignore_aliases=*/ true);
|
||||
const auto key = toString(hash);
|
||||
group_by_hashes.insert(key);
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
for (auto & elem : group_by->children)
|
||||
{
|
||||
const auto hash = elem->getTreeHash(/*ignore_aliases=*/ true);
|
||||
const auto key = toString(hash);
|
||||
group_by_hashes.insert(key);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
auto sorting_key_columns = result.storage_snapshot ? result.storage_snapshot->metadata->getSortingKeyColumns() : Names{};
|
||||
|
||||
bool is_sorting_key_prefix = true;
|
||||
for (size_t i = 0; i < order_by->children.size(); ++i)
|
||||
{
|
||||
auto * order_by_element = order_by->children[i]->as<ASTOrderByElement>();
|
||||
|
||||
auto & ast_func = order_by_element->children[0];
|
||||
if (!ast_func->as<ASTFunction>())
|
||||
continue;
|
||||
|
||||
if (i >= sorting_key_columns.size() || ast_func->getColumnName() != sorting_key_columns[i])
|
||||
is_sorting_key_prefix = false;
|
||||
|
||||
/// If order by expression matches the sorting key, do not remove
|
||||
/// functions to allow execute reading in order of key.
|
||||
if (is_sorting_key_prefix)
|
||||
continue;
|
||||
|
||||
MonotonicityCheckVisitor::Data data{tables_with_columns, context, group_by_hashes};
|
||||
MonotonicityCheckVisitor(data).visit(ast_func);
|
||||
|
||||
if (!data.isRejected())
|
||||
{
|
||||
ast_func = data.identifier->clone();
|
||||
ast_func->setAlias("");
|
||||
if (!data.monotonicity.is_positive)
|
||||
order_by_element->direction *= -1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// If ORDER BY has argument x followed by f(x) transforms it to ORDER BY x.
|
||||
/// Optimize ORDER BY x, y, f(x), g(x, y), f(h(x)), t(f(x), g(x)) into ORDER BY x, y
|
||||
/// in case if f(), g(), h(), t() are deterministic (in scope of query).
|
||||
@ -789,10 +703,6 @@ void TreeOptimizer::apply(ASTPtr & query, TreeRewriterResult & result,
|
||||
if (settings.optimize_redundant_functions_in_order_by)
|
||||
optimizeRedundantFunctionsInOrderBy(select_query, context);
|
||||
|
||||
/// Replace monotonous functions with its argument
|
||||
if (settings.optimize_monotonous_functions_in_order_by)
|
||||
optimizeMonotonousFunctionsInOrderBy(select_query, context, tables_with_columns, result);
|
||||
|
||||
/// Remove duplicate items from ORDER BY.
|
||||
/// Execute it after all order by optimizations,
|
||||
/// because they can produce duplicated columns.
|
||||
|
||||
@ -357,6 +357,16 @@ bool ParserFilterClause::parseImpl(Pos & pos, ASTPtr & node, Expected & expected
|
||||
return false;
|
||||
}
|
||||
|
||||
if (function.name == "count")
|
||||
{
|
||||
/// Remove child from function.arguments if it's '*' because countIf(*) is not supported.
|
||||
/// See https://github.com/ClickHouse/ClickHouse/issues/61004
|
||||
std::erase_if(function.arguments->children, [] (const ASTPtr & child)
|
||||
{
|
||||
return typeid_cast<const ASTAsterisk *>(child.get()) || typeid_cast<const ASTQualifiedAsterisk *>(child.get());
|
||||
});
|
||||
}
|
||||
|
||||
function.name += "If";
|
||||
function.arguments->children.push_back(condition->children[0]);
|
||||
return true;
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
#include <cassert>
|
||||
#include <Parsers/CommonParsers.h>
|
||||
|
||||
#include <Parsers/obfuscateQueries.h>
|
||||
#include <Parsers/Lexer.h>
|
||||
@ -11,6 +11,12 @@
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <IO/ReadBufferFromMemory.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <cassert>
|
||||
#include <iterator>
|
||||
|
||||
#include <boost/algorithm/string.hpp>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -24,413 +30,54 @@ namespace ErrorCodes
|
||||
namespace
|
||||
{
|
||||
|
||||
const std::unordered_set<std::string_view> keywords
|
||||
const std::unordered_set<std::string> & getObfuscateKeywords()
|
||||
{
|
||||
"!=",
|
||||
"",
|
||||
"%",
|
||||
"*",
|
||||
"+",
|
||||
"-",
|
||||
"->",
|
||||
".",
|
||||
"/",
|
||||
":",
|
||||
"::",
|
||||
"<",
|
||||
"<=",
|
||||
"<>",
|
||||
"=",
|
||||
"==",
|
||||
"<=>",
|
||||
">",
|
||||
">=",
|
||||
"?",
|
||||
"[",
|
||||
"]+",
|
||||
"]+|[",
|
||||
"^[",
|
||||
"||",
|
||||
"]+$",
|
||||
"ACCESS",
|
||||
"ACTION",
|
||||
"ADD",
|
||||
"ADMIN",
|
||||
"AFTER",
|
||||
"ALGORITHM",
|
||||
"ALIAS",
|
||||
"ALL",
|
||||
"ALLOWED_LATENESS",
|
||||
"ALTER",
|
||||
"AND",
|
||||
"ANTI",
|
||||
"ANY",
|
||||
"APPLY",
|
||||
"ARRAY",
|
||||
"AS",
|
||||
"ASC",
|
||||
"ASCENDING",
|
||||
"ASOF",
|
||||
"ASSUME",
|
||||
"AST",
|
||||
"ASYNC",
|
||||
"ATTACH",
|
||||
"AUTO_INCREMENT",
|
||||
"BACKUP",
|
||||
"BASE_BACKUP",
|
||||
"BEGIN",
|
||||
"BETWEEN",
|
||||
"BIDIRECTIONAL",
|
||||
"BOTH",
|
||||
"BY",
|
||||
"CACHE",
|
||||
"CACHES",
|
||||
"CASCADE",
|
||||
"CASE",
|
||||
"CASEWITHEXPRESSION",
|
||||
"CAST",
|
||||
"CHANGE",
|
||||
"CHANGEABLE_IN_READONLY",
|
||||
"CHANGED",
|
||||
"CHAR",
|
||||
"CHARACTER",
|
||||
"CHECK",
|
||||
"CLEANUP",
|
||||
"CLEAR",
|
||||
"CLUSTER",
|
||||
"CLUSTER_HOST_IDS",
|
||||
"CLUSTERS",
|
||||
"CN",
|
||||
"CODEC",
|
||||
"COLLATE",
|
||||
"COLLECTION",
|
||||
"COLUMN",
|
||||
"COLUMNS",
|
||||
"COMMENT",
|
||||
"COMMIT",
|
||||
"COMPRESSION",
|
||||
"CONCAT",
|
||||
"CONSTRAINT",
|
||||
"CREATE",
|
||||
"CROSS",
|
||||
"CUBE",
|
||||
"CURRENT",
|
||||
"CURRENT_USER",
|
||||
"DATABASE",
|
||||
"DATABASES",
|
||||
"DATE",
|
||||
"DATE_ADD",
|
||||
"DATEADD",
|
||||
"DATE_DIFF",
|
||||
"DATEDIFF",
|
||||
"DATE_SUB",
|
||||
"DATESUB",
|
||||
"DAY",
|
||||
"DD",
|
||||
"DDL",
|
||||
"DEDUPLICATE",
|
||||
"DEFAULT",
|
||||
"DELAY",
|
||||
"DELETE",
|
||||
"DESC",
|
||||
"DESCENDING",
|
||||
"DESCRIBE",
|
||||
"DETACH",
|
||||
"DETACHED",
|
||||
"DICTIONARIES",
|
||||
"DICTIONARY",
|
||||
"DISK",
|
||||
"DISTINCT",
|
||||
"DIV",
|
||||
"DOUBLE_SHA1_HASH",
|
||||
"DROP",
|
||||
"ELSE",
|
||||
"EMPTY",
|
||||
"ENABLED",
|
||||
"END",
|
||||
"ENFORCED",
|
||||
"ENGINE",
|
||||
"EPHEMERAL",
|
||||
"EQUALS",
|
||||
"ESTIMATE",
|
||||
"EVENT",
|
||||
"EVENTS",
|
||||
"EXCEPT",
|
||||
"EXCHANGE",
|
||||
"EXISTS",
|
||||
"EXPLAIN",
|
||||
"EXPRESSION",
|
||||
"EXTERNAL",
|
||||
"EXTRACT",
|
||||
"FALSE",
|
||||
"FETCH",
|
||||
"FILE",
|
||||
"FILESYSTEM",
|
||||
"FILL",
|
||||
"FILTER",
|
||||
"FINAL",
|
||||
"FIRST",
|
||||
"FOLLOWING",
|
||||
"FOR",
|
||||
"FOREIGN",
|
||||
"FORMAT",
|
||||
"FREEZE",
|
||||
"FROM",
|
||||
"FULL",
|
||||
"FULLTEXT",
|
||||
"FUNCTION",
|
||||
"GLOBAL",
|
||||
"GRANT",
|
||||
"GRANTEES",
|
||||
"GRANTS",
|
||||
"GRANULARITY",
|
||||
"GREATER",
|
||||
"GREATEROREQUALS",
|
||||
"GROUP",
|
||||
"GROUPING",
|
||||
"GROUPS",
|
||||
"HASH",
|
||||
"HAVING",
|
||||
"HDFS",
|
||||
"HH",
|
||||
"HIERARCHICAL",
|
||||
"HOST",
|
||||
"HOUR",
|
||||
"ID",
|
||||
"IDENTIFIED",
|
||||
"IF",
|
||||
"ILIKE",
|
||||
"IN",
|
||||
"INDEX",
|
||||
"INFILE",
|
||||
"INHERIT",
|
||||
"INJECTIVE",
|
||||
"INNER",
|
||||
"INSERT",
|
||||
"INTERPOLATE",
|
||||
"INTERSECT",
|
||||
"INTERVAL",
|
||||
"INTO",
|
||||
"INVISIBLE",
|
||||
"IP",
|
||||
"IS",
|
||||
"IS_OBJECT_ID",
|
||||
"JOIN",
|
||||
"KEY",
|
||||
"KEYED",
|
||||
"KILL",
|
||||
"LAMBDA",
|
||||
"LARGE",
|
||||
"LAST",
|
||||
"LAYOUT",
|
||||
"LEADING",
|
||||
"LEFT",
|
||||
"LESS",
|
||||
"LESSOREQUALS",
|
||||
"LEVEL",
|
||||
"LIFETIME",
|
||||
"LIKE",
|
||||
"LIMIT",
|
||||
"LIMITS",
|
||||
"LINEAR",
|
||||
"LIST",
|
||||
"LITERAL",
|
||||
"LIVE",
|
||||
"LOCAL",
|
||||
"LTRIM",
|
||||
"MATCH",
|
||||
"MATERIALIZE",
|
||||
"MATERIALIZED",
|
||||
"MAX",
|
||||
"MCS",
|
||||
"MEMORY",
|
||||
"MI",
|
||||
"MICROSECOND",
|
||||
"MILLISECOND",
|
||||
"MIN",
|
||||
"MINUS",
|
||||
"MINUTE",
|
||||
"MM",
|
||||
"MOD",
|
||||
"MODIFY",
|
||||
"MONTH",
|
||||
"MOVE",
|
||||
"MS",
|
||||
"MULTIIF",
|
||||
"MUTATION",
|
||||
"NAME",
|
||||
"NAMED",
|
||||
"NANOSECOND",
|
||||
"NEXT",
|
||||
"NO",
|
||||
"NONE",
|
||||
"NOT",
|
||||
"NOTEQUALS",
|
||||
"NOTIN",
|
||||
"NS",
|
||||
"NULL",
|
||||
"NULLS",
|
||||
"OBJECT",
|
||||
"OFFSET",
|
||||
"ON",
|
||||
"ONLY",
|
||||
"OPTIMIZE",
|
||||
"OPTION",
|
||||
"OR",
|
||||
"ORDER",
|
||||
"OUTER",
|
||||
"OUTFILE",
|
||||
"OVER",
|
||||
"OVERRIDE",
|
||||
"PART",
|
||||
"PARTIAL",
|
||||
"PARTITION",
|
||||
"PARTITIONS",
|
||||
"PART_MOVE_TO_SHARD",
|
||||
"PERMANENTLY",
|
||||
"PERMISSIVE",
|
||||
"PIPELINE",
|
||||
"PLAN",
|
||||
"PLUS",
|
||||
"POLICY",
|
||||
"POPULATE",
|
||||
"POSITION",
|
||||
"PRECEDING",
|
||||
"PRECISION",
|
||||
"PREWHERE",
|
||||
"PRIMARY",
|
||||
"PRIVILEGES",
|
||||
"PROCESSLIST",
|
||||
"PROFILE",
|
||||
"PROJECTION",
|
||||
"QQ",
|
||||
"QUARTER",
|
||||
"QUERY",
|
||||
"QUOTA",
|
||||
"RANDOMIZED",
|
||||
"RANGE",
|
||||
"READONLY",
|
||||
"REALM",
|
||||
"RECOMPRESS",
|
||||
"REFERENCES",
|
||||
"REFRESH",
|
||||
"REGEXP",
|
||||
"REGEXPQUOTEMETA",
|
||||
"REMOVE",
|
||||
"RENAME",
|
||||
"REPLACE",
|
||||
"REPLACEREGEXPALL",
|
||||
"REPLACEREGEXPONE",
|
||||
"RESET",
|
||||
"RESTORE",
|
||||
"RESTRICT",
|
||||
"RESTRICTIVE",
|
||||
"RESUME",
|
||||
"REVOKE",
|
||||
"RIGHT",
|
||||
"ROLE",
|
||||
"ROLES",
|
||||
"ROLLBACK",
|
||||
"ROLLUP",
|
||||
"ROW",
|
||||
"ROWS",
|
||||
"RTRIM",
|
||||
"S3",
|
||||
"SALT",
|
||||
"SAMPLE",
|
||||
"SECOND",
|
||||
"SELECT",
|
||||
"SEMI",
|
||||
"SERVER",
|
||||
"SET",
|
||||
"SETS",
|
||||
"SETTING",
|
||||
"SETTINGS",
|
||||
"SHA256_HASH",
|
||||
"SHARD",
|
||||
"SHOW",
|
||||
"SIGNED",
|
||||
"SIMPLE",
|
||||
"SINGLEVALUEORNULL",
|
||||
"SNAPSHOT",
|
||||
"SOURCE",
|
||||
"SPATIAL",
|
||||
"SS",
|
||||
"STDOUT",
|
||||
"STEP",
|
||||
"STORAGE",
|
||||
"STRICT",
|
||||
"STRICTLY_ASCENDING",
|
||||
"SUBPARTITION",
|
||||
"SUBPARTITIONS",
|
||||
"SUBSTRING",
|
||||
"SUSPEND",
|
||||
"SYNC",
|
||||
"SYNTAX",
|
||||
"SYSTEM",
|
||||
"TABLE",
|
||||
"TABLES",
|
||||
"TEMPORARY",
|
||||
"TEST",
|
||||
"THAN",
|
||||
"THEN",
|
||||
"TIES",
|
||||
"TIMESTAMP",
|
||||
"TIMESTAMP_ADD",
|
||||
"TIMESTAMPADD",
|
||||
"TIMESTAMP_DIFF",
|
||||
"TIMESTAMPDIFF",
|
||||
"TIMESTAMP_SUB",
|
||||
"TIMESTAMPSUB",
|
||||
"TO",
|
||||
"TODATE",
|
||||
"TODATETIME",
|
||||
"TOP",
|
||||
"TOTALS",
|
||||
"TRACKING",
|
||||
"TRAILING",
|
||||
"TRANSACTION",
|
||||
"TREE",
|
||||
"TRIGGER",
|
||||
"TRIM",
|
||||
"TRIMBOTH",
|
||||
"TRIMLEFT",
|
||||
"TRIMRIGHT",
|
||||
"TRUE",
|
||||
"TRUNCATE",
|
||||
"TTL",
|
||||
"TUPLE",
|
||||
"TYPE",
|
||||
"UNBOUNDED",
|
||||
"UNFREEZE",
|
||||
"UNION",
|
||||
"UNIQUE",
|
||||
"UNSIGNED",
|
||||
"UNTUPLE",
|
||||
"UPDATE",
|
||||
"URL",
|
||||
"USE",
|
||||
"USER",
|
||||
"USING",
|
||||
"UUID",
|
||||
"VALUES",
|
||||
"VARYING",
|
||||
"VIEW",
|
||||
"VIEWIFPERMITTED",
|
||||
"VISIBLE",
|
||||
"VOLUME",
|
||||
"WATCH",
|
||||
"WATERMARK",
|
||||
"WEEK",
|
||||
"WHEN",
|
||||
"WHERE",
|
||||
"WINDOW",
|
||||
"WITH",
|
||||
"WK",
|
||||
"WRITABLE",
|
||||
"YEAR",
|
||||
"YYYY",
|
||||
"ZKPATH"
|
||||
auto initialize = []()
|
||||
{
|
||||
std::unordered_set<std::string> instance = {
|
||||
"!=",
|
||||
"",
|
||||
"%",
|
||||
"*",
|
||||
"+",
|
||||
"-",
|
||||
"->",
|
||||
".",
|
||||
"/",
|
||||
":",
|
||||
"::",
|
||||
"<",
|
||||
"<=",
|
||||
"<>",
|
||||
"=",
|
||||
"==",
|
||||
"<=>",
|
||||
">",
|
||||
">=",
|
||||
"?",
|
||||
"[",
|
||||
"]+",
|
||||
"]+|[",
|
||||
"^[",
|
||||
"||",
|
||||
"]+$"
|
||||
};
|
||||
|
||||
for (const auto & keyword : getAllKeyWords())
|
||||
{
|
||||
/// The keyword may consist of several tokens (ORDER BY or GROUP BY)
|
||||
/// We will split them and add separately.
|
||||
std::vector<std::string> tokens;
|
||||
boost::split(tokens, keyword, [](char c) { return c == ' '; });
|
||||
for (const auto & token : tokens)
|
||||
instance.insert(token);
|
||||
}
|
||||
|
||||
return instance;
|
||||
};
|
||||
|
||||
static std::unordered_set<std::string> instance = initialize();
|
||||
return instance;
|
||||
};
|
||||
|
||||
/// We want to keep some words inside quotes. For example we want to keep HOUR inside:
|
||||
@ -1309,11 +956,9 @@ void obfuscateQueries(
|
||||
|
||||
if (token.type == TokenType::BareWord)
|
||||
{
|
||||
std::string whole_token_uppercase(whole_token);
|
||||
Poco::toUpperInPlace(whole_token_uppercase);
|
||||
auto whole_token_uppercase = Poco::toUpper(toString(whole_token));
|
||||
|
||||
if (keywords.contains(whole_token_uppercase)
|
||||
|| known_identifier_func(whole_token))
|
||||
if (getObfuscateKeywords().contains(whole_token_uppercase) || known_identifier_func(whole_token))
|
||||
{
|
||||
/// Keep keywords as is.
|
||||
result.write(token.begin, token.size());
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
#include "GRPCServer.h"
|
||||
#include <limits>
|
||||
#include <memory>
|
||||
#include <Poco/Net/SocketAddress.h>
|
||||
#if USE_GRPC
|
||||
|
||||
#include <Columns/ColumnString.h>
|
||||
@ -320,8 +321,27 @@ namespace
|
||||
|
||||
Poco::Net::SocketAddress getClientAddress() const
|
||||
{
|
||||
String peer = grpc_context.peer();
|
||||
return Poco::Net::SocketAddress{peer.substr(peer.find(':') + 1)};
|
||||
/// Returns a string like ipv4:127.0.0.1:55930 or ipv6:%5B::1%5D:55930
|
||||
String uri_encoded_peer = grpc_context.peer();
|
||||
|
||||
constexpr const std::string_view ipv4_prefix = "ipv4:";
|
||||
constexpr const std::string_view ipv6_prefix = "ipv6:";
|
||||
|
||||
bool ipv4 = uri_encoded_peer.starts_with(ipv4_prefix);
|
||||
bool ipv6 = uri_encoded_peer.starts_with(ipv6_prefix);
|
||||
|
||||
if (!ipv4 && !ipv6)
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Expected ipv4 or ipv6 protocol in peer address, got {}", uri_encoded_peer);
|
||||
|
||||
auto prefix = ipv4 ? ipv4_prefix : ipv6_prefix;
|
||||
auto family = ipv4 ? Poco::Net::AddressFamily::Family::IPv4 : Poco::Net::AddressFamily::Family::IPv6;
|
||||
|
||||
uri_encoded_peer= uri_encoded_peer.substr(prefix.length());
|
||||
|
||||
String peer;
|
||||
Poco::URI::decode(uri_encoded_peer, peer);
|
||||
|
||||
return Poco::Net::SocketAddress{family, peer};
|
||||
}
|
||||
|
||||
std::optional<String> getClientHeader(const String & key) const
|
||||
|
||||
@ -364,12 +364,12 @@ bool HTTPHandler::authenticateUser(
|
||||
/// The header 'X-ClickHouse-SSL-Certificate-Auth: on' enables checking the common name
|
||||
/// extracted from the SSL certificate used for this connection instead of checking password.
|
||||
bool has_ssl_certificate_auth = (request.get("X-ClickHouse-SSL-Certificate-Auth", "") == "on");
|
||||
bool has_auth_headers = !user.empty() || !password.empty() || !quota_key.empty() || has_ssl_certificate_auth;
|
||||
bool has_auth_headers = !user.empty() || !password.empty() || has_ssl_certificate_auth;
|
||||
|
||||
/// User name and password can be passed using HTTP Basic auth or query parameters
|
||||
/// (both methods are insecure).
|
||||
bool has_http_credentials = request.hasCredentials();
|
||||
bool has_credentials_in_query_params = params.has("user") || params.has("password") || params.has("quota_key");
|
||||
bool has_credentials_in_query_params = params.has("user") || params.has("password");
|
||||
|
||||
std::string spnego_challenge;
|
||||
std::string certificate_common_name;
|
||||
@ -435,15 +435,12 @@ bool HTTPHandler::authenticateUser(
|
||||
{
|
||||
throw Exception(ErrorCodes::AUTHENTICATION_FAILED, "Invalid authentication: '{}' HTTP Authorization scheme is not supported", scheme);
|
||||
}
|
||||
|
||||
quota_key = params.get("quota_key", "");
|
||||
}
|
||||
else
|
||||
{
|
||||
/// If the user name is not set we assume it's the 'default' user.
|
||||
user = params.get("user", "default");
|
||||
password = params.get("password", "");
|
||||
quota_key = params.get("quota_key", "");
|
||||
}
|
||||
|
||||
if (!certificate_common_name.empty())
|
||||
@ -495,6 +492,16 @@ bool HTTPHandler::authenticateUser(
|
||||
basic_credentials->setPassword(password);
|
||||
}
|
||||
|
||||
if (params.has("quota_key"))
|
||||
{
|
||||
if (!quota_key.empty())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS,
|
||||
"Invalid authentication: it is not allowed "
|
||||
"to use quota key as HTTP header and as parameter simultaneously");
|
||||
|
||||
quota_key = params.get("quota_key");
|
||||
}
|
||||
|
||||
/// Set client info. It will be used for quota accounting parameters in 'setUser' method.
|
||||
|
||||
session->setHTTPClientInfo(request);
|
||||
|
||||
@ -793,6 +793,8 @@ bool TCPHandler::readDataNext()
|
||||
|
||||
/// We accept and process data.
|
||||
read_ok = receivePacket();
|
||||
/// Reset the timeout on Ping packet (NOTE: there is no Ping for INSERT queries yet).
|
||||
watch.restart();
|
||||
break;
|
||||
}
|
||||
|
||||
|
||||
@ -8371,4 +8371,29 @@ bool MergeTreeData::initializeDiskOnConfigChange(const std::set<String> & new_ad
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
bool updateAlterConversionsMutations(const MutationCommands & commands, std::atomic<ssize_t> & alter_conversions_mutations, bool remove)
|
||||
{
|
||||
for (const auto & command : commands)
|
||||
{
|
||||
if (AlterConversions::supportsMutationCommandType(command.type))
|
||||
{
|
||||
if (remove)
|
||||
{
|
||||
--alter_conversions_mutations;
|
||||
if (alter_conversions_mutations < 0)
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "On-fly mutations counter is negative ({})", alter_conversions_mutations);
|
||||
}
|
||||
else
|
||||
{
|
||||
if (alter_conversions_mutations < 0)
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "On-fly mutations counter is negative ({})", alter_conversions_mutations);
|
||||
++alter_conversions_mutations;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -1708,4 +1708,8 @@ struct CurrentlySubmergingEmergingTagger
|
||||
|| (settings.min_compressed_bytes_to_fsync_after_merge && input_bytes >= settings.min_compressed_bytes_to_fsync_after_merge));
|
||||
}
|
||||
|
||||
/// Look at MutationCommands if it contains mutations for AlterConversions, update the counter.
|
||||
/// Return true if the counter had been updated
|
||||
bool updateAlterConversionsMutations(const MutationCommands & commands, std::atomic<ssize_t> & alter_conversions_mutations, bool remove);
|
||||
|
||||
}
|
||||
|
||||
@ -6,8 +6,11 @@
|
||||
#include <Storages/MergeTree/ReplicatedMergeTreeMergeStrategyPicker.h>
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <IO/WriteHelpers.h>
|
||||
#include <Common/noexcept_scope.h>
|
||||
#include <Common/StringUtils/StringUtils.h>
|
||||
#include <Common/CurrentMetrics.h>
|
||||
#include <Storages/MutationCommands.h>
|
||||
#include <base/defines.h>
|
||||
#include <Parsers/formatAST.h>
|
||||
#include <base/sort.h>
|
||||
#include <ranges>
|
||||
@ -942,7 +945,14 @@ int32_t ReplicatedMergeTreeQueue::updateMutations(zkutil::ZooKeeperPtr zookeeper
|
||||
mutations_by_partition.erase(partition_and_block_num.first);
|
||||
}
|
||||
|
||||
it = mutations_by_znode.erase(it);
|
||||
if (!it->second.is_done)
|
||||
{
|
||||
const auto commands = entry.commands;
|
||||
it = mutations_by_znode.erase(it);
|
||||
updateAlterConversionsMutations(commands, alter_conversions_mutations, /* remove= */ true);
|
||||
}
|
||||
else
|
||||
it = mutations_by_znode.erase(it);
|
||||
}
|
||||
else
|
||||
++it;
|
||||
@ -991,12 +1001,15 @@ int32_t ReplicatedMergeTreeQueue::updateMutations(zkutil::ZooKeeperPtr zookeeper
|
||||
auto & mutation = mutations_by_znode.emplace(entry->znode_name, MutationStatus(entry, format_version))
|
||||
.first->second;
|
||||
|
||||
for (const auto & pair : entry->block_numbers)
|
||||
{
|
||||
const String & partition_id = pair.first;
|
||||
Int64 block_num = pair.second;
|
||||
mutations_by_partition[partition_id].emplace(block_num, &mutation);
|
||||
}
|
||||
updateAlterConversionsMutations(entry->commands, alter_conversions_mutations, /* remove= */ false);
|
||||
NOEXCEPT_SCOPE({
|
||||
for (const auto & pair : entry->block_numbers)
|
||||
{
|
||||
const String & partition_id = pair.first;
|
||||
Int64 block_num = pair.second;
|
||||
mutations_by_partition[partition_id].emplace(block_num, &mutation);
|
||||
}
|
||||
});
|
||||
LOG_TRACE(log, "Adding mutation {} for {} partitions (data versions: {})",
|
||||
entry->znode_name, entry->block_numbers.size(), entry->getBlockNumbersForLogs());
|
||||
|
||||
@ -1062,6 +1075,8 @@ ReplicatedMergeTreeMutationEntryPtr ReplicatedMergeTreeQueue::removeMutation(
|
||||
}
|
||||
|
||||
mutations_by_znode.erase(it);
|
||||
/// updateAlterConversionsMutations() will be called in updateMutations()
|
||||
|
||||
LOG_DEBUG(log, "Removed mutation {} from local state.", entry->znode_name);
|
||||
}
|
||||
|
||||
@ -1887,6 +1902,15 @@ ReplicatedMergeTreeMergePredicate ReplicatedMergeTreeQueue::getMergePredicate(zk
|
||||
|
||||
MutationCommands ReplicatedMergeTreeQueue::getAlterMutationCommandsForPart(const MergeTreeData::DataPartPtr & part) const
|
||||
{
|
||||
int32_t part_metadata_version = part->getMetadataVersion();
|
||||
int32_t metadata_version = storage.getInMemoryMetadataPtr()->getMetadataVersion();
|
||||
|
||||
chassert(alter_conversions_mutations >= 0);
|
||||
/// NOTE: that just checking part_metadata_version is not enough, since we
|
||||
/// need to check for non-metadata mutations as well.
|
||||
if (alter_conversions_mutations == 0 && metadata_version == part_metadata_version)
|
||||
return {};
|
||||
|
||||
std::unique_lock lock(state_mutex);
|
||||
|
||||
auto in_partition = mutations_by_partition.find(part->info.partition_id);
|
||||
@ -1894,13 +1918,18 @@ MutationCommands ReplicatedMergeTreeQueue::getAlterMutationCommandsForPart(const
|
||||
return {};
|
||||
|
||||
Int64 part_data_version = part->info.getDataVersion();
|
||||
Int64 part_metadata_version = part->getMetadataVersion();
|
||||
|
||||
MutationCommands result;
|
||||
|
||||
bool seen_all_data_mutations = false;
|
||||
bool seen_all_metadata_mutations = false;
|
||||
|
||||
auto add_to_result = [&](const ReplicatedMergeTreeMutationEntryPtr & entry)
|
||||
{
|
||||
for (const auto & command : entry->commands | std::views::reverse)
|
||||
if (AlterConversions::supportsMutationCommandType(command.type))
|
||||
result.emplace_back(command);
|
||||
};
|
||||
|
||||
/// Here we return mutation commands for part which has bigger alter version than part metadata version.
|
||||
/// Please note, we don't use getDataVersion(). It's because these alter commands are used for in-fly conversions
|
||||
/// of part's metadata.
|
||||
@ -1911,28 +1940,22 @@ MutationCommands ReplicatedMergeTreeQueue::getAlterMutationCommandsForPart(const
|
||||
|
||||
auto & entry = mutation_status->entry;
|
||||
|
||||
auto add_to_result = [&] {
|
||||
for (const auto & command : entry->commands | std::views::reverse)
|
||||
if (AlterConversions::supportsMutationCommandType(command.type))
|
||||
result.emplace_back(command);
|
||||
};
|
||||
|
||||
auto alter_version = entry->alter_version;
|
||||
if (alter_version != -1)
|
||||
{
|
||||
if (alter_version > storage.getInMemoryMetadataPtr()->getMetadataVersion())
|
||||
if (alter_version > metadata_version)
|
||||
continue;
|
||||
|
||||
/// We take commands with bigger metadata version
|
||||
if (alter_version > part_metadata_version)
|
||||
add_to_result();
|
||||
add_to_result(entry);
|
||||
else
|
||||
seen_all_metadata_mutations = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
if (mutation_version > part_data_version)
|
||||
add_to_result();
|
||||
add_to_result(entry);
|
||||
else
|
||||
seen_all_data_mutations = true;
|
||||
}
|
||||
@ -2019,6 +2042,8 @@ bool ReplicatedMergeTreeQueue::tryFinalizeMutations(zkutil::ZooKeeperPtr zookeep
|
||||
"were executed concurrently on different replicas.", znode);
|
||||
mutation.parts_to_do.clear();
|
||||
}
|
||||
|
||||
updateAlterConversionsMutations(mutation.entry->commands, alter_conversions_mutations, /* remove= */ true);
|
||||
}
|
||||
else if (mutation.parts_to_do.size() == 0)
|
||||
{
|
||||
@ -2075,6 +2100,7 @@ bool ReplicatedMergeTreeQueue::tryFinalizeMutations(zkutil::ZooKeeperPtr zookeep
|
||||
LOG_TRACE(log, "Finishing data alter with version {} for entry {}", entry->alter_version, entry->znode_name);
|
||||
alter_sequence.finishDataAlter(entry->alter_version, lock);
|
||||
}
|
||||
updateAlterConversionsMutations(entry->commands, alter_conversions_mutations, /* remove= */ true);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -151,6 +151,8 @@ private:
|
||||
|
||||
/// Mapping from znode path to Mutations Status
|
||||
std::map<String, MutationStatus> mutations_by_znode;
|
||||
/// Unfinished mutations that is required AlterConversions (see getAlterMutationCommandsForPart())
|
||||
std::atomic<ssize_t> alter_conversions_mutations = 0;
|
||||
/// Partition -> (block_number -> MutationStatus)
|
||||
std::unordered_map<String, std::map<Int64, MutationStatus *>> mutations_by_partition;
|
||||
/// Znode ID of the latest mutation that is done.
|
||||
|
||||
@ -521,9 +521,18 @@ Int64 StorageMergeTree::startMutation(const MutationCommands & commands, Context
|
||||
String mutation_id = entry.file_name;
|
||||
if (txn)
|
||||
txn->addMutation(shared_from_this(), mutation_id);
|
||||
|
||||
bool alter_conversions_mutations_updated = updateAlterConversionsMutations(entry.commands, alter_conversions_mutations, /* remove= */ false);
|
||||
bool inserted = current_mutations_by_version.try_emplace(version, std::move(entry)).second;
|
||||
if (!inserted)
|
||||
{
|
||||
if (alter_conversions_mutations_updated)
|
||||
{
|
||||
--alter_conversions_mutations;
|
||||
chassert(alter_conversions_mutations >= 0);
|
||||
}
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Mutation {} already exists, it's a bug", version);
|
||||
}
|
||||
|
||||
LOG_INFO(log, "Added mutation: {}{}", mutation_id, additional_info);
|
||||
}
|
||||
@ -559,6 +568,8 @@ void StorageMergeTree::updateMutationEntriesErrors(FutureMergedMutatedPartPtr re
|
||||
entry.latest_fail_reason.clear();
|
||||
if (static_cast<UInt64>(result_part->part_info.mutation) == it->first)
|
||||
mutation_backoff_policy.removePartFromFailed(failed_part->name);
|
||||
|
||||
updateAlterConversionsMutations(it->second.commands, alter_conversions_mutations, /* remove= */ true);
|
||||
}
|
||||
}
|
||||
else
|
||||
@ -837,8 +848,20 @@ CancellationCode StorageMergeTree::killMutation(const String & mutation_id)
|
||||
auto it = current_mutations_by_version.find(mutation_version);
|
||||
if (it != current_mutations_by_version.end())
|
||||
{
|
||||
bool mutation_finished = true;
|
||||
if (std::optional<Int64> min_version = getMinPartDataVersion())
|
||||
mutation_finished = *min_version > static_cast<Int64>(mutation_version);
|
||||
|
||||
to_kill.emplace(std::move(it->second));
|
||||
current_mutations_by_version.erase(it);
|
||||
|
||||
if (!mutation_finished)
|
||||
{
|
||||
const auto commands = it->second.commands;
|
||||
current_mutations_by_version.erase(it);
|
||||
updateAlterConversionsMutations(commands, alter_conversions_mutations, /* remove= */ true);
|
||||
}
|
||||
else
|
||||
current_mutations_by_version.erase(it);
|
||||
}
|
||||
}
|
||||
|
||||
@ -916,6 +939,7 @@ void StorageMergeTree::loadMutations()
|
||||
auto inserted = current_mutations_by_version.try_emplace(block_number, std::move(entry)).second;
|
||||
if (!inserted)
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Mutation {} already exists, it's a bug", block_number);
|
||||
updateAlterConversionsMutations(entry.commands, alter_conversions_mutations, /* remove= */ false);
|
||||
}
|
||||
else if (startsWith(it->name(), "tmp_mutation_"))
|
||||
{
|
||||
@ -2159,10 +2183,6 @@ void StorageMergeTree::replacePartitionFrom(const StoragePtr & source_table, con
|
||||
|
||||
void StorageMergeTree::movePartitionToTable(const StoragePtr & dest_table, const ASTPtr & partition, ContextPtr local_context)
|
||||
{
|
||||
auto lock1 = lockForShare(local_context->getCurrentQueryId(), local_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto lock2 = dest_table->lockForShare(local_context->getCurrentQueryId(), local_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto merges_blocker = stopMergesAndWait();
|
||||
|
||||
auto dest_table_storage = std::dynamic_pointer_cast<StorageMergeTree>(dest_table);
|
||||
if (!dest_table_storage)
|
||||
throw Exception(ErrorCodes::NOT_IMPLEMENTED,
|
||||
@ -2176,6 +2196,13 @@ void StorageMergeTree::movePartitionToTable(const StoragePtr & dest_table, const
|
||||
this->getStoragePolicy()->getName(), dest_table_storage->getStorageID().getNameForLogs(),
|
||||
dest_table_storage->getStoragePolicy()->getName());
|
||||
|
||||
// Use the same back-pressure (delay/throw) logic as for INSERTs to be consistent and avoid possibility of exceeding part limits using MOVE PARTITION queries
|
||||
dest_table_storage->delayInsertOrThrowIfNeeded(nullptr, local_context, true);
|
||||
|
||||
auto lock1 = lockForShare(local_context->getCurrentQueryId(), local_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto lock2 = dest_table->lockForShare(local_context->getCurrentQueryId(), local_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto merges_blocker = stopMergesAndWait();
|
||||
|
||||
auto dest_metadata_snapshot = dest_table->getInMemoryMetadataPtr();
|
||||
auto metadata_snapshot = getInMemoryMetadataPtr();
|
||||
Stopwatch watch;
|
||||
@ -2409,6 +2436,13 @@ void StorageMergeTree::attachRestoredParts(MutableDataPartsVector && parts)
|
||||
|
||||
MutationCommands StorageMergeTree::getAlterMutationCommandsForPart(const DataPartPtr & part) const
|
||||
{
|
||||
/// NOTE: there is no need to check part metadata_version, since
|
||||
/// ALTER_METADATA cannot be done asynchronously, like in
|
||||
/// ReplicatedMergeTree.
|
||||
chassert(alter_conversions_mutations >= 0);
|
||||
if (alter_conversions_mutations == 0)
|
||||
return {};
|
||||
|
||||
std::lock_guard lock(currently_processing_in_background_mutex);
|
||||
|
||||
UInt64 part_data_version = part->info.getDataVersion();
|
||||
|
||||
@ -147,6 +147,8 @@ private:
|
||||
DataParts currently_merging_mutating_parts;
|
||||
|
||||
std::map<UInt64, MergeTreeMutationEntry> current_mutations_by_version;
|
||||
/// Unfinished mutations that is required AlterConversions (see getAlterMutationCommandsForPart())
|
||||
std::atomic<ssize_t> alter_conversions_mutations = 0;
|
||||
|
||||
std::atomic<bool> shutdown_called {false};
|
||||
std::atomic<bool> flush_called {false};
|
||||
|
||||
@ -8244,10 +8244,6 @@ void StorageReplicatedMergeTree::replacePartitionFrom(
|
||||
|
||||
void StorageReplicatedMergeTree::movePartitionToTable(const StoragePtr & dest_table, const ASTPtr & partition, ContextPtr query_context)
|
||||
{
|
||||
auto lock1 = lockForShare(query_context->getCurrentQueryId(), query_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto lock2 = dest_table->lockForShare(query_context->getCurrentQueryId(), query_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto storage_settings_ptr = getSettings();
|
||||
|
||||
auto dest_table_storage = std::dynamic_pointer_cast<StorageReplicatedMergeTree>(dest_table);
|
||||
if (!dest_table_storage)
|
||||
throw Exception(ErrorCodes::NOT_IMPLEMENTED,
|
||||
@ -8261,6 +8257,13 @@ void StorageReplicatedMergeTree::movePartitionToTable(const StoragePtr & dest_ta
|
||||
this->getStoragePolicy()->getName(), getStorageID().getNameForLogs(),
|
||||
dest_table_storage->getStoragePolicy()->getName());
|
||||
|
||||
// Use the same back-pressure (delay/throw) logic as for INSERTs to be consistent and avoid possibility of exceeding part limits using MOVE PARTITION queries
|
||||
dest_table_storage->delayInsertOrThrowIfNeeded(nullptr, query_context, true);
|
||||
|
||||
auto lock1 = lockForShare(query_context->getCurrentQueryId(), query_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto lock2 = dest_table->lockForShare(query_context->getCurrentQueryId(), query_context->getSettingsRef().lock_acquire_timeout);
|
||||
auto storage_settings_ptr = getSettings();
|
||||
|
||||
auto dest_metadata_snapshot = dest_table->getInMemoryMetadataPtr();
|
||||
auto metadata_snapshot = getInMemoryMetadataPtr();
|
||||
|
||||
|
||||
@ -1261,18 +1261,6 @@ def _print_results(result: Any, outfile: Optional[str], pretty: bool = False) ->
|
||||
raise AssertionError(f"Unexpected type for 'res': {type(result)}")
|
||||
|
||||
|
||||
def _update_config_for_docs_only(jobs_data: dict) -> None:
|
||||
DOCS_CHECK_JOBS = [JobNames.DOCS_CHECK, JobNames.STYLE_CHECK]
|
||||
print(f"NOTE: Will keep only docs related jobs: [{DOCS_CHECK_JOBS}]")
|
||||
jobs_to_do = jobs_data.get("jobs_to_do", [])
|
||||
jobs_data["jobs_to_do"] = [job for job in jobs_to_do if job in DOCS_CHECK_JOBS]
|
||||
jobs_data["jobs_to_wait"] = {
|
||||
job: params
|
||||
for job, params in jobs_data["jobs_to_wait"].items()
|
||||
if job in DOCS_CHECK_JOBS
|
||||
}
|
||||
|
||||
|
||||
def _configure_docker_jobs(docker_digest_or_latest: bool) -> Dict:
|
||||
print("::group::Docker images check")
|
||||
# generate docker jobs data
|
||||
@ -1332,8 +1320,31 @@ def _configure_jobs(
|
||||
jobs_to_skip: List[str] = []
|
||||
digests: Dict[str, str] = {}
|
||||
|
||||
# FIXME: find better place for these config variables
|
||||
DOCS_CHECK_JOBS = [JobNames.DOCS_CHECK, JobNames.STYLE_CHECK]
|
||||
MQ_JOBS = [JobNames.STYLE_CHECK, JobNames.FAST_TEST]
|
||||
# Must always calculate digest for these jobs for CI Cache to function (they define s3 paths where records are stored)
|
||||
REQUIRED_DIGESTS = [JobNames.DOCS_CHECK, Build.PACKAGE_RELEASE]
|
||||
if pr_info.has_changes_in_documentation_only():
|
||||
print(f"WARNING: Only docs are changed - will run only [{DOCS_CHECK_JOBS}]")
|
||||
if pr_info.is_merge_queue:
|
||||
print(f"WARNING: It's a MQ run - will run only [{MQ_JOBS}]")
|
||||
|
||||
print("::group::Job Digests")
|
||||
for job in CI_CONFIG.job_generator(pr_info.head_ref if CI else "dummy_branch_name"):
|
||||
if (
|
||||
pr_info.is_merge_queue
|
||||
and job not in MQ_JOBS
|
||||
and job not in REQUIRED_DIGESTS
|
||||
):
|
||||
# We still need digest for JobNames.DOCS_CHECK since CiCache depends on it (FIXME)
|
||||
continue
|
||||
if (
|
||||
pr_info.has_changes_in_documentation_only()
|
||||
and job not in DOCS_CHECK_JOBS
|
||||
and job not in REQUIRED_DIGESTS
|
||||
):
|
||||
continue
|
||||
digest = job_digester.get_job_digest(CI_CONFIG.get_digest_config(job))
|
||||
digests[job] = digest
|
||||
print(f" job [{job.rjust(50)}] has digest [{digest}]")
|
||||
@ -1354,6 +1365,8 @@ def _configure_jobs(
|
||||
batches_to_do: List[int] = []
|
||||
add_to_skip = False
|
||||
|
||||
if pr_info.is_merge_queue and job not in MQ_JOBS:
|
||||
continue
|
||||
if job_config.pr_only and pr_info.is_release_branch:
|
||||
continue
|
||||
if job_config.release_only and not pr_info.is_release_branch:
|
||||
@ -1435,12 +1448,6 @@ def _configure_jobs(
|
||||
jobs_to_do, jobs_to_skip, jobs_params
|
||||
)
|
||||
|
||||
if pr_info.is_merge_queue:
|
||||
# FIXME: Quick support for MQ workflow which is only StyleCheck for now
|
||||
jobs_to_do = [JobNames.STYLE_CHECK]
|
||||
jobs_to_skip = []
|
||||
print(f"NOTE: This is Merge Queue CI: set jobs to do: [{jobs_to_do}]")
|
||||
|
||||
return {
|
||||
"digests": digests,
|
||||
"jobs_to_do": jobs_to_do,
|
||||
@ -1904,9 +1911,6 @@ def main() -> int:
|
||||
else {}
|
||||
)
|
||||
|
||||
if not args.skip_jobs and pr_info.has_changes_in_documentation_only():
|
||||
_update_config_for_docs_only(jobs_data)
|
||||
|
||||
if not args.skip_jobs:
|
||||
ci_cache = CiCache(s3, jobs_data["digests"])
|
||||
|
||||
@ -1930,8 +1934,7 @@ def main() -> int:
|
||||
jobs_to_skip.append(job)
|
||||
del jobs_params[job]
|
||||
|
||||
# set planned jobs as pending in the CI cache if on the master
|
||||
if pr_info.is_master:
|
||||
# set planned jobs as in-progress in CI cache
|
||||
for job in jobs_data["jobs_to_do"]:
|
||||
config = CI_CONFIG.get_job_config(job)
|
||||
if config.run_always or config.run_by_label:
|
||||
|
||||
@ -49,7 +49,7 @@ class CILabels(metaclass=WithIter):
|
||||
CI_SET_FAST = "ci_set_fast"
|
||||
CI_SET_ARM = "ci_set_arm"
|
||||
CI_SET_INTEGRATION = "ci_set_integration"
|
||||
CI_SET_ANALYZER = "ci_set_analyzer"
|
||||
CI_SET_OLD_ANALYZER = "ci_set_old_analyzer"
|
||||
CI_SET_STATLESS = "ci_set_stateless"
|
||||
CI_SET_STATEFUL = "ci_set_stateful"
|
||||
CI_SET_STATLESS_ASAN = "ci_set_stateless_asan"
|
||||
@ -98,15 +98,16 @@ class JobNames(metaclass=WithIter):
|
||||
STATELESS_TEST_TSAN = "Stateless tests (tsan)"
|
||||
STATELESS_TEST_MSAN = "Stateless tests (msan)"
|
||||
STATELESS_TEST_UBSAN = "Stateless tests (ubsan)"
|
||||
STATELESS_TEST_ANALYZER_S3_REPLICATED_RELEASE = (
|
||||
STATELESS_TEST_OLD_ANALYZER_S3_REPLICATED_RELEASE = (
|
||||
"Stateless tests (release, old analyzer, s3, DatabaseReplicated)"
|
||||
)
|
||||
# merged into STATELESS_TEST_ANALYZER_S3_REPLICATED_RELEASE:
|
||||
# STATELESS_TEST_ANALYZER_RELEASE = "Stateless tests (release, analyzer)"
|
||||
# merged into STATELESS_TEST_OLD_ANALYZER_S3_REPLICATED_RELEASE:
|
||||
# STATELESS_TEST_OLD_ANALYZER_RELEASE = "Stateless tests (release, analyzer)"
|
||||
# STATELESS_TEST_DB_REPL_RELEASE = "Stateless tests (release, DatabaseReplicated)"
|
||||
# STATELESS_TEST_S3_RELEASE = "Stateless tests (release, s3 storage)"
|
||||
STATELESS_TEST_S3_DEBUG = "Stateless tests (debug, s3 storage)"
|
||||
STATELESS_TEST_S3_TSAN = "Stateless tests (tsan, s3 storage)"
|
||||
STATELESS_TEST_AZURE_ASAN = "Stateless tests (azure, asan)"
|
||||
STATELESS_TEST_FLAKY_ASAN = "Stateless tests flaky check (asan)"
|
||||
|
||||
STATEFUL_TEST_DEBUG = "Stateful tests (debug)"
|
||||
@ -129,10 +130,11 @@ class JobNames(metaclass=WithIter):
|
||||
STRESS_TEST_UBSAN = "Stress test (ubsan)"
|
||||
STRESS_TEST_MSAN = "Stress test (msan)"
|
||||
STRESS_TEST_DEBUG = "Stress test (debug)"
|
||||
STRESS_TEST_AZURE_TSAN = "Stress test (azure, tsan)"
|
||||
|
||||
INTEGRATION_TEST = "Integration tests (release)"
|
||||
INTEGRATION_TEST_ASAN = "Integration tests (asan)"
|
||||
INTEGRATION_TEST_ASAN_ANALYZER = "Integration tests (asan, old analyzer)"
|
||||
INTEGRATION_TEST_ASAN_OLD_ANALYZER = "Integration tests (asan, old analyzer)"
|
||||
INTEGRATION_TEST_TSAN = "Integration tests (tsan)"
|
||||
INTEGRATION_TEST_ARM = "Integration tests (aarch64)"
|
||||
INTEGRATION_TEST_FLAKY = "Integration tests flaky check (asan)"
|
||||
@ -846,14 +848,14 @@ CI_CONFIG = CIConfig(
|
||||
JobNames.INTEGRATION_TEST,
|
||||
]
|
||||
),
|
||||
CILabels.CI_SET_ANALYZER: LabelConfig(
|
||||
CILabels.CI_SET_OLD_ANALYZER: LabelConfig(
|
||||
run_jobs=[
|
||||
JobNames.STYLE_CHECK,
|
||||
JobNames.FAST_TEST,
|
||||
Build.PACKAGE_RELEASE,
|
||||
Build.PACKAGE_ASAN,
|
||||
JobNames.STATELESS_TEST_ANALYZER_S3_REPLICATED_RELEASE,
|
||||
JobNames.INTEGRATION_TEST_ASAN_ANALYZER,
|
||||
JobNames.STATELESS_TEST_OLD_ANALYZER_S3_REPLICATED_RELEASE,
|
||||
JobNames.INTEGRATION_TEST_ASAN_OLD_ANALYZER,
|
||||
]
|
||||
),
|
||||
CILabels.CI_SET_STATLESS: LabelConfig(
|
||||
@ -1193,7 +1195,7 @@ CI_CONFIG = CIConfig(
|
||||
JobNames.STATELESS_TEST_AARCH64: TestConfig(
|
||||
Build.PACKAGE_AARCH64, job_config=JobConfig(**statless_test_common_params) # type: ignore
|
||||
),
|
||||
JobNames.STATELESS_TEST_ANALYZER_S3_REPLICATED_RELEASE: TestConfig(
|
||||
JobNames.STATELESS_TEST_OLD_ANALYZER_S3_REPLICATED_RELEASE: TestConfig(
|
||||
Build.PACKAGE_RELEASE,
|
||||
job_config=JobConfig(num_batches=4, **statless_test_common_params), # type: ignore
|
||||
),
|
||||
@ -1201,6 +1203,10 @@ CI_CONFIG = CIConfig(
|
||||
Build.PACKAGE_DEBUG,
|
||||
job_config=JobConfig(num_batches=6, **statless_test_common_params), # type: ignore
|
||||
),
|
||||
JobNames.STATELESS_TEST_AZURE_ASAN: TestConfig(
|
||||
Build.PACKAGE_ASAN,
|
||||
job_config=JobConfig(num_batches=4, **statless_test_common_params, release_only=True), # type: ignore
|
||||
),
|
||||
JobNames.STATELESS_TEST_S3_TSAN: TestConfig(
|
||||
Build.PACKAGE_TSAN,
|
||||
job_config=JobConfig(num_batches=5, **statless_test_common_params), # type: ignore
|
||||
@ -1223,6 +1229,9 @@ CI_CONFIG = CIConfig(
|
||||
JobNames.UPGRADE_TEST_ASAN: TestConfig(
|
||||
Build.PACKAGE_ASAN, job_config=JobConfig(pr_only=True, random_bucket="upgrade_with_sanitizer", **upgrade_test_common_params) # type: ignore
|
||||
),
|
||||
JobNames.STRESS_TEST_AZURE_TSAN: TestConfig(
|
||||
Build.PACKAGE_TSAN, job_config=JobConfig(**stress_test_common_params, release_only=True) # type: ignore
|
||||
),
|
||||
JobNames.UPGRADE_TEST_TSAN: TestConfig(
|
||||
Build.PACKAGE_TSAN, job_config=JobConfig(pr_only=True, random_bucket="upgrade_with_sanitizer", **upgrade_test_common_params) # type: ignore
|
||||
),
|
||||
@ -1236,7 +1245,7 @@ CI_CONFIG = CIConfig(
|
||||
Build.PACKAGE_ASAN,
|
||||
job_config=JobConfig(num_batches=4, **integration_test_common_params, release_only=True), # type: ignore
|
||||
),
|
||||
JobNames.INTEGRATION_TEST_ASAN_ANALYZER: TestConfig(
|
||||
JobNames.INTEGRATION_TEST_ASAN_OLD_ANALYZER: TestConfig(
|
||||
Build.PACKAGE_ASAN,
|
||||
job_config=JobConfig(num_batches=6, **integration_test_common_params), # type: ignore
|
||||
),
|
||||
@ -1368,8 +1377,8 @@ REQUIRED_CHECKS = [
|
||||
JobNames.UNIT_TEST,
|
||||
JobNames.UNIT_TEST_TSAN,
|
||||
JobNames.UNIT_TEST_UBSAN,
|
||||
JobNames.INTEGRATION_TEST_ASAN_ANALYZER,
|
||||
JobNames.STATELESS_TEST_ANALYZER_S3_REPLICATED_RELEASE,
|
||||
JobNames.INTEGRATION_TEST_ASAN_OLD_ANALYZER,
|
||||
JobNames.STATELESS_TEST_OLD_ANALYZER_S3_REPLICATED_RELEASE,
|
||||
]
|
||||
|
||||
|
||||
|
||||
@ -443,8 +443,7 @@ def update_mergeable_check(commit: Commit, pr_info: PRInfo, check_name: str) ->
|
||||
or pr_info.number == 0
|
||||
)
|
||||
|
||||
# FIXME: For now, always set mergeable check in the Merge Queue. It's required to pass MQ
|
||||
if not_run and not pr_info.is_merge_queue:
|
||||
if not_run:
|
||||
# Let's avoid unnecessary work
|
||||
return
|
||||
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
#!/usr/bin/env python3
|
||||
import logging
|
||||
import sys
|
||||
|
||||
from github import Github
|
||||
|
||||
@ -8,6 +9,7 @@ from commit_status_helper import (
|
||||
get_commit,
|
||||
get_commit_filtered_statuses,
|
||||
post_commit_status,
|
||||
set_mergeable_check,
|
||||
trigger_mergeable_check,
|
||||
)
|
||||
from get_robot_token import get_best_robot_token
|
||||
@ -18,14 +20,28 @@ from report import PENDING, SUCCESS
|
||||
def main():
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
|
||||
has_failure = False
|
||||
|
||||
# FIXME: temporary hack to fail Mergeable Check in MQ if pipeline has any failed jobs
|
||||
if len(sys.argv) > 1 and sys.argv[1] == "--pipeline-failure":
|
||||
has_failure = True
|
||||
|
||||
pr_info = PRInfo(need_orgs=True)
|
||||
gh = Github(get_best_robot_token(), per_page=100)
|
||||
commit = get_commit(gh, pr_info.sha)
|
||||
# Unconditionally update the Mergeable Check at the final step
|
||||
statuses = get_commit_filtered_statuses(commit)
|
||||
trigger_mergeable_check(commit, statuses)
|
||||
statuses = None
|
||||
|
||||
if pr_info.is_merge_queue:
|
||||
# in MQ Mergeable check status must never be green if any failures in workflow
|
||||
if has_failure:
|
||||
set_mergeable_check(commit, "workflow failed", "failure")
|
||||
else:
|
||||
# This must be the only place where green MCheck is set in the MQ (in the end of CI) to avoid early merge
|
||||
set_mergeable_check(commit, "workflow passed", "success")
|
||||
else:
|
||||
statuses = get_commit_filtered_statuses(commit)
|
||||
trigger_mergeable_check(commit, statuses)
|
||||
|
||||
if not pr_info.is_merge_queue:
|
||||
statuses = [s for s in statuses if s.context == StatusNames.CI]
|
||||
if not statuses:
|
||||
return
|
||||
|
||||
@ -15,6 +15,7 @@ from clickhouse_helper import CiLogsCredentials
|
||||
from docker_images_helper import DockerImage, get_docker_image, pull_image
|
||||
from download_release_packages import download_last_release
|
||||
from env_helper import REPO_COPY, REPORT_PATH, TEMP_PATH
|
||||
from get_robot_token import get_parameter_from_ssm
|
||||
from pr_info import PRInfo
|
||||
from report import ERROR, SUCCESS, JobReport, StatusType, TestResults, read_test_results
|
||||
from stopwatch import Stopwatch
|
||||
@ -27,6 +28,8 @@ def get_additional_envs(
|
||||
check_name: str, run_by_hash_num: int, run_by_hash_total: int
|
||||
) -> List[str]:
|
||||
result = []
|
||||
azure_connection_string = get_parameter_from_ssm("azure_connection_string")
|
||||
result.append(f"AZURE_CONNECTION_STRING='{azure_connection_string}'")
|
||||
if "DatabaseReplicated" in check_name:
|
||||
result.append("USE_DATABASE_REPLICATED=1")
|
||||
if "DatabaseOrdinary" in check_name:
|
||||
@ -40,6 +43,9 @@ def get_additional_envs(
|
||||
result.append("RANDOMIZE_OBJECT_KEY_TYPE=1")
|
||||
if "analyzer" in check_name:
|
||||
result.append("USE_OLD_ANALYZER=1")
|
||||
if "azure" in check_name:
|
||||
assert "USE_S3_STORAGE_FOR_MERGE_TREE=1" not in result
|
||||
result.append("USE_AZURE_STORAGE_FOR_MERGE_TREE=1")
|
||||
|
||||
if run_by_hash_total != 0:
|
||||
result.append(f"RUN_BY_HASH_NUM={run_by_hash_num}")
|
||||
|
||||
@ -265,7 +265,9 @@ class ClickhouseIntegrationTestsRunner:
|
||||
self.start_time = time.time()
|
||||
self.soft_deadline_time = self.start_time + (TASK_TIMEOUT - MAX_TIME_IN_SANDBOX)
|
||||
|
||||
self.use_analyzer = os.environ.get("CLICKHOUSE_USE_OLD_ANALYZER") is not None
|
||||
self.use_old_analyzer = (
|
||||
os.environ.get("CLICKHOUSE_USE_OLD_ANALYZER") is not None
|
||||
)
|
||||
|
||||
if "run_by_hash_total" in self.params:
|
||||
self.run_by_hash_total = self.params["run_by_hash_total"]
|
||||
@ -414,8 +416,8 @@ class ClickhouseIntegrationTestsRunner:
|
||||
result.append("--tmpfs")
|
||||
if self.disable_net_host:
|
||||
result.append("--disable-net-host")
|
||||
if self.use_analyzer:
|
||||
result.append("--analyzer")
|
||||
if self.use_old_analyzer:
|
||||
result.append("--old-analyzer")
|
||||
|
||||
return " ".join(result)
|
||||
|
||||
|
||||
@ -318,7 +318,7 @@ class PRInfo:
|
||||
|
||||
@property
|
||||
def is_release_branch(self) -> bool:
|
||||
return self.number == 0
|
||||
return self.number == 0 and not self.is_merge_queue
|
||||
|
||||
@property
|
||||
def is_pr(self):
|
||||
|
||||
@ -19,7 +19,6 @@ def get_options(i: int, upgrade_check: bool) -> str:
|
||||
|
||||
if i % 3 == 2 and not upgrade_check:
|
||||
options.append(f'''--db-engine="Replicated('/test/db/test_{i}', 's1', 'r1')"''')
|
||||
client_options.append("allow_experimental_database_replicated=1")
|
||||
client_options.append("enable_deflate_qpl_codec=1")
|
||||
client_options.append("enable_zstd_qat_codec=1")
|
||||
|
||||
|
||||
@ -12,18 +12,23 @@ from build_download_helper import download_all_deb_packages
|
||||
from clickhouse_helper import CiLogsCredentials
|
||||
from docker_images_helper import DockerImage, get_docker_image, pull_image
|
||||
from env_helper import REPO_COPY, REPORT_PATH, TEMP_PATH
|
||||
from get_robot_token import get_parameter_from_ssm
|
||||
from pr_info import PRInfo
|
||||
from report import ERROR, JobReport, TestResult, TestResults, read_test_results
|
||||
from stopwatch import Stopwatch
|
||||
from tee_popen import TeePopen
|
||||
|
||||
|
||||
def get_additional_envs() -> List[str]:
|
||||
def get_additional_envs(check_name: str) -> List[str]:
|
||||
result = []
|
||||
azure_connection_string = get_parameter_from_ssm("azure_connection_string")
|
||||
result.append(f"AZURE_CONNECTION_STRING='{azure_connection_string}'")
|
||||
# some cloud-specific features require feature flags enabled
|
||||
# so we need this ENV to be able to disable the randomization
|
||||
# of feature flags
|
||||
result.append("RANDOMIZE_KEEPER_FEATURE_FLAGS=1")
|
||||
if "azure" in check_name:
|
||||
result.append("USE_AZURE_STORAGE_FOR_MERGE_TREE=1")
|
||||
|
||||
return result
|
||||
|
||||
@ -143,7 +148,7 @@ def run_stress_test(docker_image_name: str) -> None:
|
||||
pr_info, stopwatch.start_time_str, check_name
|
||||
)
|
||||
|
||||
additional_envs = get_additional_envs()
|
||||
additional_envs = get_additional_envs(check_name)
|
||||
|
||||
run_command = get_run_command(
|
||||
packages_path,
|
||||
|
||||
@ -4,7 +4,6 @@
|
||||
|
||||
import unittest
|
||||
from ci import CiOptions
|
||||
from ci_config import JobNames
|
||||
|
||||
_TEST_BODY_1 = """
|
||||
#### Run only:
|
||||
@ -44,6 +43,85 @@ _TEST_BODY_3 = """
|
||||
- [x] <!---ci_include_analyzer--> Must include all tests for analyzer
|
||||
"""
|
||||
|
||||
_TEST_JOB_LIST = [
|
||||
"Style check",
|
||||
"Fast test",
|
||||
"package_release",
|
||||
"package_asan",
|
||||
"Docker server image",
|
||||
"Docker keeper image",
|
||||
"Install packages (amd64)",
|
||||
"Install packages (arm64)",
|
||||
"Stateless tests (debug)",
|
||||
"Stateless tests (release)",
|
||||
"Stateless tests (coverage)",
|
||||
"Stateless tests (aarch64)",
|
||||
"Stateless tests (asan)",
|
||||
"Stateless tests (tsan)",
|
||||
"Stateless tests (msan)",
|
||||
"Stateless tests (ubsan)",
|
||||
"Stateless tests (release, old analyzer, s3, DatabaseReplicated)",
|
||||
"Stateless tests (debug, s3 storage)",
|
||||
"Stateless tests (tsan, s3 storage)",
|
||||
"Stateless tests flaky check (asan)",
|
||||
"Stateful tests (debug)",
|
||||
"Stateful tests (release)",
|
||||
"Stateful tests (coverage)",
|
||||
"Stateful tests (aarch64)",
|
||||
"Stateful tests (asan)",
|
||||
"Stateful tests (tsan)",
|
||||
"Stateful tests (msan)",
|
||||
"Stateful tests (ubsan)",
|
||||
"Stateful tests (release, ParallelReplicas)",
|
||||
"Stateful tests (debug, ParallelReplicas)",
|
||||
"Stateful tests (asan, ParallelReplicas)",
|
||||
"Stateful tests (msan, ParallelReplicas)",
|
||||
"Stateful tests (ubsan, ParallelReplicas)",
|
||||
"Stateful tests (tsan, ParallelReplicas)",
|
||||
"Stress test (asan)",
|
||||
"Stress test (tsan)",
|
||||
"Stress test (ubsan)",
|
||||
"Stress test (msan)",
|
||||
"Stress test (debug)",
|
||||
"Integration tests (release)",
|
||||
"Integration tests (asan)",
|
||||
"Integration tests (asan, old analyzer)",
|
||||
"Integration tests (tsan)",
|
||||
"Integration tests (aarch64)",
|
||||
"Integration tests flaky check (asan)",
|
||||
"Upgrade check (debug)",
|
||||
"Upgrade check (asan)",
|
||||
"Upgrade check (tsan)",
|
||||
"Upgrade check (msan)",
|
||||
"Unit tests (release)",
|
||||
"Unit tests (asan)",
|
||||
"Unit tests (msan)",
|
||||
"Unit tests (tsan)",
|
||||
"Unit tests (ubsan)",
|
||||
"AST fuzzer (debug)",
|
||||
"AST fuzzer (asan)",
|
||||
"AST fuzzer (msan)",
|
||||
"AST fuzzer (tsan)",
|
||||
"AST fuzzer (ubsan)",
|
||||
"ClickHouse Keeper Jepsen",
|
||||
"ClickHouse Server Jepsen",
|
||||
"Performance Comparison",
|
||||
"Performance Comparison Aarch64",
|
||||
"Sqllogic test (release)",
|
||||
"SQLancer (release)",
|
||||
"SQLancer (debug)",
|
||||
"SQLTest",
|
||||
"Compatibility check (amd64)",
|
||||
"Compatibility check (aarch64)",
|
||||
"ClickBench (amd64)",
|
||||
"ClickBench (aarch64)",
|
||||
"libFuzzer tests",
|
||||
"ClickHouse build check",
|
||||
"ClickHouse special build check",
|
||||
"Docs check",
|
||||
"Bugfix validation",
|
||||
]
|
||||
|
||||
|
||||
class TestCIOptions(unittest.TestCase):
|
||||
def test_pr_body_parsing(self):
|
||||
@ -69,7 +147,7 @@ class TestCIOptions(unittest.TestCase):
|
||||
ci_options.exclude_keywords,
|
||||
["tsan", "aarch64", "analyzer", "s3_storage", "coverage"],
|
||||
)
|
||||
jobs_to_do = list(JobNames)
|
||||
jobs_to_do = list(_TEST_JOB_LIST)
|
||||
jobs_to_skip = []
|
||||
job_params = {}
|
||||
jobs_to_do, jobs_to_skip, job_params = ci_options.apply(
|
||||
@ -81,9 +159,6 @@ class TestCIOptions(unittest.TestCase):
|
||||
"Style check",
|
||||
"package_release",
|
||||
"package_asan",
|
||||
"package_ubsan",
|
||||
"package_debug",
|
||||
"package_msan",
|
||||
"Stateless tests (asan)",
|
||||
"Stateless tests flaky check (asan)",
|
||||
"Stateless tests (msan)",
|
||||
@ -103,7 +178,7 @@ class TestCIOptions(unittest.TestCase):
|
||||
)
|
||||
self.assertCountEqual(ci_options.include_keywords, ["analyzer"])
|
||||
self.assertIsNone(ci_options.exclude_keywords)
|
||||
jobs_to_do = list(JobNames)
|
||||
jobs_to_do = list(_TEST_JOB_LIST)
|
||||
jobs_to_skip = []
|
||||
job_params = {}
|
||||
jobs_to_do, jobs_to_skip, job_params = ci_options.apply(
|
||||
|
||||
@ -1646,8 +1646,8 @@ class TestCase:
|
||||
|
||||
client_options = self.add_random_settings(client_options)
|
||||
|
||||
if not is_valid_utf_8(self.case_file) or not is_valid_utf_8(
|
||||
self.reference_file
|
||||
if not is_valid_utf_8(self.case_file) or (
|
||||
self.reference_file and not is_valid_utf_8(self.reference_file)
|
||||
):
|
||||
proc, stdout, stderr, debug_log, total_time = self.run_single_test(
|
||||
server_logs_level, client_options
|
||||
|
||||
@ -4,13 +4,10 @@
|
||||
<azure>
|
||||
<type>object_storage</type>
|
||||
<object_storage_type>azure</object_storage_type>
|
||||
<storage_account_url>http://localhost:10000/devstoreaccount1</storage_account_url>
|
||||
<container_name>cont</container_name>
|
||||
<skip_access_check>false</skip_access_check>
|
||||
<!-- default credentials for Azurite storage account -->
|
||||
<account_name>devstoreaccount1</account_name>
|
||||
<account_key>Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==</account_key>
|
||||
<max_single_part_upload_size>33554432</max_single_part_upload_size>
|
||||
<container_name>openbucketforpublicci</container_name>
|
||||
<connection_string from_env="AZURE_CONNECTION_STRING"/>
|
||||
</azure>
|
||||
<cached_azure>
|
||||
<type>cache</type>
|
||||
|
||||
@ -0,0 +1,5 @@
|
||||
<clickhouse>
|
||||
<merge_tree>
|
||||
<storage_policy>azure_cache</storage_policy>
|
||||
</merge_tree>
|
||||
</clickhouse>
|
||||
@ -156,7 +156,7 @@ if [[ -n "$USE_DATABASE_ORDINARY" ]] && [[ "$USE_DATABASE_ORDINARY" -eq 1 ]]; th
|
||||
ln -sf $SRC_PATH/users.d/database_ordinary.xml $DEST_SERVER_PATH/users.d/
|
||||
fi
|
||||
|
||||
if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TREE" -eq 1 ]]; then
|
||||
if [[ "$USE_S3_STORAGE_FOR_MERGE_TREE" == "1" ]]; then
|
||||
object_key_types_options=("generate-suffix" "generate-full-key" "generate-template-key")
|
||||
object_key_type="${object_key_types_options[0]}"
|
||||
|
||||
@ -177,6 +177,8 @@ if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TR
|
||||
ln -sf $SRC_PATH/config.d/s3_storage_policy_by_default.xml $DEST_SERVER_PATH/config.d/
|
||||
;;
|
||||
esac
|
||||
elif [[ "$USE_AZURE_STORAGE_FOR_MERGE_TREE" == "1" ]]; then
|
||||
ln -sf $SRC_PATH/config.d/azure_storage_policy_by_default.xml $DEST_SERVER_PATH/config.d/
|
||||
fi
|
||||
|
||||
ARM="aarch64"
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
<clickhouse>
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
<distributed_ddl_output_mode>none</distributed_ddl_output_mode>
|
||||
<database_replicated_initial_query_timeout_sec>120</database_replicated_initial_query_timeout_sec>
|
||||
<distributed_ddl_task_timeout>120</distributed_ddl_task_timeout>
|
||||
|
||||
@ -1601,7 +1601,7 @@ class ClickHouseCluster:
|
||||
with_jdbc_bridge=False,
|
||||
with_hive=False,
|
||||
with_coredns=False,
|
||||
use_old_analyzer=False,
|
||||
use_old_analyzer=None,
|
||||
hostname=None,
|
||||
env_variables=None,
|
||||
instance_env_variables=False,
|
||||
@ -4405,8 +4405,18 @@ class ClickHouseInstance:
|
||||
)
|
||||
|
||||
write_embedded_config("0_common_instance_users.xml", users_d_dir)
|
||||
if self.use_old_analyzer:
|
||||
write_embedded_config("0_common_enable_analyzer.xml", users_d_dir)
|
||||
|
||||
use_old_analyzer = os.environ.get("CLICKHOUSE_USE_OLD_ANALYZER") is not None
|
||||
# If specific version was used there can be no
|
||||
# allow_experimental_analyzer setting, so do this only if it was
|
||||
# explicitly requested.
|
||||
if self.tag:
|
||||
use_old_analyzer = False
|
||||
# Prefer specified in the test option:
|
||||
if self.use_old_analyzer is not None:
|
||||
use_old_analyzer = self.use_old_analyzer
|
||||
if use_old_analyzer:
|
||||
write_embedded_config("0_common_enable_old_analyzer.xml", users_d_dir)
|
||||
|
||||
if len(self.custom_dictionaries_paths):
|
||||
write_embedded_config("0_common_enable_dictionaries.xml", self.config_d_dir)
|
||||
|
||||
@ -285,11 +285,11 @@ if __name__ == "__main__":
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--analyzer",
|
||||
"--old-analyzer",
|
||||
action="store_true",
|
||||
default=False,
|
||||
dest="analyzer",
|
||||
help="Use new analyzer infrastructure",
|
||||
dest="old_analyzer",
|
||||
help="Use old analyzer infrastructure",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
@ -385,9 +385,9 @@ if __name__ == "__main__":
|
||||
if args.keyword_expression:
|
||||
args.pytest_args += ["-k", args.keyword_expression]
|
||||
|
||||
use_analyzer = ""
|
||||
if args.analyzer:
|
||||
use_analyzer = "-e CLICKHOUSE_USE_OLD_ANALYZER=1"
|
||||
use_old_analyzer = ""
|
||||
if args.old_analyzer:
|
||||
use_old_analyzer = "-e CLICKHOUSE_USE_OLD_ANALYZER=1"
|
||||
|
||||
# NOTE: since pytest options is in the argument value already we need to additionally escape '"'
|
||||
pytest_opts = " ".join(
|
||||
@ -408,7 +408,7 @@ if __name__ == "__main__":
|
||||
f"--volume={args.utils_dir}/backupview:/ClickHouse/utils/backupview "
|
||||
f"--volume={args.utils_dir}/grpc-client/pb2:/ClickHouse/utils/grpc-client/pb2 "
|
||||
f"--volume=/run:/run/host:ro {dockerd_internal_volume} {env_tags} {env_cleanup} "
|
||||
f"-e DOCKER_CLIENT_TIMEOUT=300 -e COMPOSE_HTTP_TIMEOUT=600 {use_analyzer} -e PYTHONUNBUFFERED=1 "
|
||||
f"-e DOCKER_CLIENT_TIMEOUT=300 -e COMPOSE_HTTP_TIMEOUT=600 {use_old_analyzer} -e PYTHONUNBUFFERED=1 "
|
||||
f'-e PYTEST_ADDOPTS="{parallel_args} {pytest_opts} {tests_list} {rand_args} -vvv"'
|
||||
f" {DIND_INTEGRATION_TESTS_IMAGE_NAME}:{args.docker_image_version}"
|
||||
)
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
<clickhouse>
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
</default>
|
||||
</profiles>
|
||||
<users>
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
<clickhouse>
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
<allow_deprecated_database_ordinary>1</allow_deprecated_database_ordinary>
|
||||
</default>
|
||||
</profiles>
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
<clickhouse>
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
</default>
|
||||
</profiles>
|
||||
</clickhouse>
|
||||
|
||||
@ -1,8 +1,8 @@
|
||||
<clickhouse>
|
||||
<access_control_improvements>
|
||||
<users_without_row_policies_can_read_rows remove="remove"/>
|
||||
<select_from_system_db_requires_grant remove="remove"/>
|
||||
<select_from_information_schema_requires_grant remove="remove"/>
|
||||
<settings_constraints_replace_previous remove="remove"/>
|
||||
<users_without_row_policies_can_read_rows>false</users_without_row_policies_can_read_rows>
|
||||
<select_from_system_db_requires_grant>false</select_from_system_db_requires_grant>
|
||||
<select_from_information_schema_requires_grant>false</select_from_information_schema_requires_grant>
|
||||
<settings_constraints_replace_previous>false</settings_constraints_replace_previous>
|
||||
</access_control_improvements>
|
||||
</clickhouse>
|
||||
|
||||
@ -295,7 +295,6 @@ def test_replicated_database(cluster):
|
||||
node1 = cluster.instances["node3"]
|
||||
node1.query(
|
||||
"CREATE DATABASE rdb ENGINE=Replicated('/test/rdb', 's1', 'r1')",
|
||||
settings={"allow_experimental_database_replicated": 1},
|
||||
)
|
||||
|
||||
global uuids
|
||||
@ -312,7 +311,6 @@ def test_replicated_database(cluster):
|
||||
node2 = cluster.instances["node2"]
|
||||
node2.query(
|
||||
"CREATE DATABASE rdb ENGINE=Replicated('/test/rdb', 's1', 'r2')",
|
||||
settings={"allow_experimental_database_replicated": 1},
|
||||
)
|
||||
node2.query("SYSTEM SYNC DATABASE REPLICA rdb")
|
||||
|
||||
|
||||
@ -7,7 +7,7 @@ import uuid
|
||||
import time
|
||||
|
||||
from helpers.client import QueryRuntimeException
|
||||
from helpers.cluster import ClickHouseCluster
|
||||
from helpers.cluster import ClickHouseCluster, CLICKHOUSE_CI_MIN_TESTED_VERSION
|
||||
|
||||
cluster = ClickHouseCluster(__file__)
|
||||
|
||||
@ -23,9 +23,20 @@ def make_instance(name, cfg, *args, **kwargs):
|
||||
)
|
||||
|
||||
|
||||
# DBMS_MIN_REVISION_WITH_INTERSERVER_SECRET_V2 added in 23.3, ensure that CLICKHOUSE_CI_MIN_TESTED_VERSION fits
|
||||
assert CLICKHOUSE_CI_MIN_TESTED_VERSION < "23.3"
|
||||
|
||||
# _n1/_n2 contains cluster with different <secret> -- should fail
|
||||
n1 = make_instance("n1", "configs/remote_servers_n1.xml")
|
||||
n2 = make_instance("n2", "configs/remote_servers_n2.xml")
|
||||
backward = make_instance(
|
||||
"backward",
|
||||
"configs/remote_servers_backward.xml",
|
||||
image="clickhouse/clickhouse-server",
|
||||
# version without DBMS_MIN_REVISION_WITH_INTERSERVER_SECRET_V2
|
||||
tag=CLICKHOUSE_CI_MIN_TESTED_VERSION,
|
||||
with_installed_binary=True,
|
||||
)
|
||||
|
||||
users = pytest.mark.parametrize(
|
||||
"user,password",
|
||||
@ -399,3 +410,25 @@ def test_per_user_protocol_settings_secure_cluster(user, password):
|
||||
assert int(get_query_setting_on_shard(n1, id_, "max_memory_usage_for_user")) == int(
|
||||
1e9
|
||||
)
|
||||
|
||||
|
||||
@users
|
||||
def test_user_secure_cluster_with_backward(user, password):
|
||||
id_ = "with-backward-query-dist_secure-" + user
|
||||
n1.query(
|
||||
f"SELECT *, '{id_}' FROM dist_secure_backward", user=user, password=password
|
||||
)
|
||||
assert get_query_user_info(n1, id_) == [user, user]
|
||||
assert get_query_user_info(backward, id_) == [user, user]
|
||||
|
||||
|
||||
@users
|
||||
def test_user_secure_cluster_from_backward(user, password):
|
||||
id_ = "from-backward-query-dist_secure-" + user
|
||||
backward.query(f"SELECT *, '{id_}' FROM dist_secure", user=user, password=password)
|
||||
assert get_query_user_info(n1, id_) == [user, user]
|
||||
assert get_query_user_info(backward, id_) == [user, user]
|
||||
|
||||
assert n1.contains_in_log(
|
||||
"Using deprecated interserver protocol because the client is too old. Consider upgrading all nodes in cluster."
|
||||
)
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
<tcp_port>9000</tcp_port>
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
</default>
|
||||
</profiles>
|
||||
<users>
|
||||
|
||||
@ -37,18 +37,13 @@ def start_cluster():
|
||||
|
||||
|
||||
def test_drop_if_empty(start_cluster):
|
||||
settings = {
|
||||
"allow_experimental_database_replicated": 1,
|
||||
}
|
||||
node1.query(
|
||||
"CREATE DATABASE replicateddb "
|
||||
"ENGINE = Replicated('/clickhouse/databases/replicateddb', 'shard1', 'node1')",
|
||||
settings=settings,
|
||||
)
|
||||
node2.query(
|
||||
"CREATE DATABASE replicateddb "
|
||||
"ENGINE = Replicated('/clickhouse/databases/replicateddb', 'shard1', 'node2')",
|
||||
settings=settings,
|
||||
)
|
||||
node1.query(
|
||||
"CREATE TABLE default.tbl ON CLUSTER 'cluster' ("
|
||||
|
||||
@ -66,7 +66,6 @@ def test_ddl(started_cluster):
|
||||
def test_ddl_replicated(started_cluster):
|
||||
control_node.query(
|
||||
"CREATE DATABASE test_db ON CLUSTER 'external' ENGINE=Replicated('/replicated')",
|
||||
settings={"allow_experimental_database_replicated": 1},
|
||||
)
|
||||
# Exception is expected
|
||||
assert "It's not initial query" in control_node.query_and_get_error(
|
||||
|
||||
@ -27,6 +27,8 @@ if is_arm():
|
||||
|
||||
# Utilities
|
||||
|
||||
IPV6_ADDRESS = "2001:3984:3989::1:1111"
|
||||
|
||||
config_dir = os.path.join(script_dir, "./configs")
|
||||
cluster = ClickHouseCluster(__file__)
|
||||
node = cluster.add_instance(
|
||||
@ -36,12 +38,15 @@ node = cluster.add_instance(
|
||||
env_variables={
|
||||
"TSAN_OPTIONS": "report_atomic_races=0 " + os.getenv("TSAN_OPTIONS", default="")
|
||||
},
|
||||
ipv6_address=IPV6_ADDRESS,
|
||||
)
|
||||
main_channel = None
|
||||
|
||||
|
||||
def create_channel():
|
||||
node_ip_with_grpc_port = cluster.get_instance_ip("node") + ":" + str(GRPC_PORT)
|
||||
def create_channel(hostname=None):
|
||||
if not hostname:
|
||||
hostname = cluster.get_instance_ip("node")
|
||||
node_ip_with_grpc_port = hostname + ":" + str(GRPC_PORT)
|
||||
channel = grpc.insecure_channel(node_ip_with_grpc_port)
|
||||
grpc.channel_ready_future(channel).result(timeout=10)
|
||||
global main_channel
|
||||
@ -204,6 +209,11 @@ def test_select_one():
|
||||
assert query("SELECT 1") == "1\n"
|
||||
|
||||
|
||||
def test_ipv6_select_one():
|
||||
with create_channel(f"[{IPV6_ADDRESS}]") as channel:
|
||||
assert query("SELECT 1", channel=channel) == "1\n"
|
||||
|
||||
|
||||
def test_ordinary_query():
|
||||
assert query("SELECT count() FROM numbers(100)") == "100\n"
|
||||
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_drop_detached>1</allow_drop_detached>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
<allow_experimental_alter_materialized_view_structure>1</allow_experimental_alter_materialized_view_structure>
|
||||
<allow_experimental_object_type>0</allow_experimental_object_type>
|
||||
<allow_suspicious_codecs>0</allow_suspicious_codecs>
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
<profiles>
|
||||
<default>
|
||||
<allow_drop_detached>1</allow_drop_detached>
|
||||
<allow_experimental_database_replicated>1</allow_experimental_database_replicated>
|
||||
<allow_experimental_alter_materialized_view_structure>1</allow_experimental_alter_materialized_view_structure>
|
||||
</default>
|
||||
</profiles>
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user