mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-25 09:02:00 +00:00
Merge branch 'master' into format-settings-parsing
This commit is contained in:
commit
0a493b88f2
49
.github/workflows/backport_branches.yml
vendored
49
.github/workflows/backport_branches.yml
vendored
@ -159,33 +159,24 @@ jobs:
|
||||
############################################################################################
|
||||
##################################### BUILD REPORTER #######################################
|
||||
############################################################################################
|
||||
BuilderReport:
|
||||
Builds_Report:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() }}
|
||||
needs:
|
||||
- RunConfig
|
||||
- BuilderDebAarch64
|
||||
- BuilderDebAsan
|
||||
- BuilderDebDebug
|
||||
- BuilderDebRelease
|
||||
- BuilderDebTsan
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse build check
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
BuilderSpecialReport:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() }}
|
||||
needs:
|
||||
- RunConfig
|
||||
- BuilderBinDarwin
|
||||
- BuilderBinDarwinAarch64
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse special build check
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
|
||||
needs: [RunConfig, BuilderDebAarch64, BuilderDebAsan, BuilderDebDebug, BuilderDebRelease, BuilderDebTsan, BuilderBinDarwin, BuilderBinDarwinAarch64]
|
||||
runs-on: [self-hosted, style-checker-aarch64]
|
||||
steps:
|
||||
- name: Check out repository code
|
||||
uses: ClickHouse/checkout@v1
|
||||
- name: Download reports
|
||||
run: |
|
||||
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --pre --job-name Builds
|
||||
- name: Builds report
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
python3 ./build_report_check.py --reports package_release package_aarch64 package_asan package_tsan package_debug binary_darwin binary_darwin_aarch64
|
||||
- name: Set status
|
||||
run: |
|
||||
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --post --job-name Builds
|
||||
############################################################################################
|
||||
#################################### INSTALL PACKAGES ######################################
|
||||
############################################################################################
|
||||
@ -256,8 +247,7 @@ jobs:
|
||||
FinishCheck:
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
needs:
|
||||
- BuilderReport
|
||||
- BuilderSpecialReport
|
||||
- Builds_Report
|
||||
- FunctionalStatelessTestAsan
|
||||
- FunctionalStatefulTestDebug
|
||||
- StressTestTsan
|
||||
@ -273,5 +263,8 @@ jobs:
|
||||
- name: Finish label
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
# update mergeable check
|
||||
python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
# update overall ci report
|
||||
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
python3 merge_pr.py
|
||||
|
29
.github/workflows/create_release.yml
vendored
Normal file
29
.github/workflows/create_release.yml
vendored
Normal file
@ -0,0 +1,29 @@
|
||||
name: CreateRelease
|
||||
|
||||
concurrency:
|
||||
group: release
|
||||
|
||||
'on':
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
sha:
|
||||
description: 'The SHA hash of the commit from which to create the release'
|
||||
required: true
|
||||
type: string
|
||||
type:
|
||||
description: 'The type of release: "new" for a new release or "patch" for a patch release'
|
||||
required: true
|
||||
type: choice
|
||||
options:
|
||||
- new
|
||||
- patch
|
||||
|
||||
jobs:
|
||||
Release:
|
||||
runs-on: [self-hosted, style-checker-aarch64]
|
||||
steps:
|
||||
- name: Check out repository code
|
||||
uses: ClickHouse/checkout@v1
|
||||
- name: Print greeting
|
||||
run: |
|
||||
python3 ./tests/ci/release.py --commit ${{ inputs.sha }} --type ${{ inputs.type }} --dry-run
|
4
.github/workflows/master.yml
vendored
4
.github/workflows/master.yml
vendored
@ -117,11 +117,11 @@ jobs:
|
||||
# Reports should run even if Builds_1/2 fail - run them separately, not in Tests_1/2/3
|
||||
Builds_Report:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
|
||||
needs: [RunConfig, Builds_1, Builds_2]
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse build check
|
||||
test_name: Builds
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
|
||||
|
15
.github/workflows/merge_queue.yml
vendored
15
.github/workflows/merge_queue.yml
vendored
@ -96,20 +96,15 @@ jobs:
|
||||
stage: Tests_1
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
|
||||
################################# Stage Final #################################
|
||||
#
|
||||
FinishCheck:
|
||||
if: ${{ !cancelled() }}
|
||||
CheckReadyForMerge:
|
||||
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
|
||||
# Test_2 or Test_3 must not have jobs required for Mergeable check
|
||||
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Tests_1]
|
||||
runs-on: [self-hosted, style-checker-aarch64]
|
||||
steps:
|
||||
- name: Check out repository code
|
||||
uses: ClickHouse/checkout@v1
|
||||
- name: Check sync status
|
||||
- name: Check and set merge status
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
python3 sync_pr.py --status
|
||||
- name: Finish label
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
|
4
.github/workflows/pull_request.yml
vendored
4
.github/workflows/pull_request.yml
vendored
@ -146,11 +146,11 @@ jobs:
|
||||
# Reports should run even if Builds_1/2 fail - run them separately (not in Tests_1/2/3)
|
||||
Builds_Report:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
|
||||
needs: [RunConfig, StyleCheck, Builds_1, Builds_2]
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse build check
|
||||
test_name: Builds
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
|
||||
|
51
.github/workflows/release_branches.yml
vendored
51
.github/workflows/release_branches.yml
vendored
@ -176,35 +176,24 @@ jobs:
|
||||
############################################################################################
|
||||
##################################### BUILD REPORTER #######################################
|
||||
############################################################################################
|
||||
BuilderReport:
|
||||
Builds_Report:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() }}
|
||||
needs:
|
||||
- RunConfig
|
||||
- BuilderDebRelease
|
||||
- BuilderDebAarch64
|
||||
- BuilderDebAsan
|
||||
- BuilderDebTsan
|
||||
- BuilderDebUBsan
|
||||
- BuilderDebMsan
|
||||
- BuilderDebDebug
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse build check
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
BuilderSpecialReport:
|
||||
# run report check for failed builds to indicate the CI error
|
||||
if: ${{ !cancelled() }}
|
||||
needs:
|
||||
- RunConfig
|
||||
- BuilderBinDarwin
|
||||
- BuilderBinDarwinAarch64
|
||||
uses: ./.github/workflows/reusable_test.yml
|
||||
with:
|
||||
test_name: ClickHouse special build check
|
||||
runner_type: style-checker-aarch64
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
if: ${{ !cancelled() && needs.RunConfig.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Builds') }}
|
||||
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64, BuilderDebAsan, BuilderDebUBsan, BuilderDebMsan, BuilderDebTsan, BuilderDebDebug, BuilderBinDarwin, BuilderBinDarwinAarch64]
|
||||
runs-on: [self-hosted, style-checker-aarch64]
|
||||
steps:
|
||||
- name: Check out repository code
|
||||
uses: ClickHouse/checkout@v1
|
||||
- name: Download reports
|
||||
run: |
|
||||
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --pre --job-name Builds
|
||||
- name: Builds report
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
python3 ./build_report_check.py --reports package_release package_aarch64 package_asan package_msan package_ubsan package_tsan package_debug binary_darwin binary_darwin_aarch64
|
||||
- name: Set status
|
||||
run: |
|
||||
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(needs.RunConfig.outputs.data) }} --post --job-name Builds
|
||||
MarkReleaseReady:
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
needs:
|
||||
@ -460,8 +449,7 @@ jobs:
|
||||
needs:
|
||||
- DockerServerImage
|
||||
- DockerKeeperImage
|
||||
- BuilderReport
|
||||
- BuilderSpecialReport
|
||||
- Builds_Report
|
||||
- MarkReleaseReady
|
||||
- FunctionalStatelessTestDebug
|
||||
- FunctionalStatelessTestRelease
|
||||
@ -496,4 +484,7 @@ jobs:
|
||||
- name: Finish label
|
||||
run: |
|
||||
cd "$GITHUB_WORKSPACE/tests/ci"
|
||||
# update mergeable check
|
||||
python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
# update overall ci report
|
||||
python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
|
||||
|
10
CHANGELOG.md
10
CHANGELOG.md
@ -29,17 +29,17 @@
|
||||
* Added `merge_workload` and `mutation_workload` settings to regulate how resources are utilized and shared between merges, mutations and other workloads. [#64061](https://github.com/ClickHouse/ClickHouse/pull/64061) ([Sergei Trifonov](https://github.com/serxa)).
|
||||
* Add support for comparing IPv4 and IPv6 types using the `=` operator. [#64292](https://github.com/ClickHouse/ClickHouse/pull/64292) ([Francisco J. Jurado Moreno](https://github.com/Beetelbrox)).
|
||||
* Allow to store named collections in zookeeper. [#64574](https://github.com/ClickHouse/ClickHouse/pull/64574) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Support decimal arguments in binary math functions (pow(), atan2(), max2, min2(), hypot(). [#64582](https://github.com/ClickHouse/ClickHouse/pull/64582) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
|
||||
* Support decimal arguments in binary math functions (pow, atan2, max2, min2, hypot). [#64582](https://github.com/ClickHouse/ClickHouse/pull/64582) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
|
||||
* Add support for index analysis over `hilbertEncode`. [#64662](https://github.com/ClickHouse/ClickHouse/pull/64662) ([Artem Mustafin](https://github.com/Artemmm91)).
|
||||
* Added SQL functions `parseReadableSize` (along with `OrNull` and `OrZero` variants). [#64742](https://github.com/ClickHouse/ClickHouse/pull/64742) ([Francisco J. Jurado Moreno](https://github.com/Beetelbrox)).
|
||||
* Add server settings `max_table_num_to_throw` and `max_database_num_to_throw` to limit the number of databases or tables on `CREATE` queries. [#64781](https://github.com/ClickHouse/ClickHouse/pull/64781) ([Xu Jia](https://github.com/XuJia0210)).
|
||||
* Add _time virtual column to file alike storages (s3/file/hdfs/url/azureBlobStorage). [#64947](https://github.com/ClickHouse/ClickHouse/pull/64947) ([Ilya Golshtein](https://github.com/ilejn)).
|
||||
* Introduced new functions `base64UrlEncode`, `base64UrlDecode` and `tryBase64UrlDecode`. [#64991](https://github.com/ClickHouse/ClickHouse/pull/64991) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
|
||||
* Introduced new functions `base64URLEncode`, `base64URLDecode` and `tryBase64URLDecode`. [#64991](https://github.com/ClickHouse/ClickHouse/pull/64991) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
|
||||
* Add new function `editDistanceUTF8`, which calculates the [edit distance](https://en.wikipedia.org/wiki/Edit_distance) between two UTF8 strings. [#65269](https://github.com/ClickHouse/ClickHouse/pull/65269) ([LiuNeng](https://github.com/liuneng1994)).
|
||||
|
||||
#### Performance Improvement
|
||||
* Add a native parquet reader, which can read parquet binary to ClickHouse Columns directly. It's controlled by the setting `input_format_parquet_use_native_reader` (disabled by default). [#60361](https://github.com/ClickHouse/ClickHouse/pull/60361) ([ZhiHong Zhang](https://github.com/copperybean)).
|
||||
* Reduce the number of virtual function calls in ColumnNullable::size(). [#60556](https://github.com/ClickHouse/ClickHouse/pull/60556) ([HappenLee](https://github.com/HappenLee)).
|
||||
* Reduce the number of virtual function calls in ColumnNullable::size. [#60556](https://github.com/ClickHouse/ClickHouse/pull/60556) ([HappenLee](https://github.com/HappenLee)).
|
||||
* Speedup `splitByRegexp` when the regular expression argument is a single-character. [#62696](https://github.com/ClickHouse/ClickHouse/pull/62696) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Speed up FixedHashTable by keeping track of the min and max keys used. This allows to reduce the number of cells that need to be verified. [#62746](https://github.com/ClickHouse/ClickHouse/pull/62746) ([Jiebin Sun](https://github.com/jiebinn)).
|
||||
* Optimize the resolution of in(LowCardinality, ConstantSet). [#64060](https://github.com/ClickHouse/ClickHouse/pull/64060) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
|
||||
@ -51,7 +51,7 @@
|
||||
* Improve function least/greatest for nullable numberic type arguments. [#64668](https://github.com/ClickHouse/ClickHouse/pull/64668) ([KevinyhZou](https://github.com/KevinyhZou)).
|
||||
* Allow merging two consequent `FilterSteps` of a query plan. This improves filter-push-down optimization if the filter condition can be pushed down from the parent step. [#64760](https://github.com/ClickHouse/ClickHouse/pull/64760) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Remove bad optimization in vertical final implementation and re-enable vertical final algorithm by default. [#64783](https://github.com/ClickHouse/ClickHouse/pull/64783) ([Duc Canh Le](https://github.com/canhld94)).
|
||||
* Remove ALIAS nodes from the filter expression. This slightly improves performance for queries with `PREWHERE` (with new analyzer). [#64793](https://github.com/ClickHouse/ClickHouse/pull/64793) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Remove ALIAS nodes from the filter expression. This slightly improves performance for queries with `PREWHERE` (with the new analyzer). [#64793](https://github.com/ClickHouse/ClickHouse/pull/64793) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Fix performance regression in cross join introduced in [#60459](https://github.com/ClickHouse/ClickHouse/issues/60459) (24.5). [#65243](https://github.com/ClickHouse/ClickHouse/pull/65243) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
|
||||
#### Improvement
|
||||
@ -63,7 +63,7 @@
|
||||
* Reduce the memory usage when using Azure object storage by using fixed memory allocation, avoiding the allocation of an extra buffer. [#63160](https://github.com/ClickHouse/ClickHouse/pull/63160) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
|
||||
* Several minor corner case fixes to proxy support & tunneling. [#63427](https://github.com/ClickHouse/ClickHouse/pull/63427) ([Arthur Passos](https://github.com/arthurpassos)).
|
||||
* Add `http_response_headers` setting to support custom response headers in custom HTTP handlers. [#63562](https://github.com/ClickHouse/ClickHouse/pull/63562) ([Grigorii](https://github.com/GSokol)).
|
||||
* Improve io_uring resubmits visibility. Rename profile event `IOUringSQEsResubmits` -> `IOUringSQEsResubmitsAsync` and add a new one `IOUringSQEsResubmitsSync`. [#63699](https://github.com/ClickHouse/ClickHouse/pull/63699) ([Tomer Shafir](https://github.com/tomershafir)).
|
||||
* Improve io_uring resubmit visibility. Rename profile event `IOUringSQEsResubmits` -> `IOUringSQEsResubmitsAsync` and add a new one `IOUringSQEsResubmitsSync`. [#63699](https://github.com/ClickHouse/ClickHouse/pull/63699) ([Tomer Shafir](https://github.com/tomershafir)).
|
||||
* Introduce assertions to verify all functions are called with columns of the right size. [#63723](https://github.com/ClickHouse/ClickHouse/pull/63723) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* `SHOW CREATE TABLE` executed on top of system tables will now show the super handy comment unique for each table which will explain why this table is needed. [#63788](https://github.com/ClickHouse/ClickHouse/pull/63788) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
|
||||
* Added setting `metadata_storage_type` to keep free space on metadata storage disk. [#64128](https://github.com/ClickHouse/ClickHouse/pull/64128) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
|
||||
|
@ -6,6 +6,9 @@ namespace
|
||||
{
|
||||
std::string getFQDNOrHostNameImpl()
|
||||
{
|
||||
#if defined(OS_DARWIN)
|
||||
return Poco::Net::DNS::hostName();
|
||||
#else
|
||||
try
|
||||
{
|
||||
return Poco::Net::DNS::thisHost().name();
|
||||
@ -14,6 +17,7 @@ namespace
|
||||
{
|
||||
return Poco::Net::DNS::hostName();
|
||||
}
|
||||
#endif
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -34,7 +34,7 @@ if (OS_LINUX)
|
||||
# avoid spurious latencies and additional work associated with
|
||||
# MADV_DONTNEED. See
|
||||
# https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
|
||||
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
|
||||
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
|
||||
else()
|
||||
set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
|
||||
endif()
|
||||
|
@ -37,6 +37,7 @@ RUN pip3 install \
|
||||
tqdm==4.66.4 \
|
||||
types-requests \
|
||||
unidiff \
|
||||
jwt \
|
||||
&& rm -rf /root/.cache/pip
|
||||
|
||||
RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && locale-gen en_US.UTF-8
|
||||
|
@ -267,7 +267,7 @@ A pull request can be created even if the work is not completed yet. In this cas
|
||||
|
||||
Testing will commence as soon as ClickHouse employees label your PR with a tag “can be tested”. The results of some first checks (e.g. code style) will come in within several minutes. Build check results will arrive within half an hour. And the main set of tests will report itself within an hour.
|
||||
|
||||
The system will prepare ClickHouse binary builds for your pull request individually. To retrieve these builds click the “Details” link next to “ClickHouse build check” entry in the list of checks. There you will find direct links to the built .deb packages of ClickHouse which you can deploy even on your production servers (if you have no fear).
|
||||
The system will prepare ClickHouse binary builds for your pull request individually. To retrieve these builds click the “Details” link next to “Builds” entry in the list of checks. There you will find direct links to the built .deb packages of ClickHouse which you can deploy even on your production servers (if you have no fear).
|
||||
|
||||
Most probably some of the builds will fail at first times. This is due to the fact that we check builds both with gcc as well as with clang, with almost all of existing warnings (always with the `-Werror` flag) enabled for clang. On that same page, you can find all of the build logs so that you do not have to build ClickHouse in all of the possible ways.
|
||||
|
||||
|
@ -28,7 +28,7 @@ run, for example, the test `01428_hash_set_nan_key`, change to the repository
|
||||
folder and run the following command:
|
||||
|
||||
```
|
||||
PATH=$PATH:<path to clickhouse-client> tests/clickhouse-test 01428_hash_set_nan_key
|
||||
PATH=<path to clickhouse-client>:$PATH tests/clickhouse-test 01428_hash_set_nan_key
|
||||
```
|
||||
|
||||
Test results (`stderr` and `stdout`) are written to files `01428_hash_set_nan_key.[stderr|stdout]` which
|
||||
|
@ -56,6 +56,15 @@ SELECT * FROM test_table;
|
||||
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
|
||||
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
|
||||
|
||||
## Authentication
|
||||
|
||||
Currently there are 3 ways to authenticate:
|
||||
- `Managed Identity` - Can be used by providing an `endpoint`, `connection_string` or `storage_account_url`.
|
||||
- `SAS Token` - Can be used by providing an `endpoint`, `connection_string` or `storage_account_url`. It is identified by presence of '?' in the url.
|
||||
- `Workload Identity` - Can be used by providing an `endpoint` or `storage_account_url`. If `use_workload_identity` parameter is set in config, ([workload identity](https://github.com/Azure/azure-sdk-for-cpp/tree/main/sdk/identity/azure-identity#authenticate-azure-hosted-applications)) is used for authentication.
|
||||
|
||||
|
||||
|
||||
## See also
|
||||
|
||||
[Azure Blob Storage Table Function](/docs/en/sql-reference/table-functions/azureBlobStorage)
|
||||
|
@ -28,6 +28,8 @@ CREATE TABLE s3_queue_engine_table (name String, value UInt32)
|
||||
[s3queue_cleanup_interval_max_ms = 30000,]
|
||||
```
|
||||
|
||||
Starting with `24.7` settings without `s3queue_` prefix are also supported.
|
||||
|
||||
**Engine parameters**
|
||||
|
||||
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [below](#wildcards-in-path).
|
||||
|
@ -314,7 +314,7 @@ For example, to download a aarch64 binary for ClickHouse v23.4, follow these ste
|
||||
- Find the GitHub pull request for release v23.4: [Release pull request for branch 23.4](https://github.com/ClickHouse/ClickHouse/pull/49238)
|
||||
- Click "Commits", then click a commit similar to "Update autogenerated version to 23.4.2.1 and contributors" for the particular version you like to install.
|
||||
- Click the green check / yellow dot / red cross to open the list of CI checks.
|
||||
- Click "Details" next to "ClickHouse Build Check" in the list, it will open a page similar to [this page](https://s3.amazonaws.com/clickhouse-test-reports/46793/b460eb70bf29b19eadd19a1f959b15d186705394/clickhouse_build_check/report.html)
|
||||
- Click "Details" next to "Builds" in the list, it will open a page similar to [this page](https://s3.amazonaws.com/clickhouse-test-reports/46793/b460eb70bf29b19eadd19a1f959b15d186705394/clickhouse_build_check/report.html)
|
||||
- Find the rows with compiler = "clang-*-aarch64" - there are multiple rows.
|
||||
- Download the artifacts for these builds.
|
||||
|
||||
|
@ -193,6 +193,7 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va
|
||||
- `--hardware-utilization` — Print hardware utilization information in progress bar.
|
||||
- `--print-profile-events` – Print `ProfileEvents` packets.
|
||||
- `--profile-events-delay-ms` – Delay between printing `ProfileEvents` packets (-1 - print only totals, 0 - print every single packet).
|
||||
- `--jwt` – If specified, enables authorization via JSON Web Token. Server JWT authorization is available only in ClickHouse Cloud.
|
||||
|
||||
Instead of `--host`, `--port`, `--user` and `--password` options, ClickHouse client also supports connection strings (see next section).
|
||||
|
||||
|
@ -2169,6 +2169,7 @@ To exchange data with Hadoop, you can use [HDFS table engine](/docs/en/engines/t
|
||||
- [output_format_parquet_compression_method](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_compression_method) - compression method used in output Parquet format. Default value - `lz4`.
|
||||
- [input_format_parquet_max_block_size](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_max_block_size) - Max block row size for parquet reader. Default value - `65409`.
|
||||
- [input_format_parquet_prefer_block_bytes](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_prefer_block_bytes) - Average block bytes output by parquet reader. Default value - `16744704`.
|
||||
- [output_format_parquet_write_page_index](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_max_block_size) - Add a possibility to write page index into parquet files. Need to disable `output_format_parquet_use_custom_encoder` at present. Default value - `true`.
|
||||
|
||||
## ParquetMetadata {data-format-parquet-metadata}
|
||||
|
||||
|
@ -5,6 +5,10 @@ sidebar_label: "Named collections"
|
||||
title: "Named collections"
|
||||
---
|
||||
|
||||
import CloudNotSupportedBadge from '@theme/badges/CloudNotSupportedBadge';
|
||||
|
||||
<CloudNotSupportedBadge />
|
||||
|
||||
Named collections provide a way to store collections of key-value pairs to be
|
||||
used to configure integrations with external sources. You can use named collections with
|
||||
dictionaries, tables, table functions, and object storage.
|
||||
|
@ -498,6 +498,8 @@ Default: 0.9
|
||||
Interval in seconds during which the server's maximum allowed memory consumption is adjusted by the corresponding threshold in cgroups. (see
|
||||
settings `cgroup_memory_watcher_hard_limit_ratio` and `cgroup_memory_watcher_soft_limit_ratio`).
|
||||
|
||||
To disable the cgroup observer, set this value to `0`.
|
||||
|
||||
Type: UInt64
|
||||
|
||||
Default: 15
|
||||
@ -1463,6 +1465,9 @@ Keys:
|
||||
- `size` – Size of the file. Applies to `log` and `errorlog`. Once the file reaches `size`, ClickHouse archives and renames it, and creates a new log file in its place.
|
||||
- `count` – The number of archived log files that ClickHouse stores.
|
||||
- `console` – Send `log` and `errorlog` to the console instead of file. To enable, set to `1` or `true`.
|
||||
- `console_log_level` – Logging level for console. Default to `level`.
|
||||
- `use_syslog` - Log to syslog as well.
|
||||
- `syslog_level` - Logging level for logging to syslog.
|
||||
- `stream_compress` – Compress `log` and `errorlog` with `lz4` stream compression. To enable, set to `1` or `true`.
|
||||
- `formatting` – Specify log format to be printed in console log (currently only `json` supported).
|
||||
|
||||
|
@ -1428,6 +1428,13 @@ Average block bytes output by parquet reader. Lowering the configuration in the
|
||||
|
||||
Default value: `65409 * 256 = 16744704`
|
||||
|
||||
### output_format_parquet_write_page_index {#input_format_parquet_max_block_size}
|
||||
|
||||
Could add page index into parquet files. To enable this, need set `output_format_parquet_use_custom_encoder`=`false` and
|
||||
`output_format_parquet_write_page_index`=`true`.
|
||||
|
||||
Enable by default.
|
||||
|
||||
## Hive format settings {#hive-format-settings}
|
||||
|
||||
### input_format_hive_text_fields_delimiter {#input_format_hive_text_fields_delimiter}
|
||||
|
@ -36,9 +36,24 @@ $ echo 0 | sudo tee /proc/sys/vm/overcommit_memory
|
||||
Use `perf top` to watch the time spent in the kernel for memory management.
|
||||
Permanent huge pages also do not need to be allocated.
|
||||
|
||||
:::warning
|
||||
If your system has less than 16 GB of RAM, you may experience various memory exceptions because default settings do not match this amount of memory. The recommended amount of RAM is 32 GB or more. You can use ClickHouse in a system with a small amount of RAM, even with 2 GB of RAM, but it requires additional tuning and can ingest at a low rate.
|
||||
:::
|
||||
### Using less than 16GB of RAM
|
||||
|
||||
The recommended amount of RAM is 32 GB or more.
|
||||
|
||||
If your system has less than 16 GB of RAM, you may experience various memory exceptions because default settings do not match this amount of memory. You can use ClickHouse in a system with a small amount of RAM (as low as 2 GB), but these setups require additional tuning and can only ingest at a low rate.
|
||||
|
||||
When using ClickHouse with less than 16GB of RAM, we recommend the following:
|
||||
|
||||
- Lower the size of the mark cache in the `config.xml`. It can be set as low as 500 MB, but it cannot be set to zero.
|
||||
- Lower the number of query processing threads down to `1`.
|
||||
- Lower the `max_block_size` to `8192`. Values as low as `1024` can still be practical.
|
||||
- Lower `max_download_threads` to `1`.
|
||||
- Set `input_format_parallel_parsing` and `output_format_parallel_formatting` to `0`.
|
||||
|
||||
Additional notes:
|
||||
- To flush the memory cached by the memory allocator, you can run the `SYSTEM JEMALLOC PURGE`
|
||||
command.
|
||||
- We do not recommend using S3 or Kafka integrations on low-memory machines because they require significant memory for buffers.
|
||||
|
||||
## Storage Subsystem {#storage-subsystem}
|
||||
|
||||
|
@ -236,10 +236,10 @@ Read 2 rows, 32.00 B in 0.000 sec., 5182 rows/sec., 80.97 KiB/sec.
|
||||
Previous example is the same as:
|
||||
|
||||
``` bash
|
||||
$ echo -e "1,2\n3,4" | clickhouse-local --query "
|
||||
$ echo -e "1,2\n3,4" | clickhouse-local -n --query "
|
||||
CREATE TABLE table (a Int64, b Int64) ENGINE = File(CSV, stdin);
|
||||
SELECT a, b FROM table;
|
||||
DROP TABLE table"
|
||||
DROP TABLE table;"
|
||||
Read 2 rows, 32.00 B in 0.000 sec., 4987 rows/sec., 77.93 KiB/sec.
|
||||
1 2
|
||||
3 4
|
||||
|
@ -6,26 +6,297 @@ sidebar_label: NLP (experimental)
|
||||
|
||||
# Natural Language Processing (NLP) Functions
|
||||
|
||||
:::note
|
||||
:::warning
|
||||
This is an experimental feature that is currently in development and is not ready for general use. It will change in unpredictable backwards-incompatible ways in future releases. Set `allow_experimental_nlp_functions = 1` to enable it.
|
||||
:::
|
||||
|
||||
## detectCharset
|
||||
|
||||
The `detectCharset` function detects the character set of the non-UTF8-encoded input string.
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectCharset('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- A `String` containing the code of the detected character set
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectCharset('Ich bleibe für ein paar Tage.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectCharset('Ich bleibe für ein paar Tage.')─┐
|
||||
│ WINDOWS-1252 │
|
||||
└────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## detectLanguage
|
||||
|
||||
Detects the language of the UTF8-encoded input string. The function uses the [CLD2 library](https://github.com/CLD2Owners/cld2) for detection, and it returns the 2-letter ISO language code.
|
||||
|
||||
The `detectLanguage` function works best when providing over 200 characters in the input string.
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectLanguage('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- The 2-letter ISO code of the detected language
|
||||
|
||||
Other possible results:
|
||||
|
||||
- `un` = unknown, can not detect any language.
|
||||
- `other` = the detected language does not have 2 letter code.
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguage('Je pense que je ne parviendrai jamais à parler français comme un natif. Where there’s a will, there’s a way.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
fr
|
||||
```
|
||||
|
||||
## detectLanguageMixed
|
||||
|
||||
Similar to the `detectLanguage` function, but `detectLanguageMixed` returns a `Map` of 2-letter language codes that are mapped to the percentage of the certain language in the text.
|
||||
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectLanguageMixed('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- `Map(String, Float32)`: The keys are 2-letter ISO codes and the values are a percentage of text found for that language
|
||||
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguageMixed('二兎を追う者は一兎をも得ず二兎を追う者は一兎をも得ず A vaincre sans peril, on triomphe sans gloire.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectLanguageMixed()─┐
|
||||
│ {'ja':0.62,'fr':0.36 │
|
||||
└───────────────────────┘
|
||||
```
|
||||
|
||||
## detectProgrammingLanguage
|
||||
|
||||
Determines the programming language from the source code. Calculates all the unigrams and bigrams of commands in the source code.
|
||||
Then using a marked-up dictionary with weights of unigrams and bigrams of commands for various programming languages finds the biggest weight of the programming language and returns it.
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectProgrammingLanguage('source_code')
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `source_code` — String representation of the source code to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- Programming language. [String](../data-types/string.md).
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectProgrammingLanguage('#include <iostream>');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectProgrammingLanguage('#include <iostream>')─┐
|
||||
│ C++ │
|
||||
└──────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## detectLanguageUnknown
|
||||
|
||||
Similar to the `detectLanguage` function, except the `detectLanguageUnknown` function works with non-UTF8-encoded strings. Prefer this version when your character set is UTF-16 or UTF-32.
|
||||
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectLanguageUnknown('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- The 2-letter ISO code of the detected language
|
||||
|
||||
Other possible results:
|
||||
|
||||
- `un` = unknown, can not detect any language.
|
||||
- `other` = the detected language does not have 2 letter code.
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguageUnknown('Ich bleibe für ein paar Tage.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectLanguageUnknown('Ich bleibe für ein paar Tage.')─┐
|
||||
│ de │
|
||||
└────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## detectTonality
|
||||
|
||||
Determines the sentiment of text data. Uses a marked-up sentiment dictionary, in which each word has a tonality ranging from `-12` to `6`.
|
||||
For each text, it calculates the average sentiment value of its words and returns it in the range `[-1,1]`.
|
||||
|
||||
:::note
|
||||
This function is limited in its current form. Currently it makes use of the embedded emotional dictionary at `/contrib/nlp-data/tonality_ru.zst` and only works for the Russian language.
|
||||
:::
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
detectTonality(text)
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `text` — The text to be analyzed. [String](../data-types/string.md#string).
|
||||
|
||||
*Returned value*
|
||||
|
||||
- The average sentiment value of the words in `text`. [Float32](../data-types/float.md).
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectTonality('Шарик - хороший пёс'), -- Sharik is a good dog
|
||||
detectTonality('Шарик - пёс'), -- Sharik is a dog
|
||||
detectTonality('Шарик - плохой пёс'); -- Sharkik is a bad dog
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectTonality('Шарик - хороший пёс')─┬─detectTonality('Шарик - пёс')─┬─detectTonality('Шарик - плохой пёс')─┐
|
||||
│ 0.44445 │ 0 │ -0.3 │
|
||||
└───────────────────────────────────────┴───────────────────────────────┴──────────────────────────────────────┘
|
||||
```
|
||||
## lemmatize
|
||||
|
||||
Performs lemmatization on a given word. Needs dictionaries to operate, which can be obtained [here](https://github.com/vpodpecan/lemmagen3/tree/master/src/lemmagen3/models).
|
||||
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
lemmatize('language', word)
|
||||
```
|
||||
|
||||
*Arguments*
|
||||
|
||||
- `language` — Language which rules will be applied. [String](../data-types/string.md#string).
|
||||
- `word` — Word that needs to be lemmatized. Must be lowercase. [String](../data-types/string.md#string).
|
||||
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT lemmatize('en', 'wolves');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─lemmatize("wolves")─┐
|
||||
│ "wolf" │
|
||||
└─────────────────────┘
|
||||
```
|
||||
|
||||
*Configuration*
|
||||
|
||||
This configuration specifies that the dictionary `en.bin` should be used for lemmatization of English (`en`) words. The `.bin` files can be downloaded from
|
||||
[here](https://github.com/vpodpecan/lemmagen3/tree/master/src/lemmagen3/models).
|
||||
|
||||
``` xml
|
||||
<lemmatizers>
|
||||
<lemmatizer>
|
||||
<!-- highlight-start -->
|
||||
<lang>en</lang>
|
||||
<path>en.bin</path>
|
||||
<!-- highlight-end -->
|
||||
</lemmatizer>
|
||||
</lemmatizers>
|
||||
```
|
||||
|
||||
## stem
|
||||
|
||||
Performs stemming on a given word.
|
||||
|
||||
### Syntax
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
stem('language', word)
|
||||
```
|
||||
|
||||
### Arguments
|
||||
*Arguments*
|
||||
|
||||
- `language` — Language which rules will be applied. Use the two letter [ISO 639-1 code](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes).
|
||||
- `word` — word that needs to be stemmed. Must be in lowercase. [String](../data-types/string.md#string).
|
||||
|
||||
### Examples
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
@ -40,7 +311,7 @@ Result:
|
||||
│ ['I','think','it','is','a','bless','in','disguis'] │
|
||||
└────────────────────────────────────────────────────┘
|
||||
```
|
||||
### Supported languages for stem()
|
||||
*Supported languages for stem()*
|
||||
|
||||
:::note
|
||||
The stem() function uses the [Snowball stemming](https://snowballstem.org/) library, see the Snowball website for updated languages etc.
|
||||
@ -76,53 +347,6 @@ The stem() function uses the [Snowball stemming](https://snowballstem.org/) libr
|
||||
- Turkish
|
||||
- Yiddish
|
||||
|
||||
## lemmatize
|
||||
|
||||
Performs lemmatization on a given word. Needs dictionaries to operate, which can be obtained [here](https://github.com/vpodpecan/lemmagen3/tree/master/src/lemmagen3/models).
|
||||
|
||||
### Syntax
|
||||
|
||||
``` sql
|
||||
lemmatize('language', word)
|
||||
```
|
||||
|
||||
### Arguments
|
||||
|
||||
- `language` — Language which rules will be applied. [String](../data-types/string.md#string).
|
||||
- `word` — Word that needs to be lemmatized. Must be lowercase. [String](../data-types/string.md#string).
|
||||
|
||||
### Examples
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT lemmatize('en', 'wolves');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─lemmatize("wolves")─┐
|
||||
│ "wolf" │
|
||||
└─────────────────────┘
|
||||
```
|
||||
|
||||
### Configuration
|
||||
|
||||
This configuration specifies that the dictionary `en.bin` should be used for lemmatization of English (`en`) words. The `.bin` files can be downloaded from
|
||||
[here](https://github.com/vpodpecan/lemmagen3/tree/master/src/lemmagen3/models).
|
||||
|
||||
``` xml
|
||||
<lemmatizers>
|
||||
<lemmatizer>
|
||||
<!-- highlight-start -->
|
||||
<lang>en</lang>
|
||||
<path>en.bin</path>
|
||||
<!-- highlight-end -->
|
||||
</lemmatizer>
|
||||
</lemmatizers>
|
||||
```
|
||||
|
||||
## synonyms
|
||||
|
||||
Finds synonyms to a given word. There are two types of synonym extensions: `plain` and `wordnet`.
|
||||
@ -131,18 +355,18 @@ With the `plain` extension type we need to provide a path to a simple text file,
|
||||
|
||||
With the `wordnet` extension type we need to provide a path to a directory with WordNet thesaurus in it. Thesaurus must contain a WordNet sense index.
|
||||
|
||||
### Syntax
|
||||
*Syntax*
|
||||
|
||||
``` sql
|
||||
synonyms('extension_name', word)
|
||||
```
|
||||
|
||||
### Arguments
|
||||
*Arguments*
|
||||
|
||||
- `extension_name` — Name of the extension in which search will be performed. [String](../data-types/string.md#string).
|
||||
- `word` — Word that will be searched in extension. [String](../data-types/string.md#string).
|
||||
|
||||
### Examples
|
||||
*Examples*
|
||||
|
||||
Query:
|
||||
|
||||
@ -158,7 +382,7 @@ Result:
|
||||
└──────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Configuration
|
||||
*Configuration*
|
||||
``` xml
|
||||
<synonyms_extensions>
|
||||
<extension>
|
||||
@ -172,154 +396,4 @@ Result:
|
||||
<path>en/</path>
|
||||
</extension>
|
||||
</synonyms_extensions>
|
||||
```
|
||||
|
||||
## detectLanguage
|
||||
|
||||
Detects the language of the UTF8-encoded input string. The function uses the [CLD2 library](https://github.com/CLD2Owners/cld2) for detection, and it returns the 2-letter ISO language code.
|
||||
|
||||
The `detectLanguage` function works best when providing over 200 characters in the input string.
|
||||
|
||||
### Syntax
|
||||
|
||||
``` sql
|
||||
detectLanguage('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
### Arguments
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
### Returned value
|
||||
|
||||
- The 2-letter ISO code of the detected language
|
||||
|
||||
Other possible results:
|
||||
|
||||
- `un` = unknown, can not detect any language.
|
||||
- `other` = the detected language does not have 2 letter code.
|
||||
|
||||
### Examples
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguage('Je pense que je ne parviendrai jamais à parler français comme un natif. Where there’s a will, there’s a way.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
fr
|
||||
```
|
||||
|
||||
## detectLanguageMixed
|
||||
|
||||
Similar to the `detectLanguage` function, but `detectLanguageMixed` returns a `Map` of 2-letter language codes that are mapped to the percentage of the certain language in the text.
|
||||
|
||||
|
||||
### Syntax
|
||||
|
||||
``` sql
|
||||
detectLanguageMixed('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
### Arguments
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
### Returned value
|
||||
|
||||
- `Map(String, Float32)`: The keys are 2-letter ISO codes and the values are a percentage of text found for that language
|
||||
|
||||
|
||||
### Examples
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguageMixed('二兎を追う者は一兎をも得ず二兎を追う者は一兎をも得ず A vaincre sans peril, on triomphe sans gloire.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectLanguageMixed()─┐
|
||||
│ {'ja':0.62,'fr':0.36 │
|
||||
└───────────────────────┘
|
||||
```
|
||||
|
||||
## detectLanguageUnknown
|
||||
|
||||
Similar to the `detectLanguage` function, except the `detectLanguageUnknown` function works with non-UTF8-encoded strings. Prefer this version when your character set is UTF-16 or UTF-32.
|
||||
|
||||
|
||||
### Syntax
|
||||
|
||||
``` sql
|
||||
detectLanguageUnknown('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
### Arguments
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
### Returned value
|
||||
|
||||
- The 2-letter ISO code of the detected language
|
||||
|
||||
Other possible results:
|
||||
|
||||
- `un` = unknown, can not detect any language.
|
||||
- `other` = the detected language does not have 2 letter code.
|
||||
|
||||
### Examples
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectLanguageUnknown('Ich bleibe für ein paar Tage.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectLanguageUnknown('Ich bleibe für ein paar Tage.')─┐
|
||||
│ de │
|
||||
└────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## detectCharset
|
||||
|
||||
The `detectCharset` function detects the character set of the non-UTF8-encoded input string.
|
||||
|
||||
|
||||
### Syntax
|
||||
|
||||
``` sql
|
||||
detectCharset('text_to_be_analyzed')
|
||||
```
|
||||
|
||||
### Arguments
|
||||
|
||||
- `text_to_be_analyzed` — A collection (or sentences) of strings to analyze. [String](../data-types/string.md#string).
|
||||
|
||||
### Returned value
|
||||
|
||||
- A `String` containing the code of the detected character set
|
||||
|
||||
### Examples
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT detectCharset('Ich bleibe für ein paar Tage.');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─detectCharset('Ich bleibe für ein paar Tage.')─┐
|
||||
│ WINDOWS-1252 │
|
||||
└────────────────────────────────────────────────┘
|
||||
```
|
||||
```
|
@ -3820,3 +3820,43 @@ Result:
|
||||
10. │ df │ │
|
||||
└────┴───────────────────────┘
|
||||
```
|
||||
|
||||
## displayName
|
||||
|
||||
Returns the value of `display_name` from [config](../../operations/configuration-files.md/#configuration-files) or server Fully Qualified Domain Name (FQDN) if not set.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
displayName()
|
||||
```
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Value of `display_name` from config or server FQDN if not set. [String](../data-types/string.md).
|
||||
|
||||
**Example**
|
||||
|
||||
The `display_name` can be set in `config.xml`. Taking for example a server with `display_name` configured to 'production':
|
||||
|
||||
```xml
|
||||
<!-- It is the name that will be shown in the clickhouse-client.
|
||||
By default, anything with "production" will be highlighted in red in query prompt.
|
||||
-->
|
||||
<display_name>production</display_name>
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT displayName();
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─displayName()─┐
|
||||
│ production │
|
||||
└───────────────┘
|
||||
```
|
||||
|
||||
|
@ -1168,14 +1168,14 @@ Result:
|
||||
└────────────────────────────┘
|
||||
```
|
||||
|
||||
## base64UrlEncode
|
||||
## base64URLEncode
|
||||
|
||||
Encodes an URL (String or FixedString) as base64 with URL-specific modifications, according to [RFC 4648](https://datatracker.ietf.org/doc/html/rfc4648#section-5).
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
base64UrlEncode(url)
|
||||
base64URLEncode(url)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
@ -1189,13 +1189,13 @@ base64UrlEncode(url)
|
||||
**Example**
|
||||
|
||||
``` sql
|
||||
SELECT base64UrlEncode('https://clickhouse.com');
|
||||
SELECT base64URLEncode('https://clickhouse.com');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```result
|
||||
┌─base64UrlEncode('https://clickhouse.com')─┐
|
||||
┌─base64URLEncode('https://clickhouse.com')─┐
|
||||
│ aHR0cDovL2NsaWNraG91c2UuY29t │
|
||||
└───────────────────────────────────────────┘
|
||||
```
|
||||
@ -1234,19 +1234,19 @@ Result:
|
||||
└──────────────────────────────────┘
|
||||
```
|
||||
|
||||
## base64UrlDecode
|
||||
## base64URLDecode
|
||||
|
||||
Accepts a base64-encoded URL and decodes it from base64 with URL-specific modifications, according to [RFC 4648](https://datatracker.ietf.org/doc/html/rfc4648#section-5). Throws an exception in case of an error.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
base64UrlDecode(encodedUrl)
|
||||
base64URLDecode(encodedUrl)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
|
||||
- `encodedUrl` — [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, an exception is thrown.
|
||||
- `encodedURL` — [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, an exception is thrown.
|
||||
|
||||
**Returned value**
|
||||
|
||||
@ -1255,13 +1255,13 @@ base64UrlDecode(encodedUrl)
|
||||
**Example**
|
||||
|
||||
``` sql
|
||||
SELECT base64UrlDecode('aHR0cDovL2NsaWNraG91c2UuY29t');
|
||||
SELECT base64URLDecode('aHR0cDovL2NsaWNraG91c2UuY29t');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```result
|
||||
┌─base64UrlDecode('aHR0cDovL2NsaWNraG91c2UuY29t')─┐
|
||||
┌─base64URLDecode('aHR0cDovL2NsaWNraG91c2UuY29t')─┐
|
||||
│ https://clickhouse.com │
|
||||
└─────────────────────────────────────────────────┘
|
||||
```
|
||||
@ -1298,19 +1298,19 @@ SELECT tryBase64Decode('RW5jb2RlZA==') as res, tryBase64Decode('invalid') as res
|
||||
└────────────┴─────────────┘
|
||||
```
|
||||
|
||||
## tryBase64UrlDecode
|
||||
## tryBase64URLDecode
|
||||
|
||||
Like `base64UrlDecode` but returns an empty string in case of error.
|
||||
Like `base64URLDecode` but returns an empty string in case of error.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
tryBase64UrlDecode(encodedUrl)
|
||||
tryBase64URLDecode(encodedUrl)
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `encodedUrl`: [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string.
|
||||
- `encodedURL`: [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string.
|
||||
|
||||
**Returned value**
|
||||
|
||||
@ -1321,7 +1321,7 @@ tryBase64UrlDecode(encodedUrl)
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT tryBase64UrlDecode('aHR0cDovL2NsaWNraG91c2UuY29t') as res, tryBase64Decode('aHR0cHM6Ly9jbGlja') as res_invalid;
|
||||
SELECT tryBase64URLDecode('aHR0cDovL2NsaWNraG91c2UuY29t') as res, tryBase64Decode('aHR0cHM6Ly9jbGlja') as res_invalid;
|
||||
```
|
||||
|
||||
```response
|
||||
|
@ -818,6 +818,40 @@ The same as above, but including query string and fragment.
|
||||
|
||||
Example: `/top/news.html?page=2#comments`.
|
||||
|
||||
### protocol
|
||||
|
||||
Extracts the protocol from a URL.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
protocol(url)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
|
||||
- `url` — URL to extract protocol from. [String](../data-types/string.md).
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Protocol, or an empty string if it cannot be determined. [String](../data-types/string.md).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT protocol('https://clickhouse.com/');
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
┌─protocol('https://clickhouse.com/')─┐
|
||||
│ https │
|
||||
└─────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### queryString
|
||||
|
||||
Returns the query string without the initial question mark, `#` and everything after `#`.
|
||||
|
@ -9,8 +9,8 @@ sidebar_label: CONSTRAINT
|
||||
Constraints could be added or deleted using following syntax:
|
||||
|
||||
``` sql
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] ADD CONSTRAINT constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] DROP CONSTRAINT constraint_name;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] ADD CONSTRAINT [IF NOT EXISTS] constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] DROP CONSTRAINT [IF EXISTS] constraint_name;
|
||||
```
|
||||
|
||||
See more on [constraints](../../../sql-reference/statements/create/table.md#constraints).
|
||||
|
@ -3,6 +3,10 @@ slug: /en/sql-reference/statements/alter/named-collection
|
||||
sidebar_label: NAMED COLLECTION
|
||||
---
|
||||
|
||||
import CloudNotSupportedBadge from '@theme/badges/CloudNotSupportedBadge';
|
||||
|
||||
<CloudNotSupportedBadge />
|
||||
|
||||
# ALTER NAMED COLLECTION
|
||||
|
||||
This query intends to modify already existing named collections.
|
||||
|
@ -134,8 +134,8 @@ PRIMARY KEY (event_type, ts)
|
||||
ORDER BY (event_type, ts, browser)
|
||||
SETTINGS index_granularity = 8192
|
||||
|
||||
-- !!! The columns' definition is unchanged but it does not matter, we are not quering
|
||||
-- MATERIALIZED VIEW, we are quering TO (storage) table.
|
||||
-- !!! The columns' definition is unchanged but it does not matter, we are not querying
|
||||
-- MATERIALIZED VIEW, we are querying TO (storage) table.
|
||||
-- SELECT section is updated.
|
||||
|
||||
SHOW CREATE TABLE mv FORMAT TSVRaw;
|
||||
|
@ -3,6 +3,10 @@ slug: /en/sql-reference/statements/create/named-collection
|
||||
sidebar_label: NAMED COLLECTION
|
||||
---
|
||||
|
||||
import CloudNotSupportedBadge from '@theme/badges/CloudNotSupportedBadge';
|
||||
|
||||
<CloudNotSupportedBadge />
|
||||
|
||||
# CREATE NAMED COLLECTION
|
||||
|
||||
Creates a new named collection.
|
||||
|
@ -283,7 +283,7 @@ Pull request можно создать, даже если работа над з
|
||||
|
||||
Тесты будут запущены, как только сотрудники ClickHouse поставят для pull request тег «Can be tested». Результаты первых проверок (стиль кода) появятся уже через несколько минут. Результаты сборки появятся примерно через пол часа. Результаты основного набора тестов будут доступны в пределах часа.
|
||||
|
||||
Система подготовит сборки ClickHouse специально для вашего pull request. Для их получения, нажмите на ссылку «Details» у проверки «Clickhouse build check». Там вы сможете найти прямые ссылки на собранные .deb пакеты ClickHouse, которые, при желании, вы даже сможете установить на свои продакшен серверы (если не страшно).
|
||||
Система подготовит сборки ClickHouse специально для вашего pull request. Для их получения, нажмите на ссылку «Details» у проверки «Builds». Там вы сможете найти прямые ссылки на собранные .deb пакеты ClickHouse, которые, при желании, вы даже сможете установить на свои продакшен серверы (если не страшно).
|
||||
|
||||
Вероятнее всего, часть сборок не будет успешной с первого раза. Ведь мы проверяем сборку кода и gcc и clang, а при сборке с помощью clang включаются почти все существующие в природе warnings (всегда с флагом `-Werror`). На той же странице, вы сможете найти логи сборки - вам не обязательно самому собирать ClickHouse всеми возможными способами.
|
||||
|
||||
|
@ -141,6 +141,7 @@ $ clickhouse-client --param_tbl="numbers" --param_db="system" --param_col="numbe
|
||||
- `--secure` — если указано, будет использован безопасный канал.
|
||||
- `--history_file` - путь к файлу с историей команд.
|
||||
- `--param_<name>` — значение параметра для [запроса с параметрами](#cli-queries-with-parameters).
|
||||
- `--jwt` – авторизация с использованием JSON Web Token. Доступно только в ClickHouse Cloud.
|
||||
|
||||
Вместо параметров `--host`, `--port`, `--user` и `--password` клиент ClickHouse также поддерживает строки подключения (смотри следующий раздел).
|
||||
|
||||
|
@ -538,7 +538,7 @@ SELECT base58Decode('3dc8KtHrwM');
|
||||
|
||||
Синоним: `TO_BASE64`.
|
||||
|
||||
## base64UrlEncode(s)
|
||||
## base64URLEncode(s)
|
||||
|
||||
Производит кодирование URL (String или FixedString) в base64-представление в соответствии с [RFC 4648](https://tools.ietf.org/html/rfc4648).
|
||||
|
||||
@ -548,7 +548,7 @@ SELECT base58Decode('3dc8KtHrwM');
|
||||
|
||||
Синоним: `FROM_BASE64`.
|
||||
|
||||
## base64UrlDecode(s)
|
||||
## base64URLDecode(s)
|
||||
|
||||
Декодирует base64-представление URL в исходную строку в соответствии с [RFC 4648](https://tools.ietf.org/html/rfc4648). При невозможности декодирования выбрасывает исключение
|
||||
|
||||
@ -556,9 +556,9 @@ SELECT base58Decode('3dc8KtHrwM');
|
||||
|
||||
Функционал аналогичен base64Decode, но при невозможности декодирования возвращает пустую строку.
|
||||
|
||||
## tryBase64UrlDecode(s)
|
||||
## tryBase64URLDecode(s)
|
||||
|
||||
Функционал аналогичен base64UrlDecode, но при невозможности декодирования возвращает пустую строку.
|
||||
Функционал аналогичен base64URLDecode, но при невозможности декодирования возвращает пустую строку.
|
||||
|
||||
## endsWith(s, suffix) {#endswith}
|
||||
|
||||
|
@ -11,8 +11,8 @@ sidebar_label: "Манипуляции с ограничениями"
|
||||
Добавить или удалить ограничение можно с помощью запросов
|
||||
|
||||
``` sql
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] ADD CONSTRAINT constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] DROP CONSTRAINT constraint_name;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] ADD CONSTRAINT [IF NOT EXISTS] constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] DROP CONSTRAINT [IF EXISTS] constraint_name;
|
||||
```
|
||||
|
||||
Запросы выполняют добавление или удаление метаданных об ограничениях таблицы `[db].name`, поэтому выполняются мгновенно.
|
||||
|
@ -9,8 +9,8 @@ sidebar_label: 约束
|
||||
约束可以使用以下语法添加或删除:
|
||||
|
||||
``` sql
|
||||
ALTER TABLE [db].name ADD CONSTRAINT constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name DROP CONSTRAINT constraint_name;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] ADD CONSTRAINT [IF NOT EXISTS] constraint_name CHECK expression;
|
||||
ALTER TABLE [db].name [ON CLUSTER cluster] DROP CONSTRAINT [IF EXISTS] constraint_name;
|
||||
```
|
||||
|
||||
查看[constraints](../../../sql-reference/statements/create/table.mdx#constraints)。
|
||||
|
@ -63,6 +63,7 @@ namespace ErrorCodes
|
||||
extern const int NETWORK_ERROR;
|
||||
extern const int AUTHENTICATION_FAILED;
|
||||
extern const int NO_ELEMENTS_IN_CONFIG;
|
||||
extern const int USER_EXPIRED;
|
||||
}
|
||||
|
||||
|
||||
@ -73,6 +74,12 @@ void Client::processError(const String & query) const
|
||||
fmt::print(stderr, "Received exception from server (version {}):\n{}\n",
|
||||
server_version,
|
||||
getExceptionMessage(*server_exception, print_stack_trace, true));
|
||||
|
||||
if (server_exception->code() == ErrorCodes::USER_EXPIRED)
|
||||
{
|
||||
server_exception->rethrow();
|
||||
}
|
||||
|
||||
if (is_interactive)
|
||||
{
|
||||
fmt::print(stderr, "\n");
|
||||
@ -240,6 +247,10 @@ std::vector<String> Client::loadWarningMessages()
|
||||
}
|
||||
}
|
||||
|
||||
Poco::Util::LayeredConfiguration & Client::getClientConfiguration()
|
||||
{
|
||||
return config();
|
||||
}
|
||||
|
||||
void Client::initialize(Poco::Util::Application & self)
|
||||
{
|
||||
@ -680,9 +691,7 @@ bool Client::processWithFuzzing(const String & full_query)
|
||||
const char * begin = full_query.data();
|
||||
orig_ast = parseQuery(begin, begin + full_query.size(),
|
||||
global_context->getSettingsRef(),
|
||||
/*allow_multi_statements=*/ true,
|
||||
/*is_interactive=*/ is_interactive,
|
||||
/*ignore_error=*/ ignore_error);
|
||||
/*allow_multi_statements=*/ true);
|
||||
}
|
||||
catch (const Exception & e)
|
||||
{
|
||||
@ -934,6 +943,7 @@ void Client::addOptions(OptionsDescription & options_description)
|
||||
("ssh-key-file", po::value<std::string>(), "File containing the SSH private key for authenticate with the server.")
|
||||
("ssh-key-passphrase", po::value<std::string>(), "Passphrase for the SSH private key specified by --ssh-key-file.")
|
||||
("quota_key", po::value<std::string>(), "A string to differentiate quotas when the user have keyed quotas configured on server")
|
||||
("jwt", po::value<std::string>(), "Use JWT for authentication")
|
||||
|
||||
("max_client_network_bandwidth", po::value<int>(), "the maximum speed of data exchange over the network for the client in bytes per second.")
|
||||
("compression", po::value<bool>(), "enable or disable compression (enabled by default for remote communication and disabled for localhost communication).")
|
||||
@ -1092,6 +1102,12 @@ void Client::processOptions(const OptionsDescription & options_description,
|
||||
config().setBool("no-warnings", true);
|
||||
if (options.count("fake-drop"))
|
||||
config().setString("ignore_drop_queries_probability", "1");
|
||||
if (options.count("jwt"))
|
||||
{
|
||||
if (!options["user"].defaulted())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "User and JWT flags can't be specified together");
|
||||
config().setString("jwt", options["jwt"].as<std::string>());
|
||||
}
|
||||
if (options.count("accept-invalid-certificate"))
|
||||
{
|
||||
config().setString("openSSL.client.invalidCertificateHandler.name", "AcceptCertificateHandler");
|
||||
|
@ -16,6 +16,9 @@ public:
|
||||
int main(const std::vector<String> & /*args*/) override;
|
||||
|
||||
protected:
|
||||
|
||||
Poco::Util::LayeredConfiguration & getClientConfiguration() override;
|
||||
|
||||
bool processWithFuzzing(const String & full_query) override;
|
||||
std::optional<bool> processFuzzingStep(const String & query_to_execute, const ASTPtr & parsed_query);
|
||||
|
||||
|
@ -383,6 +383,9 @@ int KeeperClient::main(const std::vector<String> & /* args */)
|
||||
|
||||
for (const auto & key : keys)
|
||||
{
|
||||
if (key != "node")
|
||||
continue;
|
||||
|
||||
String prefix = "zookeeper." + key;
|
||||
String host = clickhouse_config.configuration->getString(prefix + ".host");
|
||||
String port = clickhouse_config.configuration->getString(prefix + ".port");
|
||||
@ -401,6 +404,7 @@ int KeeperClient::main(const std::vector<String> & /* args */)
|
||||
zk_args.hosts.push_back(host + ":" + port);
|
||||
}
|
||||
|
||||
zk_args.availability_zones.resize(zk_args.hosts.size());
|
||||
zk_args.connection_timeout_ms = config().getInt("connection-timeout", 10) * 1000;
|
||||
zk_args.session_timeout_ms = config().getInt("session-timeout", 10) * 1000;
|
||||
zk_args.operation_timeout_ms = config().getInt("operation-timeout", 10) * 1000;
|
||||
|
@ -355,10 +355,7 @@ try
|
||||
|
||||
std::string include_from_path = config().getString("include_from", "/etc/metrika.xml");
|
||||
|
||||
if (config().has(DB::PlacementInfo::PLACEMENT_CONFIG_PREFIX))
|
||||
{
|
||||
PlacementInfo::PlacementInfo::instance().initialize(config());
|
||||
}
|
||||
PlacementInfo::PlacementInfo::instance().initialize(config());
|
||||
|
||||
GlobalThreadPool::initialize(
|
||||
/// We need to have sufficient amount of threads for connections + nuraft workers + keeper workers, 1000 is an estimation
|
||||
@ -577,8 +574,7 @@ try
|
||||
#if USE_SSL
|
||||
CertificateReloader::instance().tryLoad(*config);
|
||||
#endif
|
||||
},
|
||||
/* already_loaded = */ false); /// Reload it right now (initial loading)
|
||||
});
|
||||
|
||||
SCOPE_EXIT({
|
||||
LOG_INFO(log, "Shutting down.");
|
||||
|
@ -11,7 +11,6 @@ set (CLICKHOUSE_LIBRARY_BRIDGE_SOURCES
|
||||
LibraryBridgeHandlers.cpp
|
||||
SharedLibrary.cpp
|
||||
library-bridge.cpp
|
||||
createFunctionBaseCast.cpp
|
||||
)
|
||||
|
||||
clickhouse_add_executable(clickhouse-library-bridge ${CLICKHOUSE_LIBRARY_BRIDGE_SOURCES})
|
||||
@ -20,6 +19,7 @@ target_link_libraries(clickhouse-library-bridge PRIVATE
|
||||
daemon
|
||||
dbms
|
||||
bridge
|
||||
clickhouse_functions
|
||||
)
|
||||
|
||||
set_target_properties(clickhouse-library-bridge PROPERTIES RUNTIME_OUTPUT_DIRECTORY ..)
|
||||
|
@ -79,6 +79,11 @@ void applySettingsOverridesForLocal(ContextMutablePtr context)
|
||||
context->setSettings(settings);
|
||||
}
|
||||
|
||||
Poco::Util::LayeredConfiguration & LocalServer::getClientConfiguration()
|
||||
{
|
||||
return config();
|
||||
}
|
||||
|
||||
void LocalServer::processError(const String &) const
|
||||
{
|
||||
if (ignore_error)
|
||||
@ -114,19 +119,19 @@ void LocalServer::initialize(Poco::Util::Application & self)
|
||||
Poco::Util::Application::initialize(self);
|
||||
|
||||
/// Load config files if exists
|
||||
if (config().has("config-file") || fs::exists("config.xml"))
|
||||
if (getClientConfiguration().has("config-file") || fs::exists("config.xml"))
|
||||
{
|
||||
const auto config_path = config().getString("config-file", "config.xml");
|
||||
const auto config_path = getClientConfiguration().getString("config-file", "config.xml");
|
||||
ConfigProcessor config_processor(config_path, false, true);
|
||||
ConfigProcessor::setConfigPath(fs::path(config_path).parent_path());
|
||||
auto loaded_config = config_processor.loadConfig();
|
||||
config().add(loaded_config.configuration.duplicate(), PRIO_DEFAULT, false);
|
||||
getClientConfiguration().add(loaded_config.configuration.duplicate(), PRIO_DEFAULT, false);
|
||||
}
|
||||
|
||||
GlobalThreadPool::initialize(
|
||||
config().getUInt("max_thread_pool_size", 10000),
|
||||
config().getUInt("max_thread_pool_free_size", 1000),
|
||||
config().getUInt("thread_pool_queue_size", 10000)
|
||||
getClientConfiguration().getUInt("max_thread_pool_size", 10000),
|
||||
getClientConfiguration().getUInt("max_thread_pool_free_size", 1000),
|
||||
getClientConfiguration().getUInt("thread_pool_queue_size", 10000)
|
||||
);
|
||||
|
||||
#if USE_AZURE_BLOB_STORAGE
|
||||
@ -138,18 +143,18 @@ void LocalServer::initialize(Poco::Util::Application & self)
|
||||
#endif
|
||||
|
||||
getIOThreadPool().initialize(
|
||||
config().getUInt("max_io_thread_pool_size", 100),
|
||||
config().getUInt("max_io_thread_pool_free_size", 0),
|
||||
config().getUInt("io_thread_pool_queue_size", 10000));
|
||||
getClientConfiguration().getUInt("max_io_thread_pool_size", 100),
|
||||
getClientConfiguration().getUInt("max_io_thread_pool_free_size", 0),
|
||||
getClientConfiguration().getUInt("io_thread_pool_queue_size", 10000));
|
||||
|
||||
|
||||
const size_t active_parts_loading_threads = config().getUInt("max_active_parts_loading_thread_pool_size", 64);
|
||||
const size_t active_parts_loading_threads = getClientConfiguration().getUInt("max_active_parts_loading_thread_pool_size", 64);
|
||||
getActivePartsLoadingThreadPool().initialize(
|
||||
active_parts_loading_threads,
|
||||
0, // We don't need any threads one all the parts will be loaded
|
||||
active_parts_loading_threads);
|
||||
|
||||
const size_t outdated_parts_loading_threads = config().getUInt("max_outdated_parts_loading_thread_pool_size", 32);
|
||||
const size_t outdated_parts_loading_threads = getClientConfiguration().getUInt("max_outdated_parts_loading_thread_pool_size", 32);
|
||||
getOutdatedPartsLoadingThreadPool().initialize(
|
||||
outdated_parts_loading_threads,
|
||||
0, // We don't need any threads one all the parts will be loaded
|
||||
@ -157,7 +162,7 @@ void LocalServer::initialize(Poco::Util::Application & self)
|
||||
|
||||
getOutdatedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);
|
||||
|
||||
const size_t unexpected_parts_loading_threads = config().getUInt("max_unexpected_parts_loading_thread_pool_size", 32);
|
||||
const size_t unexpected_parts_loading_threads = getClientConfiguration().getUInt("max_unexpected_parts_loading_thread_pool_size", 32);
|
||||
getUnexpectedPartsLoadingThreadPool().initialize(
|
||||
unexpected_parts_loading_threads,
|
||||
0, // We don't need any threads one all the parts will be loaded
|
||||
@ -165,7 +170,7 @@ void LocalServer::initialize(Poco::Util::Application & self)
|
||||
|
||||
getUnexpectedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);
|
||||
|
||||
const size_t cleanup_threads = config().getUInt("max_parts_cleaning_thread_pool_size", 128);
|
||||
const size_t cleanup_threads = getClientConfiguration().getUInt("max_parts_cleaning_thread_pool_size", 128);
|
||||
getPartsCleaningThreadPool().initialize(
|
||||
cleanup_threads,
|
||||
0, // We don't need any threads one all the parts will be deleted
|
||||
@ -198,10 +203,10 @@ void LocalServer::tryInitPath()
|
||||
{
|
||||
std::string path;
|
||||
|
||||
if (config().has("path"))
|
||||
if (getClientConfiguration().has("path"))
|
||||
{
|
||||
// User-supplied path.
|
||||
path = config().getString("path");
|
||||
path = getClientConfiguration().getString("path");
|
||||
Poco::trimInPlace(path);
|
||||
|
||||
if (path.empty())
|
||||
@ -260,13 +265,13 @@ void LocalServer::tryInitPath()
|
||||
|
||||
global_context->setUserFilesPath(""); /// user's files are everywhere
|
||||
|
||||
std::string user_scripts_path = config().getString("user_scripts_path", fs::path(path) / "user_scripts/");
|
||||
std::string user_scripts_path = getClientConfiguration().getString("user_scripts_path", fs::path(path) / "user_scripts/");
|
||||
global_context->setUserScriptsPath(user_scripts_path);
|
||||
|
||||
/// top_level_domains_lists
|
||||
const std::string & top_level_domains_path = config().getString("top_level_domains_path", fs::path(path) / "top_level_domains/");
|
||||
const std::string & top_level_domains_path = getClientConfiguration().getString("top_level_domains_path", fs::path(path) / "top_level_domains/");
|
||||
if (!top_level_domains_path.empty())
|
||||
TLDListsHolder::getInstance().parseConfig(fs::path(top_level_domains_path) / "", config());
|
||||
TLDListsHolder::getInstance().parseConfig(fs::path(top_level_domains_path) / "", getClientConfiguration());
|
||||
}
|
||||
|
||||
|
||||
@ -308,14 +313,14 @@ void LocalServer::cleanup()
|
||||
|
||||
std::string LocalServer::getInitialCreateTableQuery()
|
||||
{
|
||||
if (!config().has("table-structure") && !config().has("table-file") && !config().has("table-data-format") && (!isRegularFile(STDIN_FILENO) || queries.empty()))
|
||||
if (!getClientConfiguration().has("table-structure") && !getClientConfiguration().has("table-file") && !getClientConfiguration().has("table-data-format") && (!isRegularFile(STDIN_FILENO) || queries.empty()))
|
||||
return {};
|
||||
|
||||
auto table_name = backQuoteIfNeed(config().getString("table-name", "table"));
|
||||
auto table_structure = config().getString("table-structure", "auto");
|
||||
auto table_name = backQuoteIfNeed(getClientConfiguration().getString("table-name", "table"));
|
||||
auto table_structure = getClientConfiguration().getString("table-structure", "auto");
|
||||
|
||||
String table_file;
|
||||
if (!config().has("table-file") || config().getString("table-file") == "-")
|
||||
if (!getClientConfiguration().has("table-file") || getClientConfiguration().getString("table-file") == "-")
|
||||
{
|
||||
/// Use Unix tools stdin naming convention
|
||||
table_file = "stdin";
|
||||
@ -323,7 +328,7 @@ std::string LocalServer::getInitialCreateTableQuery()
|
||||
else
|
||||
{
|
||||
/// Use regular file
|
||||
auto file_name = config().getString("table-file");
|
||||
auto file_name = getClientConfiguration().getString("table-file");
|
||||
table_file = quoteString(file_name);
|
||||
}
|
||||
|
||||
@ -371,18 +376,18 @@ void LocalServer::setupUsers()
|
||||
|
||||
ConfigurationPtr users_config;
|
||||
auto & access_control = global_context->getAccessControl();
|
||||
access_control.setNoPasswordAllowed(config().getBool("allow_no_password", true));
|
||||
access_control.setPlaintextPasswordAllowed(config().getBool("allow_plaintext_password", true));
|
||||
if (config().has("config-file") || fs::exists("config.xml"))
|
||||
access_control.setNoPasswordAllowed(getClientConfiguration().getBool("allow_no_password", true));
|
||||
access_control.setPlaintextPasswordAllowed(getClientConfiguration().getBool("allow_plaintext_password", true));
|
||||
if (getClientConfiguration().has("config-file") || fs::exists("config.xml"))
|
||||
{
|
||||
String config_path = config().getString("config-file", "");
|
||||
bool has_user_directories = config().has("user_directories");
|
||||
String config_path = getClientConfiguration().getString("config-file", "");
|
||||
bool has_user_directories = getClientConfiguration().has("user_directories");
|
||||
const auto config_dir = fs::path{config_path}.remove_filename().string();
|
||||
String users_config_path = config().getString("users_config", "");
|
||||
String users_config_path = getClientConfiguration().getString("users_config", "");
|
||||
|
||||
if (users_config_path.empty() && has_user_directories)
|
||||
{
|
||||
users_config_path = config().getString("user_directories.users_xml.path");
|
||||
users_config_path = getClientConfiguration().getString("user_directories.users_xml.path");
|
||||
if (fs::path(users_config_path).is_relative() && fs::exists(fs::path(config_dir) / users_config_path))
|
||||
users_config_path = fs::path(config_dir) / users_config_path;
|
||||
}
|
||||
@ -406,10 +411,10 @@ void LocalServer::setupUsers()
|
||||
|
||||
void LocalServer::connect()
|
||||
{
|
||||
connection_parameters = ConnectionParameters(config(), "localhost");
|
||||
connection_parameters = ConnectionParameters(getClientConfiguration(), "localhost");
|
||||
|
||||
ReadBuffer * in;
|
||||
auto table_file = config().getString("table-file", "-");
|
||||
auto table_file = getClientConfiguration().getString("table-file", "-");
|
||||
if (table_file == "-" || table_file == "stdin")
|
||||
{
|
||||
in = &std_in;
|
||||
@ -429,7 +434,7 @@ try
|
||||
{
|
||||
UseSSL use_ssl;
|
||||
|
||||
StackTrace::setShowAddresses(config().getBool("show_addresses_in_stack_traces", true));
|
||||
StackTrace::setShowAddresses(getClientConfiguration().getBool("show_addresses_in_stack_traces", true));
|
||||
|
||||
setupSignalHandler();
|
||||
|
||||
@ -444,7 +449,7 @@ try
|
||||
|
||||
if (rlim.rlim_cur < rlim.rlim_max)
|
||||
{
|
||||
rlim.rlim_cur = config().getUInt("max_open_files", static_cast<unsigned>(rlim.rlim_max));
|
||||
rlim.rlim_cur = getClientConfiguration().getUInt("max_open_files", static_cast<unsigned>(rlim.rlim_max));
|
||||
int rc = setrlimit(RLIMIT_NOFILE, &rlim);
|
||||
if (rc != 0)
|
||||
std::cerr << fmt::format("Cannot set max number of file descriptors to {}. Try to specify max_open_files according to your system limits. error: {}", rlim.rlim_cur, errnoToString()) << '\n';
|
||||
@ -452,8 +457,8 @@ try
|
||||
}
|
||||
|
||||
is_interactive = stdin_is_a_tty
|
||||
&& (config().hasOption("interactive")
|
||||
|| (queries.empty() && !config().has("table-structure") && queries_files.empty() && !config().has("table-file")));
|
||||
&& (getClientConfiguration().hasOption("interactive")
|
||||
|| (queries.empty() && !getClientConfiguration().has("table-structure") && queries_files.empty() && !getClientConfiguration().has("table-file")));
|
||||
|
||||
if (!is_interactive)
|
||||
{
|
||||
@ -477,7 +482,7 @@ try
|
||||
|
||||
SCOPE_EXIT({ cleanup(); });
|
||||
|
||||
initTTYBuffer(toProgressOption(config().getString("progress", "default")));
|
||||
initTTYBuffer(toProgressOption(getClientConfiguration().getString("progress", "default")));
|
||||
ASTAlterCommand::setFormatAlterCommandsWithParentheses(true);
|
||||
|
||||
applyCmdSettings(global_context);
|
||||
@ -485,7 +490,7 @@ try
|
||||
/// try to load user defined executable functions, throw on error and die
|
||||
try
|
||||
{
|
||||
global_context->loadOrReloadUserDefinedExecutableFunctions(config());
|
||||
global_context->loadOrReloadUserDefinedExecutableFunctions(getClientConfiguration());
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
@ -526,7 +531,7 @@ try
|
||||
}
|
||||
catch (const DB::Exception & e)
|
||||
{
|
||||
bool need_print_stack_trace = config().getBool("stacktrace", false);
|
||||
bool need_print_stack_trace = getClientConfiguration().getBool("stacktrace", false);
|
||||
std::cerr << getExceptionMessage(e, need_print_stack_trace, true) << std::endl;
|
||||
return e.code() ? e.code() : -1;
|
||||
}
|
||||
@ -538,42 +543,42 @@ catch (...)
|
||||
|
||||
void LocalServer::updateLoggerLevel(const String & logs_level)
|
||||
{
|
||||
config().setString("logger.level", logs_level);
|
||||
updateLevels(config(), logger());
|
||||
getClientConfiguration().setString("logger.level", logs_level);
|
||||
updateLevels(getClientConfiguration(), logger());
|
||||
}
|
||||
|
||||
void LocalServer::processConfig()
|
||||
{
|
||||
if (!queries.empty() && config().has("queries-file"))
|
||||
if (!queries.empty() && getClientConfiguration().has("queries-file"))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--query' and '--queries-file' cannot be specified at the same time");
|
||||
|
||||
if (config().has("multiquery"))
|
||||
if (getClientConfiguration().has("multiquery"))
|
||||
is_multiquery = true;
|
||||
|
||||
pager = config().getString("pager", "");
|
||||
pager = getClientConfiguration().getString("pager", "");
|
||||
|
||||
delayed_interactive = config().has("interactive") && (!queries.empty() || config().has("queries-file"));
|
||||
delayed_interactive = getClientConfiguration().has("interactive") && (!queries.empty() || getClientConfiguration().has("queries-file"));
|
||||
if (!is_interactive || delayed_interactive)
|
||||
{
|
||||
echo_queries = config().hasOption("echo") || config().hasOption("verbose");
|
||||
ignore_error = config().getBool("ignore-error", false);
|
||||
echo_queries = getClientConfiguration().hasOption("echo") || getClientConfiguration().hasOption("verbose");
|
||||
ignore_error = getClientConfiguration().getBool("ignore-error", false);
|
||||
}
|
||||
|
||||
print_stack_trace = config().getBool("stacktrace", false);
|
||||
print_stack_trace = getClientConfiguration().getBool("stacktrace", false);
|
||||
const std::string clickhouse_dialect{"clickhouse"};
|
||||
load_suggestions = (is_interactive || delayed_interactive) && !config().getBool("disable_suggestion", false)
|
||||
&& config().getString("dialect", clickhouse_dialect) == clickhouse_dialect;
|
||||
wait_for_suggestions_to_load = config().getBool("wait_for_suggestions_to_load", false);
|
||||
load_suggestions = (is_interactive || delayed_interactive) && !getClientConfiguration().getBool("disable_suggestion", false)
|
||||
&& getClientConfiguration().getString("dialect", clickhouse_dialect) == clickhouse_dialect;
|
||||
wait_for_suggestions_to_load = getClientConfiguration().getBool("wait_for_suggestions_to_load", false);
|
||||
|
||||
auto logging = (config().has("logger.console")
|
||||
|| config().has("logger.level")
|
||||
|| config().has("log-level")
|
||||
|| config().has("send_logs_level")
|
||||
|| config().has("logger.log"));
|
||||
auto logging = (getClientConfiguration().has("logger.console")
|
||||
|| getClientConfiguration().has("logger.level")
|
||||
|| getClientConfiguration().has("log-level")
|
||||
|| getClientConfiguration().has("send_logs_level")
|
||||
|| getClientConfiguration().has("logger.log"));
|
||||
|
||||
auto level = config().getString("log-level", "trace");
|
||||
auto level = getClientConfiguration().getString("log-level", "trace");
|
||||
|
||||
if (config().has("server_logs_file"))
|
||||
if (getClientConfiguration().has("server_logs_file"))
|
||||
{
|
||||
auto poco_logs_level = Poco::Logger::parseLevel(level);
|
||||
Poco::Logger::root().setLevel(poco_logs_level);
|
||||
@ -583,10 +588,10 @@ void LocalServer::processConfig()
|
||||
}
|
||||
else
|
||||
{
|
||||
config().setString("logger", "logger");
|
||||
getClientConfiguration().setString("logger", "logger");
|
||||
auto log_level_default = logging ? level : "fatal";
|
||||
config().setString("logger.level", config().getString("log-level", config().getString("send_logs_level", log_level_default)));
|
||||
buildLoggers(config(), logger(), "clickhouse-local");
|
||||
getClientConfiguration().setString("logger.level", getClientConfiguration().getString("log-level", getClientConfiguration().getString("send_logs_level", log_level_default)));
|
||||
buildLoggers(getClientConfiguration(), logger(), "clickhouse-local");
|
||||
}
|
||||
|
||||
shared_context = Context::createShared();
|
||||
@ -600,13 +605,13 @@ void LocalServer::processConfig()
|
||||
LoggerRawPtr log = &logger();
|
||||
|
||||
/// Maybe useless
|
||||
if (config().has("macros"))
|
||||
global_context->setMacros(std::make_unique<Macros>(config(), "macros", log));
|
||||
if (getClientConfiguration().has("macros"))
|
||||
global_context->setMacros(std::make_unique<Macros>(getClientConfiguration(), "macros", log));
|
||||
|
||||
setDefaultFormatsAndCompressionFromConfiguration();
|
||||
|
||||
/// Sets external authenticators config (LDAP, Kerberos).
|
||||
global_context->setExternalAuthenticatorsConfig(config());
|
||||
global_context->setExternalAuthenticatorsConfig(getClientConfiguration());
|
||||
|
||||
setupUsers();
|
||||
|
||||
@ -615,12 +620,12 @@ void LocalServer::processConfig()
|
||||
global_context->getProcessList().setMaxSize(0);
|
||||
|
||||
const size_t physical_server_memory = getMemoryAmount();
|
||||
const double cache_size_to_ram_max_ratio = config().getDouble("cache_size_to_ram_max_ratio", 0.5);
|
||||
const double cache_size_to_ram_max_ratio = getClientConfiguration().getDouble("cache_size_to_ram_max_ratio", 0.5);
|
||||
const size_t max_cache_size = static_cast<size_t>(physical_server_memory * cache_size_to_ram_max_ratio);
|
||||
|
||||
String uncompressed_cache_policy = config().getString("uncompressed_cache_policy", DEFAULT_UNCOMPRESSED_CACHE_POLICY);
|
||||
size_t uncompressed_cache_size = config().getUInt64("uncompressed_cache_size", DEFAULT_UNCOMPRESSED_CACHE_MAX_SIZE);
|
||||
double uncompressed_cache_size_ratio = config().getDouble("uncompressed_cache_size_ratio", DEFAULT_UNCOMPRESSED_CACHE_SIZE_RATIO);
|
||||
String uncompressed_cache_policy = getClientConfiguration().getString("uncompressed_cache_policy", DEFAULT_UNCOMPRESSED_CACHE_POLICY);
|
||||
size_t uncompressed_cache_size = getClientConfiguration().getUInt64("uncompressed_cache_size", DEFAULT_UNCOMPRESSED_CACHE_MAX_SIZE);
|
||||
double uncompressed_cache_size_ratio = getClientConfiguration().getDouble("uncompressed_cache_size_ratio", DEFAULT_UNCOMPRESSED_CACHE_SIZE_RATIO);
|
||||
if (uncompressed_cache_size > max_cache_size)
|
||||
{
|
||||
uncompressed_cache_size = max_cache_size;
|
||||
@ -628,9 +633,9 @@ void LocalServer::processConfig()
|
||||
}
|
||||
global_context->setUncompressedCache(uncompressed_cache_policy, uncompressed_cache_size, uncompressed_cache_size_ratio);
|
||||
|
||||
String mark_cache_policy = config().getString("mark_cache_policy", DEFAULT_MARK_CACHE_POLICY);
|
||||
size_t mark_cache_size = config().getUInt64("mark_cache_size", DEFAULT_MARK_CACHE_MAX_SIZE);
|
||||
double mark_cache_size_ratio = config().getDouble("mark_cache_size_ratio", DEFAULT_MARK_CACHE_SIZE_RATIO);
|
||||
String mark_cache_policy = getClientConfiguration().getString("mark_cache_policy", DEFAULT_MARK_CACHE_POLICY);
|
||||
size_t mark_cache_size = getClientConfiguration().getUInt64("mark_cache_size", DEFAULT_MARK_CACHE_MAX_SIZE);
|
||||
double mark_cache_size_ratio = getClientConfiguration().getDouble("mark_cache_size_ratio", DEFAULT_MARK_CACHE_SIZE_RATIO);
|
||||
if (!mark_cache_size)
|
||||
LOG_ERROR(log, "Too low mark cache size will lead to severe performance degradation.");
|
||||
if (mark_cache_size > max_cache_size)
|
||||
@ -640,9 +645,9 @@ void LocalServer::processConfig()
|
||||
}
|
||||
global_context->setMarkCache(mark_cache_policy, mark_cache_size, mark_cache_size_ratio);
|
||||
|
||||
String index_uncompressed_cache_policy = config().getString("index_uncompressed_cache_policy", DEFAULT_INDEX_UNCOMPRESSED_CACHE_POLICY);
|
||||
size_t index_uncompressed_cache_size = config().getUInt64("index_uncompressed_cache_size", DEFAULT_INDEX_UNCOMPRESSED_CACHE_MAX_SIZE);
|
||||
double index_uncompressed_cache_size_ratio = config().getDouble("index_uncompressed_cache_size_ratio", DEFAULT_INDEX_UNCOMPRESSED_CACHE_SIZE_RATIO);
|
||||
String index_uncompressed_cache_policy = getClientConfiguration().getString("index_uncompressed_cache_policy", DEFAULT_INDEX_UNCOMPRESSED_CACHE_POLICY);
|
||||
size_t index_uncompressed_cache_size = getClientConfiguration().getUInt64("index_uncompressed_cache_size", DEFAULT_INDEX_UNCOMPRESSED_CACHE_MAX_SIZE);
|
||||
double index_uncompressed_cache_size_ratio = getClientConfiguration().getDouble("index_uncompressed_cache_size_ratio", DEFAULT_INDEX_UNCOMPRESSED_CACHE_SIZE_RATIO);
|
||||
if (index_uncompressed_cache_size > max_cache_size)
|
||||
{
|
||||
index_uncompressed_cache_size = max_cache_size;
|
||||
@ -650,9 +655,9 @@ void LocalServer::processConfig()
|
||||
}
|
||||
global_context->setIndexUncompressedCache(index_uncompressed_cache_policy, index_uncompressed_cache_size, index_uncompressed_cache_size_ratio);
|
||||
|
||||
String index_mark_cache_policy = config().getString("index_mark_cache_policy", DEFAULT_INDEX_MARK_CACHE_POLICY);
|
||||
size_t index_mark_cache_size = config().getUInt64("index_mark_cache_size", DEFAULT_INDEX_MARK_CACHE_MAX_SIZE);
|
||||
double index_mark_cache_size_ratio = config().getDouble("index_mark_cache_size_ratio", DEFAULT_INDEX_MARK_CACHE_SIZE_RATIO);
|
||||
String index_mark_cache_policy = getClientConfiguration().getString("index_mark_cache_policy", DEFAULT_INDEX_MARK_CACHE_POLICY);
|
||||
size_t index_mark_cache_size = getClientConfiguration().getUInt64("index_mark_cache_size", DEFAULT_INDEX_MARK_CACHE_MAX_SIZE);
|
||||
double index_mark_cache_size_ratio = getClientConfiguration().getDouble("index_mark_cache_size_ratio", DEFAULT_INDEX_MARK_CACHE_SIZE_RATIO);
|
||||
if (index_mark_cache_size > max_cache_size)
|
||||
{
|
||||
index_mark_cache_size = max_cache_size;
|
||||
@ -660,7 +665,7 @@ void LocalServer::processConfig()
|
||||
}
|
||||
global_context->setIndexMarkCache(index_mark_cache_policy, index_mark_cache_size, index_mark_cache_size_ratio);
|
||||
|
||||
size_t mmap_cache_size = config().getUInt64("mmap_cache_size", DEFAULT_MMAP_CACHE_MAX_SIZE);
|
||||
size_t mmap_cache_size = getClientConfiguration().getUInt64("mmap_cache_size", DEFAULT_MMAP_CACHE_MAX_SIZE);
|
||||
if (mmap_cache_size > max_cache_size)
|
||||
{
|
||||
mmap_cache_size = max_cache_size;
|
||||
@ -672,8 +677,8 @@ void LocalServer::processConfig()
|
||||
global_context->setQueryCache(0, 0, 0, 0);
|
||||
|
||||
#if USE_EMBEDDED_COMPILER
|
||||
size_t compiled_expression_cache_max_size_in_bytes = config().getUInt64("compiled_expression_cache_size", DEFAULT_COMPILED_EXPRESSION_CACHE_MAX_SIZE);
|
||||
size_t compiled_expression_cache_max_elements = config().getUInt64("compiled_expression_cache_elements_size", DEFAULT_COMPILED_EXPRESSION_CACHE_MAX_ENTRIES);
|
||||
size_t compiled_expression_cache_max_size_in_bytes = getClientConfiguration().getUInt64("compiled_expression_cache_size", DEFAULT_COMPILED_EXPRESSION_CACHE_MAX_SIZE);
|
||||
size_t compiled_expression_cache_max_elements = getClientConfiguration().getUInt64("compiled_expression_cache_elements_size", DEFAULT_COMPILED_EXPRESSION_CACHE_MAX_ENTRIES);
|
||||
CompiledExpressionCacheFactory::instance().init(compiled_expression_cache_max_size_in_bytes, compiled_expression_cache_max_elements);
|
||||
#endif
|
||||
|
||||
@ -685,16 +690,16 @@ void LocalServer::processConfig()
|
||||
applyCmdOptions(global_context);
|
||||
|
||||
/// Load global settings from default_profile and system_profile.
|
||||
global_context->setDefaultProfiles(config());
|
||||
global_context->setDefaultProfiles(getClientConfiguration());
|
||||
|
||||
/// We load temporary database first, because projections need it.
|
||||
DatabaseCatalog::instance().initializeAndLoadTemporaryDatabase();
|
||||
|
||||
std::string default_database = config().getString("default_database", "default");
|
||||
std::string default_database = getClientConfiguration().getString("default_database", "default");
|
||||
DatabaseCatalog::instance().attachDatabase(default_database, createClickHouseLocalDatabaseOverlay(default_database, global_context));
|
||||
global_context->setCurrentDatabase(default_database);
|
||||
|
||||
if (config().has("path"))
|
||||
if (getClientConfiguration().has("path"))
|
||||
{
|
||||
String path = global_context->getPath();
|
||||
fs::create_directories(fs::path(path));
|
||||
@ -709,7 +714,7 @@ void LocalServer::processConfig()
|
||||
attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA_UPPERCASE));
|
||||
waitLoad(TablesLoaderForegroundPoolId, startup_system_tasks);
|
||||
|
||||
if (!config().has("only-system-tables"))
|
||||
if (!getClientConfiguration().has("only-system-tables"))
|
||||
{
|
||||
DatabaseCatalog::instance().createBackgroundTasks();
|
||||
waitLoad(loadMetadata(global_context));
|
||||
@ -721,15 +726,15 @@ void LocalServer::processConfig()
|
||||
|
||||
LOG_DEBUG(log, "Loaded metadata.");
|
||||
}
|
||||
else if (!config().has("no-system-tables"))
|
||||
else if (!getClientConfiguration().has("no-system-tables"))
|
||||
{
|
||||
attachSystemTablesServer(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::SYSTEM_DATABASE), false);
|
||||
attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA));
|
||||
attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA_UPPERCASE));
|
||||
}
|
||||
|
||||
server_display_name = config().getString("display_name", "");
|
||||
prompt_by_server_display_name = config().getRawString("prompt_by_server_display_name.default", ":) ");
|
||||
server_display_name = getClientConfiguration().getString("display_name", "");
|
||||
prompt_by_server_display_name = getClientConfiguration().getRawString("prompt_by_server_display_name.default", ":) ");
|
||||
|
||||
global_context->setQueryKindInitial();
|
||||
global_context->setQueryKind(query_kind);
|
||||
@ -807,7 +812,7 @@ void LocalServer::applyCmdSettings(ContextMutablePtr context)
|
||||
|
||||
void LocalServer::applyCmdOptions(ContextMutablePtr context)
|
||||
{
|
||||
context->setDefaultFormat(config().getString("output-format", config().getString("format", is_interactive ? "PrettyCompact" : "TSV")));
|
||||
context->setDefaultFormat(getClientConfiguration().getString("output-format", getClientConfiguration().getString("format", is_interactive ? "PrettyCompact" : "TSV")));
|
||||
applyCmdSettings(context);
|
||||
}
|
||||
|
||||
@ -815,33 +820,33 @@ void LocalServer::applyCmdOptions(ContextMutablePtr context)
|
||||
void LocalServer::processOptions(const OptionsDescription &, const CommandLineOptions & options, const std::vector<Arguments> &, const std::vector<Arguments> &)
|
||||
{
|
||||
if (options.count("table"))
|
||||
config().setString("table-name", options["table"].as<std::string>());
|
||||
getClientConfiguration().setString("table-name", options["table"].as<std::string>());
|
||||
if (options.count("file"))
|
||||
config().setString("table-file", options["file"].as<std::string>());
|
||||
getClientConfiguration().setString("table-file", options["file"].as<std::string>());
|
||||
if (options.count("structure"))
|
||||
config().setString("table-structure", options["structure"].as<std::string>());
|
||||
getClientConfiguration().setString("table-structure", options["structure"].as<std::string>());
|
||||
if (options.count("no-system-tables"))
|
||||
config().setBool("no-system-tables", true);
|
||||
getClientConfiguration().setBool("no-system-tables", true);
|
||||
if (options.count("only-system-tables"))
|
||||
config().setBool("only-system-tables", true);
|
||||
getClientConfiguration().setBool("only-system-tables", true);
|
||||
if (options.count("database"))
|
||||
config().setString("default_database", options["database"].as<std::string>());
|
||||
getClientConfiguration().setString("default_database", options["database"].as<std::string>());
|
||||
|
||||
if (options.count("input-format"))
|
||||
config().setString("table-data-format", options["input-format"].as<std::string>());
|
||||
getClientConfiguration().setString("table-data-format", options["input-format"].as<std::string>());
|
||||
if (options.count("output-format"))
|
||||
config().setString("output-format", options["output-format"].as<std::string>());
|
||||
getClientConfiguration().setString("output-format", options["output-format"].as<std::string>());
|
||||
|
||||
if (options.count("logger.console"))
|
||||
config().setBool("logger.console", options["logger.console"].as<bool>());
|
||||
getClientConfiguration().setBool("logger.console", options["logger.console"].as<bool>());
|
||||
if (options.count("logger.log"))
|
||||
config().setString("logger.log", options["logger.log"].as<std::string>());
|
||||
getClientConfiguration().setString("logger.log", options["logger.log"].as<std::string>());
|
||||
if (options.count("logger.level"))
|
||||
config().setString("logger.level", options["logger.level"].as<std::string>());
|
||||
getClientConfiguration().setString("logger.level", options["logger.level"].as<std::string>());
|
||||
if (options.count("send_logs_level"))
|
||||
config().setString("send_logs_level", options["send_logs_level"].as<std::string>());
|
||||
getClientConfiguration().setString("send_logs_level", options["send_logs_level"].as<std::string>());
|
||||
if (options.count("wait_for_suggestions_to_load"))
|
||||
config().setBool("wait_for_suggestions_to_load", true);
|
||||
getClientConfiguration().setBool("wait_for_suggestions_to_load", true);
|
||||
}
|
||||
|
||||
void LocalServer::readArguments(int argc, char ** argv, Arguments & common_arguments, std::vector<Arguments> &, std::vector<Arguments> &)
|
||||
|
@ -30,6 +30,9 @@ public:
|
||||
int main(const std::vector<String> & /*args*/) override;
|
||||
|
||||
protected:
|
||||
|
||||
Poco::Util::LayeredConfiguration & getClientConfiguration() override;
|
||||
|
||||
void connect() override;
|
||||
|
||||
void processError(const String & query) const override;
|
||||
|
@ -13,7 +13,6 @@ set (CLICKHOUSE_ODBC_BRIDGE_SOURCES
|
||||
getIdentifierQuote.cpp
|
||||
odbc-bridge.cpp
|
||||
validateODBCConnectionString.cpp
|
||||
createFunctionBaseCast.cpp
|
||||
)
|
||||
|
||||
clickhouse_add_executable(clickhouse-odbc-bridge ${CLICKHOUSE_ODBC_BRIDGE_SOURCES})
|
||||
@ -25,6 +24,7 @@ target_link_libraries(clickhouse-odbc-bridge PRIVATE
|
||||
clickhouse_parsers
|
||||
ch_contrib::nanodbc
|
||||
ch_contrib::unixodbc
|
||||
clickhouse_functions
|
||||
)
|
||||
|
||||
set_target_properties(clickhouse-odbc-bridge PROPERTIES RUNTIME_OUTPUT_DIRECTORY ..)
|
||||
|
@ -1003,6 +1003,8 @@ try
|
||||
|
||||
ServerUUID::load(path / "uuid", log);
|
||||
|
||||
PlacementInfo::PlacementInfo::instance().initialize(config());
|
||||
|
||||
zkutil::validateZooKeeperConfig(config());
|
||||
bool has_zookeeper = zkutil::hasZooKeeperConfig(config());
|
||||
|
||||
@ -1540,6 +1542,8 @@ try
|
||||
global_context->setMaxDictionaryNumToWarn(new_server_settings.max_dictionary_num_to_warn);
|
||||
global_context->setMaxDatabaseNumToWarn(new_server_settings.max_database_num_to_warn);
|
||||
global_context->setMaxPartNumToWarn(new_server_settings.max_part_num_to_warn);
|
||||
/// Only for system.server_settings
|
||||
global_context->setConfigReloaderInterval(new_server_settings.config_reload_interval_ms);
|
||||
|
||||
SlotCount concurrent_threads_soft_limit = UnlimitedSlots;
|
||||
if (new_server_settings.concurrent_threads_soft_limit_num > 0 && new_server_settings.concurrent_threads_soft_limit_num < concurrent_threads_soft_limit)
|
||||
@ -1702,8 +1706,7 @@ try
|
||||
|
||||
/// Must be the last.
|
||||
latest_config = config;
|
||||
},
|
||||
/* already_loaded = */ false); /// Reload it right now (initial loading)
|
||||
});
|
||||
|
||||
const auto listen_hosts = getListenHosts(config());
|
||||
const auto interserver_listen_hosts = getInterserverListenHosts(config());
|
||||
@ -1816,11 +1819,6 @@ try
|
||||
|
||||
}
|
||||
|
||||
if (config().has(DB::PlacementInfo::PLACEMENT_CONFIG_PREFIX))
|
||||
{
|
||||
PlacementInfo::PlacementInfo::instance().initialize(config());
|
||||
}
|
||||
|
||||
{
|
||||
std::lock_guard lock(servers_lock);
|
||||
/// We should start interserver communications before (and more important shutdown after) tables.
|
||||
|
@ -29,7 +29,14 @@
|
||||
-->
|
||||
<size>1000M</size>
|
||||
<count>10</count>
|
||||
|
||||
<!-- <console>1</console> --> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
|
||||
<!-- <console_log_level>trace</console_log_level> -->
|
||||
|
||||
<!-- <use_syslog>0</use_syslog> -->
|
||||
<!-- <syslog_level>trace</syslog_level> -->
|
||||
|
||||
<!-- <stream_compress>0</stream_compress> -->
|
||||
|
||||
<!-- Per level overrides (legacy):
|
||||
|
||||
@ -408,13 +415,11 @@
|
||||
|
||||
<!-- Approximate size of mark cache, used in tables of MergeTree family.
|
||||
In bytes. Cache is single for server. Memory is allocated only on demand.
|
||||
You should not lower this value.
|
||||
-->
|
||||
<mark_cache_size>5368709120</mark_cache_size>
|
||||
You should not lower this value. -->
|
||||
<!-- <mark_cache_size>5368709120</mark_cache_size> -->
|
||||
|
||||
<!-- For marks of secondary indices.
|
||||
-->
|
||||
<index_mark_cache_size>5368709120</index_mark_cache_size>
|
||||
<!-- For marks of secondary indices. -->
|
||||
<!-- <index_mark_cache_size>5368709120</index_mark_cache_size> -->
|
||||
|
||||
<!-- If you enable the `min_bytes_to_use_mmap_io` setting,
|
||||
the data in MergeTree tables can be read with mmap to avoid copying from kernel to userspace.
|
||||
@ -432,13 +437,23 @@
|
||||
The cache is dropped (the files are closed) automatically on removal of old parts in MergeTree,
|
||||
also it can be dropped manually by the SYSTEM DROP MMAP CACHE query.
|
||||
-->
|
||||
<mmap_cache_size>1000</mmap_cache_size>
|
||||
<!-- <mmap_cache_size>1024</mmap_cache_size> -->
|
||||
|
||||
<!-- Cache size in bytes for compiled expressions.-->
|
||||
<compiled_expression_cache_size>134217728</compiled_expression_cache_size>
|
||||
<!-- <compiled_expression_cache_size>134217728</compiled_expression_cache_size> -->
|
||||
|
||||
<!-- Cache size in elements for compiled expressions.-->
|
||||
<compiled_expression_cache_elements_size>10000</compiled_expression_cache_elements_size>
|
||||
<!-- <compiled_expression_cache_elements_size>10000</compiled_expression_cache_elements_size> -->
|
||||
|
||||
<!-- Configuration for the query cache -->
|
||||
<!--
|
||||
<query_cache>
|
||||
<max_size_in_bytes>1073741824</max_size_in_bytes>
|
||||
<max_entries>1024</max_entries>
|
||||
<max_entry_size_in_bytes>1048576</max_entry_size_in_bytes>
|
||||
<max_entry_size_in_rows>30000000</max_entry_size_in_rows>
|
||||
</query_cache>
|
||||
-->
|
||||
|
||||
<!-- Cache path for custom (created from SQL) cached disks -->
|
||||
<custom_cached_disks_base_directory>/var/lib/clickhouse/caches/</custom_cached_disks_base_directory>
|
||||
@ -1642,14 +1657,6 @@
|
||||
-->
|
||||
<!-- </kafka> -->
|
||||
|
||||
<!-- Configuration for the query cache -->
|
||||
<query_cache>
|
||||
<max_size_in_bytes>1073741824</max_size_in_bytes>
|
||||
<max_entries>1024</max_entries>
|
||||
<max_entry_size_in_bytes>1048576</max_entry_size_in_bytes>
|
||||
<max_entry_size_in_rows>30000000</max_entry_size_in_rows>
|
||||
</query_cache>
|
||||
|
||||
<backups>
|
||||
<allowed_path>backups</allowed_path>
|
||||
|
||||
|
@ -260,7 +260,10 @@ uncompressed_cache_size: 8589934592
|
||||
# Approximate size of mark cache, used in tables of MergeTree family.
|
||||
# In bytes. Cache is single for server. Memory is allocated only on demand.
|
||||
# You should not lower this value.
|
||||
mark_cache_size: 5368709120
|
||||
# mark_cache_size: 5368709120
|
||||
|
||||
# For marks of secondary indices.
|
||||
# index_mark_cache_size: 5368709120
|
||||
|
||||
# If you enable the `min_bytes_to_use_mmap_io` setting,
|
||||
# the data in MergeTree tables can be read with mmap to avoid copying from kernel to userspace.
|
||||
@ -277,13 +280,20 @@ mark_cache_size: 5368709120
|
||||
# in query or server memory usage - because this memory can be discarded similar to OS page cache.
|
||||
# The cache is dropped (the files are closed) automatically on removal of old parts in MergeTree,
|
||||
# also it can be dropped manually by the SYSTEM DROP MMAP CACHE query.
|
||||
mmap_cache_size: 1000
|
||||
# mmap_cache_size: 1024
|
||||
|
||||
# Cache size in bytes for compiled expressions.
|
||||
compiled_expression_cache_size: 134217728
|
||||
# compiled_expression_cache_size: 134217728
|
||||
|
||||
# Cache size in elements for compiled expressions.
|
||||
compiled_expression_cache_elements_size: 10000
|
||||
# compiled_expression_cache_elements_size: 10000
|
||||
|
||||
# Configuration for the query cache
|
||||
# query_cache:
|
||||
# max_size_in_bytes: 1073741824
|
||||
# max_entries: 1024
|
||||
# max_entry_size_in_bytes: 1048576
|
||||
# max_entry_size_in_rows: 30000000
|
||||
|
||||
# Path to data directory, with trailing slash.
|
||||
path: /var/lib/clickhouse/
|
||||
|
@ -108,6 +108,9 @@ bool Authentication::areCredentialsValid(
|
||||
case AuthenticationType::HTTP:
|
||||
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
|
||||
|
||||
case AuthenticationType::JWT:
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
|
||||
case AuthenticationType::KERBEROS:
|
||||
return external_authenticators.checkKerberosCredentials(auth_data.getKerberosRealm(), *gss_acceptor_context);
|
||||
|
||||
@ -149,6 +152,9 @@ bool Authentication::areCredentialsValid(
|
||||
case AuthenticationType::SSL_CERTIFICATE:
|
||||
throw Authentication::Require<BasicCredentials>("ClickHouse X.509 Authentication");
|
||||
|
||||
case AuthenticationType::JWT:
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
|
||||
case AuthenticationType::SSH_KEY:
|
||||
#if USE_SSH
|
||||
throw Authentication::Require<SshCredentials>("SSH Keys Authentication");
|
||||
@ -193,6 +199,9 @@ bool Authentication::areCredentialsValid(
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
|
||||
#endif
|
||||
|
||||
case AuthenticationType::JWT:
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
|
||||
case AuthenticationType::BCRYPT_PASSWORD:
|
||||
return checkPasswordBcrypt(basic_credentials->getPassword(), auth_data.getPasswordHashBinary());
|
||||
|
||||
@ -222,6 +231,9 @@ bool Authentication::areCredentialsValid(
|
||||
case AuthenticationType::HTTP:
|
||||
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
|
||||
|
||||
case AuthenticationType::JWT:
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
|
||||
case AuthenticationType::KERBEROS:
|
||||
throw Authentication::Require<GSSAcceptorContext>(auth_data.getKerberosRealm());
|
||||
|
||||
@ -254,6 +266,9 @@ bool Authentication::areCredentialsValid(
|
||||
case AuthenticationType::HTTP:
|
||||
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
|
||||
|
||||
case AuthenticationType::JWT:
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
|
||||
case AuthenticationType::KERBEROS:
|
||||
throw Authentication::Require<GSSAcceptorContext>(auth_data.getKerberosRealm());
|
||||
|
||||
|
@ -135,6 +135,7 @@ void AuthenticationData::setPassword(const String & password_)
|
||||
case AuthenticationType::BCRYPT_PASSWORD:
|
||||
case AuthenticationType::NO_PASSWORD:
|
||||
case AuthenticationType::LDAP:
|
||||
case AuthenticationType::JWT:
|
||||
case AuthenticationType::KERBEROS:
|
||||
case AuthenticationType::SSL_CERTIFICATE:
|
||||
case AuthenticationType::SSH_KEY:
|
||||
@ -251,6 +252,7 @@ void AuthenticationData::setPasswordHashBinary(const Digest & hash)
|
||||
|
||||
case AuthenticationType::NO_PASSWORD:
|
||||
case AuthenticationType::LDAP:
|
||||
case AuthenticationType::JWT:
|
||||
case AuthenticationType::KERBEROS:
|
||||
case AuthenticationType::SSL_CERTIFICATE:
|
||||
case AuthenticationType::SSH_KEY:
|
||||
@ -322,6 +324,10 @@ std::shared_ptr<ASTAuthenticationData> AuthenticationData::toAST() const
|
||||
node->children.push_back(std::make_shared<ASTLiteral>(getLDAPServerName()));
|
||||
break;
|
||||
}
|
||||
case AuthenticationType::JWT:
|
||||
{
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
|
||||
}
|
||||
case AuthenticationType::KERBEROS:
|
||||
{
|
||||
const auto & realm = getKerberosRealm();
|
||||
|
@ -72,6 +72,11 @@ const AuthenticationTypeInfo & AuthenticationTypeInfo::get(AuthenticationType ty
|
||||
static const auto info = make_info(Keyword::HTTP);
|
||||
return info;
|
||||
}
|
||||
case AuthenticationType::JWT:
|
||||
{
|
||||
static const auto info = make_info(Keyword::JWT);
|
||||
return info;
|
||||
}
|
||||
case AuthenticationType::MAX:
|
||||
break;
|
||||
}
|
||||
|
@ -41,6 +41,9 @@ enum class AuthenticationType : uint8_t
|
||||
/// Authentication through HTTP protocol
|
||||
HTTP,
|
||||
|
||||
/// JSON Web Token
|
||||
JWT,
|
||||
|
||||
MAX,
|
||||
};
|
||||
|
||||
|
@ -33,6 +33,8 @@ void User::setName(const String & name_)
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "User name '{}' is reserved", name_);
|
||||
if (name_.starts_with(EncodedUserInfo::SSH_KEY_AUTHENTICAION_MARKER))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "User name '{}' is reserved", name_);
|
||||
if (name_.starts_with(EncodedUserInfo::JWT_AUTHENTICAION_MARKER))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "User name '{}' is reserved", name_);
|
||||
name = name_;
|
||||
}
|
||||
|
||||
|
@ -880,8 +880,7 @@ void UsersConfigAccessStorage::load(
|
||||
Settings::checkNoSettingNamesAtTopLevel(*new_config, users_config_path);
|
||||
parseFromConfig(*new_config);
|
||||
access_control.getChangesNotifier().sendNotifications();
|
||||
},
|
||||
/* already_loaded = */ false);
|
||||
});
|
||||
}
|
||||
|
||||
void UsersConfigAccessStorage::startPeriodicReloading()
|
||||
|
283
src/AggregateFunctions/AggregateFunctionGroupConcat.cpp
Normal file
283
src/AggregateFunctions/AggregateFunctionGroupConcat.cpp
Normal file
@ -0,0 +1,283 @@
|
||||
#include <AggregateFunctions/IAggregateFunction.h>
|
||||
#include <AggregateFunctions/AggregateFunctionFactory.h>
|
||||
#include <AggregateFunctions/FactoryHelpers.h>
|
||||
|
||||
#include <Columns/IColumn.h>
|
||||
#include <Columns/ColumnNullable.h>
|
||||
#include <Columns/ColumnString.h>
|
||||
|
||||
#include <Core/ServerSettings.h>
|
||||
#include <Core/ColumnWithTypeAndName.h>
|
||||
|
||||
#include <Common/ArenaAllocator.h>
|
||||
#include <Common/assert_cast.h>
|
||||
#include <Interpreters/castColumn.h>
|
||||
|
||||
#include <DataTypes/IDataType.h>
|
||||
#include <DataTypes/DataTypeArray.h>
|
||||
#include <DataTypes/DataTypeString.h>
|
||||
#include <DataTypes/DataTypesNumber.h>
|
||||
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <IO/WriteHelpers.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
struct Settings;
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int TOO_MANY_ARGUMENTS_FOR_FUNCTION;
|
||||
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
|
||||
extern const int BAD_ARGUMENTS;
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
struct GroupConcatDataBase
|
||||
{
|
||||
UInt64 data_size = 0;
|
||||
UInt64 allocated_size = 0;
|
||||
char * data = nullptr;
|
||||
|
||||
void checkAndUpdateSize(UInt64 add, Arena * arena)
|
||||
{
|
||||
if (data_size + add >= allocated_size)
|
||||
{
|
||||
auto old_size = allocated_size;
|
||||
allocated_size = std::max(2 * allocated_size, data_size + add);
|
||||
data = arena->realloc(data, old_size, allocated_size);
|
||||
}
|
||||
}
|
||||
|
||||
void insertChar(const char * str, UInt64 str_size, Arena * arena)
|
||||
{
|
||||
checkAndUpdateSize(str_size, arena);
|
||||
memcpy(data + data_size, str, str_size);
|
||||
data_size += str_size;
|
||||
}
|
||||
|
||||
void insert(const IColumn * column, const SerializationPtr & serialization, size_t row_num, Arena * arena)
|
||||
{
|
||||
WriteBufferFromOwnString buff;
|
||||
serialization->serializeText(*column, row_num, buff, FormatSettings{});
|
||||
auto string = buff.stringView();
|
||||
insertChar(string.data(), string.size(), arena);
|
||||
}
|
||||
|
||||
};
|
||||
|
||||
template <bool has_limit>
|
||||
struct GroupConcatData;
|
||||
|
||||
template<>
|
||||
struct GroupConcatData<false> final : public GroupConcatDataBase
|
||||
{
|
||||
};
|
||||
|
||||
template<>
|
||||
struct GroupConcatData<true> final : public GroupConcatDataBase
|
||||
{
|
||||
using Offset = UInt64;
|
||||
using Allocator = MixedAlignedArenaAllocator<alignof(Offset), 4096>;
|
||||
using Offsets = PODArray<Offset, 32, Allocator>;
|
||||
|
||||
/// offset[i * 2] - beginning of the i-th row, offset[i * 2 + 1] - end of the i-th row
|
||||
Offsets offsets;
|
||||
UInt64 num_rows = 0;
|
||||
|
||||
UInt64 getSize(size_t i) const { return offsets[i * 2 + 1] - offsets[i * 2]; }
|
||||
|
||||
UInt64 getString(size_t i) const { return offsets[i * 2]; }
|
||||
|
||||
void insert(const IColumn * column, const SerializationPtr & serialization, size_t row_num, Arena * arena)
|
||||
{
|
||||
WriteBufferFromOwnString buff;
|
||||
serialization->serializeText(*column, row_num, buff, {});
|
||||
auto string = buff.stringView();
|
||||
|
||||
checkAndUpdateSize(string.size(), arena);
|
||||
memcpy(data + data_size, string.data(), string.size());
|
||||
offsets.push_back(data_size, arena);
|
||||
data_size += string.size();
|
||||
offsets.push_back(data_size, arena);
|
||||
num_rows++;
|
||||
}
|
||||
};
|
||||
|
||||
template <bool has_limit>
|
||||
class GroupConcatImpl final
|
||||
: public IAggregateFunctionDataHelper<GroupConcatData<has_limit>, GroupConcatImpl<has_limit>>
|
||||
{
|
||||
static constexpr auto name = "groupConcat";
|
||||
|
||||
SerializationPtr serialization;
|
||||
UInt64 limit;
|
||||
const String delimiter;
|
||||
|
||||
public:
|
||||
GroupConcatImpl(const DataTypePtr & data_type_, const Array & parameters_, UInt64 limit_, const String & delimiter_)
|
||||
: IAggregateFunctionDataHelper<GroupConcatData<has_limit>, GroupConcatImpl<has_limit>>(
|
||||
{data_type_}, parameters_, std::make_shared<DataTypeString>())
|
||||
, serialization(this->argument_types[0]->getDefaultSerialization())
|
||||
, limit(limit_)
|
||||
, delimiter(delimiter_)
|
||||
{
|
||||
}
|
||||
|
||||
String getName() const override { return name; }
|
||||
|
||||
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
|
||||
{
|
||||
auto & cur_data = this->data(place);
|
||||
|
||||
if constexpr (has_limit)
|
||||
if (cur_data.num_rows >= limit)
|
||||
return;
|
||||
|
||||
if (cur_data.data_size != 0)
|
||||
cur_data.insertChar(delimiter.c_str(), delimiter.size(), arena);
|
||||
|
||||
cur_data.insert(columns[0], serialization, row_num, arena);
|
||||
}
|
||||
|
||||
void merge(AggregateDataPtr __restrict place, ConstAggregateDataPtr rhs, Arena * arena) const override
|
||||
{
|
||||
auto & cur_data = this->data(place);
|
||||
auto & rhs_data = this->data(rhs);
|
||||
|
||||
if (rhs_data.data_size == 0)
|
||||
return;
|
||||
|
||||
if constexpr (has_limit)
|
||||
{
|
||||
UInt64 new_elems_count = std::min(rhs_data.num_rows, limit - cur_data.num_rows);
|
||||
for (UInt64 i = 0; i < new_elems_count; ++i)
|
||||
{
|
||||
if (cur_data.data_size != 0)
|
||||
cur_data.insertChar(delimiter.c_str(), delimiter.size(), arena);
|
||||
|
||||
cur_data.offsets.push_back(cur_data.data_size, arena);
|
||||
cur_data.insertChar(rhs_data.data + rhs_data.getString(i), rhs_data.getSize(i), arena);
|
||||
cur_data.num_rows++;
|
||||
cur_data.offsets.push_back(cur_data.data_size, arena);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (cur_data.data_size != 0)
|
||||
cur_data.insertChar(delimiter.c_str(), delimiter.size(), arena);
|
||||
|
||||
cur_data.insertChar(rhs_data.data, rhs_data.data_size, arena);
|
||||
}
|
||||
}
|
||||
|
||||
void serialize(ConstAggregateDataPtr __restrict place, WriteBuffer & buf, std::optional<size_t> /* version */) const override
|
||||
{
|
||||
auto & cur_data = this->data(place);
|
||||
|
||||
writeVarUInt(cur_data.data_size, buf);
|
||||
|
||||
buf.write(cur_data.data, cur_data.data_size);
|
||||
|
||||
if constexpr (has_limit)
|
||||
{
|
||||
writeVarUInt(cur_data.num_rows, buf);
|
||||
for (const auto & offset : cur_data.offsets)
|
||||
writeVarUInt(offset, buf);
|
||||
}
|
||||
}
|
||||
|
||||
void deserialize(AggregateDataPtr __restrict place, ReadBuffer & buf, std::optional<size_t> /* version */, Arena * arena) const override
|
||||
{
|
||||
auto & cur_data = this->data(place);
|
||||
|
||||
UInt64 temp_size = 0;
|
||||
readVarUInt(temp_size, buf);
|
||||
|
||||
cur_data.checkAndUpdateSize(temp_size, arena);
|
||||
|
||||
buf.readStrict(cur_data.data + cur_data.data_size, temp_size);
|
||||
cur_data.data_size = temp_size;
|
||||
|
||||
if constexpr (has_limit)
|
||||
{
|
||||
readVarUInt(cur_data.num_rows, buf);
|
||||
cur_data.offsets.resize_exact(cur_data.num_rows * 2, arena);
|
||||
for (auto & offset : cur_data.offsets)
|
||||
readVarUInt(offset, buf);
|
||||
}
|
||||
}
|
||||
|
||||
void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
|
||||
{
|
||||
auto & cur_data = this->data(place);
|
||||
|
||||
if (cur_data.data_size == 0)
|
||||
{
|
||||
to.insertDefault();
|
||||
return;
|
||||
}
|
||||
|
||||
auto & column_string = assert_cast<ColumnString &>(to);
|
||||
column_string.insertData(cur_data.data, cur_data.data_size);
|
||||
}
|
||||
|
||||
bool allocatesMemoryInArena() const override { return true; }
|
||||
};
|
||||
|
||||
AggregateFunctionPtr createAggregateFunctionGroupConcat(
|
||||
const std::string & name, const DataTypes & argument_types, const Array & parameters, const Settings *)
|
||||
{
|
||||
assertUnary(name, argument_types);
|
||||
|
||||
bool has_limit = false;
|
||||
UInt64 limit = 0;
|
||||
String delimiter;
|
||||
|
||||
if (parameters.size() > 2)
|
||||
throw Exception(ErrorCodes::TOO_MANY_ARGUMENTS_FOR_FUNCTION,
|
||||
"Incorrect number of parameters for aggregate function {}, should be 0, 1 or 2, got: {}", name, parameters.size());
|
||||
|
||||
if (!parameters.empty())
|
||||
{
|
||||
auto type = parameters[0].getType();
|
||||
if (type != Field::Types::String)
|
||||
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "First parameter for aggregate function {} should be string", name);
|
||||
|
||||
delimiter = parameters[0].get<String>();
|
||||
}
|
||||
if (parameters.size() == 2)
|
||||
{
|
||||
auto type = parameters[1].getType();
|
||||
|
||||
if (type != Field::Types::Int64 && type != Field::Types::UInt64)
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Second parameter for aggregate function {} should be a positive number", name);
|
||||
|
||||
if ((type == Field::Types::Int64 && parameters[1].get<Int64>() <= 0) ||
|
||||
(type == Field::Types::UInt64 && parameters[1].get<UInt64>() == 0))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Second parameter for aggregate function {} should be a positive number, got: {}", name, parameters[1].get<Int64>());
|
||||
|
||||
has_limit = true;
|
||||
limit = parameters[1].get<UInt64>();
|
||||
}
|
||||
|
||||
if (has_limit)
|
||||
return std::make_shared<GroupConcatImpl</* has_limit= */ true>>(argument_types[0], parameters, limit, delimiter);
|
||||
else
|
||||
return std::make_shared<GroupConcatImpl</* has_limit= */ false>>(argument_types[0], parameters, limit, delimiter);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
void registerAggregateFunctionGroupConcat(AggregateFunctionFactory & factory)
|
||||
{
|
||||
AggregateFunctionProperties properties = { .returns_default_when_only_null = false, .is_order_dependent = true };
|
||||
|
||||
factory.registerFunction("groupConcat", { createAggregateFunctionGroupConcat, properties });
|
||||
factory.registerAlias("group_concat", "groupConcat", AggregateFunctionFactory::CaseInsensitive);
|
||||
}
|
||||
|
||||
}
|
@ -91,7 +91,8 @@ public:
|
||||
return std::make_shared<DataTypeNumber<PointType>>();
|
||||
}
|
||||
|
||||
bool allocatesMemoryInArena() const override { return false; }
|
||||
/// MaxIntersectionsData::Allocator uses the arena
|
||||
bool allocatesMemoryInArena() const override { return true; }
|
||||
|
||||
void add(AggregateDataPtr __restrict place, const IColumn ** columns, size_t row_num, Arena * arena) const override
|
||||
{
|
||||
|
@ -19,6 +19,7 @@ void registerAggregateFunctionGroupArraySorted(AggregateFunctionFactory & factor
|
||||
void registerAggregateFunctionGroupUniqArray(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionGroupArrayInsertAt(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionGroupArrayIntersect(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionGroupConcat(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionsQuantile(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionsQuantileDeterministic(AggregateFunctionFactory &);
|
||||
void registerAggregateFunctionsQuantileExact(AggregateFunctionFactory &);
|
||||
@ -120,6 +121,7 @@ void registerAggregateFunctions()
|
||||
registerAggregateFunctionGroupUniqArray(factory);
|
||||
registerAggregateFunctionGroupArrayInsertAt(factory);
|
||||
registerAggregateFunctionGroupArrayIntersect(factory);
|
||||
registerAggregateFunctionGroupConcat(factory);
|
||||
registerAggregateFunctionsQuantile(factory);
|
||||
registerAggregateFunctionsQuantileDeterministic(factory);
|
||||
registerAggregateFunctionsQuantileExact(factory);
|
||||
|
@ -43,50 +43,56 @@ public:
|
||||
bool replaced_argument = false;
|
||||
auto replaced_uniq_function_arguments_nodes = function_node->getArguments().getNodes();
|
||||
|
||||
for (auto & uniq_function_argument_node : replaced_uniq_function_arguments_nodes)
|
||||
/// Replace injective function with its single argument
|
||||
auto remove_injective_function = [&replaced_argument](QueryTreeNodePtr & arg) -> bool
|
||||
{
|
||||
auto * uniq_function_argument_node_typed = uniq_function_argument_node->as<FunctionNode>();
|
||||
if (!uniq_function_argument_node_typed || !uniq_function_argument_node_typed->isOrdinaryFunction())
|
||||
continue;
|
||||
|
||||
auto & uniq_function_argument_node_argument_nodes = uniq_function_argument_node_typed->getArguments().getNodes();
|
||||
auto * arg_typed = arg->as<FunctionNode>();
|
||||
if (!arg_typed || !arg_typed->isOrdinaryFunction())
|
||||
return false;
|
||||
|
||||
/// Do not apply optimization if injective function contains multiple arguments
|
||||
if (uniq_function_argument_node_argument_nodes.size() != 1)
|
||||
continue;
|
||||
auto & arg_arguments_nodes = arg_typed->getArguments().getNodes();
|
||||
if (arg_arguments_nodes.size() != 1)
|
||||
return false;
|
||||
|
||||
const auto & uniq_function_argument_node_function = uniq_function_argument_node_typed->getFunction();
|
||||
if (!uniq_function_argument_node_function->isInjective({}))
|
||||
continue;
|
||||
const auto & arg_function = arg_typed->getFunction();
|
||||
if (!arg_function->isInjective({}))
|
||||
return false;
|
||||
|
||||
/// Replace injective function with its single argument
|
||||
uniq_function_argument_node = uniq_function_argument_node_argument_nodes[0];
|
||||
replaced_argument = true;
|
||||
arg = arg_arguments_nodes[0];
|
||||
return replaced_argument = true;
|
||||
};
|
||||
|
||||
for (auto & uniq_function_argument_node : replaced_uniq_function_arguments_nodes)
|
||||
{
|
||||
while (remove_injective_function(uniq_function_argument_node))
|
||||
;
|
||||
}
|
||||
|
||||
if (!replaced_argument)
|
||||
return;
|
||||
|
||||
DataTypes argument_types;
|
||||
argument_types.reserve(replaced_uniq_function_arguments_nodes.size());
|
||||
DataTypes replaced_argument_types;
|
||||
replaced_argument_types.reserve(replaced_uniq_function_arguments_nodes.size());
|
||||
|
||||
for (const auto & function_node_argument : replaced_uniq_function_arguments_nodes)
|
||||
argument_types.emplace_back(function_node_argument->getResultType());
|
||||
replaced_argument_types.emplace_back(function_node_argument->getResultType());
|
||||
|
||||
auto current_aggregate_function = function_node->getAggregateFunction();
|
||||
AggregateFunctionProperties properties;
|
||||
auto aggregate_function = AggregateFunctionFactory::instance().get(
|
||||
auto replaced_aggregate_function = AggregateFunctionFactory::instance().get(
|
||||
function_node->getFunctionName(),
|
||||
NullsAction::EMPTY,
|
||||
argument_types,
|
||||
function_node->getAggregateFunction()->getParameters(),
|
||||
replaced_argument_types,
|
||||
current_aggregate_function->getParameters(),
|
||||
properties);
|
||||
|
||||
/// uniqCombined returns nullable with nullable arguments so the result type might change which breaks the pass
|
||||
if (!aggregate_function->getResultType()->equals(*function_node->getAggregateFunction()->getResultType()))
|
||||
if (!replaced_aggregate_function->getResultType()->equals(*current_aggregate_function->getResultType()))
|
||||
return;
|
||||
|
||||
function_node->getArguments().getNodes() = replaced_uniq_function_arguments_nodes;
|
||||
function_node->resolveAsAggregateFunction(std::move(aggregate_function));
|
||||
function_node->getArguments().getNodes() = std::move(replaced_uniq_function_arguments_nodes);
|
||||
function_node->resolveAsAggregateFunction(std::move(replaced_aggregate_function));
|
||||
}
|
||||
};
|
||||
|
||||
|
@ -1,3 +1,5 @@
|
||||
#include <Common/FieldVisitorToString.h>
|
||||
|
||||
#include <DataTypes/DataTypesNumber.h>
|
||||
#include <DataTypes/DataTypeString.h>
|
||||
#include <DataTypes/DataTypeNullable.h>
|
||||
@ -3495,7 +3497,8 @@ ProjectionNames QueryAnalyzer::resolveFunction(QueryTreeNodePtr & node, Identifi
|
||||
*
|
||||
* 4. If node has alias, update its value in scope alias map. Deregister alias from expression_aliases_in_resolve_process.
|
||||
*/
|
||||
ProjectionNames QueryAnalyzer::resolveExpressionNode(QueryTreeNodePtr & node, IdentifierResolveScope & scope, bool allow_lambda_expression, bool allow_table_expression, bool ignore_alias)
|
||||
ProjectionNames QueryAnalyzer::resolveExpressionNode(
|
||||
QueryTreeNodePtr & node, IdentifierResolveScope & scope, bool allow_lambda_expression, bool allow_table_expression, bool ignore_alias)
|
||||
{
|
||||
checkStackSize();
|
||||
|
||||
@ -4505,7 +4508,36 @@ void QueryAnalyzer::resolveTableFunction(QueryTreeNodePtr & table_function_node,
|
||||
table_name = table_identifier[1];
|
||||
}
|
||||
|
||||
auto parametrized_view_storage = scope_context->getQueryContext()->buildParametrizedViewStorage(function_ast, database_name, table_name);
|
||||
/// Collect parametrized view arguments
|
||||
NameToNameMap view_params;
|
||||
for (const auto & argument : table_function_node_typed.getArguments())
|
||||
{
|
||||
if (auto * arg_func = argument->as<FunctionNode>())
|
||||
{
|
||||
if (arg_func->getFunctionName() != "equals")
|
||||
continue;
|
||||
|
||||
auto nodes = arg_func->getArguments().getNodes();
|
||||
if (nodes.size() != 2)
|
||||
continue;
|
||||
|
||||
if (auto * identifier_node = nodes[0]->as<IdentifierNode>())
|
||||
{
|
||||
resolveExpressionNode(nodes[1], scope, /* allow_lambda_expression */false, /* allow_table_function */false);
|
||||
if (auto * constant = nodes[1]->as<ConstantNode>())
|
||||
{
|
||||
view_params[identifier_node->getIdentifier().getFullName()] = convertFieldToString(constant->getValue());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
auto context = scope_context->getQueryContext();
|
||||
auto parametrized_view_storage = context->buildParametrizedViewStorage(
|
||||
database_name,
|
||||
table_name,
|
||||
view_params);
|
||||
|
||||
if (parametrized_view_storage)
|
||||
{
|
||||
auto fake_table_node = std::make_shared<TableNode>(parametrized_view_storage, scope_context);
|
||||
|
@ -438,7 +438,7 @@ void RestorerFromBackup::findTableInBackupImpl(const QualifiedTableName & table_
|
||||
String create_table_query_str = serializeAST(*create_table_query);
|
||||
|
||||
bool is_predefined_table = DatabaseCatalog::instance().isPredefinedTable(StorageID{table_name.database, table_name.table});
|
||||
auto table_dependencies = getDependenciesFromCreateQuery(context, table_name, create_table_query);
|
||||
auto table_dependencies = getDependenciesFromCreateQuery(context, table_name, create_table_query, context->getCurrentDatabase());
|
||||
bool table_has_data = backup->hasFiles(data_path_in_backup);
|
||||
|
||||
std::lock_guard lock{mutex};
|
||||
|
@ -222,7 +222,7 @@ add_object_library(clickhouse_storages_mergetree Storages/MergeTree)
|
||||
add_object_library(clickhouse_storages_statistics Storages/Statistics)
|
||||
add_object_library(clickhouse_storages_liveview Storages/LiveView)
|
||||
add_object_library(clickhouse_storages_windowview Storages/WindowView)
|
||||
add_object_library(clickhouse_storages_s3queue Storages/S3Queue)
|
||||
add_object_library(clickhouse_storages_s3queue Storages/ObjectStorageQueue)
|
||||
add_object_library(clickhouse_storages_materializedview Storages/MaterializedView)
|
||||
add_object_library(clickhouse_client Client)
|
||||
add_object_library(clickhouse_bridge BridgeHelper)
|
||||
|
@ -110,6 +110,7 @@ namespace ErrorCodes
|
||||
extern const int USER_SESSION_LIMIT_EXCEEDED;
|
||||
extern const int NOT_IMPLEMENTED;
|
||||
extern const int CANNOT_READ_FROM_FILE_DESCRIPTOR;
|
||||
extern const int USER_EXPIRED;
|
||||
}
|
||||
|
||||
}
|
||||
@ -302,8 +303,29 @@ public:
|
||||
|
||||
|
||||
ClientBase::~ClientBase() = default;
|
||||
ClientBase::ClientBase() = default;
|
||||
|
||||
ClientBase::ClientBase(
|
||||
int in_fd_,
|
||||
int out_fd_,
|
||||
int err_fd_,
|
||||
std::istream & input_stream_,
|
||||
std::ostream & output_stream_,
|
||||
std::ostream & error_stream_
|
||||
)
|
||||
: std_in(in_fd_)
|
||||
, std_out(out_fd_)
|
||||
, progress_indication(output_stream_, in_fd_, err_fd_)
|
||||
, in_fd(in_fd_)
|
||||
, out_fd(out_fd_)
|
||||
, err_fd(err_fd_)
|
||||
, input_stream(input_stream_)
|
||||
, output_stream(output_stream_)
|
||||
, error_stream(error_stream_)
|
||||
{
|
||||
stdin_is_a_tty = isatty(in_fd);
|
||||
stdout_is_a_tty = isatty(out_fd);
|
||||
stderr_is_a_tty = isatty(err_fd);
|
||||
terminal_width = getTerminalWidth(in_fd, err_fd);
|
||||
}
|
||||
|
||||
void ClientBase::setupSignalHandler()
|
||||
{
|
||||
@ -330,7 +352,7 @@ void ClientBase::setupSignalHandler()
|
||||
}
|
||||
|
||||
|
||||
ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements, bool is_interactive, bool ignore_error)
|
||||
ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements)
|
||||
{
|
||||
std::unique_ptr<IParserBase> parser;
|
||||
ASTPtr res;
|
||||
@ -359,7 +381,7 @@ ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, const Setting
|
||||
|
||||
if (!res)
|
||||
{
|
||||
std::cerr << std::endl << message << std::endl << std::endl;
|
||||
error_stream << std::endl << message << std::endl << std::endl;
|
||||
return nullptr;
|
||||
}
|
||||
}
|
||||
@ -373,11 +395,11 @@ ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, const Setting
|
||||
|
||||
if (is_interactive)
|
||||
{
|
||||
std::cout << std::endl;
|
||||
WriteBufferFromOStream res_buf(std::cout, 4096);
|
||||
output_stream << std::endl;
|
||||
WriteBufferFromOStream res_buf(output_stream, 4096);
|
||||
formatAST(*res, res_buf);
|
||||
res_buf.finalize();
|
||||
std::cout << std::endl << std::endl;
|
||||
output_stream << std::endl << std::endl;
|
||||
}
|
||||
|
||||
return res;
|
||||
@ -481,7 +503,7 @@ void ClientBase::onData(Block & block, ASTPtr parsed_query)
|
||||
if (need_render_progress && tty_buf)
|
||||
{
|
||||
if (select_into_file && !select_into_file_and_stdout)
|
||||
std::cerr << "\r";
|
||||
error_stream << "\r";
|
||||
progress_indication.writeProgress(*tty_buf);
|
||||
}
|
||||
}
|
||||
@ -741,17 +763,17 @@ bool ClientBase::isRegularFile(int fd)
|
||||
|
||||
void ClientBase::setDefaultFormatsAndCompressionFromConfiguration()
|
||||
{
|
||||
if (config().has("output-format"))
|
||||
if (getClientConfiguration().has("output-format"))
|
||||
{
|
||||
default_output_format = config().getString("output-format");
|
||||
default_output_format = getClientConfiguration().getString("output-format");
|
||||
is_default_format = false;
|
||||
}
|
||||
else if (config().has("format"))
|
||||
else if (getClientConfiguration().has("format"))
|
||||
{
|
||||
default_output_format = config().getString("format");
|
||||
default_output_format = getClientConfiguration().getString("format");
|
||||
is_default_format = false;
|
||||
}
|
||||
else if (config().has("vertical"))
|
||||
else if (getClientConfiguration().has("vertical"))
|
||||
{
|
||||
default_output_format = "Vertical";
|
||||
is_default_format = false;
|
||||
@ -777,17 +799,17 @@ void ClientBase::setDefaultFormatsAndCompressionFromConfiguration()
|
||||
default_output_format = "TSV";
|
||||
}
|
||||
|
||||
if (config().has("input-format"))
|
||||
if (getClientConfiguration().has("input-format"))
|
||||
{
|
||||
default_input_format = config().getString("input-format");
|
||||
default_input_format = getClientConfiguration().getString("input-format");
|
||||
}
|
||||
else if (config().has("format"))
|
||||
else if (getClientConfiguration().has("format"))
|
||||
{
|
||||
default_input_format = config().getString("format");
|
||||
default_input_format = getClientConfiguration().getString("format");
|
||||
}
|
||||
else if (config().getString("table-file", "-") != "-")
|
||||
else if (getClientConfiguration().getString("table-file", "-") != "-")
|
||||
{
|
||||
auto file_name = config().getString("table-file");
|
||||
auto file_name = getClientConfiguration().getString("table-file");
|
||||
std::optional<String> format_from_file_name = FormatFactory::instance().tryGetFormatFromFileName(file_name);
|
||||
if (format_from_file_name)
|
||||
default_input_format = *format_from_file_name;
|
||||
@ -803,7 +825,7 @@ void ClientBase::setDefaultFormatsAndCompressionFromConfiguration()
|
||||
default_input_format = "TSV";
|
||||
}
|
||||
|
||||
format_max_block_size = config().getUInt64("format_max_block_size",
|
||||
format_max_block_size = getClientConfiguration().getUInt64("format_max_block_size",
|
||||
global_context->getSettingsRef().max_block_size);
|
||||
|
||||
/// Setting value from cmd arg overrides one from config
|
||||
@ -813,7 +835,7 @@ void ClientBase::setDefaultFormatsAndCompressionFromConfiguration()
|
||||
}
|
||||
else
|
||||
{
|
||||
insert_format_max_block_size = config().getUInt64("insert_format_max_block_size",
|
||||
insert_format_max_block_size = getClientConfiguration().getUInt64("insert_format_max_block_size",
|
||||
global_context->getSettingsRef().max_insert_block_size);
|
||||
}
|
||||
}
|
||||
@ -924,9 +946,7 @@ void ClientBase::processTextAsSingleQuery(const String & full_query)
|
||||
const char * begin = full_query.data();
|
||||
auto parsed_query = parseQuery(begin, begin + full_query.size(),
|
||||
global_context->getSettingsRef(),
|
||||
/*allow_multi_statements=*/ false,
|
||||
is_interactive,
|
||||
ignore_error);
|
||||
/*allow_multi_statements=*/ false);
|
||||
|
||||
if (!parsed_query)
|
||||
return;
|
||||
@ -1100,7 +1120,7 @@ void ClientBase::processOrdinaryQuery(const String & query_to_execute, ASTPtr pa
|
||||
/// has been received yet.
|
||||
if (processed_rows == 0 && e.code() == ErrorCodes::DEADLOCK_AVOIDED && --retries_left)
|
||||
{
|
||||
std::cerr << "Got a transient error from the server, will"
|
||||
error_stream << "Got a transient error from the server, will"
|
||||
<< " retry (" << retries_left << " retries left)";
|
||||
}
|
||||
else
|
||||
@ -1154,7 +1174,7 @@ void ClientBase::receiveResult(ASTPtr parsed_query, Int32 signals_before_stop, b
|
||||
double elapsed = receive_watch.elapsedSeconds();
|
||||
if (break_on_timeout && elapsed > receive_timeout.totalSeconds())
|
||||
{
|
||||
std::cout << "Timeout exceeded while receiving data from server."
|
||||
output_stream << "Timeout exceeded while receiving data from server."
|
||||
<< " Waited for " << static_cast<size_t>(elapsed) << " seconds,"
|
||||
<< " timeout is " << receive_timeout.totalSeconds() << " seconds." << std::endl;
|
||||
|
||||
@ -1189,7 +1209,7 @@ void ClientBase::receiveResult(ASTPtr parsed_query, Int32 signals_before_stop, b
|
||||
|
||||
if (cancelled && is_interactive)
|
||||
{
|
||||
std::cout << "Query was cancelled." << std::endl;
|
||||
output_stream << "Query was cancelled." << std::endl;
|
||||
cancelled_printed = true;
|
||||
}
|
||||
}
|
||||
@ -1308,9 +1328,9 @@ void ClientBase::onEndOfStream()
|
||||
if (is_interactive)
|
||||
{
|
||||
if (cancelled && !cancelled_printed)
|
||||
std::cout << "Query was cancelled." << std::endl;
|
||||
output_stream << "Query was cancelled." << std::endl;
|
||||
else if (!written_first_block)
|
||||
std::cout << "Ok." << std::endl;
|
||||
output_stream << "Ok." << std::endl;
|
||||
}
|
||||
}
|
||||
|
||||
@ -1863,7 +1883,7 @@ void ClientBase::cancelQuery()
|
||||
progress_indication.clearProgressOutput(*tty_buf);
|
||||
|
||||
if (is_interactive)
|
||||
std::cout << "Cancelling query." << std::endl;
|
||||
output_stream << "Cancelling query." << std::endl;
|
||||
|
||||
cancelled = true;
|
||||
}
|
||||
@ -1993,7 +2013,7 @@ void ClientBase::processParsedSingleQuery(const String & full_query, const Strin
|
||||
{
|
||||
const String & new_database = use_query->getDatabase();
|
||||
/// If the client initiates the reconnection, it takes the settings from the config.
|
||||
config().setString("database", new_database);
|
||||
getClientConfiguration().setString("database", new_database);
|
||||
/// If the connection initiates the reconnection, it uses its variable.
|
||||
connection->setDefaultDatabase(new_database);
|
||||
}
|
||||
@ -2013,21 +2033,21 @@ void ClientBase::processParsedSingleQuery(const String & full_query, const Strin
|
||||
|
||||
if (is_interactive)
|
||||
{
|
||||
std::cout << std::endl;
|
||||
output_stream << std::endl;
|
||||
if (!server_exception || processed_rows != 0)
|
||||
std::cout << processed_rows << " row" << (processed_rows == 1 ? "" : "s") << " in set. ";
|
||||
std::cout << "Elapsed: " << progress_indication.elapsedSeconds() << " sec. ";
|
||||
output_stream << processed_rows << " row" << (processed_rows == 1 ? "" : "s") << " in set. ";
|
||||
output_stream << "Elapsed: " << progress_indication.elapsedSeconds() << " sec. ";
|
||||
progress_indication.writeFinalProgress();
|
||||
std::cout << std::endl << std::endl;
|
||||
output_stream << std::endl << std::endl;
|
||||
}
|
||||
else if (print_time_to_stderr)
|
||||
else if (getClientConfiguration().getBool("print-time-to-stderr", false))
|
||||
{
|
||||
std::cerr << progress_indication.elapsedSeconds() << "\n";
|
||||
error_stream << progress_indication.elapsedSeconds() << "\n";
|
||||
}
|
||||
|
||||
if (!is_interactive && print_num_processed_rows)
|
||||
if (!is_interactive && getClientConfiguration().getBool("print-num-processed-rows", false))
|
||||
{
|
||||
std::cout << "Processed rows: " << processed_rows << "\n";
|
||||
output_stream << "Processed rows: " << processed_rows << "\n";
|
||||
}
|
||||
|
||||
if (have_error && report_error)
|
||||
@ -2077,9 +2097,7 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
|
||||
{
|
||||
parsed_query = parseQuery(this_query_end, all_queries_end,
|
||||
global_context->getSettingsRef(),
|
||||
/*allow_multi_statements=*/ true,
|
||||
is_interactive,
|
||||
ignore_error);
|
||||
/*allow_multi_statements=*/ true);
|
||||
}
|
||||
catch (const Exception & e)
|
||||
{
|
||||
@ -2238,7 +2256,7 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
|
||||
catch (...)
|
||||
{
|
||||
// Surprisingly, this is a client error. A server error would
|
||||
// have been reported without throwing (see onReceiveSeverException()).
|
||||
// have been reported without throwing (see onReceiveExceptionFromServer()).
|
||||
client_exception = std::make_unique<Exception>(getCurrentExceptionMessageAndPattern(print_stack_trace), getCurrentExceptionCode());
|
||||
have_error = true;
|
||||
}
|
||||
@ -2395,12 +2413,12 @@ void ClientBase::initQueryIdFormats()
|
||||
return;
|
||||
|
||||
/// Initialize query_id_formats if any
|
||||
if (config().has("query_id_formats"))
|
||||
if (getClientConfiguration().has("query_id_formats"))
|
||||
{
|
||||
Poco::Util::AbstractConfiguration::Keys keys;
|
||||
config().keys("query_id_formats", keys);
|
||||
getClientConfiguration().keys("query_id_formats", keys);
|
||||
for (const auto & name : keys)
|
||||
query_id_formats.emplace_back(name + ":", config().getString("query_id_formats." + name));
|
||||
query_id_formats.emplace_back(name + ":", getClientConfiguration().getString("query_id_formats." + name));
|
||||
}
|
||||
|
||||
if (query_id_formats.empty())
|
||||
@ -2445,9 +2463,9 @@ bool ClientBase::addMergeTreeSettings(ASTCreateQuery & ast_create)
|
||||
|
||||
void ClientBase::runInteractive()
|
||||
{
|
||||
if (config().has("query_id"))
|
||||
if (getClientConfiguration().has("query_id"))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "query_id could be specified only in non-interactive mode");
|
||||
if (print_time_to_stderr)
|
||||
if (getClientConfiguration().getBool("print-time-to-stderr", false))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "time option could be specified only in non-interactive mode");
|
||||
|
||||
initQueryIdFormats();
|
||||
@ -2460,9 +2478,9 @@ void ClientBase::runInteractive()
|
||||
{
|
||||
/// Load suggestion data from the server.
|
||||
if (global_context->getApplicationType() == Context::ApplicationType::CLIENT)
|
||||
suggest->load<Connection>(global_context, connection_parameters, config().getInt("suggestion_limit"), wait_for_suggestions_to_load);
|
||||
suggest->load<Connection>(global_context, connection_parameters, getClientConfiguration().getInt("suggestion_limit"), wait_for_suggestions_to_load);
|
||||
else if (global_context->getApplicationType() == Context::ApplicationType::LOCAL)
|
||||
suggest->load<LocalConnection>(global_context, connection_parameters, config().getInt("suggestion_limit"), wait_for_suggestions_to_load);
|
||||
suggest->load<LocalConnection>(global_context, connection_parameters, getClientConfiguration().getInt("suggestion_limit"), wait_for_suggestions_to_load);
|
||||
}
|
||||
|
||||
if (home_path.empty())
|
||||
@ -2473,8 +2491,8 @@ void ClientBase::runInteractive()
|
||||
}
|
||||
|
||||
/// Load command history if present.
|
||||
if (config().has("history_file"))
|
||||
history_file = config().getString("history_file");
|
||||
if (getClientConfiguration().has("history_file"))
|
||||
history_file = getClientConfiguration().getString("history_file");
|
||||
else
|
||||
{
|
||||
auto * history_file_from_env = getenv("CLICKHOUSE_HISTORY_FILE"); // NOLINT(concurrency-mt-unsafe)
|
||||
@ -2495,7 +2513,7 @@ void ClientBase::runInteractive()
|
||||
{
|
||||
if (e.getErrno() != EEXIST)
|
||||
{
|
||||
std::cerr << getCurrentExceptionMessage(false) << '\n';
|
||||
error_stream << getCurrentExceptionMessage(false) << '\n';
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -2506,13 +2524,13 @@ void ClientBase::runInteractive()
|
||||
|
||||
#if USE_REPLXX
|
||||
replxx::Replxx::highlighter_callback_t highlight_callback{};
|
||||
if (config().getBool("highlight", true))
|
||||
if (getClientConfiguration().getBool("highlight", true))
|
||||
highlight_callback = highlight;
|
||||
|
||||
ReplxxLineReader lr(
|
||||
*suggest,
|
||||
history_file,
|
||||
config().has("multiline"),
|
||||
getClientConfiguration().has("multiline"),
|
||||
query_extenders,
|
||||
query_delimiters,
|
||||
word_break_characters,
|
||||
@ -2520,7 +2538,7 @@ void ClientBase::runInteractive()
|
||||
#else
|
||||
LineReader lr(
|
||||
history_file,
|
||||
config().has("multiline"),
|
||||
getClientConfiguration().has("multiline"),
|
||||
query_extenders,
|
||||
query_delimiters,
|
||||
word_break_characters);
|
||||
@ -2600,7 +2618,7 @@ void ClientBase::runInteractive()
|
||||
{
|
||||
// If a separate connection loading suggestions failed to open a new session,
|
||||
// use the main session to receive them.
|
||||
suggest->load(*connection, connection_parameters.timeouts, config().getInt("suggestion_limit"), global_context->getClientInfo());
|
||||
suggest->load(*connection, connection_parameters.timeouts, getClientConfiguration().getInt("suggestion_limit"), global_context->getClientInfo());
|
||||
}
|
||||
|
||||
try
|
||||
@ -2611,8 +2629,11 @@ void ClientBase::runInteractive()
|
||||
}
|
||||
catch (const Exception & e)
|
||||
{
|
||||
if (e.code() == ErrorCodes::USER_EXPIRED)
|
||||
break;
|
||||
|
||||
/// We don't need to handle the test hints in the interactive mode.
|
||||
std::cerr << "Exception on client:" << std::endl << getExceptionMessage(e, print_stack_trace, true) << std::endl << std::endl;
|
||||
error_stream << "Exception on client:" << std::endl << getExceptionMessage(e, print_stack_trace, true) << std::endl << std::endl;
|
||||
client_exception.reset(e.clone());
|
||||
}
|
||||
|
||||
@ -2629,11 +2650,11 @@ void ClientBase::runInteractive()
|
||||
while (true);
|
||||
|
||||
if (isNewYearMode())
|
||||
std::cout << "Happy new year." << std::endl;
|
||||
output_stream << "Happy new year." << std::endl;
|
||||
else if (isChineseNewYearMode(local_tz))
|
||||
std::cout << "Happy Chinese new year. 春节快乐!" << std::endl;
|
||||
output_stream << "Happy Chinese new year. 春节快乐!" << std::endl;
|
||||
else
|
||||
std::cout << "Bye." << std::endl;
|
||||
output_stream << "Bye." << std::endl;
|
||||
}
|
||||
|
||||
|
||||
@ -2644,7 +2665,7 @@ bool ClientBase::processMultiQueryFromFile(const String & file_name)
|
||||
ReadBufferFromFile in(file_name);
|
||||
readStringUntilEOF(queries_from_file, in);
|
||||
|
||||
if (!has_log_comment)
|
||||
if (!getClientConfiguration().has("log_comment"))
|
||||
{
|
||||
/// NOTE: cannot use even weakly_canonical() since it fails for /dev/stdin due to resolving of "pipe:[X]"
|
||||
global_context->setSetting("log_comment", String(fs::absolute(fs::path(file_name))));
|
||||
@ -2751,13 +2772,13 @@ void ClientBase::clearTerminal()
|
||||
/// It is needed if garbage is left in terminal.
|
||||
/// Show cursor. It can be left hidden by invocation of previous programs.
|
||||
/// A test for this feature: perl -e 'print "x"x100000'; echo -ne '\033[0;0H\033[?25l'; clickhouse-client
|
||||
std::cout << "\033[0J" "\033[?25h";
|
||||
output_stream << "\033[0J" "\033[?25h";
|
||||
}
|
||||
|
||||
|
||||
void ClientBase::showClientVersion()
|
||||
{
|
||||
std::cout << VERSION_NAME << " " + getName() + " version " << VERSION_STRING << VERSION_OFFICIAL << "." << std::endl;
|
||||
output_stream << VERSION_NAME << " " + getName() + " version " << VERSION_STRING << VERSION_OFFICIAL << "." << std::endl;
|
||||
}
|
||||
|
||||
namespace
|
||||
@ -2824,7 +2845,10 @@ private:
|
||||
|
||||
}
|
||||
|
||||
|
||||
/// Enable optimizations even in debug builds because otherwise options parsing becomes extremely slow affecting .sh tests
|
||||
#if defined(__clang__)
|
||||
#pragma clang optimize on
|
||||
#endif
|
||||
void ClientBase::parseAndCheckOptions(OptionsDescription & options_description, po::variables_map & options, Arguments & arguments)
|
||||
{
|
||||
if (allow_repeated_settings)
|
||||
@ -3043,18 +3067,18 @@ void ClientBase::init(int argc, char ** argv)
|
||||
|
||||
if (options.count("version-clean"))
|
||||
{
|
||||
std::cout << VERSION_STRING;
|
||||
output_stream << VERSION_STRING;
|
||||
exit(0); // NOLINT(concurrency-mt-unsafe)
|
||||
}
|
||||
|
||||
if (options.count("verbose"))
|
||||
config().setBool("verbose", true);
|
||||
getClientConfiguration().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.
|
||||
{
|
||||
if (config().getBool("verbose", false))
|
||||
if (getClientConfiguration().getBool("verbose", false))
|
||||
printHelpMessage(options_description, true);
|
||||
else
|
||||
printHelpMessage(options_description_non_verbose, false);
|
||||
@ -3062,72 +3086,75 @@ void ClientBase::init(int argc, char ** argv)
|
||||
}
|
||||
|
||||
/// Common options for clickhouse-client and clickhouse-local.
|
||||
|
||||
/// Output execution time to stderr in batch mode.
|
||||
if (options.count("time"))
|
||||
print_time_to_stderr = true;
|
||||
getClientConfiguration().setBool("print-time-to-stderr", true);
|
||||
if (options.count("query"))
|
||||
queries = options["query"].as<std::vector<std::string>>();
|
||||
if (options.count("query_id"))
|
||||
config().setString("query_id", options["query_id"].as<std::string>());
|
||||
getClientConfiguration().setString("query_id", options["query_id"].as<std::string>());
|
||||
if (options.count("database"))
|
||||
config().setString("database", options["database"].as<std::string>());
|
||||
getClientConfiguration().setString("database", options["database"].as<std::string>());
|
||||
if (options.count("config-file"))
|
||||
config().setString("config-file", options["config-file"].as<std::string>());
|
||||
getClientConfiguration().setString("config-file", options["config-file"].as<std::string>());
|
||||
if (options.count("queries-file"))
|
||||
queries_files = options["queries-file"].as<std::vector<std::string>>();
|
||||
if (options.count("multiline"))
|
||||
config().setBool("multiline", true);
|
||||
getClientConfiguration().setBool("multiline", true);
|
||||
if (options.count("multiquery"))
|
||||
config().setBool("multiquery", true);
|
||||
getClientConfiguration().setBool("multiquery", true);
|
||||
if (options.count("ignore-error"))
|
||||
config().setBool("ignore-error", true);
|
||||
getClientConfiguration().setBool("ignore-error", true);
|
||||
if (options.count("format"))
|
||||
config().setString("format", options["format"].as<std::string>());
|
||||
getClientConfiguration().setString("format", options["format"].as<std::string>());
|
||||
if (options.count("output-format"))
|
||||
config().setString("output-format", options["output-format"].as<std::string>());
|
||||
getClientConfiguration().setString("output-format", options["output-format"].as<std::string>());
|
||||
if (options.count("vertical"))
|
||||
config().setBool("vertical", true);
|
||||
getClientConfiguration().setBool("vertical", true);
|
||||
if (options.count("stacktrace"))
|
||||
config().setBool("stacktrace", true);
|
||||
getClientConfiguration().setBool("stacktrace", true);
|
||||
if (options.count("print-profile-events"))
|
||||
config().setBool("print-profile-events", true);
|
||||
getClientConfiguration().setBool("print-profile-events", true);
|
||||
if (options.count("profile-events-delay-ms"))
|
||||
config().setUInt64("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
|
||||
getClientConfiguration().setUInt64("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
|
||||
/// Whether to print the number of processed rows at
|
||||
if (options.count("processed-rows"))
|
||||
print_num_processed_rows = true;
|
||||
getClientConfiguration().setBool("print-num-processed-rows", true);
|
||||
if (options.count("progress"))
|
||||
{
|
||||
switch (options["progress"].as<ProgressOption>())
|
||||
{
|
||||
case DEFAULT:
|
||||
config().setString("progress", "default");
|
||||
getClientConfiguration().setString("progress", "default");
|
||||
break;
|
||||
case OFF:
|
||||
config().setString("progress", "off");
|
||||
getClientConfiguration().setString("progress", "off");
|
||||
break;
|
||||
case TTY:
|
||||
config().setString("progress", "tty");
|
||||
getClientConfiguration().setString("progress", "tty");
|
||||
break;
|
||||
case ERR:
|
||||
config().setString("progress", "err");
|
||||
getClientConfiguration().setString("progress", "err");
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (options.count("echo"))
|
||||
config().setBool("echo", true);
|
||||
getClientConfiguration().setBool("echo", true);
|
||||
if (options.count("disable_suggestion"))
|
||||
config().setBool("disable_suggestion", true);
|
||||
getClientConfiguration().setBool("disable_suggestion", true);
|
||||
if (options.count("wait_for_suggestions_to_load"))
|
||||
config().setBool("wait_for_suggestions_to_load", true);
|
||||
getClientConfiguration().setBool("wait_for_suggestions_to_load", true);
|
||||
if (options.count("suggestion_limit"))
|
||||
config().setInt("suggestion_limit", options["suggestion_limit"].as<int>());
|
||||
getClientConfiguration().setInt("suggestion_limit", options["suggestion_limit"].as<int>());
|
||||
if (options.count("highlight"))
|
||||
config().setBool("highlight", options["highlight"].as<bool>());
|
||||
getClientConfiguration().setBool("highlight", options["highlight"].as<bool>());
|
||||
if (options.count("history_file"))
|
||||
config().setString("history_file", options["history_file"].as<std::string>());
|
||||
getClientConfiguration().setString("history_file", options["history_file"].as<std::string>());
|
||||
if (options.count("interactive"))
|
||||
config().setBool("interactive", true);
|
||||
getClientConfiguration().setBool("interactive", true);
|
||||
if (options.count("pager"))
|
||||
config().setString("pager", options["pager"].as<std::string>());
|
||||
getClientConfiguration().setString("pager", options["pager"].as<std::string>());
|
||||
|
||||
if (options.count("log-level"))
|
||||
Poco::Logger::root().setLevel(options["log-level"].as<std::string>());
|
||||
@ -3145,13 +3172,13 @@ void ClientBase::init(int argc, char ** argv)
|
||||
alias_names.reserve(options_description.main_description->options().size());
|
||||
for (const auto& option : options_description.main_description->options())
|
||||
alias_names.insert(option->long_name());
|
||||
argsToConfig(common_arguments, config(), 100, &alias_names);
|
||||
argsToConfig(common_arguments, getClientConfiguration(), 100, &alias_names);
|
||||
}
|
||||
|
||||
clearPasswordFromCommandLine(argc, argv);
|
||||
|
||||
/// Limit on total memory usage
|
||||
std::string max_client_memory_usage = config().getString("max_memory_usage_in_client", "0" /*default value*/);
|
||||
std::string max_client_memory_usage = getClientConfiguration().getString("max_memory_usage_in_client", "0" /*default value*/);
|
||||
if (max_client_memory_usage != "0")
|
||||
{
|
||||
UInt64 max_client_memory_usage_int = parseWithSizeSuffix<UInt64>(max_client_memory_usage.c_str(), max_client_memory_usage.length());
|
||||
@ -3160,8 +3187,6 @@ void ClientBase::init(int argc, char ** argv)
|
||||
total_memory_tracker.setDescription("(total)");
|
||||
total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);
|
||||
}
|
||||
|
||||
has_log_comment = config().has("log_comment");
|
||||
}
|
||||
|
||||
}
|
||||
|
@ -18,7 +18,6 @@
|
||||
#include <Storages/SelectQueryInfo.h>
|
||||
#include <Storages/MergeTree/MergeTreeSettings.h>
|
||||
|
||||
|
||||
namespace po = boost::program_options;
|
||||
|
||||
|
||||
@ -67,13 +66,22 @@ class ClientBase : public Poco::Util::Application, public IHints<2>
|
||||
public:
|
||||
using Arguments = std::vector<String>;
|
||||
|
||||
ClientBase();
|
||||
explicit ClientBase
|
||||
(
|
||||
int in_fd_ = STDIN_FILENO,
|
||||
int out_fd_ = STDOUT_FILENO,
|
||||
int err_fd_ = STDERR_FILENO,
|
||||
std::istream & input_stream_ = std::cin,
|
||||
std::ostream & output_stream_ = std::cout,
|
||||
std::ostream & error_stream_ = std::cerr
|
||||
);
|
||||
|
||||
~ClientBase() override;
|
||||
|
||||
void init(int argc, char ** argv);
|
||||
|
||||
std::vector<String> getAllRegisteredNames() const override { return cmd_options; }
|
||||
static ASTPtr parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements, bool is_interactive, bool ignore_error);
|
||||
ASTPtr parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements);
|
||||
|
||||
protected:
|
||||
void runInteractive();
|
||||
@ -82,6 +90,9 @@ protected:
|
||||
char * argv0 = nullptr;
|
||||
void runLibFuzzer();
|
||||
|
||||
/// This is the analogue of Poco::Application::config()
|
||||
virtual Poco::Util::LayeredConfiguration & getClientConfiguration() = 0;
|
||||
|
||||
virtual bool processWithFuzzing(const String &)
|
||||
{
|
||||
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Query processing with fuzzing is not implemented");
|
||||
@ -107,7 +118,7 @@ protected:
|
||||
String & query_to_execute, ASTPtr & parsed_query, const String & all_queries_text,
|
||||
std::unique_ptr<Exception> & current_exception);
|
||||
|
||||
static void clearTerminal();
|
||||
void clearTerminal();
|
||||
void showClientVersion();
|
||||
|
||||
using ProgramOptionsDescription = boost::program_options::options_description;
|
||||
@ -129,6 +140,7 @@ protected:
|
||||
const std::vector<Arguments> & hosts_and_ports_arguments) = 0;
|
||||
virtual void processConfig() = 0;
|
||||
|
||||
/// Returns true if query processing was successful.
|
||||
bool processQueryText(const String & text);
|
||||
|
||||
virtual void readArguments(
|
||||
@ -206,7 +218,6 @@ protected:
|
||||
|
||||
bool echo_queries = false; /// Print queries before execution in batch mode.
|
||||
bool ignore_error = false; /// In case of errors, don't print error message, continue to next query. Only applicable for non-interactive mode.
|
||||
bool print_time_to_stderr = false; /// Output execution time to stderr in batch mode.
|
||||
|
||||
std::optional<Suggest> suggest;
|
||||
bool load_suggestions = false;
|
||||
@ -248,9 +259,9 @@ protected:
|
||||
ConnectionParameters connection_parameters;
|
||||
|
||||
/// Buffer that reads from stdin in batch mode.
|
||||
ReadBufferFromFileDescriptor std_in{STDIN_FILENO};
|
||||
ReadBufferFromFileDescriptor std_in;
|
||||
/// Console output.
|
||||
WriteBufferFromFileDescriptor std_out{STDOUT_FILENO};
|
||||
WriteBufferFromFileDescriptor std_out;
|
||||
std::unique_ptr<ShellCommand> pager_cmd;
|
||||
|
||||
/// The user can specify to redirect query output to a file.
|
||||
@ -281,7 +292,6 @@ protected:
|
||||
bool need_render_profile_events = true;
|
||||
bool written_first_block = false;
|
||||
size_t processed_rows = 0; /// How many rows have been read or written.
|
||||
bool print_num_processed_rows = false; /// Whether to print the number of processed rows at
|
||||
|
||||
bool print_stack_trace = false;
|
||||
/// The last exception that was received from the server. Is used for the
|
||||
@ -329,8 +339,14 @@ protected:
|
||||
bool cancelled = false;
|
||||
bool cancelled_printed = false;
|
||||
|
||||
/// Does log_comment has specified by user?
|
||||
bool has_log_comment = false;
|
||||
/// Unpacked descriptors and streams for the ease of use.
|
||||
int in_fd = STDIN_FILENO;
|
||||
int out_fd = STDOUT_FILENO;
|
||||
int err_fd = STDERR_FILENO;
|
||||
std::istream & input_stream;
|
||||
std::ostream & output_stream;
|
||||
std::ostream & error_stream;
|
||||
|
||||
};
|
||||
|
||||
}
|
||||
|
@ -1,3 +1,4 @@
|
||||
#include <cstddef>
|
||||
#include <memory>
|
||||
#include <Poco/Net/NetException.h>
|
||||
#include <Core/Defines.h>
|
||||
@ -37,6 +38,7 @@
|
||||
#include <Common/FailPoint.h>
|
||||
|
||||
#include <Common/config_version.h>
|
||||
#include <Core/Types.h>
|
||||
#include "config.h"
|
||||
|
||||
#if USE_SSL
|
||||
@ -68,12 +70,23 @@ namespace ErrorCodes
|
||||
extern const int EMPTY_DATA_PASSED;
|
||||
}
|
||||
|
||||
Connection::~Connection() = default;
|
||||
Connection::~Connection()
|
||||
{
|
||||
try{
|
||||
if (connected)
|
||||
Connection::disconnect();
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
tryLogCurrentException(__PRETTY_FUNCTION__);
|
||||
}
|
||||
}
|
||||
|
||||
Connection::Connection(const String & host_, UInt16 port_,
|
||||
const String & default_database_,
|
||||
const String & user_, const String & password_,
|
||||
[[maybe_unused]] const SSHKey & ssh_private_key_,
|
||||
const String & jwt_,
|
||||
const String & quota_key_,
|
||||
const String & cluster_,
|
||||
const String & cluster_secret_,
|
||||
@ -86,6 +99,7 @@ Connection::Connection(const String & host_, UInt16 port_,
|
||||
, ssh_private_key(ssh_private_key_)
|
||||
#endif
|
||||
, quota_key(quota_key_)
|
||||
, jwt(jwt_)
|
||||
, cluster(cluster_)
|
||||
, cluster_secret(cluster_secret_)
|
||||
, client_name(client_name_)
|
||||
@ -257,13 +271,31 @@ void Connection::connect(const ConnectionTimeouts & timeouts)
|
||||
|
||||
void Connection::disconnect()
|
||||
{
|
||||
maybe_compressed_out = nullptr;
|
||||
in = nullptr;
|
||||
last_input_packet_type.reset();
|
||||
std::exception_ptr finalize_exception;
|
||||
|
||||
try
|
||||
{
|
||||
// finalize() can write and throw an exception.
|
||||
if (maybe_compressed_out)
|
||||
maybe_compressed_out->finalize();
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
/// Don't throw an exception here, it will leave Connection in invalid state.
|
||||
finalize_exception = std::current_exception();
|
||||
|
||||
if (out)
|
||||
{
|
||||
out->cancel();
|
||||
out = nullptr;
|
||||
}
|
||||
}
|
||||
maybe_compressed_out = nullptr;
|
||||
|
||||
try
|
||||
{
|
||||
// finalize() can write to socket and throw an exception.
|
||||
if (out)
|
||||
out->finalize();
|
||||
}
|
||||
@ -276,6 +308,7 @@ void Connection::disconnect()
|
||||
|
||||
if (socket)
|
||||
socket->close();
|
||||
|
||||
socket = nullptr;
|
||||
connected = false;
|
||||
nonce.reset();
|
||||
@ -341,6 +374,11 @@ void Connection::sendHello()
|
||||
performHandshakeForSSHAuth();
|
||||
}
|
||||
#endif
|
||||
else if (!jwt.empty())
|
||||
{
|
||||
writeStringBinary(EncodedUserInfo::JWT_AUTHENTICAION_MARKER, *out);
|
||||
writeStringBinary(jwt, *out);
|
||||
}
|
||||
else
|
||||
{
|
||||
writeStringBinary(user, *out);
|
||||
@ -767,6 +805,8 @@ void Connection::sendQuery(
|
||||
}
|
||||
|
||||
maybe_compressed_in.reset();
|
||||
if (maybe_compressed_out && maybe_compressed_out != out)
|
||||
maybe_compressed_out->cancel();
|
||||
maybe_compressed_out.reset();
|
||||
block_in.reset();
|
||||
block_logs_in.reset();
|
||||
@ -1310,6 +1350,7 @@ ServerConnectionPtr Connection::createConnection(const ConnectionParameters & pa
|
||||
parameters.user,
|
||||
parameters.password,
|
||||
parameters.ssh_private_key,
|
||||
parameters.jwt,
|
||||
parameters.quota_key,
|
||||
"", /* cluster */
|
||||
"", /* cluster_secret */
|
||||
|
@ -53,6 +53,7 @@ public:
|
||||
const String & default_database_,
|
||||
const String & user_, const String & password_,
|
||||
const SSHKey & ssh_private_key_,
|
||||
const String & jwt_,
|
||||
const String & quota_key_,
|
||||
const String & cluster_,
|
||||
const String & cluster_secret_,
|
||||
@ -173,6 +174,7 @@ private:
|
||||
SSHKey ssh_private_key;
|
||||
#endif
|
||||
String quota_key;
|
||||
String jwt;
|
||||
|
||||
/// For inter-server authorization
|
||||
String cluster;
|
||||
|
@ -52,31 +52,11 @@ ConnectionParameters::ConnectionParameters(const Poco::Util::AbstractConfigurati
|
||||
/// changed the default value to "default" to fix the issue when the user in the prompt is blank
|
||||
user = config.getString("user", "default");
|
||||
|
||||
if (!config.has("ssh-key-file"))
|
||||
if (config.has("jwt"))
|
||||
{
|
||||
bool password_prompt = false;
|
||||
if (config.getBool("ask-password", false))
|
||||
{
|
||||
if (config.has("password"))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Specified both --password and --ask-password. Remove one of them");
|
||||
password_prompt = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
password = config.getString("password", "");
|
||||
/// if the value of --password is omitted, the password will be set implicitly to "\n"
|
||||
if (password == ASK_PASSWORD)
|
||||
password_prompt = true;
|
||||
}
|
||||
if (password_prompt)
|
||||
{
|
||||
std::string prompt{"Password for user (" + user + "): "};
|
||||
char buf[1000] = {};
|
||||
if (auto * result = readpassphrase(prompt.c_str(), buf, sizeof(buf), 0))
|
||||
password = result;
|
||||
}
|
||||
jwt = config.getString("jwt");
|
||||
}
|
||||
else
|
||||
else if (config.has("ssh-key-file"))
|
||||
{
|
||||
#if USE_SSH
|
||||
std::string filename = config.getString("ssh-key-file");
|
||||
@ -102,6 +82,30 @@ ConnectionParameters::ConnectionParameters(const Poco::Util::AbstractConfigurati
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
|
||||
#endif
|
||||
}
|
||||
else
|
||||
{
|
||||
bool password_prompt = false;
|
||||
if (config.getBool("ask-password", false))
|
||||
{
|
||||
if (config.has("password"))
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Specified both --password and --ask-password. Remove one of them");
|
||||
password_prompt = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
password = config.getString("password", "");
|
||||
/// if the value of --password is omitted, the password will be set implicitly to "\n"
|
||||
if (password == ASK_PASSWORD)
|
||||
password_prompt = true;
|
||||
}
|
||||
if (password_prompt)
|
||||
{
|
||||
std::string prompt{"Password for user (" + user + "): "};
|
||||
char buf[1000] = {};
|
||||
if (auto * result = readpassphrase(prompt.c_str(), buf, sizeof(buf), 0))
|
||||
password = result;
|
||||
}
|
||||
}
|
||||
|
||||
quota_key = config.getString("quota_key", "");
|
||||
|
||||
@ -139,7 +143,7 @@ ConnectionParameters::ConnectionParameters(const Poco::Util::AbstractConfigurati
|
||||
}
|
||||
|
||||
UInt16 ConnectionParameters::getPortFromConfig(const Poco::Util::AbstractConfiguration & config,
|
||||
std::string connection_host)
|
||||
const std::string & connection_host)
|
||||
{
|
||||
bool is_secure = enableSecureConnection(config, connection_host);
|
||||
return config.getInt("port",
|
||||
|
@ -22,6 +22,7 @@ struct ConnectionParameters
|
||||
std::string password;
|
||||
std::string quota_key;
|
||||
SSHKey ssh_private_key;
|
||||
std::string jwt;
|
||||
Protocol::Secure security = Protocol::Secure::Disable;
|
||||
Protocol::Compression compression = Protocol::Compression::Enable;
|
||||
ConnectionTimeouts timeouts;
|
||||
@ -30,7 +31,7 @@ struct ConnectionParameters
|
||||
ConnectionParameters(const Poco::Util::AbstractConfiguration & config, std::string host);
|
||||
ConnectionParameters(const Poco::Util::AbstractConfiguration & config, std::string host, std::optional<UInt16> port);
|
||||
|
||||
static UInt16 getPortFromConfig(const Poco::Util::AbstractConfiguration & config, std::string connection_host);
|
||||
static UInt16 getPortFromConfig(const Poco::Util::AbstractConfiguration & config, const std::string & connection_host);
|
||||
|
||||
/// Ask to enter the user's password if password option contains this value.
|
||||
/// "\n" is used because there is hardly a chance that a user would use '\n' as password.
|
||||
|
@ -123,7 +123,7 @@ protected:
|
||||
{
|
||||
return std::make_shared<Connection>(
|
||||
host, port,
|
||||
default_database, user, password, SSHKey(), quota_key,
|
||||
default_database, user, password, SSHKey(), /*jwt*/ "", quota_key,
|
||||
cluster, cluster_secret,
|
||||
client_name, compression, secure);
|
||||
}
|
||||
|
@ -23,14 +23,6 @@ void trim(String & s)
|
||||
s.erase(std::find_if(s.rbegin(), s.rend(), [](int ch) { return !std::isspace(ch); }).base(), s.end());
|
||||
}
|
||||
|
||||
/// Check if multi-line query is inserted from the paste buffer.
|
||||
/// Allows delaying the start of query execution until the entirety of query is inserted.
|
||||
bool hasInputData()
|
||||
{
|
||||
pollfd fd{STDIN_FILENO, POLLIN, 0};
|
||||
return poll(&fd, 1, 0) == 1;
|
||||
}
|
||||
|
||||
struct NoCaseCompare
|
||||
{
|
||||
bool operator()(const std::string & str1, const std::string & str2)
|
||||
@ -63,6 +55,14 @@ void addNewWords(Words & to, const Words & from, Compare comp)
|
||||
namespace DB
|
||||
{
|
||||
|
||||
/// Check if multi-line query is inserted from the paste buffer.
|
||||
/// Allows delaying the start of query execution until the entirety of query is inserted.
|
||||
bool LineReader::hasInputData() const
|
||||
{
|
||||
pollfd fd{in_fd, POLLIN, 0};
|
||||
return poll(&fd, 1, 0) == 1;
|
||||
}
|
||||
|
||||
replxx::Replxx::completions_t LineReader::Suggest::getCompletions(const String & prefix, size_t prefix_length, const char * word_break_characters)
|
||||
{
|
||||
std::string_view last_word;
|
||||
@ -131,11 +131,22 @@ void LineReader::Suggest::addWords(Words && new_words) // NOLINT(cppcoreguidelin
|
||||
}
|
||||
}
|
||||
|
||||
LineReader::LineReader(const String & history_file_path_, bool multiline_, Patterns extenders_, Patterns delimiters_)
|
||||
LineReader::LineReader(
|
||||
const String & history_file_path_,
|
||||
bool multiline_,
|
||||
Patterns extenders_,
|
||||
Patterns delimiters_,
|
||||
std::istream & input_stream_,
|
||||
std::ostream & output_stream_,
|
||||
int in_fd_
|
||||
)
|
||||
: history_file_path(history_file_path_)
|
||||
, multiline(multiline_)
|
||||
, extenders(std::move(extenders_))
|
||||
, delimiters(std::move(delimiters_))
|
||||
, input_stream(input_stream_)
|
||||
, output_stream(output_stream_)
|
||||
, in_fd(in_fd_)
|
||||
{
|
||||
/// FIXME: check extender != delimiter
|
||||
}
|
||||
@ -212,9 +223,9 @@ LineReader::InputStatus LineReader::readOneLine(const String & prompt)
|
||||
input.clear();
|
||||
|
||||
{
|
||||
std::cout << prompt;
|
||||
std::getline(std::cin, input);
|
||||
if (!std::cin.good())
|
||||
output_stream << prompt;
|
||||
std::getline(input_stream, input);
|
||||
if (!input_stream.good())
|
||||
return ABORT;
|
||||
}
|
||||
|
||||
|
@ -1,5 +1,7 @@
|
||||
#pragma once
|
||||
|
||||
#include <iostream>
|
||||
#include <unistd.h>
|
||||
#include <mutex>
|
||||
#include <atomic>
|
||||
#include <vector>
|
||||
@ -37,7 +39,16 @@ public:
|
||||
|
||||
using Patterns = std::vector<const char *>;
|
||||
|
||||
LineReader(const String & history_file_path, bool multiline, Patterns extenders, Patterns delimiters);
|
||||
LineReader(
|
||||
const String & history_file_path,
|
||||
bool multiline,
|
||||
Patterns extenders,
|
||||
Patterns delimiters,
|
||||
std::istream & input_stream_ = std::cin,
|
||||
std::ostream & output_stream_ = std::cout,
|
||||
int in_fd_ = STDIN_FILENO
|
||||
);
|
||||
|
||||
virtual ~LineReader() = default;
|
||||
|
||||
/// Reads the whole line until delimiter (in multiline mode) or until the last line without extender.
|
||||
@ -56,6 +67,8 @@ public:
|
||||
virtual void enableBracketedPaste() {}
|
||||
virtual void disableBracketedPaste() {}
|
||||
|
||||
bool hasInputData() const;
|
||||
|
||||
protected:
|
||||
enum InputStatus
|
||||
{
|
||||
@ -77,6 +90,10 @@ protected:
|
||||
|
||||
virtual InputStatus readOneLine(const String & prompt);
|
||||
virtual void addToHistory(const String &) {}
|
||||
|
||||
std::istream & input_stream;
|
||||
std::ostream & output_stream;
|
||||
int in_fd;
|
||||
};
|
||||
|
||||
}
|
||||
|
@ -16,7 +16,10 @@
|
||||
#include <Storages/IStorage.h>
|
||||
#include <Common/ConcurrentBoundedQueue.h>
|
||||
#include <Common/CurrentThread.h>
|
||||
|
||||
#include <Parsers/ParserQuery.h>
|
||||
#include <Parsers/PRQL/ParserPRQLQuery.h>
|
||||
#include <Parsers/Kusto/ParserKQLStatement.h>
|
||||
#include <Parsers/Kusto/parseKQLQuery.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -150,12 +153,26 @@ void LocalConnection::sendQuery(
|
||||
state->block = sample;
|
||||
|
||||
String current_format = "Values";
|
||||
|
||||
const auto & settings = context->getSettingsRef();
|
||||
const char * begin = state->query.data();
|
||||
auto parsed_query = ClientBase::parseQuery(begin, begin + state->query.size(),
|
||||
context->getSettingsRef(),
|
||||
/*allow_multi_statements=*/ false,
|
||||
/*is_interactive=*/ false,
|
||||
/*ignore_error=*/ false);
|
||||
const char * end = begin + state->query.size();
|
||||
const Dialect & dialect = settings.dialect;
|
||||
|
||||
std::unique_ptr<IParserBase> parser;
|
||||
if (dialect == Dialect::kusto)
|
||||
parser = std::make_unique<ParserKQLStatement>(end, settings.allow_settings_after_format_in_insert);
|
||||
else if (dialect == Dialect::prql)
|
||||
parser = std::make_unique<ParserPRQLQuery>(settings.max_query_size, settings.max_parser_depth, settings.max_parser_backtracks);
|
||||
else
|
||||
parser = std::make_unique<ParserQuery>(end, settings.allow_settings_after_format_in_insert);
|
||||
|
||||
ASTPtr parsed_query;
|
||||
if (dialect == Dialect::kusto)
|
||||
parsed_query = parseKQLQueryAndMovePosition(*parser, begin, end, "", /*allow_multi_statements*/false, settings.max_query_size, settings.max_parser_depth, settings.max_parser_backtracks);
|
||||
else
|
||||
parsed_query = parseQueryAndMovePosition(*parser, begin, end, "", /*allow_multi_statements*/false, settings.max_query_size, settings.max_parser_depth, settings.max_parser_backtracks);
|
||||
|
||||
if (const auto * insert = parsed_query->as<ASTInsertQuery>())
|
||||
{
|
||||
if (!insert->format.empty())
|
||||
|
@ -297,8 +297,15 @@ ReplxxLineReader::ReplxxLineReader(
|
||||
Patterns extenders_,
|
||||
Patterns delimiters_,
|
||||
const char word_break_characters_[],
|
||||
replxx::Replxx::highlighter_callback_t highlighter_)
|
||||
: LineReader(history_file_path_, multiline_, std::move(extenders_), std::move(delimiters_)), highlighter(std::move(highlighter_))
|
||||
replxx::Replxx::highlighter_callback_t highlighter_,
|
||||
[[ maybe_unused ]] std::istream & input_stream_,
|
||||
[[ maybe_unused ]] std::ostream & output_stream_,
|
||||
[[ maybe_unused ]] int in_fd_,
|
||||
[[ maybe_unused ]] int out_fd_,
|
||||
[[ maybe_unused ]] int err_fd_
|
||||
)
|
||||
: LineReader(history_file_path_, multiline_, std::move(extenders_), std::move(delimiters_), input_stream_, output_stream_, in_fd_)
|
||||
, highlighter(std::move(highlighter_))
|
||||
, word_break_characters(word_break_characters_)
|
||||
, editor(getEditor())
|
||||
{
|
||||
@ -471,7 +478,7 @@ ReplxxLineReader::ReplxxLineReader(
|
||||
|
||||
ReplxxLineReader::~ReplxxLineReader()
|
||||
{
|
||||
if (close(history_file_fd))
|
||||
if (history_file_fd >= 0 && close(history_file_fd))
|
||||
rx.print("Close of history file failed: %s\n", errnoToString().c_str());
|
||||
}
|
||||
|
||||
@ -496,7 +503,7 @@ void ReplxxLineReader::addToHistory(const String & line)
|
||||
// but replxx::Replxx::history_load() does not
|
||||
// and that is why flock() is added here.
|
||||
bool locked = false;
|
||||
if (flock(history_file_fd, LOCK_EX))
|
||||
if (history_file_fd >= 0 && flock(history_file_fd, LOCK_EX))
|
||||
rx.print("Lock of history file failed: %s\n", errnoToString().c_str());
|
||||
else
|
||||
locked = true;
|
||||
@ -507,7 +514,7 @@ void ReplxxLineReader::addToHistory(const String & line)
|
||||
if (!rx.history_save(history_file_path))
|
||||
rx.print("Saving history failed: %s\n", errnoToString().c_str());
|
||||
|
||||
if (locked && 0 != flock(history_file_fd, LOCK_UN))
|
||||
if (history_file_fd >= 0 && locked && 0 != flock(history_file_fd, LOCK_UN))
|
||||
rx.print("Unlock of history file failed: %s\n", errnoToString().c_str());
|
||||
}
|
||||
|
||||
|
@ -1,6 +1,7 @@
|
||||
#pragma once
|
||||
|
||||
#include "LineReader.h"
|
||||
#include <Client/LineReader.h>
|
||||
#include <base/strong_typedef.h>
|
||||
#include <replxx.hxx>
|
||||
|
||||
namespace DB
|
||||
@ -9,14 +10,22 @@ namespace DB
|
||||
class ReplxxLineReader : public LineReader
|
||||
{
|
||||
public:
|
||||
ReplxxLineReader(
|
||||
ReplxxLineReader
|
||||
(
|
||||
Suggest & suggest,
|
||||
const String & history_file_path,
|
||||
bool multiline,
|
||||
Patterns extenders_,
|
||||
Patterns delimiters_,
|
||||
const char word_break_characters_[],
|
||||
replxx::Replxx::highlighter_callback_t highlighter_);
|
||||
replxx::Replxx::highlighter_callback_t highlighter_,
|
||||
std::istream & input_stream_ = std::cin,
|
||||
std::ostream & output_stream_ = std::cout,
|
||||
int in_fd_ = STDIN_FILENO,
|
||||
int out_fd_ = STDOUT_FILENO,
|
||||
int err_fd_ = STDERR_FILENO
|
||||
);
|
||||
|
||||
~ReplxxLineReader() override;
|
||||
|
||||
void enableBracketedPaste() override;
|
||||
|
@ -19,8 +19,7 @@ ConfigReloader::ConfigReloader(
|
||||
const std::string & preprocessed_dir_,
|
||||
zkutil::ZooKeeperNodeCache && zk_node_cache_,
|
||||
const zkutil::EventPtr & zk_changed_event_,
|
||||
Updater && updater_,
|
||||
bool already_loaded)
|
||||
Updater && updater_)
|
||||
: config_path(config_path_)
|
||||
, extra_paths(extra_paths_)
|
||||
, preprocessed_dir(preprocessed_dir_)
|
||||
@ -28,10 +27,15 @@ ConfigReloader::ConfigReloader(
|
||||
, zk_changed_event(zk_changed_event_)
|
||||
, updater(std::move(updater_))
|
||||
{
|
||||
if (!already_loaded)
|
||||
reloadIfNewer(/* force = */ true, /* throw_on_error = */ true, /* fallback_to_preprocessed = */ true, /* initial_loading = */ true);
|
||||
}
|
||||
auto config = reloadIfNewer(/* force = */ true, /* throw_on_error = */ true, /* fallback_to_preprocessed = */ true, /* initial_loading = */ true);
|
||||
|
||||
if (config.has_value())
|
||||
reload_interval = std::chrono::milliseconds(config->configuration->getInt64("config_reload_interval_ms", DEFAULT_RELOAD_INTERVAL.count()));
|
||||
else
|
||||
reload_interval = DEFAULT_RELOAD_INTERVAL;
|
||||
|
||||
LOG_TRACE(log, "Config reload interval set to {}ms", reload_interval.count());
|
||||
}
|
||||
|
||||
void ConfigReloader::start()
|
||||
{
|
||||
@ -82,7 +86,17 @@ void ConfigReloader::run()
|
||||
if (quit)
|
||||
return;
|
||||
|
||||
reloadIfNewer(zk_changed, /* throw_on_error = */ false, /* fallback_to_preprocessed = */ false, /* initial_loading = */ false);
|
||||
auto config = reloadIfNewer(zk_changed, /* throw_on_error = */ false, /* fallback_to_preprocessed = */ false, /* initial_loading = */ false);
|
||||
if (config.has_value())
|
||||
{
|
||||
auto new_reload_interval = std::chrono::milliseconds(config->configuration->getInt64("config_reload_interval_ms", DEFAULT_RELOAD_INTERVAL.count()));
|
||||
if (new_reload_interval != reload_interval)
|
||||
{
|
||||
reload_interval = new_reload_interval;
|
||||
LOG_TRACE(log, "Config reload interval changed to {}ms", reload_interval.count());
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
@ -92,7 +106,7 @@ void ConfigReloader::run()
|
||||
}
|
||||
}
|
||||
|
||||
void ConfigReloader::reloadIfNewer(bool force, bool throw_on_error, bool fallback_to_preprocessed, bool initial_loading)
|
||||
std::optional<ConfigProcessor::LoadedConfig> ConfigReloader::reloadIfNewer(bool force, bool throw_on_error, bool fallback_to_preprocessed, bool initial_loading)
|
||||
{
|
||||
std::lock_guard lock(reload_mutex);
|
||||
|
||||
@ -120,7 +134,7 @@ void ConfigReloader::reloadIfNewer(bool force, bool throw_on_error, bool fallbac
|
||||
throw;
|
||||
|
||||
tryLogCurrentException(log, "ZooKeeper error when loading config from '" + config_path + "'");
|
||||
return;
|
||||
return std::nullopt;
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
@ -128,7 +142,7 @@ void ConfigReloader::reloadIfNewer(bool force, bool throw_on_error, bool fallbac
|
||||
throw;
|
||||
|
||||
tryLogCurrentException(log, "Error loading config from '" + config_path + "'");
|
||||
return;
|
||||
return std::nullopt;
|
||||
}
|
||||
config_processor.savePreprocessedConfig(loaded_config, preprocessed_dir);
|
||||
|
||||
@ -154,11 +168,13 @@ void ConfigReloader::reloadIfNewer(bool force, bool throw_on_error, bool fallbac
|
||||
if (throw_on_error)
|
||||
throw;
|
||||
tryLogCurrentException(log, "Error updating configuration from '" + config_path + "' config.");
|
||||
return;
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
LOG_DEBUG(log, "Loaded config '{}', performed update on configuration", config_path);
|
||||
return loaded_config;
|
||||
}
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
struct ConfigReloader::FileWithTimestamp
|
||||
|
@ -17,8 +17,6 @@ namespace Poco { class Logger; }
|
||||
namespace DB
|
||||
{
|
||||
|
||||
class Context;
|
||||
|
||||
/** Every two seconds checks configuration files for update.
|
||||
* If configuration is changed, then config will be reloaded by ConfigProcessor
|
||||
* and the reloaded config will be applied via Updater functor.
|
||||
@ -27,6 +25,8 @@ class Context;
|
||||
class ConfigReloader
|
||||
{
|
||||
public:
|
||||
static constexpr auto DEFAULT_RELOAD_INTERVAL = std::chrono::milliseconds(2000);
|
||||
|
||||
using Updater = std::function<void(ConfigurationPtr, bool)>;
|
||||
|
||||
ConfigReloader(
|
||||
@ -35,8 +35,7 @@ public:
|
||||
const std::string & preprocessed_dir,
|
||||
zkutil::ZooKeeperNodeCache && zk_node_cache,
|
||||
const zkutil::EventPtr & zk_changed_event,
|
||||
Updater && updater,
|
||||
bool already_loaded);
|
||||
Updater && updater);
|
||||
|
||||
~ConfigReloader();
|
||||
|
||||
@ -53,7 +52,7 @@ public:
|
||||
private:
|
||||
void run();
|
||||
|
||||
void reloadIfNewer(bool force, bool throw_on_error, bool fallback_to_preprocessed, bool initial_loading);
|
||||
std::optional<ConfigProcessor::LoadedConfig> reloadIfNewer(bool force, bool throw_on_error, bool fallback_to_preprocessed, bool initial_loading);
|
||||
|
||||
struct FileWithTimestamp;
|
||||
|
||||
@ -67,8 +66,6 @@ private:
|
||||
|
||||
FilesChangesTracker getNewFileList() const;
|
||||
|
||||
static constexpr auto reload_interval = std::chrono::seconds(2);
|
||||
|
||||
LoggerPtr log = getLogger("ConfigReloader");
|
||||
|
||||
std::string config_path;
|
||||
@ -85,6 +82,8 @@ private:
|
||||
std::atomic<bool> quit{false};
|
||||
ThreadFromGlobalPool thread;
|
||||
|
||||
std::chrono::milliseconds reload_interval = DEFAULT_RELOAD_INTERVAL;
|
||||
|
||||
/// Locked inside reloadIfNewer.
|
||||
std::mutex reload_mutex;
|
||||
};
|
||||
|
@ -60,4 +60,26 @@ GetPriorityForLoadBalancing::getPriorityFunc(LoadBalancing load_balance, size_t
|
||||
return get_priority;
|
||||
}
|
||||
|
||||
/// Some load balancing strategies (such as "nearest hostname") have preferred nodes to connect to.
|
||||
/// Usually it's a node in the same data center/availability zone.
|
||||
/// For other strategies there's no difference between nodes.
|
||||
bool GetPriorityForLoadBalancing::hasOptimalNode() const
|
||||
{
|
||||
switch (load_balancing)
|
||||
{
|
||||
case LoadBalancing::NEAREST_HOSTNAME:
|
||||
return true;
|
||||
case LoadBalancing::HOSTNAME_LEVENSHTEIN_DISTANCE:
|
||||
return true;
|
||||
case LoadBalancing::IN_ORDER:
|
||||
return false;
|
||||
case LoadBalancing::RANDOM:
|
||||
return false;
|
||||
case LoadBalancing::FIRST_OR_RANDOM:
|
||||
return true;
|
||||
case LoadBalancing::ROUND_ROBIN:
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
@ -30,6 +30,8 @@ public:
|
||||
|
||||
Func getPriorityFunc(LoadBalancing load_balance, size_t offset, size_t pool_size) const;
|
||||
|
||||
bool hasOptimalNode() const;
|
||||
|
||||
std::vector<size_t> hostname_prefix_distance; /// Prefix distances from name of this host to the names of hosts of pools.
|
||||
std::vector<size_t> hostname_levenshtein_distance; /// Levenshtein Distances from name of this host to the names of hosts of pools.
|
||||
|
||||
|
@ -637,11 +637,11 @@ The server successfully detected this situation and will download merged part fr
|
||||
M(S3QueueSetFileProcessingMicroseconds, "Time spent to set file as processing")\
|
||||
M(S3QueueSetFileProcessedMicroseconds, "Time spent to set file as processed")\
|
||||
M(S3QueueSetFileFailedMicroseconds, "Time spent to set file as failed")\
|
||||
M(S3QueueFailedFiles, "Number of files which failed to be processed")\
|
||||
M(S3QueueProcessedFiles, "Number of files which were processed")\
|
||||
M(S3QueueCleanupMaxSetSizeOrTTLMicroseconds, "Time spent to set file as failed")\
|
||||
M(S3QueuePullMicroseconds, "Time spent to read file data")\
|
||||
M(S3QueueLockLocalFileStatusesMicroseconds, "Time spent to lock local file statuses")\
|
||||
M(ObjectStorageQueueFailedFiles, "Number of files which failed to be processed")\
|
||||
M(ObjectStorageQueueProcessedFiles, "Number of files which were processed")\
|
||||
M(ObjectStorageQueueCleanupMaxSetSizeOrTTLMicroseconds, "Time spent to set file as failed")\
|
||||
M(ObjectStorageQueuePullMicroseconds, "Time spent to read file data")\
|
||||
M(ObjectStorageQueueLockLocalFileStatusesMicroseconds, "Time spent to lock local file statuses")\
|
||||
\
|
||||
M(ServerStartupMilliseconds, "Time elapsed from starting server to listening to sockets in milliseconds")\
|
||||
M(IOUringSQEsSubmitted, "Total number of io_uring SQEs submitted") \
|
||||
|
@ -92,19 +92,19 @@ void ProgressIndication::writeFinalProgress()
|
||||
if (progress.read_rows < 1000)
|
||||
return;
|
||||
|
||||
std::cout << "Processed " << formatReadableQuantity(progress.read_rows) << " rows, "
|
||||
output_stream << "Processed " << formatReadableQuantity(progress.read_rows) << " rows, "
|
||||
<< formatReadableSizeWithDecimalSuffix(progress.read_bytes);
|
||||
|
||||
UInt64 elapsed_ns = getElapsedNanoseconds();
|
||||
if (elapsed_ns)
|
||||
std::cout << " (" << formatReadableQuantity(progress.read_rows * 1000000000.0 / elapsed_ns) << " rows/s., "
|
||||
output_stream << " (" << formatReadableQuantity(progress.read_rows * 1000000000.0 / elapsed_ns) << " rows/s., "
|
||||
<< formatReadableSizeWithDecimalSuffix(progress.read_bytes * 1000000000.0 / elapsed_ns) << "/s.)";
|
||||
else
|
||||
std::cout << ". ";
|
||||
output_stream << ". ";
|
||||
|
||||
auto peak_memory_usage = getMemoryUsage().peak;
|
||||
if (peak_memory_usage >= 0)
|
||||
std::cout << "\nPeak memory usage: " << formatReadableSizeWithBinarySuffix(peak_memory_usage) << ".";
|
||||
output_stream << "\nPeak memory usage: " << formatReadableSizeWithBinarySuffix(peak_memory_usage) << ".";
|
||||
}
|
||||
|
||||
void ProgressIndication::writeProgress(WriteBufferFromFileDescriptor & message)
|
||||
@ -125,7 +125,7 @@ void ProgressIndication::writeProgress(WriteBufferFromFileDescriptor & message)
|
||||
|
||||
const char * indicator = indicators[increment % 8];
|
||||
|
||||
size_t terminal_width = getTerminalWidth();
|
||||
size_t terminal_width = getTerminalWidth(in_fd, err_fd);
|
||||
|
||||
if (!written_progress_chars)
|
||||
{
|
||||
|
@ -32,6 +32,19 @@ using HostToTimesMap = std::unordered_map<String, ThreadEventData>;
|
||||
class ProgressIndication
|
||||
{
|
||||
public:
|
||||
|
||||
explicit ProgressIndication
|
||||
(
|
||||
std::ostream & output_stream_ = std::cout,
|
||||
int in_fd_ = STDIN_FILENO,
|
||||
int err_fd_ = STDERR_FILENO
|
||||
)
|
||||
: output_stream(output_stream_),
|
||||
in_fd(in_fd_),
|
||||
err_fd(err_fd_)
|
||||
{
|
||||
}
|
||||
|
||||
/// Write progress bar.
|
||||
void writeProgress(WriteBufferFromFileDescriptor & message);
|
||||
void clearProgressOutput(WriteBufferFromFileDescriptor & message);
|
||||
@ -103,6 +116,10 @@ private:
|
||||
/// - hosts_data/cpu_usage_meter (guarded with profile_events_mutex)
|
||||
mutable std::mutex profile_events_mutex;
|
||||
mutable std::mutex progress_mutex;
|
||||
|
||||
std::ostream & output_stream;
|
||||
int in_fd;
|
||||
int err_fd;
|
||||
};
|
||||
|
||||
}
|
||||
|
@ -11,7 +11,7 @@
|
||||
#include <Interpreters/TextLog.h>
|
||||
#include <Interpreters/TraceLog.h>
|
||||
#include <Interpreters/FilesystemCacheLog.h>
|
||||
#include <Interpreters/S3QueueLog.h>
|
||||
#include <Interpreters/ObjectStorageQueueLog.h>
|
||||
#include <Interpreters/FilesystemReadPrefetchesLog.h>
|
||||
#include <Interpreters/ProcessorsProfileLog.h>
|
||||
#include <Interpreters/ZooKeeperLog.h>
|
||||
|
@ -25,7 +25,7 @@
|
||||
M(ZooKeeperLogElement) \
|
||||
M(ProcessorProfileLogElement) \
|
||||
M(TextLogElement) \
|
||||
M(S3QueueLogElement) \
|
||||
M(ObjectStorageQueueLogElement) \
|
||||
M(FilesystemCacheLogElement) \
|
||||
M(FilesystemReadPrefetchesLogElement) \
|
||||
M(AsynchronousInsertLogElement) \
|
||||
|
@ -13,17 +13,17 @@ namespace DB::ErrorCodes
|
||||
extern const int SYSTEM_ERROR;
|
||||
}
|
||||
|
||||
uint16_t getTerminalWidth()
|
||||
uint16_t getTerminalWidth(int in_fd, int err_fd)
|
||||
{
|
||||
struct winsize terminal_size {};
|
||||
if (isatty(STDIN_FILENO))
|
||||
if (isatty(in_fd))
|
||||
{
|
||||
if (ioctl(STDIN_FILENO, TIOCGWINSZ, &terminal_size))
|
||||
if (ioctl(in_fd, TIOCGWINSZ, &terminal_size))
|
||||
throw DB::ErrnoException(DB::ErrorCodes::SYSTEM_ERROR, "Cannot obtain terminal window size (ioctl TIOCGWINSZ)");
|
||||
}
|
||||
else if (isatty(STDERR_FILENO))
|
||||
else if (isatty(err_fd))
|
||||
{
|
||||
if (ioctl(STDERR_FILENO, TIOCGWINSZ, &terminal_size))
|
||||
if (ioctl(err_fd, TIOCGWINSZ, &terminal_size))
|
||||
throw DB::ErrnoException(DB::ErrorCodes::SYSTEM_ERROR, "Cannot obtain terminal window size (ioctl TIOCGWINSZ)");
|
||||
}
|
||||
/// Default - 0.
|
||||
|
@ -1,16 +1,16 @@
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
#include <unistd.h>
|
||||
#include <boost/program_options.hpp>
|
||||
|
||||
|
||||
namespace po = boost::program_options;
|
||||
|
||||
|
||||
uint16_t getTerminalWidth();
|
||||
uint16_t getTerminalWidth(int in_fd = STDIN_FILENO, int err_fd = STDERR_FILENO);
|
||||
|
||||
/** Creates po::options_description with name and an appropriate size for option displaying
|
||||
* when program is called with option --help
|
||||
* */
|
||||
po::options_description createOptionsDescription(const std::string &caption, unsigned short terminal_width); /// NOLINT
|
||||
|
||||
|
@ -559,6 +559,8 @@ public:
|
||||
/// Useful to check owner of ephemeral node.
|
||||
virtual int64_t getSessionID() const = 0;
|
||||
|
||||
virtual String tryGetAvailabilityZone() { return ""; }
|
||||
|
||||
/// If the method will throw an exception, callbacks won't be called.
|
||||
///
|
||||
/// After the method is executed successfully, you must wait for callbacks
|
||||
@ -635,10 +637,6 @@ public:
|
||||
|
||||
virtual const DB::KeeperFeatureFlags * getKeeperFeatureFlags() const { return nullptr; }
|
||||
|
||||
/// A ZooKeeper session can have an optional deadline set on it.
|
||||
/// After it has been reached, the session needs to be finalized.
|
||||
virtual bool hasReachedDeadline() const = 0;
|
||||
|
||||
/// Expire session and finish all pending requests
|
||||
virtual void finalize(const String & reason) = 0;
|
||||
};
|
||||
|
@ -39,7 +39,6 @@ public:
|
||||
~TestKeeper() override;
|
||||
|
||||
bool isExpired() const override { return expired; }
|
||||
bool hasReachedDeadline() const override { return false; }
|
||||
Int8 getConnectedNodeIdx() const override { return 0; }
|
||||
String getConnectedHostPort() const override { return "TestKeeper:0000"; }
|
||||
int32_t getConnectionXid() const override { return 0; }
|
||||
|
@ -8,6 +8,7 @@
|
||||
#include <functional>
|
||||
#include <ranges>
|
||||
#include <vector>
|
||||
#include <chrono>
|
||||
|
||||
#include <Common/ZooKeeper/Types.h>
|
||||
#include <Common/ZooKeeper/ZooKeeperCommon.h>
|
||||
@ -16,10 +17,12 @@
|
||||
#include <base/sort.h>
|
||||
#include <base/getFQDNOrHostName.h>
|
||||
#include <Core/ServerUUID.h>
|
||||
#include <Core/BackgroundSchedulePool.h>
|
||||
#include "Common/ZooKeeper/IKeeper.h"
|
||||
#include <Common/DNSResolver.h>
|
||||
#include <Common/StringUtils.h>
|
||||
#include <Common/Exception.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
#include <Poco/Net/NetException.h>
|
||||
#include <Poco/Net/DNS.h>
|
||||
@ -55,70 +58,120 @@ static void check(Coordination::Error code, const std::string & path)
|
||||
throw KeeperException::fromPath(code, path);
|
||||
}
|
||||
|
||||
UInt64 getSecondsUntilReconnect(const ZooKeeperArgs & args)
|
||||
{
|
||||
std::uniform_int_distribution<UInt32> fallback_session_lifetime_distribution
|
||||
{
|
||||
args.fallback_session_lifetime.min_sec,
|
||||
args.fallback_session_lifetime.max_sec,
|
||||
};
|
||||
UInt32 session_lifetime_seconds = fallback_session_lifetime_distribution(thread_local_rng);
|
||||
return session_lifetime_seconds;
|
||||
}
|
||||
|
||||
void ZooKeeper::init(ZooKeeperArgs args_)
|
||||
|
||||
void ZooKeeper::updateAvailabilityZones()
|
||||
{
|
||||
ShuffleHosts shuffled_hosts = shuffleHosts();
|
||||
|
||||
for (const auto & node : shuffled_hosts)
|
||||
{
|
||||
try
|
||||
{
|
||||
ShuffleHosts single_node{node};
|
||||
auto tmp_impl = std::make_unique<Coordination::ZooKeeper>(single_node, args, zk_log);
|
||||
auto idx = node.original_index;
|
||||
availability_zones[idx] = tmp_impl->tryGetAvailabilityZone();
|
||||
LOG_TEST(log, "Got availability zone for {}: {}", args.hosts[idx], availability_zones[idx]);
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
DB::tryLogCurrentException(log, "Failed to get availability zone for " + node.host);
|
||||
}
|
||||
}
|
||||
LOG_DEBUG(log, "Updated availability zones: [{}]", fmt::join(availability_zones, ", "));
|
||||
}
|
||||
|
||||
void ZooKeeper::init(ZooKeeperArgs args_, std::unique_ptr<Coordination::IKeeper> existing_impl)
|
||||
{
|
||||
args = std::move(args_);
|
||||
log = getLogger("ZooKeeper");
|
||||
|
||||
if (args.implementation == "zookeeper")
|
||||
if (existing_impl)
|
||||
{
|
||||
chassert(args.implementation == "zookeeper");
|
||||
impl = std::move(existing_impl);
|
||||
LOG_INFO(log, "Switching to connection to a more optimal node {}", impl->getConnectedHostPort());
|
||||
}
|
||||
else if (args.implementation == "zookeeper")
|
||||
{
|
||||
if (args.hosts.empty())
|
||||
throw KeeperException::fromMessage(Coordination::Error::ZBADARGUMENTS, "No hosts passed to ZooKeeper constructor.");
|
||||
|
||||
Coordination::ZooKeeper::Nodes nodes;
|
||||
nodes.reserve(args.hosts.size());
|
||||
chassert(args.availability_zones.size() == args.hosts.size());
|
||||
if (availability_zones.empty())
|
||||
{
|
||||
/// availability_zones is empty on server startup or after config reloading
|
||||
/// We will keep the az info when starting new sessions
|
||||
availability_zones = args.availability_zones;
|
||||
LOG_TEST(log, "Availability zones from config: [{}], client: {}", fmt::join(availability_zones, ", "), args.client_availability_zone);
|
||||
if (args.availability_zone_autodetect)
|
||||
updateAvailabilityZones();
|
||||
}
|
||||
chassert(availability_zones.size() == args.hosts.size());
|
||||
|
||||
/// Shuffle the hosts to distribute the load among ZooKeeper nodes.
|
||||
std::vector<ShuffleHost> shuffled_hosts = shuffleHosts();
|
||||
ShuffleHosts shuffled_hosts = shuffleHosts();
|
||||
|
||||
bool dns_error = false;
|
||||
for (auto & host : shuffled_hosts)
|
||||
{
|
||||
auto & host_string = host.host;
|
||||
try
|
||||
{
|
||||
const bool secure = startsWith(host_string, "secure://");
|
||||
|
||||
if (secure)
|
||||
host_string.erase(0, strlen("secure://"));
|
||||
|
||||
/// We want to resolve all hosts without DNS cache for keeper connection.
|
||||
Coordination::DNSResolver::instance().removeHostFromCache(host_string);
|
||||
|
||||
const Poco::Net::SocketAddress host_socket_addr{host_string};
|
||||
LOG_TEST(log, "Adding ZooKeeper host {} ({})", host_string, host_socket_addr.toString());
|
||||
nodes.emplace_back(Coordination::ZooKeeper::Node{host_socket_addr, host.original_index, secure});
|
||||
}
|
||||
catch (const Poco::Net::HostNotFoundException & e)
|
||||
{
|
||||
/// Most likely it's misconfiguration and wrong hostname was specified
|
||||
LOG_ERROR(log, "Cannot use ZooKeeper host {}, reason: {}", host_string, e.displayText());
|
||||
}
|
||||
catch (const Poco::Net::DNSException & e)
|
||||
{
|
||||
/// Most likely DNS is not available now
|
||||
dns_error = true;
|
||||
LOG_ERROR(log, "Cannot use ZooKeeper host {} due to DNS error: {}", host_string, e.displayText());
|
||||
}
|
||||
}
|
||||
|
||||
if (nodes.empty())
|
||||
{
|
||||
/// For DNS errors we throw exception with ZCONNECTIONLOSS code, so it will be considered as hardware error, not user error
|
||||
if (dns_error)
|
||||
throw KeeperException::fromMessage(Coordination::Error::ZCONNECTIONLOSS, "Cannot resolve any of provided ZooKeeper hosts due to DNS error");
|
||||
else
|
||||
throw KeeperException::fromMessage(Coordination::Error::ZCONNECTIONLOSS, "Cannot use any of provided ZooKeeper nodes");
|
||||
}
|
||||
|
||||
impl = std::make_unique<Coordination::ZooKeeper>(nodes, args, zk_log);
|
||||
impl = std::make_unique<Coordination::ZooKeeper>(shuffled_hosts, args, zk_log);
|
||||
Int8 node_idx = impl->getConnectedNodeIdx();
|
||||
|
||||
if (args.chroot.empty())
|
||||
LOG_TRACE(log, "Initialized, hosts: {}", fmt::join(args.hosts, ","));
|
||||
else
|
||||
LOG_TRACE(log, "Initialized, hosts: {}, chroot: {}", fmt::join(args.hosts, ","), args.chroot);
|
||||
|
||||
|
||||
/// If the balancing strategy has an optimal node then it will be the first in the list
|
||||
bool connected_to_suboptimal_node = node_idx != shuffled_hosts[0].original_index;
|
||||
bool respect_az = args.prefer_local_availability_zone && !args.client_availability_zone.empty();
|
||||
bool may_benefit_from_reconnecting = respect_az || args.get_priority_load_balancing.hasOptimalNode();
|
||||
if (connected_to_suboptimal_node && may_benefit_from_reconnecting)
|
||||
{
|
||||
auto reconnect_timeout_sec = getSecondsUntilReconnect(args);
|
||||
LOG_DEBUG(log, "Connected to a suboptimal ZooKeeper host ({}, index {})."
|
||||
" To preserve balance in ZooKeeper usage, this ZooKeeper session will expire in {} seconds",
|
||||
impl->getConnectedHostPort(), node_idx, reconnect_timeout_sec);
|
||||
|
||||
auto reconnect_task_holder = DB::Context::getGlobalContextInstance()->getSchedulePool().createTask("ZKReconnect", [this, optimal_host = shuffled_hosts[0]]()
|
||||
{
|
||||
try
|
||||
{
|
||||
LOG_DEBUG(log, "Trying to connect to a more optimal node {}", optimal_host.host);
|
||||
ShuffleHosts node{optimal_host};
|
||||
std::unique_ptr<Coordination::IKeeper> new_impl = std::make_unique<Coordination::ZooKeeper>(node, args, zk_log);
|
||||
Int8 new_node_idx = new_impl->getConnectedNodeIdx();
|
||||
|
||||
/// Maybe the node was unavailable when getting AZs first time, update just in case
|
||||
if (args.availability_zone_autodetect && availability_zones[new_node_idx].empty())
|
||||
{
|
||||
availability_zones[new_node_idx] = new_impl->tryGetAvailabilityZone();
|
||||
LOG_DEBUG(log, "Got availability zone for {}: {}", optimal_host.host, availability_zones[new_node_idx]);
|
||||
}
|
||||
|
||||
optimal_impl = std::move(new_impl);
|
||||
impl->finalize("Connected to a more optimal node");
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
LOG_WARNING(log, "Failed to connect to a more optimal ZooKeeper, will try again later: {}", DB::getCurrentExceptionMessage(/*with_stacktrace*/ false));
|
||||
(*reconnect_task)->scheduleAfter(getSecondsUntilReconnect(args) * 1000);
|
||||
}
|
||||
});
|
||||
reconnect_task = std::make_unique<DB::BackgroundSchedulePoolTaskHolder>(std::move(reconnect_task_holder));
|
||||
(*reconnect_task)->activate();
|
||||
(*reconnect_task)->scheduleAfter(reconnect_timeout_sec * 1000);
|
||||
}
|
||||
}
|
||||
else if (args.implementation == "testkeeper")
|
||||
{
|
||||
@ -152,29 +205,53 @@ void ZooKeeper::init(ZooKeeperArgs args_)
|
||||
}
|
||||
}
|
||||
|
||||
ZooKeeper::~ZooKeeper()
|
||||
{
|
||||
if (reconnect_task)
|
||||
(*reconnect_task)->deactivate();
|
||||
}
|
||||
|
||||
ZooKeeper::ZooKeeper(const ZooKeeperArgs & args_, std::shared_ptr<DB::ZooKeeperLog> zk_log_)
|
||||
: zk_log(std::move(zk_log_))
|
||||
{
|
||||
init(args_);
|
||||
init(args_, /*existing_impl*/ {});
|
||||
}
|
||||
|
||||
|
||||
ZooKeeper::ZooKeeper(const ZooKeeperArgs & args_, std::shared_ptr<DB::ZooKeeperLog> zk_log_, Strings availability_zones_, std::unique_ptr<Coordination::IKeeper> existing_impl)
|
||||
: availability_zones(std::move(availability_zones_)), zk_log(std::move(zk_log_))
|
||||
{
|
||||
if (availability_zones.size() != args_.hosts.size())
|
||||
throw DB::Exception(DB::ErrorCodes::LOGICAL_ERROR, "Argument sizes mismatch: availability_zones count {} and hosts count {}",
|
||||
availability_zones.size(), args_.hosts.size());
|
||||
init(args_, std::move(existing_impl));
|
||||
}
|
||||
|
||||
|
||||
ZooKeeper::ZooKeeper(const Poco::Util::AbstractConfiguration & config, const std::string & config_name, std::shared_ptr<DB::ZooKeeperLog> zk_log_)
|
||||
: zk_log(std::move(zk_log_))
|
||||
{
|
||||
init(ZooKeeperArgs(config, config_name));
|
||||
init(ZooKeeperArgs(config, config_name), /*existing_impl*/ {});
|
||||
}
|
||||
|
||||
std::vector<ShuffleHost> ZooKeeper::shuffleHosts() const
|
||||
ShuffleHosts ZooKeeper::shuffleHosts() const
|
||||
{
|
||||
std::function<Priority(size_t index)> get_priority = args.get_priority_load_balancing.getPriorityFunc(args.get_priority_load_balancing.load_balancing, 0, args.hosts.size());
|
||||
std::vector<ShuffleHost> shuffle_hosts;
|
||||
std::function<Priority(size_t index)> get_priority = args.get_priority_load_balancing.getPriorityFunc(
|
||||
args.get_priority_load_balancing.load_balancing, /* offset for first_or_random */ 0, args.hosts.size());
|
||||
ShuffleHosts shuffle_hosts;
|
||||
for (size_t i = 0; i < args.hosts.size(); ++i)
|
||||
{
|
||||
ShuffleHost shuffle_host;
|
||||
shuffle_host.host = args.hosts[i];
|
||||
shuffle_host.original_index = static_cast<UInt8>(i);
|
||||
|
||||
shuffle_host.secure = startsWith(shuffle_host.host, "secure://");
|
||||
if (shuffle_host.secure)
|
||||
shuffle_host.host.erase(0, strlen("secure://"));
|
||||
|
||||
if (!args.client_availability_zone.empty() && !availability_zones[i].empty())
|
||||
shuffle_host.az_info = availability_zones[i] == args.client_availability_zone ? ShuffleHost::SAME : ShuffleHost::OTHER;
|
||||
|
||||
if (get_priority)
|
||||
shuffle_host.priority = get_priority(i);
|
||||
shuffle_host.randomize();
|
||||
@ -1023,7 +1100,10 @@ ZooKeeperPtr ZooKeeper::create(const Poco::Util::AbstractConfiguration & config,
|
||||
|
||||
ZooKeeperPtr ZooKeeper::startNewSession() const
|
||||
{
|
||||
auto res = std::shared_ptr<ZooKeeper>(new ZooKeeper(args, zk_log));
|
||||
if (reconnect_task)
|
||||
(*reconnect_task)->deactivate();
|
||||
|
||||
auto res = std::shared_ptr<ZooKeeper>(new ZooKeeper(args, zk_log, availability_zones, std::move(optimal_impl)));
|
||||
res->initSession();
|
||||
return res;
|
||||
}
|
||||
@ -1456,6 +1536,16 @@ int32_t ZooKeeper::getConnectionXid() const
|
||||
return impl->getConnectionXid();
|
||||
}
|
||||
|
||||
String ZooKeeper::getConnectedHostAvailabilityZone() const
|
||||
{
|
||||
if (args.implementation != "zookeeper" || !impl)
|
||||
return "";
|
||||
Int8 idx = impl->getConnectedNodeIdx();
|
||||
if (idx < 0)
|
||||
return ""; /// session expired
|
||||
return availability_zones.at(idx);
|
||||
}
|
||||
|
||||
size_t getFailedOpIndex(Coordination::Error exception_code, const Coordination::Responses & responses)
|
||||
{
|
||||
if (responses.empty())
|
||||
|
@ -32,6 +32,7 @@ namespace DB
|
||||
{
|
||||
class ZooKeeperLog;
|
||||
class ZooKeeperWithFaultInjection;
|
||||
class BackgroundSchedulePoolTaskHolder;
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
@ -48,11 +49,23 @@ constexpr size_t MULTI_BATCH_SIZE = 100;
|
||||
|
||||
struct ShuffleHost
|
||||
{
|
||||
enum AvailabilityZoneInfo
|
||||
{
|
||||
SAME = 0,
|
||||
UNKNOWN = 1,
|
||||
OTHER = 2,
|
||||
};
|
||||
|
||||
String host;
|
||||
bool secure = false;
|
||||
UInt8 original_index = 0;
|
||||
AvailabilityZoneInfo az_info = UNKNOWN;
|
||||
Priority priority;
|
||||
UInt64 random = 0;
|
||||
|
||||
/// We should resolve it each time without caching
|
||||
mutable std::optional<Poco::Net::SocketAddress> address;
|
||||
|
||||
void randomize()
|
||||
{
|
||||
random = thread_local_rng();
|
||||
@ -60,11 +73,13 @@ struct ShuffleHost
|
||||
|
||||
static bool compare(const ShuffleHost & lhs, const ShuffleHost & rhs)
|
||||
{
|
||||
return std::forward_as_tuple(lhs.priority, lhs.random)
|
||||
< std::forward_as_tuple(rhs.priority, rhs.random);
|
||||
return std::forward_as_tuple(lhs.az_info, lhs.priority, lhs.random)
|
||||
< std::forward_as_tuple(rhs.az_info, rhs.priority, rhs.random);
|
||||
}
|
||||
};
|
||||
|
||||
using ShuffleHosts = std::vector<ShuffleHost>;
|
||||
|
||||
struct RemoveException
|
||||
{
|
||||
explicit RemoveException(std::string_view path_ = "", bool remove_subtree_ = true)
|
||||
@ -197,6 +212,9 @@ class ZooKeeper
|
||||
|
||||
explicit ZooKeeper(const ZooKeeperArgs & args_, std::shared_ptr<DB::ZooKeeperLog> zk_log_ = nullptr);
|
||||
|
||||
/// Allows to keep info about availability zones when starting a new session
|
||||
ZooKeeper(const ZooKeeperArgs & args_, std::shared_ptr<DB::ZooKeeperLog> zk_log_, Strings availability_zones_, std::unique_ptr<Coordination::IKeeper> existing_impl);
|
||||
|
||||
/** Config of the form:
|
||||
<zookeeper>
|
||||
<node>
|
||||
@ -228,7 +246,9 @@ public:
|
||||
using Ptr = std::shared_ptr<ZooKeeper>;
|
||||
using ErrorsList = std::initializer_list<Coordination::Error>;
|
||||
|
||||
std::vector<ShuffleHost> shuffleHosts() const;
|
||||
~ZooKeeper();
|
||||
|
||||
ShuffleHosts shuffleHosts() const;
|
||||
|
||||
static Ptr create(const Poco::Util::AbstractConfiguration & config,
|
||||
const std::string & config_name,
|
||||
@ -596,8 +616,6 @@ public:
|
||||
|
||||
UInt32 getSessionUptime() const { return static_cast<UInt32>(session_uptime.elapsedSeconds()); }
|
||||
|
||||
bool hasReachedDeadline() const { return impl->hasReachedDeadline(); }
|
||||
|
||||
uint64_t getSessionTimeoutMS() const { return args.session_timeout_ms; }
|
||||
|
||||
void setServerCompletelyStarted();
|
||||
@ -606,6 +624,8 @@ public:
|
||||
String getConnectedHostPort() const;
|
||||
int32_t getConnectionXid() const;
|
||||
|
||||
String getConnectedHostAvailabilityZone() const;
|
||||
|
||||
const DB::KeeperFeatureFlags * getKeeperFeatureFlags() const { return impl->getKeeperFeatureFlags(); }
|
||||
|
||||
/// Checks that our session was not killed, and allows to avoid applying a request from an old lost session.
|
||||
@ -625,7 +645,8 @@ public:
|
||||
void addCheckSessionOp(Coordination::Requests & requests) const;
|
||||
|
||||
private:
|
||||
void init(ZooKeeperArgs args_);
|
||||
void init(ZooKeeperArgs args_, std::unique_ptr<Coordination::IKeeper> existing_impl);
|
||||
void updateAvailabilityZones();
|
||||
|
||||
/// The following methods don't any throw exceptions but return error codes.
|
||||
Coordination::Error createImpl(const std::string & path, const std::string & data, int32_t mode, std::string & path_created);
|
||||
@ -690,15 +711,20 @@ private:
|
||||
}
|
||||
|
||||
std::unique_ptr<Coordination::IKeeper> impl;
|
||||
mutable std::unique_ptr<Coordination::IKeeper> optimal_impl;
|
||||
|
||||
ZooKeeperArgs args;
|
||||
|
||||
Strings availability_zones;
|
||||
|
||||
LoggerPtr log = nullptr;
|
||||
std::shared_ptr<DB::ZooKeeperLog> zk_log;
|
||||
|
||||
AtomicStopwatch session_uptime;
|
||||
|
||||
int32_t session_node_version;
|
||||
|
||||
std::unique_ptr<DB::BackgroundSchedulePoolTaskHolder> reconnect_task;
|
||||
};
|
||||
|
||||
|
||||
|
@ -5,6 +5,9 @@
|
||||
#include <Poco/Util/AbstractConfiguration.h>
|
||||
#include <Common/isLocalAddress.h>
|
||||
#include <Common/StringUtils.h>
|
||||
#include <Common/thread_local_rng.h>
|
||||
#include <Server/CloudPlacementInfo.h>
|
||||
#include <IO/S3/Credentials.h>
|
||||
#include <Poco/String.h>
|
||||
|
||||
namespace DB
|
||||
@ -53,6 +56,7 @@ ZooKeeperArgs::ZooKeeperArgs(const Poco::Util::AbstractConfiguration & config, c
|
||||
ZooKeeperArgs::ZooKeeperArgs(const String & hosts_string)
|
||||
{
|
||||
splitInto<','>(hosts, hosts_string);
|
||||
availability_zones.resize(hosts.size());
|
||||
}
|
||||
|
||||
void ZooKeeperArgs::initFromKeeperServerSection(const Poco::Util::AbstractConfiguration & config)
|
||||
@ -103,8 +107,11 @@ void ZooKeeperArgs::initFromKeeperServerSection(const Poco::Util::AbstractConfig
|
||||
for (const auto & key : keys)
|
||||
{
|
||||
if (startsWith(key, "server"))
|
||||
{
|
||||
hosts.push_back(
|
||||
(secure ? "secure://" : "") + config.getString(raft_configuration_key + "." + key + ".hostname") + ":" + tcp_port);
|
||||
availability_zones.push_back(config.getString(raft_configuration_key + "." + key + ".availability_zone", ""));
|
||||
}
|
||||
}
|
||||
|
||||
static constexpr std::array load_balancing_keys
|
||||
@ -123,11 +130,15 @@ void ZooKeeperArgs::initFromKeeperServerSection(const Poco::Util::AbstractConfig
|
||||
auto load_balancing = magic_enum::enum_cast<DB::LoadBalancing>(Poco::toUpper(load_balancing_str));
|
||||
if (!load_balancing)
|
||||
throw DB::Exception(DB::ErrorCodes::BAD_ARGUMENTS, "Unknown load balancing: {}", load_balancing_str);
|
||||
get_priority_load_balancing.load_balancing = *load_balancing;
|
||||
get_priority_load_balancing = DB::GetPriorityForLoadBalancing(*load_balancing, thread_local_rng() % hosts.size());
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
availability_zone_autodetect = config.getBool(std::string{config_name} + ".availability_zone_autodetect", false);
|
||||
prefer_local_availability_zone = config.getBool(std::string{config_name} + ".prefer_local_availability_zone", false);
|
||||
if (prefer_local_availability_zone)
|
||||
client_availability_zone = DB::PlacementInfo::PlacementInfo::instance().getAvailabilityZone();
|
||||
}
|
||||
|
||||
void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguration & config, const std::string & config_name)
|
||||
@ -137,6 +148,8 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
|
||||
Poco::Util::AbstractConfiguration::Keys keys;
|
||||
config.keys(config_name, keys);
|
||||
|
||||
std::optional<DB::LoadBalancing> load_balancing;
|
||||
|
||||
for (const auto & key : keys)
|
||||
{
|
||||
if (key.starts_with("node"))
|
||||
@ -144,6 +157,7 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
|
||||
hosts.push_back(
|
||||
(config.getBool(config_name + "." + key + ".secure", false) ? "secure://" : "")
|
||||
+ config.getString(config_name + "." + key + ".host") + ":" + config.getString(config_name + "." + key + ".port", "2181"));
|
||||
availability_zones.push_back(config.getString(config_name + "." + key + ".availability_zone", ""));
|
||||
}
|
||||
else if (key == "session_timeout_ms")
|
||||
{
|
||||
@ -199,6 +213,10 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
|
||||
{
|
||||
sessions_path = config.getString(config_name + "." + key);
|
||||
}
|
||||
else if (key == "prefer_local_availability_zone")
|
||||
{
|
||||
prefer_local_availability_zone = config.getBool(config_name + "." + key);
|
||||
}
|
||||
else if (key == "implementation")
|
||||
{
|
||||
implementation = config.getString(config_name + "." + key);
|
||||
@ -207,10 +225,9 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
|
||||
{
|
||||
String load_balancing_str = config.getString(config_name + "." + key);
|
||||
/// Use magic_enum to avoid dependency from dbms (`SettingFieldLoadBalancingTraits::fromString(...)`)
|
||||
auto load_balancing = magic_enum::enum_cast<DB::LoadBalancing>(Poco::toUpper(load_balancing_str));
|
||||
load_balancing = magic_enum::enum_cast<DB::LoadBalancing>(Poco::toUpper(load_balancing_str));
|
||||
if (!load_balancing)
|
||||
throw DB::Exception(DB::ErrorCodes::BAD_ARGUMENTS, "Unknown load balancing: {}", load_balancing_str);
|
||||
get_priority_load_balancing.load_balancing = *load_balancing;
|
||||
}
|
||||
else if (key == "fallback_session_lifetime")
|
||||
{
|
||||
@ -224,9 +241,19 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
|
||||
{
|
||||
use_compression = config.getBool(config_name + "." + key);
|
||||
}
|
||||
else if (key == "availability_zone_autodetect")
|
||||
{
|
||||
availability_zone_autodetect = config.getBool(config_name + "." + key);
|
||||
}
|
||||
else
|
||||
throw KeeperException(Coordination::Error::ZBADARGUMENTS, "Unknown key {} in config file", key);
|
||||
}
|
||||
|
||||
if (load_balancing)
|
||||
get_priority_load_balancing = DB::GetPriorityForLoadBalancing(*load_balancing, thread_local_rng() % hosts.size());
|
||||
|
||||
if (prefer_local_availability_zone)
|
||||
client_availability_zone = DB::PlacementInfo::PlacementInfo::instance().getAvailabilityZone();
|
||||
}
|
||||
|
||||
}
|
||||
|
@ -32,10 +32,12 @@ struct ZooKeeperArgs
|
||||
String zookeeper_name = "zookeeper";
|
||||
String implementation = "zookeeper";
|
||||
Strings hosts;
|
||||
Strings availability_zones;
|
||||
String auth_scheme;
|
||||
String identity;
|
||||
String chroot;
|
||||
String sessions_path = "/clickhouse/sessions";
|
||||
String client_availability_zone;
|
||||
int32_t connection_timeout_ms = Coordination::DEFAULT_CONNECTION_TIMEOUT_MS;
|
||||
int32_t session_timeout_ms = Coordination::DEFAULT_SESSION_TIMEOUT_MS;
|
||||
int32_t operation_timeout_ms = Coordination::DEFAULT_OPERATION_TIMEOUT_MS;
|
||||
@ -47,6 +49,8 @@ struct ZooKeeperArgs
|
||||
UInt64 send_sleep_ms = 0;
|
||||
UInt64 recv_sleep_ms = 0;
|
||||
bool use_compression = false;
|
||||
bool prefer_local_availability_zone = false;
|
||||
bool availability_zone_autodetect = false;
|
||||
|
||||
SessionLifetimeConfiguration fallback_session_lifetime = {};
|
||||
DB::GetPriorityForLoadBalancing get_priority_load_balancing;
|
||||
|
@ -23,6 +23,9 @@
|
||||
#include <Common/setThreadName.h>
|
||||
#include <Common/thread_local_rng.h>
|
||||
|
||||
#include <Poco/Net/NetException.h>
|
||||
#include <Poco/Net/DNS.h>
|
||||
|
||||
#include "Coordination/KeeperConstants.h"
|
||||
#include "config.h"
|
||||
|
||||
@ -338,7 +341,7 @@ ZooKeeper::~ZooKeeper()
|
||||
|
||||
|
||||
ZooKeeper::ZooKeeper(
|
||||
const Nodes & nodes,
|
||||
const zkutil::ShuffleHosts & nodes,
|
||||
const zkutil::ZooKeeperArgs & args_,
|
||||
std::shared_ptr<ZooKeeperLog> zk_log_)
|
||||
: args(args_)
|
||||
@ -426,7 +429,7 @@ ZooKeeper::ZooKeeper(
|
||||
|
||||
|
||||
void ZooKeeper::connect(
|
||||
const Nodes & nodes,
|
||||
const zkutil::ShuffleHosts & nodes,
|
||||
Poco::Timespan connection_timeout)
|
||||
{
|
||||
if (nodes.empty())
|
||||
@ -434,15 +437,51 @@ void ZooKeeper::connect(
|
||||
|
||||
static constexpr size_t num_tries = 3;
|
||||
bool connected = false;
|
||||
bool dns_error = false;
|
||||
|
||||
size_t resolved_count = 0;
|
||||
for (const auto & node : nodes)
|
||||
{
|
||||
try
|
||||
{
|
||||
const Poco::Net::SocketAddress host_socket_addr{node.host};
|
||||
LOG_TRACE(log, "Adding ZooKeeper host {} ({}), az: {}, priority: {}", node.host, host_socket_addr.toString(), node.az_info, node.priority);
|
||||
node.address = host_socket_addr;
|
||||
++resolved_count;
|
||||
}
|
||||
catch (const Poco::Net::HostNotFoundException & e)
|
||||
{
|
||||
/// Most likely it's misconfiguration and wrong hostname was specified
|
||||
LOG_ERROR(log, "Cannot use ZooKeeper host {}, reason: {}", node.host, e.displayText());
|
||||
}
|
||||
catch (const Poco::Net::DNSException & e)
|
||||
{
|
||||
/// Most likely DNS is not available now
|
||||
dns_error = true;
|
||||
LOG_ERROR(log, "Cannot use ZooKeeper host {} due to DNS error: {}", node.host, e.displayText());
|
||||
}
|
||||
}
|
||||
|
||||
if (resolved_count == 0)
|
||||
{
|
||||
/// For DNS errors we throw exception with ZCONNECTIONLOSS code, so it will be considered as hardware error, not user error
|
||||
if (dns_error)
|
||||
throw zkutil::KeeperException::fromMessage(
|
||||
Coordination::Error::ZCONNECTIONLOSS, "Cannot resolve any of provided ZooKeeper hosts due to DNS error");
|
||||
else
|
||||
throw zkutil::KeeperException::fromMessage(Coordination::Error::ZCONNECTIONLOSS, "Cannot use any of provided ZooKeeper nodes");
|
||||
}
|
||||
|
||||
WriteBufferFromOwnString fail_reasons;
|
||||
for (size_t try_no = 0; try_no < num_tries; ++try_no)
|
||||
{
|
||||
for (size_t i = 0; i < nodes.size(); ++i)
|
||||
for (const auto & node : nodes)
|
||||
{
|
||||
const auto & node = nodes[i];
|
||||
try
|
||||
{
|
||||
if (!node.address)
|
||||
continue;
|
||||
|
||||
/// Reset the state of previous attempt.
|
||||
if (node.secure)
|
||||
{
|
||||
@ -458,7 +497,7 @@ void ZooKeeper::connect(
|
||||
socket = Poco::Net::StreamSocket();
|
||||
}
|
||||
|
||||
socket.connect(node.address, connection_timeout);
|
||||
socket.connect(*node.address, connection_timeout);
|
||||
socket_address = socket.peerAddress();
|
||||
|
||||
socket.setReceiveTimeout(args.operation_timeout_ms * 1000);
|
||||
@ -498,27 +537,11 @@ void ZooKeeper::connect(
|
||||
}
|
||||
|
||||
original_index = static_cast<Int8>(node.original_index);
|
||||
|
||||
if (i != 0)
|
||||
{
|
||||
std::uniform_int_distribution<UInt32> fallback_session_lifetime_distribution
|
||||
{
|
||||
args.fallback_session_lifetime.min_sec,
|
||||
args.fallback_session_lifetime.max_sec,
|
||||
};
|
||||
UInt32 session_lifetime_seconds = fallback_session_lifetime_distribution(thread_local_rng);
|
||||
client_session_deadline = clock::now() + std::chrono::seconds(session_lifetime_seconds);
|
||||
|
||||
LOG_DEBUG(log, "Connected to a suboptimal ZooKeeper host ({}, index {})."
|
||||
" To preserve balance in ZooKeeper usage, this ZooKeeper session will expire in {} seconds",
|
||||
node.address.toString(), i, session_lifetime_seconds);
|
||||
}
|
||||
|
||||
break;
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
fail_reasons << "\n" << getCurrentExceptionMessage(false) << ", " << node.address.toString();
|
||||
fail_reasons << "\n" << getCurrentExceptionMessage(false) << ", " << node.address->toString();
|
||||
}
|
||||
}
|
||||
|
||||
@ -532,6 +555,9 @@ void ZooKeeper::connect(
|
||||
bool first = true;
|
||||
for (const auto & node : nodes)
|
||||
{
|
||||
if (!node.address)
|
||||
continue;
|
||||
|
||||
if (first)
|
||||
first = false;
|
||||
else
|
||||
@ -540,7 +566,7 @@ void ZooKeeper::connect(
|
||||
if (node.secure)
|
||||
message << "secure://";
|
||||
|
||||
message << node.address.toString();
|
||||
message << node.address->toString();
|
||||
}
|
||||
|
||||
message << fail_reasons.str() << "\n";
|
||||
@ -1153,7 +1179,6 @@ void ZooKeeper::pushRequest(RequestInfo && info)
|
||||
{
|
||||
try
|
||||
{
|
||||
checkSessionDeadline();
|
||||
info.time = clock::now();
|
||||
auto maybe_zk_log = std::atomic_load(&zk_log);
|
||||
if (maybe_zk_log)
|
||||
@ -1201,44 +1226,44 @@ bool ZooKeeper::isFeatureEnabled(KeeperFeatureFlag feature_flag) const
|
||||
return keeper_feature_flags.isEnabled(feature_flag);
|
||||
}
|
||||
|
||||
void ZooKeeper::initFeatureFlags()
|
||||
std::optional<String> ZooKeeper::tryGetSystemZnode(const std::string & path, const std::string & description)
|
||||
{
|
||||
const auto try_get = [&](const std::string & path, const std::string & description) -> std::optional<std::string>
|
||||
auto promise = std::make_shared<std::promise<Coordination::GetResponse>>();
|
||||
auto future = promise->get_future();
|
||||
|
||||
auto callback = [promise](const Coordination::GetResponse & response) mutable
|
||||
{
|
||||
auto promise = std::make_shared<std::promise<Coordination::GetResponse>>();
|
||||
auto future = promise->get_future();
|
||||
|
||||
auto callback = [promise](const Coordination::GetResponse & response) mutable
|
||||
{
|
||||
promise->set_value(response);
|
||||
};
|
||||
|
||||
get(path, std::move(callback), {});
|
||||
if (future.wait_for(std::chrono::milliseconds(args.operation_timeout_ms)) != std::future_status::ready)
|
||||
throw Exception(Error::ZOPERATIONTIMEOUT, "Failed to get {}: timeout", description);
|
||||
|
||||
auto response = future.get();
|
||||
|
||||
if (response.error == Coordination::Error::ZNONODE)
|
||||
{
|
||||
LOG_TRACE(log, "Failed to get {}", description);
|
||||
return std::nullopt;
|
||||
}
|
||||
else if (response.error != Coordination::Error::ZOK)
|
||||
{
|
||||
throw Exception(response.error, "Failed to get {}", description);
|
||||
}
|
||||
|
||||
return std::move(response.data);
|
||||
promise->set_value(response);
|
||||
};
|
||||
|
||||
if (auto feature_flags = try_get(keeper_api_feature_flags_path, "feature flags"); feature_flags.has_value())
|
||||
get(path, std::move(callback), {});
|
||||
if (future.wait_for(std::chrono::milliseconds(args.operation_timeout_ms)) != std::future_status::ready)
|
||||
throw Exception(Error::ZOPERATIONTIMEOUT, "Failed to get {}: timeout", description);
|
||||
|
||||
auto response = future.get();
|
||||
|
||||
if (response.error == Coordination::Error::ZNONODE)
|
||||
{
|
||||
LOG_TRACE(log, "Failed to get {}", description);
|
||||
return std::nullopt;
|
||||
}
|
||||
else if (response.error != Coordination::Error::ZOK)
|
||||
{
|
||||
throw Exception(response.error, "Failed to get {}", description);
|
||||
}
|
||||
|
||||
return std::move(response.data);
|
||||
}
|
||||
|
||||
void ZooKeeper::initFeatureFlags()
|
||||
{
|
||||
if (auto feature_flags = tryGetSystemZnode(keeper_api_feature_flags_path, "feature flags"); feature_flags.has_value())
|
||||
{
|
||||
keeper_feature_flags.setFeatureFlags(std::move(*feature_flags));
|
||||
return;
|
||||
}
|
||||
|
||||
auto keeper_api_version_string = try_get(keeper_api_version_path, "API version");
|
||||
auto keeper_api_version_string = tryGetSystemZnode(keeper_api_version_path, "API version");
|
||||
|
||||
DB::KeeperApiVersion keeper_api_version{DB::KeeperApiVersion::ZOOKEEPER_COMPATIBLE};
|
||||
|
||||
@ -1256,6 +1281,17 @@ void ZooKeeper::initFeatureFlags()
|
||||
keeper_feature_flags.fromApiVersion(keeper_api_version);
|
||||
}
|
||||
|
||||
String ZooKeeper::tryGetAvailabilityZone()
|
||||
{
|
||||
auto res = tryGetSystemZnode(keeper_availability_zone_path, "availability zone");
|
||||
if (res)
|
||||
{
|
||||
LOG_TRACE(log, "Availability zone for ZooKeeper at {}: {}", getConnectedHostPort(), *res);
|
||||
return *res;
|
||||
}
|
||||
return "";
|
||||
}
|
||||
|
||||
|
||||
void ZooKeeper::executeGenericRequest(
|
||||
const ZooKeeperRequestPtr & request,
|
||||
@ -1587,17 +1623,6 @@ void ZooKeeper::setupFaultDistributions()
|
||||
inject_setup.test_and_set();
|
||||
}
|
||||
|
||||
void ZooKeeper::checkSessionDeadline() const
|
||||
{
|
||||
if (unlikely(hasReachedDeadline()))
|
||||
throw Exception::fromMessage(Error::ZSESSIONEXPIRED, "Session expired (force expiry client-side)");
|
||||
}
|
||||
|
||||
bool ZooKeeper::hasReachedDeadline() const
|
||||
{
|
||||
return client_session_deadline.has_value() && clock::now() >= client_session_deadline.value();
|
||||
}
|
||||
|
||||
void ZooKeeper::maybeInjectSendFault()
|
||||
{
|
||||
if (unlikely(inject_setup.test() && send_inject_fault && send_inject_fault.value()(thread_local_rng)))
|
||||
|
@ -8,6 +8,7 @@
|
||||
#include <Common/ZooKeeper/IKeeper.h>
|
||||
#include <Common/ZooKeeper/ZooKeeperCommon.h>
|
||||
#include <Common/ZooKeeper/ZooKeeperArgs.h>
|
||||
#include <Common/ZooKeeper/ZooKeeper.h>
|
||||
#include <Coordination/KeeperConstants.h>
|
||||
#include <Coordination/KeeperFeatureFlags.h>
|
||||
|
||||
@ -102,21 +103,12 @@ using namespace DB;
|
||||
class ZooKeeper final : public IKeeper
|
||||
{
|
||||
public:
|
||||
struct Node
|
||||
{
|
||||
Poco::Net::SocketAddress address;
|
||||
UInt8 original_index;
|
||||
bool secure;
|
||||
};
|
||||
|
||||
using Nodes = std::vector<Node>;
|
||||
|
||||
/** Connection to nodes is performed in order. If you want, shuffle them manually.
|
||||
* Operation timeout couldn't be greater than session timeout.
|
||||
* Operation timeout applies independently for network read, network write, waiting for events and synchronization.
|
||||
*/
|
||||
ZooKeeper(
|
||||
const Nodes & nodes,
|
||||
const zkutil::ShuffleHosts & nodes,
|
||||
const zkutil::ZooKeeperArgs & args_,
|
||||
std::shared_ptr<ZooKeeperLog> zk_log_);
|
||||
|
||||
@ -130,9 +122,7 @@ public:
|
||||
String getConnectedHostPort() const override { return (original_index == -1) ? "" : args.hosts[original_index]; }
|
||||
int32_t getConnectionXid() const override { return next_xid.load(); }
|
||||
|
||||
/// A ZooKeeper session can have an optional deadline set on it.
|
||||
/// After it has been reached, the session needs to be finalized.
|
||||
bool hasReachedDeadline() const override;
|
||||
String tryGetAvailabilityZone() override;
|
||||
|
||||
/// Useful to check owner of ephemeral node.
|
||||
int64_t getSessionID() const override { return session_id; }
|
||||
@ -271,7 +261,6 @@ private:
|
||||
clock::time_point time;
|
||||
};
|
||||
|
||||
std::optional<clock::time_point> client_session_deadline {};
|
||||
using RequestsQueue = ConcurrentBoundedQueue<RequestInfo>;
|
||||
|
||||
RequestsQueue requests_queue{1024};
|
||||
@ -316,7 +305,7 @@ private:
|
||||
LoggerPtr log;
|
||||
|
||||
void connect(
|
||||
const Nodes & node,
|
||||
const zkutil::ShuffleHosts & node,
|
||||
Poco::Timespan connection_timeout);
|
||||
|
||||
void sendHandshake();
|
||||
@ -346,9 +335,10 @@ private:
|
||||
|
||||
void logOperationIfNeeded(const ZooKeeperRequestPtr & request, const ZooKeeperResponsePtr & response = nullptr, bool finalize = false, UInt64 elapsed_microseconds = 0);
|
||||
|
||||
std::optional<String> tryGetSystemZnode(const std::string & path, const std::string & description);
|
||||
|
||||
void initFeatureFlags();
|
||||
|
||||
void checkSessionDeadline() const;
|
||||
|
||||
CurrentMetrics::Increment active_session_metric_increment{CurrentMetrics::ZooKeeperSession};
|
||||
std::shared_ptr<ZooKeeperLog> zk_log;
|
||||
|
@ -1,15 +1,18 @@
|
||||
clickhouse_add_executable(zkutil_test_commands zkutil_test_commands.cpp)
|
||||
target_link_libraries(zkutil_test_commands PRIVATE
|
||||
clickhouse_common_zookeeper_no_log
|
||||
clickhouse_functions
|
||||
dbms)
|
||||
|
||||
clickhouse_add_executable(zkutil_test_commands_new_lib zkutil_test_commands_new_lib.cpp)
|
||||
target_link_libraries(zkutil_test_commands_new_lib PRIVATE
|
||||
clickhouse_common_zookeeper_no_log
|
||||
clickhouse_compression
|
||||
clickhouse_functions
|
||||
dbms)
|
||||
|
||||
clickhouse_add_executable(zkutil_test_async zkutil_test_async.cpp)
|
||||
target_link_libraries(zkutil_test_async PRIVATE
|
||||
clickhouse_common_zookeeper_no_log
|
||||
clickhouse_functions
|
||||
dbms)
|
||||
|
@ -25,24 +25,24 @@ try
|
||||
Poco::Logger::root().setChannel(channel);
|
||||
Poco::Logger::root().setLevel("trace");
|
||||
|
||||
std::string hosts_arg = argv[1];
|
||||
std::vector<std::string> hosts_strings;
|
||||
splitInto<','>(hosts_strings, hosts_arg);
|
||||
ZooKeeper::Nodes nodes;
|
||||
nodes.reserve(hosts_strings.size());
|
||||
for (size_t i = 0; i < hosts_strings.size(); ++i)
|
||||
zkutil::ZooKeeperArgs args{argv[1]};
|
||||
zkutil::ShuffleHosts nodes;
|
||||
nodes.reserve(args.hosts.size());
|
||||
for (size_t i = 0; i < args.hosts.size(); ++i)
|
||||
{
|
||||
std::string host_string = hosts_strings[i];
|
||||
bool secure = startsWith(host_string, "secure://");
|
||||
zkutil::ShuffleHost node;
|
||||
std::string host_string = args.hosts[i];
|
||||
node.secure = startsWith(host_string, "secure://");
|
||||
|
||||
if (secure)
|
||||
if (node.secure)
|
||||
host_string.erase(0, strlen("secure://"));
|
||||
|
||||
nodes.emplace_back(ZooKeeper::Node{Poco::Net::SocketAddress{host_string}, static_cast<UInt8>(i) , secure});
|
||||
node.host = host_string;
|
||||
node.original_index = i;
|
||||
|
||||
nodes.emplace_back(node);
|
||||
}
|
||||
|
||||
|
||||
zkutil::ZooKeeperArgs args;
|
||||
ZooKeeper zk(nodes, args, nullptr);
|
||||
|
||||
Poco::Event event(true);
|
||||
|
@ -11,10 +11,10 @@ clickhouse_add_executable (small_table small_table.cpp)
|
||||
target_link_libraries (small_table PRIVATE clickhouse_common_io)
|
||||
|
||||
clickhouse_add_executable (parallel_aggregation parallel_aggregation.cpp)
|
||||
target_link_libraries (parallel_aggregation PRIVATE dbms)
|
||||
target_link_libraries (parallel_aggregation PRIVATE dbms clickhouse_functions)
|
||||
|
||||
clickhouse_add_executable (parallel_aggregation2 parallel_aggregation2.cpp)
|
||||
target_link_libraries (parallel_aggregation2 PRIVATE dbms)
|
||||
target_link_libraries (parallel_aggregation2 PRIVATE dbms clickhouse_functions)
|
||||
|
||||
clickhouse_add_executable (int_hashes_perf int_hashes_perf.cpp)
|
||||
target_link_libraries (int_hashes_perf PRIVATE clickhouse_common_io)
|
||||
@ -85,7 +85,7 @@ target_link_libraries (interval_tree PRIVATE dbms)
|
||||
|
||||
if (ENABLE_SSL)
|
||||
clickhouse_add_executable (encrypt_decrypt encrypt_decrypt.cpp)
|
||||
target_link_libraries (encrypt_decrypt PRIVATE dbms)
|
||||
target_link_libraries (encrypt_decrypt PRIVATE dbms clickhouse_functions)
|
||||
endif()
|
||||
|
||||
clickhouse_add_executable (check_pointer_valid check_pointer_valid.cpp)
|
||||
|
@ -57,14 +57,16 @@ void CompressedWriteBuffer::nextImpl()
|
||||
}
|
||||
}
|
||||
|
||||
CompressedWriteBuffer::~CompressedWriteBuffer()
|
||||
{
|
||||
finalize();
|
||||
}
|
||||
|
||||
CompressedWriteBuffer::CompressedWriteBuffer(WriteBuffer & out_, CompressionCodecPtr codec_, size_t buf_size)
|
||||
: BufferWithOwnMemory<WriteBuffer>(buf_size), out(out_), codec(std::move(codec_))
|
||||
{
|
||||
}
|
||||
|
||||
CompressedWriteBuffer::~CompressedWriteBuffer()
|
||||
{
|
||||
if (!canceled)
|
||||
finalize();
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
@ -90,13 +90,13 @@ static constexpr auto DEFAULT_UNCOMPRESSED_CACHE_POLICY = "SLRU";
|
||||
static constexpr auto DEFAULT_UNCOMPRESSED_CACHE_MAX_SIZE = 0_MiB;
|
||||
static constexpr auto DEFAULT_UNCOMPRESSED_CACHE_SIZE_RATIO = 0.5l;
|
||||
static constexpr auto DEFAULT_MARK_CACHE_POLICY = "SLRU";
|
||||
static constexpr auto DEFAULT_MARK_CACHE_MAX_SIZE = 5368_MiB;
|
||||
static constexpr auto DEFAULT_MARK_CACHE_MAX_SIZE = 5_GiB;
|
||||
static constexpr auto DEFAULT_MARK_CACHE_SIZE_RATIO = 0.5l;
|
||||
static constexpr auto DEFAULT_INDEX_UNCOMPRESSED_CACHE_POLICY = "SLRU";
|
||||
static constexpr auto DEFAULT_INDEX_UNCOMPRESSED_CACHE_MAX_SIZE = 0;
|
||||
static constexpr auto DEFAULT_INDEX_UNCOMPRESSED_CACHE_SIZE_RATIO = 0.5;
|
||||
static constexpr auto DEFAULT_INDEX_MARK_CACHE_POLICY = "SLRU";
|
||||
static constexpr auto DEFAULT_INDEX_MARK_CACHE_MAX_SIZE = 5368_MiB;
|
||||
static constexpr auto DEFAULT_INDEX_MARK_CACHE_MAX_SIZE = 5_GiB;
|
||||
static constexpr auto DEFAULT_INDEX_MARK_CACHE_SIZE_RATIO = 0.3;
|
||||
static constexpr auto DEFAULT_MMAP_CACHE_MAX_SIZE = 1_KiB; /// chosen by rolling dice
|
||||
static constexpr auto DEFAULT_COMPILED_EXPRESSION_CACHE_MAX_SIZE = 128_MiB;
|
||||
|
@ -63,6 +63,9 @@ const char USER_INTERSERVER_MARKER[] = " INTERSERVER SECRET ";
|
||||
/// Marker for SSH-keys-based authentication (passed as the user name)
|
||||
const char SSH_KEY_AUTHENTICAION_MARKER[] = " SSH KEY AUTHENTICATION ";
|
||||
|
||||
/// Market for JSON Web Token authentication
|
||||
const char JWT_AUTHENTICAION_MARKER[] = " JWT AUTHENTICATION ";
|
||||
|
||||
};
|
||||
|
||||
namespace Protocol
|
||||
|
@ -154,6 +154,7 @@ namespace DB
|
||||
M(String, merge_workload, "default", "Name of workload to be used to access resources for all merges (may be overridden by a merge tree setting)", 0) \
|
||||
M(String, mutation_workload, "default", "Name of workload to be used to access resources for all mutations (may be overridden by a merge tree setting)", 0) \
|
||||
M(Double, gwp_asan_force_sample_probability, 0, "Probability that an allocation from specific places will be sampled by GWP Asan (i.e. PODArray allocations)", 0) \
|
||||
M(UInt64, config_reload_interval_ms, 2000, "How often clickhouse will reload config and check for new changes", 0) \
|
||||
|
||||
/// If you add a setting which can be updated at runtime, please update 'changeable_settings' map in StorageSystemServerSettings.cpp
|
||||
|
||||
|
@ -470,7 +470,7 @@ class IColumn;
|
||||
M(UInt64, max_rows_in_join, 0, "Maximum size of the hash table for JOIN (in number of rows).", 0) \
|
||||
M(UInt64, max_bytes_in_join, 0, "Maximum size of the hash table for JOIN (in number of bytes in memory).", 0) \
|
||||
M(OverflowMode, join_overflow_mode, OverflowMode::THROW, "What to do when the limit is exceeded.", 0) \
|
||||
M(Bool, join_any_take_last_row, false, "When disabled (default) ANY JOIN will take the first found row for a key. When enabled, it will take the last row seen if there are multiple rows for the same key.", IMPORTANT) \
|
||||
M(Bool, join_any_take_last_row, false, "When disabled (default) ANY JOIN will take the first found row for a key. When enabled, it will take the last row seen if there are multiple rows for the same key. Can be applied only to hash join and storage join.", IMPORTANT) \
|
||||
M(JoinAlgorithm, join_algorithm, JoinAlgorithm::DEFAULT, "Specify join algorithm.", 0) \
|
||||
M(UInt64, cross_join_min_rows_to_compress, 10000000, "Minimal count of rows to compress block in CROSS JOIN. Zero value means - disable this threshold. This block is compressed when any of the two thresholds (by rows or by bytes) are reached.", 0) \
|
||||
M(UInt64, cross_join_min_bytes_to_compress, 1_GiB, "Minimal size of block to compress in CROSS JOIN. Zero value means - disable this threshold. This block is compressed when any of the two thresholds (by rows or by bytes) are reached.", 0) \
|
||||
@ -1092,6 +1092,7 @@ class IColumn;
|
||||
M(Bool, input_format_json_defaults_for_missing_elements_in_named_tuple, true, "Insert default value in named tuple element if it's missing in json object", 0) \
|
||||
M(Bool, input_format_json_throw_on_bad_escape_sequence, true, "Throw an exception if JSON string contains bad escape sequence in JSON input formats. If disabled, bad escape sequences will remain as is in the data", 0) \
|
||||
M(Bool, input_format_json_ignore_unnecessary_fields, true, "Ignore unnecessary fields and not parse them. Enabling this may not throw exceptions on json strings of invalid format or with duplicated fields", 0) \
|
||||
M(Bool, input_format_json_ignore_key_case, false, "Ignore json key case while read json field from string", 0) \
|
||||
M(Bool, input_format_try_infer_integers, true, "Try to infer integers instead of floats while schema inference in text formats", 0) \
|
||||
M(Bool, input_format_try_infer_dates, true, "Try to infer dates from string fields while schema inference in text formats", 0) \
|
||||
M(Bool, input_format_try_infer_datetimes, true, "Try to infer datetimes from string fields while schema inference in text formats", 0) \
|
||||
@ -1160,6 +1161,7 @@ class IColumn;
|
||||
M(Bool, output_format_parquet_parallel_encoding, true, "Do Parquet encoding in multiple threads. Requires output_format_parquet_use_custom_encoder.", 0) \
|
||||
M(UInt64, output_format_parquet_data_page_size, 1024 * 1024, "Target page size in bytes, before compression.", 0) \
|
||||
M(UInt64, output_format_parquet_batch_size, 1024, "Check page size every this many rows. Consider decreasing if you have columns with average values size above a few KBs.", 0) \
|
||||
M(Bool, output_format_parquet_write_page_index, true, "Add a possibility to write page index into parquet files.", 0) \
|
||||
M(String, output_format_avro_codec, "", "Compression codec used for output. Possible values: 'null', 'deflate', 'snappy', 'zstd'.", 0) \
|
||||
M(UInt64, output_format_avro_sync_interval, 16 * 1024, "Sync interval in bytes.", 0) \
|
||||
M(String, output_format_avro_string_column_pattern, "", "For Avro format: regexp of String columns to select as AVRO string.", 0) \
|
||||
|
@ -86,6 +86,8 @@ namespace SettingsChangesHistory
|
||||
/// It's used to implement `compatibility` setting (see https://github.com/ClickHouse/ClickHouse/issues/35972)
|
||||
static const std::map<ClickHouseVersion, SettingsChangesHistory::SettingsChanges> settings_changes_history =
|
||||
{
|
||||
{"24.7", {{"output_format_parquet_write_page_index", false, true, "Add a possibility to write page index into parquet files."},
|
||||
}},
|
||||
{"24.6", {{"materialize_skip_indexes_on_insert", true, true, "Added new setting to allow to disable materialization of skip indexes on insert"},
|
||||
{"materialize_statistics_on_insert", true, true, "Added new setting to allow to disable materialization of statistics on insert"},
|
||||
{"input_format_parquet_use_native_reader", false, false, "When reading Parquet files, to use native reader instead of arrow reader."},
|
||||
@ -115,6 +117,7 @@ static const std::map<ClickHouseVersion, SettingsChangesHistory::SettingsChanges
|
||||
{"output_format_csv_serialize_tuple_into_separate_columns", true, true, "A new way of how interpret tuples in CSV format was added."},
|
||||
{"input_format_csv_deserialize_separate_columns_into_tuple", true, true, "A new way of how interpret tuples in CSV format was added."},
|
||||
{"input_format_csv_try_infer_strings_from_quoted_tuples", true, true, "A new way of how interpret tuples in CSV format was added."},
|
||||
{"input_format_json_ignore_key_case", false, false, "Ignore json key case while read json field from string."},
|
||||
}},
|
||||
{"24.5", {{"allow_deprecated_error_prone_window_functions", true, false, "Allow usage of deprecated error prone window functions (neighbor, runningAccumulate, runningDifferenceStartingWithFirstValue, runningDifference)"},
|
||||
{"allow_experimental_join_condition", false, false, "Support join with inequal conditions which involve columns from both left and right table. e.g. t1.y < t2.y."},
|
||||
|
@ -201,13 +201,13 @@ IMPLEMENT_SETTING_ENUM(ORCCompression, ErrorCodes::BAD_ARGUMENTS,
|
||||
{"zlib", FormatSettings::ORCCompression::ZLIB},
|
||||
{"lz4", FormatSettings::ORCCompression::LZ4}})
|
||||
|
||||
IMPLEMENT_SETTING_ENUM(S3QueueMode, ErrorCodes::BAD_ARGUMENTS,
|
||||
{{"ordered", S3QueueMode::ORDERED},
|
||||
{"unordered", S3QueueMode::UNORDERED}})
|
||||
IMPLEMENT_SETTING_ENUM(ObjectStorageQueueMode, ErrorCodes::BAD_ARGUMENTS,
|
||||
{{"ordered", ObjectStorageQueueMode::ORDERED},
|
||||
{"unordered", ObjectStorageQueueMode::UNORDERED}})
|
||||
|
||||
IMPLEMENT_SETTING_ENUM(S3QueueAction, ErrorCodes::BAD_ARGUMENTS,
|
||||
{{"keep", S3QueueAction::KEEP},
|
||||
{"delete", S3QueueAction::DELETE}})
|
||||
IMPLEMENT_SETTING_ENUM(ObjectStorageQueueAction, ErrorCodes::BAD_ARGUMENTS,
|
||||
{{"keep", ObjectStorageQueueAction::KEEP},
|
||||
{"delete", ObjectStorageQueueAction::DELETE}})
|
||||
|
||||
IMPLEMENT_SETTING_ENUM(ExternalCommandStderrReaction, ErrorCodes::BAD_ARGUMENTS,
|
||||
{{"none", ExternalCommandStderrReaction::NONE},
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user