thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'ClickHouse/master' into patch-1

Browse Source
This commit is contained in:
Robert Schulze 2024-06-30 08:55:58 +00:00
commit c72ce5be8a
No known key found for this signature in database
GPG Key ID: 26703B55FB13728A
279 changed files with 3847 additions and 2184 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
.github/workflows/backport_branches.yml vendored
View File

@ -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
View 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
View File

@ -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
View File

@ -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
View File

@ -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
View File

@ -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
View File

@ -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)).

4
base/base/getFQDNOrHostName.cpp
View File

@ -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
}
}

2
contrib/jemalloc-cmake/CMakeLists.txt
View File

@ -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()

2
docs/en/development/developer-instruction.md
View File

@ -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.

2
docs/en/development/tests.md
View File

@ -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

9
docs/en/engines/table-engines/integrations/azureBlobStorage.md
View File

@ -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)

2
docs/en/engines/table-engines/integrations/s3queue.md
View File

@ -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).

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

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 162 KiB

394
docs/en/getting-started/example-datasets/stackoverflow.md Normal file
View File

@ -0,0 +1,394 @@
---
slug: /en/getting-started/example-datasets/stackoverflow
sidebar_label: Stack Overflow
sidebar_position: 1
description: Analyzing Stack Overflow data with ClickHouse
---
# Analyzing Stack Overflow data with ClickHouse
This dataset contains every `Post`, `User`, `Vote`, `Comment`, `Badge, `PostHistory`, and `PostLink` that has occurred on Stack Overflow.
Users can either download pre-prepared Parquet versions of the data, containing every post up to April 2024, or download the latest data in XML format and load this. Stack Overflow provide updates to this data periodically - historically every 3 months.
The following diagram shows the schema for the available tables assuming Parquet format.
![Stack Overflow schema](./images/stackoverflow.png)
A description of the schema of this data can be found [here](https://meta.stackexchange.com/questions/2677/database-schema-documentation-for-the-public-data-dump-and-sede).
## Pre-prepared data
We provide a copy of this data in Parquet format, up to date as of April 2024. While small for ClickHouse with respect to the number of rows (60 million posts), this dataset contains significant volumes of text and large String columns.
```sql
CREATE DATABASE stackoverflow
```
The following timings are for a 96 GiB, 24 vCPU ClickHouse Cloud cluster located in `eu-west-2`. The dataset is located in `eu-west-3`.
### Posts
```sql
CREATE TABLE stackoverflow.posts
(
`Id` Int32 CODEC(Delta(4), ZSTD(1)),
`PostTypeId` Enum8('Question' = 1, 'Answer' = 2, 'Wiki' = 3, 'TagWikiExcerpt' = 4, 'TagWiki' = 5, 'ModeratorNomination' = 6, 'WikiPlaceholder' = 7, 'PrivilegeWiki' = 8),
`AcceptedAnswerId` UInt32,
`CreationDate` DateTime64(3, 'UTC'),
`Score` Int32,
`ViewCount` UInt32 CODEC(Delta(4), ZSTD(1)),
`Body` String,
`OwnerUserId` Int32,
`OwnerDisplayName` String,
`LastEditorUserId` Int32,
`LastEditorDisplayName` String,
`LastEditDate` DateTime64(3, 'UTC') CODEC(Delta(8), ZSTD(1)),
`LastActivityDate` DateTime64(3, 'UTC'),
`Title` String,
`Tags` String,
`AnswerCount` UInt16 CODEC(Delta(2), ZSTD(1)),
`CommentCount` UInt8,
`FavoriteCount` UInt8,
`ContentLicense` LowCardinality(String),
`ParentId` String,
`CommunityOwnedDate` DateTime64(3, 'UTC'),
`ClosedDate` DateTime64(3, 'UTC')
)
ENGINE = MergeTree
PARTITION BY toYear(CreationDate)
ORDER BY (PostTypeId, toDate(CreationDate), CreationDate)
INSERT INTO stackoverflow.posts SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/*.parquet')
0 rows in set. Elapsed: 265.466 sec. Processed 59.82 million rows, 38.07 GB (225.34 thousand rows/s., 143.42 MB/s.)
```
Posts are also available by year e.g. [https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/2020.parquet](https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/2020.parquet)
### Votes
```sql
CREATE TABLE stackoverflow.votes
(
`Id` UInt32,
`PostId` Int32,
`VoteTypeId` UInt8,
`CreationDate` DateTime64(3, 'UTC'),
`UserId` Int32,
`BountyAmount` UInt8
)
ENGINE = MergeTree
ORDER BY (VoteTypeId, CreationDate, PostId, UserId)
INSERT INTO stackoverflow.votes SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/votes/*.parquet')
0 rows in set. Elapsed: 21.605 sec. Processed 238.98 million rows, 2.13 GB (11.06 million rows/s., 98.46 MB/s.)
```
Votes are also available by year e.g. [https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/2020.parquet](https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/votes/2020.parquet)
### Comments
```sql
CREATE TABLE stackoverflow.comments
(
`Id` UInt32,
`PostId` UInt32,
`Score` UInt16,
`Text` String,
`CreationDate` DateTime64(3, 'UTC'),
`UserId` Int32,
`UserDisplayName` LowCardinality(String)
)
ENGINE = MergeTree
ORDER BY CreationDate
INSERT INTO stackoverflow.comments SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/comments/*.parquet')
0 rows in set. Elapsed: 56.593 sec. Processed 90.38 million rows, 11.14 GB (1.60 million rows/s., 196.78 MB/s.)
```
Comments are also available by year e.g. [https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/2020.parquet](https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/comments/2020.parquet)
### Users
```sql
CREATE TABLE stackoverflow.users
(
`Id` Int32,
`Reputation` LowCardinality(String),
`CreationDate` DateTime64(3, 'UTC') CODEC(Delta(8), ZSTD(1)),
`DisplayName` String,
`LastAccessDate` DateTime64(3, 'UTC'),
`AboutMe` String,
`Views` UInt32,
`UpVotes` UInt32,
`DownVotes` UInt32,
`WebsiteUrl` String,
`Location` LowCardinality(String),
`AccountId` Int32
)
ENGINE = MergeTree
ORDER BY (Id, CreationDate)
INSERT INTO stackoverflow.users SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/users.parquet')
0 rows in set. Elapsed: 10.988 sec. Processed 22.48 million rows, 1.36 GB (2.05 million rows/s., 124.10 MB/s.)
```
### Badges
```sql
CREATE TABLE stackoverflow.badges
(
`Id` UInt32,
`UserId` Int32,
`Name` LowCardinality(String),
`Date` DateTime64(3, 'UTC'),
`Class` Enum8('Gold' = 1, 'Silver' = 2, 'Bronze' = 3),
`TagBased` Bool
)
ENGINE = MergeTree
ORDER BY UserId
INSERT INTO stackoverflow.badges SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/badges.parquet')
0 rows in set. Elapsed: 6.635 sec. Processed 51.29 million rows, 797.05 MB (7.73 million rows/s., 120.13 MB/s.)
```
### `PostLinks`
```sql
CREATE TABLE stackoverflow.postlinks
(
`Id` UInt64,
`CreationDate` DateTime64(3, 'UTC'),
`PostId` Int32,
`RelatedPostId` Int32,
`LinkTypeId` Enum8('Linked' = 1, 'Duplicate' = 3)
)
ENGINE = MergeTree
ORDER BY (PostId, RelatedPostId)
INSERT INTO stackoverflow.postlinks SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/postlinks.parquet')
0 rows in set. Elapsed: 1.534 sec. Processed 6.55 million rows, 129.70 MB (4.27 million rows/s., 84.57 MB/s.)
```
### `PostHistory`
```sql
CREATE TABLE stackoverflow.posthistory
(
`Id` UInt64,
`PostHistoryTypeId` UInt8,
`PostId` Int32,
`RevisionGUID` String,
`CreationDate` DateTime64(3, 'UTC'),
`UserId` Int32,
`Text` String,
`ContentLicense` LowCardinality(String),
`Comment` String,
`UserDisplayName` String
)
ENGINE = MergeTree
ORDER BY (CreationDate, PostId)
INSERT INTO stackoverflow.posthistory SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posthistory/*.parquet')
0 rows in set. Elapsed: 422.795 sec. Processed 160.79 million rows, 67.08 GB (380.30 thousand rows/s., 158.67 MB/s.)
```
## Original dataset
The original dataset is available in compressed (7zip) XML format at [https://archive.org/download/stackexchange](https://archive.org/download/stackexchange) - files with prefix `stackoverflow.com*`.
### Download
```bash
wget https://archive.org/download/stackexchange/stackoverflow.com-Badges.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Comments.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-PostHistory.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-PostLinks.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Posts.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Users.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Votes.7z
```
These files are up to 35GB and can take around 30 mins to download depending on internet connection - the download server throttles at around 20MB/sec.
### Convert to JSON
At the time of writing, ClickHouse does not have native support for XML as an input format. To load the data into ClickHouse we first convert to NDJSON.
To convert XML to JSON we recommend the [`xq`](https://github.com/kislyuk/yq) linux tool, a simple `jq` wrapper for XML documents.
Install xq and jq:
```bash
sudo apt install jq
pip install yq
```
The following steps apply to any of the above files. We use the `stackoverflow.com-Posts.7z` file as an example. Modify as required.
Extract the file using [p7zip](https://p7zip.sourceforge.net/). This will produce a single xml file - in this case `Posts.xml`.
> Files are compressed approximately 4.5x. At 22GB compressed, the posts file requires around 97G uncompressed.
```bash
p7zip -d stackoverflow.com-Posts.7z
```
The following splits the xml file into files, each containing 10000 rows.
```bash
mkdir posts
cd posts
# the following splits the input xml file into sub files of 10000 rows
tail +3 ../Posts.xml | head -n -1 | split -l 10000 --filter='{ printf "<rows>\n"; cat - ; printf "</rows>\n"; } > $FILE' -
```
After running the above users will have a set of files, each with 10000 lines. This ensures the memory overhead of the next command is not excessive (xml to JSON conversion is done in memory).
```bash
find . -maxdepth 1 -type f -exec xq -c '.rows.row[]' {} \; | sed -e 's:"@:":g' > posts_v2.json
```
The above command will produce a single `posts.json` file.
Load into ClickHouse with the following command. Note the schema is specified for the `posts.json` file. This will need to be adjusted per data type to align with the target table.
```bash
clickhouse local --query "SELECT * FROM file('posts.json', JSONEachRow, 'Id Int32, PostTypeId UInt8, AcceptedAnswerId UInt32, CreationDate DateTime64(3, \'UTC\'), Score Int32, ViewCount UInt32, Body String, OwnerUserId Int32, OwnerDisplayName String, LastEditorUserId Int32, LastEditorDisplayName String, LastEditDate DateTime64(3, \'UTC\'), LastActivityDate DateTime64(3, \'UTC\'), Title String, Tags String, AnswerCount UInt16, CommentCount UInt8, FavoriteCount UInt8, ContentLicense String, ParentId String, CommunityOwnedDate DateTime64(3, \'UTC\'), ClosedDate DateTime64(3, \'UTC\')') FORMAT Native" | clickhouse client --host <host> --secure --password <password> --query "INSERT INTO stackoverflow.posts_v2 FORMAT Native"
```
## Example queries
A few simple questions to you get started.
### Most popular tags on Stack Overflow
```sql
SELECT
arrayJoin(arrayFilter(t -> (t != ''), splitByChar('|', Tags))) AS Tags,
count() AS c
FROM stackoverflow.posts
GROUP BY Tags
ORDER BY c DESC
LIMIT 10
┌─Tags───────┬───────c─┐
│ javascript │ 2527130 │
│ python │ 2189638 │
│ java │ 1916156 │
│ c# │ 1614236 │
│ php │ 1463901 │
│ android │ 1416442 │
│ html │ 1186567 │
│ jquery │ 1034621 │
│ c++ │ 806202 │
│ css │ 803755 │
└────────────┴─────────┘
10 rows in set. Elapsed: 1.013 sec. Processed 59.82 million rows, 1.21 GB (59.07 million rows/s., 1.19 GB/s.)
Peak memory usage: 224.03 MiB.
```
### User with the most answers (active accounts)
Account requires a `UserId`.
```sql
SELECT
any(OwnerUserId) UserId,
OwnerDisplayName,
count() AS c
FROM stackoverflow.posts WHERE OwnerDisplayName != '' AND PostTypeId='Answer' AND OwnerUserId != 0
GROUP BY OwnerDisplayName
ORDER BY c DESC
LIMIT 5
┌─UserId─┬─OwnerDisplayName─┬────c─┐
│ 22656 │ Jon Skeet │ 2727 │
│ 23354 │ Marc Gravell │ 2150 │
│ 12950 │ tvanfosson │ 1530 │
│ 3043 │ Joel Coehoorn │ 1438 │
│ 10661 │ S.Lott │ 1087 │
└────────┴──────────────────┴──────┘
5 rows in set. Elapsed: 0.154 sec. Processed 35.83 million rows, 193.39 MB (232.33 million rows/s., 1.25 GB/s.)
Peak memory usage: 206.45 MiB.
```
### ClickHouse related posts with the most views
```sql
SELECT
Id,
Title,
ViewCount,
AnswerCount
FROM stackoverflow.posts
WHERE Title ILIKE '%ClickHouse%'
ORDER BY ViewCount DESC
LIMIT 10
┌───────Id─┬─Title────────────────────────────────────────────────────────────────────────────┬─ViewCount─┬─AnswerCount─┐
│ 52355143 │ Is it possible to delete old records from clickhouse table? │ 41462 │ 3 │
│ 37954203 │ Clickhouse Data Import │ 38735 │ 3 │
│ 37901642 │ Updating data in Clickhouse │ 36236 │ 6 │
│ 58422110 │ Pandas: How to insert dataframe into Clickhouse │ 29731 │ 4 │
│ 63621318 │ DBeaver - Clickhouse - SQL Error [159] .. Read timed out │ 27350 │ 1 │
│ 47591813 │ How to filter clickhouse table by array column contents? │ 27078 │ 2 │
│ 58728436 │ How to search the string in query with case insensitive on Clickhouse database? │ 26567 │ 3 │
│ 65316905 │ Clickhouse: DB::Exception: Memory limit (for query) exceeded │ 24899 │ 2 │
│ 49944865 │ How to add a column in clickhouse │ 24424 │ 1 │
│ 59712399 │ How to cast date Strings to DateTime format with extended parsing in ClickHouse? │ 22620 │ 1 │
└──────────┴──────────────────────────────────────────────────────────────────────────────────┴───────────┴─────────────┘
10 rows in set. Elapsed: 0.472 sec. Processed 59.82 million rows, 1.91 GB (126.63 million rows/s., 4.03 GB/s.)
Peak memory usage: 240.01 MiB.
```
### Most controversial posts
```sql
SELECT
Id,
Title,
UpVotes,
DownVotes,
abs(UpVotes - DownVotes) AS Controversial_ratio
FROM stackoverflow.posts
INNER JOIN
(
SELECT
PostId,
countIf(VoteTypeId = 2) AS UpVotes,
countIf(VoteTypeId = 3) AS DownVotes
FROM stackoverflow.votes
GROUP BY PostId
HAVING (UpVotes > 10) AND (DownVotes > 10)
) AS votes ON posts.Id = votes.PostId
WHERE Title != ''
ORDER BY Controversial_ratio ASC
LIMIT 3
┌───────Id─┬─Title─────────────────────────────────────────────┬─UpVotes─┬─DownVotes─┬─Controversial_ratio─┐
│ 583177 │ VB.NET Infinite For Loop │ 12 │ 12 │ 0 │
│ 9756797 │ Read console input as enumerable - one statement? │ 16 │ 16 │ 0 │
│ 13329132 │ What's the point of ARGV in Ruby? │ 22 │ 22 │ 0 │
└──────────┴───────────────────────────────────────────────────┴─────────┴───────────┴─────────────────────┘
3 rows in set. Elapsed: 4.779 sec. Processed 298.80 million rows, 3.16 GB (62.52 million rows/s., 661.05 MB/s.)
Peak memory usage: 6.05 GiB.
```
## Attribution
We thank Stack Overflow for providing this data under the `cc-by-sa 4.0` license, acknowledging their efforts and the original source of the data at [https://archive.org/details/stackexchange](https://archive.org/details/stackexchange).

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

@ -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.

1
docs/en/interfaces/formats.md
View File

@ -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}

4
docs/en/operations/named-collections.md
View File

@ -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.

5
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -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).

7
docs/en/operations/settings/settings-formats.md
View File

@ -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}

4
docs/en/operations/utilities/clickhouse-local.md
View File

@ -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

28
docs/en/sql-reference/functions/string-functions.md
View File

@ -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

34
docs/en/sql-reference/functions/url-functions.md
View File

@ -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 `#`.

4
docs/en/sql-reference/statements/alter/named-collection.md
View File

@ -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.

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

@ -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;

4
docs/en/sql-reference/statements/create/named-collection.md
View File

@ -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.

2
docs/ru/development/developer-instruction.md
View File

@ -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.

8
docs/ru/sql-reference/functions/string-functions.md
View File

@ -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}

8
programs/client/Client.cpp
View File

@ -248,6 +248,10 @@ std::vector<String> Client::loadWarningMessages()
}
}
Poco::Util::LayeredConfiguration & Client::getClientConfiguration()
{
return config();
}
void Client::initialize(Poco::Util::Application & self)
{
@ -697,9 +701,7 @@ 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)
{

3
programs/client/Client.h
View File

@ -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);

4
programs/keeper-client/KeeperClient.cpp
View File

@ -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;

5
programs/keeper/Keeper.cpp
View File

@ -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

2
programs/library-bridge/CMakeLists.txt
View File

@ -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 ..)

208
programs/local/LocalServer.cpp
View File

@ -82,6 +82,11 @@ void applySettingsOverridesForLocal(ContextMutablePtr context)
context->setSettings(settings);
}
Poco::Util::LayeredConfiguration & LocalServer::getClientConfiguration()
{
return config();
}
void LocalServer::processError(const String &) const
{
if (ignore_error)
@ -117,19 +122,19 @@ 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
@ -141,18 +146,17 @@ 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
@ -160,7 +164,7 @@ 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
@ -168,7 +172,7 @@ 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
@ -201,10 +205,10 @@ 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())
@ -263,13 +267,13 @@ 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());
}
@ -311,14 +315,14 @@ 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";
@ -326,7 +330,7 @@ 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);
}
@ -374,18 +378,18 @@ 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;
}
@ -409,10 +413,10 @@ 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;
@ -433,7 +437,7 @@ try
UseSSL use_ssl;
thread_status.emplace();
StackTrace::setShowAddresses(config().getBool("show_addresses_in_stack_traces", true));
StackTrace::setShowAddresses(getClientConfiguration().getBool("show_addresses_in_stack_traces", true));
setupSignalHandler();
@ -448,7 +452,7 @@ 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';
@ -456,8 +460,8 @@ 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)
{
@ -481,7 +485,7 @@ try
SCOPE_EXIT({ cleanup(); });
initTTYBuffer(toProgressOption(config().getString("progress", "default")));
initTTYBuffer(toProgressOption(getClientConfiguration().getString("progress", "default")));
ASTAlterCommand::setFormatAlterCommandsWithParentheses(true);
applyCmdSettings(global_context);
@ -489,7 +493,7 @@ try
/// try to load user defined executable functions, throw on error and die
try
{
global_context->loadOrReloadUserDefinedExecutableFunctions(config());
global_context->loadOrReloadUserDefinedExecutableFunctions(getClientConfiguration());
}
catch (...)
{
@ -530,7 +534,7 @@ 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;
}
@ -542,42 +546,42 @@ 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);
@ -587,10 +591,10 @@ 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();
@ -604,13 +608,13 @@ 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();
@ -619,12 +623,12 @@ 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;
@ -632,9 +636,9 @@ 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)
@ -644,9 +648,9 @@ 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;
@ -654,9 +658,9 @@ 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;
@ -664,7 +668,7 @@ 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;
@ -676,8 +680,8 @@ 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
@ -689,16 +693,16 @@ 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));
@ -713,7 +717,7 @@ 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));
@ -725,15 +729,15 @@ 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);
@ -811,7 +815,7 @@ 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);
}
@ -819,33 +823,33 @@ 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> &)

3
programs/local/LocalServer.h
View File

@ -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;

9
programs/main.cpp
View File

@ -13,6 +13,7 @@
#include <fmt/format.h>
#include "config.h"
#include "config_tools.h"
#include <Common/StringUtils.h>
@ -439,6 +440,14 @@ extern "C"
}
#endif
/// Prevent messages from JeMalloc in the release build.
/// Some of these messages are non-actionable for the users, such as:
/// <jemalloc>: Number of CPUs detected is not deterministic. Per-CPU arena disabled.
#if USE_JEMALLOC && defined(NDEBUG) && !defined(SANITIZER)
extern "C" void (*malloc_message)(void *, const char *s);
__attribute__((constructor(0))) void init_je_malloc_message() { malloc_message = [](void *, const char *){}; }
#endif
/// This allows to implement assert to forbid initialization of a class in static constructors.
/// Usage:
///

2
programs/odbc-bridge/CMakeLists.txt
View File

@ -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 ..)

7
programs/server/Server.cpp
View File

@ -1003,6 +1003,8 @@ try
ServerUUID::load(path / "uuid", log);
PlacementInfo::PlacementInfo::instance().initialize(config());
zkutil::validateZooKeeperConfig(config());
bool has_zookeeper = zkutil::hasZooKeeperConfig(config());
@ -1817,11 +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.

7
programs/server/config.xml
View File

@ -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):

36
src/Analyzer/Resolve/QueryAnalyzer.cpp
View File

@ -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);

2
src/Backups/RestorerFromBackup.cpp
View File

@ -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};

2
src/CMakeLists.txt
View File

@ -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)

215
src/Client/ClientBase.cpp
View File

@ -302,8 +302,29 @@ 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 +351,7 @@ 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 +380,7 @@ 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 +394,11 @@ 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 +502,7 @@ 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 +762,17 @@ 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 +798,17 @@ 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 +824,7 @@ 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 +834,7 @@ 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 +945,7 @@ 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 +1119,7 @@ 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 +1173,7 @@ 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 +1208,7 @@ 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 +1327,9 @@ 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 +1882,7 @@ 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;
}
@ -2026,7 +2045,7 @@ 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);
}
@ -2046,21 +2065,21 @@ 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)
@ -2110,9 +2129,7 @@ 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)
{
@ -2428,12 +2445,12 @@ 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())
@ -2478,9 +2495,9 @@ 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();
@ -2493,9 +2510,9 @@ 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())
@ -2506,8 +2523,8 @@ 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)
@ -2528,7 +2545,7 @@ void ClientBase::runInteractive()
{
if (e.getErrno() != EEXIST)
{
std::cerr << getCurrentExceptionMessage(false) << '\n';
error_stream << getCurrentExceptionMessage(false) << '\n';
}
}
}
@ -2539,13 +2556,13 @@ 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,
@ -2553,7 +2570,7 @@ void ClientBase::runInteractive()
#else
LineReader lr(
history_file,
config().has("multiline"),
getClientConfiguration().has("multiline"),
query_extenders,
query_delimiters,
word_break_characters);
@ -2633,7 +2650,7 @@ 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
@ -2648,7 +2665,7 @@ void ClientBase::runInteractive()
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());
}
@ -2665,11 +2682,11 @@ 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;
}
@ -2680,7 +2697,7 @@ 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"))
{
Settings settings = global_context->getSettings();
/// NOTE: cannot use even weakly_canonical() since it fails for /dev/stdin due to resolving of "pipe:[X]"
@ -2789,13 +2806,13 @@ 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
@ -2862,7 +2879,10 @@ 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)
@ -3080,18 +3100,18 @@ 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);
@ -3099,72 +3119,75 @@ 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>());
@ -3182,13 +3205,13 @@ 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());
@ -3197,8 +3220,6 @@ 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");
}
}

35
src/Client/ClientBase.h
View File

@ -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;
@ -206,7 +217,6 @@ 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;
@ -251,9 +261,9 @@ 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.
@ -284,7 +294,6 @@ 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
@ -332,8 +341,14 @@ 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;
};
}

39
src/Client/Connection.cpp
View File

@ -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
@ -68,7 +70,17 @@ 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_,
@ -259,13 +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();
}
@ -278,6 +308,7 @@ void Connection::disconnect()
if (socket)
socket->close();
socket = nullptr;
connected = false;
nonce.reset();
@ -774,6 +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();

35
src/Client/LineReader.cpp
View File

@ -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;
}

19
src/Client/LineReader.h
View File

@ -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;
};
}

75
src/Client/LocalConnection.cpp
View File

@ -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
{
@ -151,12 +154,26 @@ 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())
@ -341,22 +358,18 @@ bool LocalConnection::poll(size_t)
if (!state->is_finished)
{
if (send_progress && (state->after_send_progress.elapsedMicroseconds() >= query_context->getSettingsRef().interactive_delay))
{
state->after_send_progress.restart();
next_packet_type = Protocol::Server::Progress;
if (needSendProgressOrMetrics())
return true;
}
if (send_profile_events && (state->after_send_profile_events.elapsedMicroseconds() >= query_context->getSettingsRef().interactive_delay))
{
sendProfileEvents();
return true;
}
try
{
pollImpl();
while (pollImpl())
{
LOG_DEBUG(&Poco::Logger::get("LocalConnection"), "Executor timeout encountered, will retry");
if (needSendProgressOrMetrics())
return true;
}
}
catch (const Exception & e)
{
@ -451,12 +464,34 @@ bool LocalConnection::poll(size_t)
return false;
}
bool LocalConnection::needSendProgressOrMetrics()
{
if (send_progress && (state->after_send_progress.elapsedMicroseconds() >= query_context->getSettingsRef().interactive_delay))
{
state->after_send_progress.restart();
next_packet_type = Protocol::Server::Progress;
return true;
}
if (send_profile_events && (state->after_send_profile_events.elapsedMicroseconds() >= query_context->getSettingsRef().interactive_delay))
{
sendProfileEvents();
return true;
}
return false;
}
bool LocalConnection::pollImpl()
{
Block block;
auto next_read = pullBlock(block);
if (block && !state->io.null_format)
if (!block && next_read)
{
return true;
}
else if (block && !state->io.null_format)
{
state->block.emplace(block);
}
@ -465,7 +500,7 @@ bool LocalConnection::pollImpl()
state->is_finished = true;
}
return true;
return false;
}
Packet LocalConnection::receivePacket()

3
src/Client/LocalConnection.h
View File

@ -151,8 +151,11 @@ private:
void sendProfileEvents();
/// Returns true on executor timeout, meaning a retryable error.
bool pollImpl();
bool needSendProgressOrMetrics();
ContextMutablePtr query_context;
Session session;

17
src/Client/ReplxxLineReader.cpp
View File

@ -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());
}

15
src/Client/ReplxxLineReader.h
View File

@ -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;

22
src/Common/GetPriorityForLoadBalancing.cpp
View File

@ -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;
}
}
}

2
src/Common/GetPriorityForLoadBalancing.h
View File

@ -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.

10
src/Common/ProfileEvents.cpp
View File

@ -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") \

10
src/Common/ProgressIndication.cpp
View File

@ -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)
{

17
src/Common/ProgressIndication.h
View File

@ -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;
};
}

2
src/Common/SystemLogBase.cpp
View File

@ -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>

2
src/Common/SystemLogBase.h
View File

@ -25,7 +25,7 @@
M(ZooKeeperLogElement) \
M(ProcessorProfileLogElement) \
M(TextLogElement) \
M(S3QueueLogElement) \
M(ObjectStorageQueueLogElement) \
M(FilesystemCacheLogElement) \
M(FilesystemReadPrefetchesLogElement) \
M(AsynchronousInsertLogElement) \

10
src/Common/TerminalSize.cpp
View File

@ -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.

4
src/Common/TerminalSize.h
View File

@ -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

6
src/Common/ZooKeeper/IKeeper.h
View File

@ -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;
};

1
src/Common/ZooKeeper/TestKeeper.h
View File

@ -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; }

194
src/Common/ZooKeeper/ZooKeeper.cpp
View File

@ -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())

38
src/Common/ZooKeeper/ZooKeeper.h
View File

@ -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;
};

33
src/Common/ZooKeeper/ZooKeeperArgs.cpp
View File

@ -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();
}
}

4
src/Common/ZooKeeper/ZooKeeperArgs.h
View File

@ -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;

153
src/Common/ZooKeeper/ZooKeeperImpl.cpp
View File

@ -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)))

22
src/Common/ZooKeeper/ZooKeeperImpl.h
View File

@ -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;

3
src/Common/ZooKeeper/examples/CMakeLists.txt
View File

@ -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)

24
src/Common/ZooKeeper/examples/zkutil_test_commands_new_lib.cpp
View File

@ -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);

6
src/Common/examples/CMakeLists.txt
View File

@ -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)

12
src/Compression/CompressedWriteBuffer.cpp
View File

@ -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();
}
}

4
src/Core/Settings.h
View File

@ -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) \

3
src/Core/SettingsChangesHistory.cpp
View File

@ -57,6 +57,8 @@ String ClickHouseVersion::toString() const
/// Note: please check if the key already exists to prevent duplicate entries.
static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory::SettingsChanges>> settings_changes_history_initializer =
{
{"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."},
@ -86,6 +88,7 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
{"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."},

12
src/Core/SettingsEnums.cpp
View File

@ -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},

8
src/Core/SettingsEnums.h
View File

@ -341,21 +341,21 @@ DECLARE_SETTING_ENUM(ParallelReplicasCustomKeyFilterType)
DECLARE_SETTING_ENUM(LocalFSReadMethod)
enum class S3QueueMode : uint8_t
enum class ObjectStorageQueueMode : uint8_t
{
ORDERED,
UNORDERED,
};
DECLARE_SETTING_ENUM(S3QueueMode)
DECLARE_SETTING_ENUM(ObjectStorageQueueMode)
enum class S3QueueAction : uint8_t
enum class ObjectStorageQueueAction : uint8_t
{
KEEP,
DELETE,
};
DECLARE_SETTING_ENUM(S3QueueAction)
DECLARE_SETTING_ENUM(ObjectStorageQueueAction)
DECLARE_SETTING_ENUM(ExternalCommandStderrReaction)

49
src/Databases/DDLDependencyVisitor.cpp
View File

@ -30,8 +30,8 @@ namespace
{
friend void tryVisitNestedSelect(const String & query, DDLDependencyVisitorData & data);
public:
DDLDependencyVisitorData(const ContextPtr & context_, const QualifiedTableName & table_name_, const ASTPtr & ast_)
: create_query(ast_), table_name(table_name_), current_database(context_->getCurrentDatabase()), context(context_)
DDLDependencyVisitorData(const ContextPtr & global_context_, const QualifiedTableName & table_name_, const ASTPtr & ast_, const String & current_database_)
: create_query(ast_), table_name(table_name_), default_database(global_context_->getCurrentDatabase()), current_database(current_database_), global_context(global_context_)
{
}
@ -71,8 +71,9 @@ namespace
ASTPtr create_query;
std::unordered_set<const IAST *> skip_asts;
QualifiedTableName table_name;
String default_database;
String current_database;
ContextPtr context;
ContextPtr global_context;
TableNamesSet dependencies;
/// CREATE TABLE or CREATE DICTIONARY or CREATE VIEW or CREATE TEMPORARY TABLE or CREATE DATABASE query.
@ -95,6 +96,11 @@ namespace
as_table.database = current_database;
dependencies.emplace(as_table);
}
/// Visit nested select query only for views, for other cases it's not
/// an actual dependency as it will be executed only once to fill the table.
if (create.select && !create.isView())
skip_asts.insert(create.select);
}
/// The definition of a dictionary: SOURCE(CLICKHOUSE(...)) LAYOUT(...) LIFETIME(...)
@ -103,8 +109,8 @@ namespace
if (!dictionary.source || dictionary.source->name != "clickhouse" || !dictionary.source->elements)
return;
auto config = getDictionaryConfigurationFromAST(create_query->as<ASTCreateQuery &>(), context);
auto info = getInfoIfClickHouseDictionarySource(config, context);
auto config = getDictionaryConfigurationFromAST(create_query->as<ASTCreateQuery &>(), global_context);
auto info = getInfoIfClickHouseDictionarySource(config, global_context);
/// We consider only dependencies on local tables.
if (!info || !info->is_local)
@ -112,14 +118,21 @@ namespace
if (!info->table_name.table.empty())
{
/// If database is not specified in dictionary source, use database of the dictionary itself, not the current/default database.
if (info->table_name.database.empty())
info->table_name.database = current_database;
info->table_name.database = table_name.database;
dependencies.emplace(std::move(info->table_name));
}
else
{
/// We don't have a table name, we have a select query instead
/// We don't have a table name, we have a select query instead.
/// All tables from select query in dictionary definition won't
/// use current database, as this query is executed with global context.
/// Use default database from global context while visiting select query.
String current_database_ = current_database;
current_database = default_database;
tryVisitNestedSelect(info->query, *this);
current_database = current_database_;
}
}
@ -176,7 +189,7 @@ namespace
if (auto cluster_name = tryGetClusterNameFromArgument(table_engine, 0))
{
auto cluster = context->tryGetCluster(*cluster_name);
auto cluster = global_context->tryGetCluster(*cluster_name);
if (cluster && cluster->getLocalShardCount())
has_local_replicas = true;
}
@ -231,7 +244,7 @@ namespace
{
if (auto cluster_name = tryGetClusterNameFromArgument(function, 0))
{
if (auto cluster = context->tryGetCluster(*cluster_name))
if (auto cluster = global_context->tryGetCluster(*cluster_name))
{
if (cluster->getLocalShardCount())
has_local_replicas = true;
@ -303,7 +316,10 @@ namespace
try
{
/// We're just searching for dependencies here, it's not safe to execute subqueries now.
auto evaluated = evaluateConstantExpressionOrIdentifierAsLiteral(arg, context);
/// Use copy of the global_context and set current database, because expressions can contain currentDatabase() function.
ContextMutablePtr global_context_copy = Context::createCopy(global_context);
global_context_copy->setCurrentDatabase(current_database);
auto evaluated = evaluateConstantExpressionOrIdentifierAsLiteral(arg, global_context_copy);
const auto * literal = evaluated->as<ASTLiteral>();
if (!literal || (literal->value.getType() != Field::Types::String))
return {};
@ -444,7 +460,7 @@ namespace
ParserSelectWithUnionQuery parser;
String description = fmt::format("Query for ClickHouse dictionary {}", data.table_name);
String fixed_query = removeWhereConditionPlaceholder(query);
const Settings & settings = data.context->getSettingsRef();
const Settings & settings = data.global_context->getSettingsRef();
ASTPtr select = parseQuery(parser, fixed_query, description,
settings.max_query_size, settings.max_parser_depth, settings.max_parser_backtracks);
@ -459,12 +475,19 @@ namespace
}
TableNamesSet getDependenciesFromCreateQuery(const ContextPtr & context, const QualifiedTableName & table_name, const ASTPtr & ast)
TableNamesSet getDependenciesFromCreateQuery(const ContextPtr & global_global_context, const QualifiedTableName & table_name, const ASTPtr & ast, const String & current_database)
{
DDLDependencyVisitor::Data data{context, table_name, ast};
DDLDependencyVisitor::Data data{global_global_context, table_name, ast, current_database};
DDLDependencyVisitor::Visitor visitor{data};
visitor.visit(ast);
return std::move(data).getDependencies();
}
TableNamesSet getDependenciesFromDictionaryNestedSelectQuery(const ContextPtr & global_context, const QualifiedTableName & table_name, const ASTPtr & ast, const String & select_query, const String & current_database)
{
DDLDependencyVisitor::Data data{global_context, table_name, ast, current_database};
tryVisitNestedSelect(select_query, data);
return std::move(data).getDependencies();
}
}

5
src/Databases/DDLDependencyVisitor.h
View File

@ -13,6 +13,9 @@ using TableNamesSet = std::unordered_set<QualifiedTableName>;
/// Returns a list of all tables explicitly referenced in the create query of a specified table.
/// For example, a column default expression can use dictGet() and thus reference a dictionary.
/// Does not validate AST, works a best-effort way.
TableNamesSet getDependenciesFromCreateQuery(const ContextPtr & context, const QualifiedTableName & table_name, const ASTPtr & ast);
TableNamesSet getDependenciesFromCreateQuery(const ContextPtr & global_context, const QualifiedTableName & table_name, const ASTPtr & ast, const String & current_database);
/// Returns a list of all tables explicitly referenced in the select query specified as a dictionary source.
TableNamesSet getDependenciesFromDictionaryNestedSelectQuery(const ContextPtr & global_context, const QualifiedTableName & table_name, const ASTPtr & ast, const String & select_query, const String & current_database);
}

21
src/Databases/DDLLoadingDependencyVisitor.cpp
View File

@ -110,19 +110,30 @@ void DDLLoadingDependencyVisitor::visit(const ASTFunctionWithKeyValueArguments &
auto config = getDictionaryConfigurationFromAST(data.create_query->as<ASTCreateQuery &>(), data.global_context);
auto info = getInfoIfClickHouseDictionarySource(config, data.global_context);
if (!info || !info->is_local || info->table_name.table.empty())
if (!info || !info->is_local)
return;
if (info->table_name.database.empty())
info->table_name.database = data.default_database;
data.dependencies.emplace(std::move(info->table_name));
if (!info->table_name.table.empty())
{
/// If database is not specified in dictionary source, use database of the dictionary itself, not the current/default database.
if (info->table_name.database.empty())
info->table_name.database = data.table_name.database;
data.dependencies.emplace(std::move(info->table_name));
}
else
{
/// We don't have a table name, we have a select query instead that will be executed during dictionary loading.
/// We need to find all tables used in this select query and add them to dependencies.
auto select_query_dependencies = getDependenciesFromDictionaryNestedSelectQuery(data.global_context, data.table_name, data.create_query, info->query, data.default_database);
data.dependencies.merge(select_query_dependencies);
}
}
void DDLLoadingDependencyVisitor::visit(const ASTStorage & storage, Data & data)
{
if (storage.ttl_table)
{
auto ttl_dependensies = getDependenciesFromCreateQuery(data.global_context, data.table_name, storage.ttl_table->ptr());
auto ttl_dependensies = getDependenciesFromCreateQuery(data.global_context, data.table_name, storage.ttl_table->ptr(), data.default_database);
data.dependencies.merge(ttl_dependensies);
}

2
src/Databases/DatabaseMemory.cpp
View File

@ -154,7 +154,7 @@ void DatabaseMemory::alterTable(ContextPtr local_context, const StorageID & tabl
applyMetadataChangesToCreateQuery(it->second, metadata);
/// The create query of the table has been just changed, we need to update dependencies too.
auto ref_dependencies = getDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), it->second);
auto ref_dependencies = getDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), it->second, local_context->getCurrentDatabase());
auto loading_dependencies = getLoadingDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), it->second);
DatabaseCatalog::instance().updateDependencies(table_id, ref_dependencies, loading_dependencies);
}

2
src/Databases/DatabaseOrdinary.cpp
View File

@ -539,7 +539,7 @@ void DatabaseOrdinary::alterTable(ContextPtr local_context, const StorageID & ta
}
/// The create query of the table has been just changed, we need to update dependencies too.
auto ref_dependencies = getDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), ast);
auto ref_dependencies = getDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), ast, local_context->getCurrentDatabase());
auto loading_dependencies = getLoadingDependenciesFromCreateQuery(local_context->getGlobalContext(), table_id.getQualifiedName(), ast);
DatabaseCatalog::instance().updateDependencies(table_id, ref_dependencies, loading_dependencies);

17
src/Databases/DatabaseReplicated.cpp
View File

@ -65,6 +65,7 @@ static constexpr const char * REPLICATED_DATABASE_MARK = "DatabaseReplicated";
static constexpr const char * DROPPED_MARK = "DROPPED";
static constexpr const char * BROKEN_TABLES_SUFFIX = "_broken_tables";
static constexpr const char * BROKEN_REPLICATED_TABLES_SUFFIX = "_broken_replicated_tables";
static constexpr const char * FIRST_REPLICA_DATABASE_NAME = "first_replica_database_name";
static constexpr size_t METADATA_FILE_BUFFER_SIZE = 32768;
@ -465,6 +466,13 @@ void DatabaseReplicated::tryConnectToZooKeeperAndInitDatabase(LoadingStrictnessL
return;
}
/// If not exist, create a node with the database name for introspection.
/// Technically, the database may have different names on different replicas, but this is not a usual case and we only save the first one
auto db_name_path = fs::path(zookeeper_path) / FIRST_REPLICA_DATABASE_NAME;
auto error_code = current_zookeeper->trySet(db_name_path, getDatabaseName());
if (error_code == Coordination::Error::ZNONODE)
current_zookeeper->tryCreate(db_name_path, getDatabaseName(), zkutil::CreateMode::Persistent);
is_readonly = false;
}
catch (...)
@ -1157,7 +1165,7 @@ void DatabaseReplicated::recoverLostReplica(const ZooKeeperPtr & current_zookeep
/// And QualifiedTableName::parseFromString doesn't handle this.
auto qualified_name = QualifiedTableName{.database = getDatabaseName(), .table = table_name};
auto query_ast = parseQueryFromMetadataInZooKeeper(table_name, create_table_query);
tables_dependencies.addDependencies(qualified_name, getDependenciesFromCreateQuery(getContext(), qualified_name, query_ast));
tables_dependencies.addDependencies(qualified_name, getDependenciesFromCreateQuery(getContext()->getGlobalContext(), qualified_name, query_ast, getContext()->getCurrentDatabase()));
}
tables_dependencies.checkNoCyclicDependencies();
@ -1382,6 +1390,13 @@ void DatabaseReplicated::drop(ContextPtr context_)
}
}
void DatabaseReplicated::renameDatabase(ContextPtr query_context, const String & new_name)
{
DatabaseAtomic::renameDatabase(query_context, new_name);
auto db_name_path = fs::path(zookeeper_path) / FIRST_REPLICA_DATABASE_NAME;
getZooKeeper()->set(db_name_path, getDatabaseName());
}
void DatabaseReplicated::stopReplication()
{
if (ddl_worker)

2
src/Databases/DatabaseReplicated.h
View File

@ -86,6 +86,8 @@ public:
std::vector<UInt8> tryGetAreReplicasActive(const ClusterPtr & cluster_) const;
void renameDatabase(ContextPtr query_context, const String & new_name) override;
friend struct DatabaseReplicatedTask;
friend class DatabaseReplicatedDDLWorker;
private:

2
src/Databases/TablesLoader.cpp
View File

@ -137,7 +137,7 @@ void TablesLoader::buildDependencyGraph()
{
for (const auto & [table_name, table_metadata] : metadata.parsed_tables)
{
auto new_ref_dependencies = getDependenciesFromCreateQuery(global_context, table_name, table_metadata.ast);
auto new_ref_dependencies = getDependenciesFromCreateQuery(global_context, table_name, table_metadata.ast, global_context->getCurrentDatabase());
auto new_loading_dependencies = getLoadingDependenciesFromCreateQuery(global_context, table_name, table_metadata.ast);
if (!new_ref_dependencies.empty())

2
src/Formats/FormatFactory.cpp
View File

@ -149,6 +149,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
format_settings.json.try_infer_objects_as_tuples = settings.input_format_json_try_infer_named_tuples_from_objects;
format_settings.json.throw_on_bad_escape_sequence = settings.input_format_json_throw_on_bad_escape_sequence;
format_settings.json.ignore_unnecessary_fields = settings.input_format_json_ignore_unnecessary_fields;
format_settings.json.ignore_key_case = settings.input_format_json_ignore_key_case;
format_settings.null_as_default = settings.input_format_null_as_default;
format_settings.force_null_for_omitted_fields = settings.input_format_force_null_for_omitted_fields;
format_settings.decimal_trailing_zeros = settings.output_format_decimal_trailing_zeros;
@ -171,6 +172,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
format_settings.parquet.parallel_encoding = settings.output_format_parquet_parallel_encoding;
format_settings.parquet.data_page_size = settings.output_format_parquet_data_page_size;
format_settings.parquet.write_batch_size = settings.output_format_parquet_batch_size;
format_settings.parquet.write_page_index = settings.output_format_parquet_write_page_index;
format_settings.parquet.local_read_min_bytes_for_seek = settings.input_format_parquet_local_file_min_bytes_for_seek;
format_settings.pretty.charset = settings.output_format_pretty_grid_charset.toString() == "ASCII" ? FormatSettings::Pretty::Charset::ASCII : FormatSettings::Pretty::Charset::UTF8;
format_settings.pretty.color = settings.output_format_pretty_color;

2
src/Formats/FormatSettings.h
View File

@ -228,6 +228,7 @@ struct FormatSettings
bool infer_incomplete_types_as_strings = true;
bool throw_on_bad_escape_sequence = true;
bool ignore_unnecessary_fields = true;
bool ignore_key_case = false;
} json{};
struct
@ -275,6 +276,7 @@ struct FormatSettings
bool output_compliant_nested_types = true;
size_t data_page_size = 1024 * 1024;
size_t write_batch_size = 1024;
bool write_page_index = false;
size_t local_read_min_bytes_for_seek = 8192;
} parquet{};

26
src/Functions/CMakeLists.txt
View File

@ -3,35 +3,9 @@ add_subdirectory(divide)
include("${ClickHouse_SOURCE_DIR}/cmake/dbms_glob_sources.cmake")
add_headers_and_sources(clickhouse_functions .)
set(DBMS_FUNCTIONS
IFunction.cpp
FunctionFactory.cpp
FunctionHelpers.cpp
extractTimeZoneFromFunctionArguments.cpp
FunctionsLogical.cpp
if.cpp
multiIf.cpp
multiMatchAny.cpp
checkHyperscanRegexp.cpp
array/has.cpp
CastOverloadResolver.cpp
# Provides dependency for cast - createFunctionBaseCast()
FunctionsConversion.cpp
)
extract_into_parent_list(clickhouse_functions_sources dbms_sources ${DBMS_FUNCTIONS})
extract_into_parent_list(clickhouse_functions_headers dbms_headers
IFunction.h
FunctionFactory.h
FunctionHelpers.h
extractTimeZoneFromFunctionArguments.h
FunctionsLogical.h
CastOverloadResolver.h
)
add_library(clickhouse_functions_obj OBJECT ${clickhouse_functions_headers} ${clickhouse_functions_sources})
if (OMIT_HEAVY_DEBUG_SYMBOLS)
target_compile_options(clickhouse_functions_obj PRIVATE "-g0")
set_source_files_properties(${DBMS_FUNCTIONS} DIRECTORY .. PROPERTIES COMPILE_FLAGS "-g0")
endif()
list (APPEND OBJECT_LIBS $<TARGET_OBJECTS:clickhouse_functions_obj>)

24
src/Functions/FunctionBase64Conversion.h
View File

@ -25,10 +25,10 @@ namespace ErrorCodes
enum class Base64Variant : uint8_t
{
Normal,
Url
URL
};
inline std::string preprocessBase64Url(std::string_view src)
inline std::string preprocessBase64URL(std::string_view src)
{
std::string padded_src;
padded_src.reserve(src.size() + 3);
@ -70,7 +70,7 @@ inline std::string preprocessBase64Url(std::string_view src)
return padded_src;
}
inline size_t postprocessBase64Url(UInt8 * dst, size_t out_len)
inline size_t postprocessBase64URL(UInt8 * dst, size_t out_len)
{
// Do symbol substitution as described in https://datatracker.ietf.org/doc/html/rfc4648#section-5
for (size_t i = 0; i < out_len; ++i)
@ -95,7 +95,7 @@ inline size_t postprocessBase64Url(UInt8 * dst, size_t out_len)
template <Base64Variant variant>
struct Base64Encode
{
static constexpr auto name = (variant == Base64Variant::Normal) ? "base64Encode" : "base64UrlEncode";
static constexpr auto name = (variant == Base64Variant::Normal) ? "base64Encode" : "base64URLEncode";
static size_t getBufferSize(size_t string_length, size_t string_count)
{
@ -111,8 +111,8 @@ struct Base64Encode
/// Memory sanitizer doesn't understand if there was uninitialized memory in SIMD register but it was not used in the result of shuffle.
__msan_unpoison(dst, outlen);
if constexpr (variant == Base64Variant::Url)
outlen = postprocessBase64Url(dst, outlen);
if constexpr (variant == Base64Variant::URL)
outlen = postprocessBase64URL(dst, outlen);
return outlen;
}
@ -121,7 +121,7 @@ struct Base64Encode
template <Base64Variant variant>
struct Base64Decode
{
static constexpr auto name = (variant == Base64Variant::Normal) ? "base64Decode" : "base64UrlDecode";
static constexpr auto name = (variant == Base64Variant::Normal) ? "base64Decode" : "base64URLDecode";
static size_t getBufferSize(size_t string_length, size_t string_count)
{
@ -132,9 +132,9 @@ struct Base64Decode
{
int rc;
size_t outlen = 0;
if constexpr (variant == Base64Variant::Url)
if constexpr (variant == Base64Variant::URL)
{
std::string src_padded = preprocessBase64Url(src);
std::string src_padded = preprocessBase64URL(src);
rc = base64_decode(src_padded.data(), src_padded.size(), reinterpret_cast<char *>(dst), &outlen, 0);
}
else
@ -156,7 +156,7 @@ struct Base64Decode
template <Base64Variant variant>
struct TryBase64Decode
{
static constexpr auto name = (variant == Base64Variant::Normal) ? "tryBase64Decode" : "tryBase64UrlDecode";
static constexpr auto name = (variant == Base64Variant::Normal) ? "tryBase64Decode" : "tryBase64URLDecode";
static size_t getBufferSize(size_t string_length, size_t string_count)
{
@ -167,9 +167,9 @@ struct TryBase64Decode
{
int rc;
size_t outlen = 0;
if constexpr (variant == Base64Variant::Url)
if constexpr (variant == Base64Variant::URL)
{
std::string src_padded = preprocessBase64Url(src);
std::string src_padded = preprocessBase64URL(src);
rc = base64_decode(src_padded.data(), src_padded.size(), reinterpret_cast<char *>(dst), &outlen, 0);
}
else

10
src/Functions/base64UrlDecode.cpp → src/Functions/base64URLDecode.cpp
View File

@ -5,16 +5,16 @@
namespace DB
{
REGISTER_FUNCTION(Base64UrlDecode)
REGISTER_FUNCTION(Base64URLDecode)
{
FunctionDocumentation::Description description = R"(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).)";
FunctionDocumentation::Syntax syntax = "base64UrlDecode(encodedUrl)";
FunctionDocumentation::Arguments arguments = {{"encodedUrl", "String column or constant. If the string is not a valid Base64-encoded value, an exception is thrown."}};
FunctionDocumentation::Syntax syntax = "base64URLDecode(encodedURL)";
FunctionDocumentation::Arguments arguments = {{"encodedURL", "String column or constant. If the string is not a valid Base64-encoded value, an exception is thrown."}};
FunctionDocumentation::ReturnedValue returned_value = "A string containing the decoded value of the argument.";
FunctionDocumentation::Examples examples = {{"Example", "SELECT base64UrlDecode('aHR0cDovL2NsaWNraG91c2UuY29t')", "https://clickhouse.com"}};
FunctionDocumentation::Examples examples = {{"Example", "SELECT base64URLDecode('aHR0cDovL2NsaWNraG91c2UuY29t')", "https://clickhouse.com"}};
FunctionDocumentation::Categories categories = {"String encoding"};
factory.registerFunction<FunctionBase64Conversion<Base64Decode<Base64Variant::Url>>>({description, syntax, arguments, returned_value, examples, categories});
factory.registerFunction<FunctionBase64Conversion<Base64Decode<Base64Variant::URL>>>({description, syntax, arguments, returned_value, examples, categories});
}
}

8
src/Functions/base64UrlEncode.cpp → src/Functions/base64URLEncode.cpp
View File

@ -5,16 +5,16 @@
namespace DB
{
REGISTER_FUNCTION(Base64UrlEncode)
REGISTER_FUNCTION(Base64URLEncode)
{
FunctionDocumentation::Description description = R"(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).)";
FunctionDocumentation::Syntax syntax = "base64UrlEncode(url)";
FunctionDocumentation::Syntax syntax = "base64URLEncode(url)";
FunctionDocumentation::Arguments arguments = {{"url", "String column or constant."}};
FunctionDocumentation::ReturnedValue returned_value = "A string containing the encoded value of the argument.";
FunctionDocumentation::Examples examples = {{"Example", "SELECT base64UrlEncode('https://clickhouse.com')", "aHR0cHM6Ly9jbGlja2hvdXNlLmNvbQ"}};
FunctionDocumentation::Examples examples = {{"Example", "SELECT base64URLEncode('https://clickhouse.com')", "aHR0cHM6Ly9jbGlja2hvdXNlLmNvbQ"}};
FunctionDocumentation::Categories categories = {"String encoding"};
factory.registerFunction<FunctionBase64Conversion<Base64Encode<Base64Variant::Url>>>({description, syntax, arguments, returned_value, examples, categories});
factory.registerFunction<FunctionBase64Conversion<Base64Encode<Base64Variant::URL>>>({description, syntax, arguments, returned_value, examples, categories});
}
}

15
src/Functions/parseDateTime.cpp
View File

@ -978,8 +978,7 @@ namespace
[[nodiscard]]
static PosOrError mysqlAmericanDate(Pos cur, Pos end, const String & fragment, DateTime<error_handling> & date)
{
if (auto status = checkSpace(cur, end, 8, "mysqlAmericanDate requires size >= 8", fragment))
return tl::unexpected(status.error());
RETURN_ERROR_IF_FAILED(checkSpace(cur, end, 8, "mysqlAmericanDate requires size >= 8", fragment))
Int32 month;
ASSIGN_RESULT_OR_RETURN_ERROR(cur, (readNumber2<Int32, NeedCheckSpace::No>(cur, end, fragment, month)))
@ -993,7 +992,7 @@ namespace
Int32 year;
ASSIGN_RESULT_OR_RETURN_ERROR(cur, (readNumber2<Int32, NeedCheckSpace::No>(cur, end, fragment, year)))
RETURN_ERROR_IF_FAILED(date.setYear(year))
RETURN_ERROR_IF_FAILED(date.setYear(year + 2000))
return cur;
}
@ -1015,8 +1014,7 @@ namespace
[[nodiscard]]
static PosOrError mysqlISO8601Date(Pos cur, Pos end, const String & fragment, DateTime<error_handling> & date)
{
if (auto status = checkSpace(cur, end, 10, "mysqlISO8601Date requires size >= 10", fragment))
return tl::unexpected(status.error());
RETURN_ERROR_IF_FAILED(checkSpace(cur, end, 10, "mysqlISO8601Date requires size >= 10", fragment))
Int32 year;
Int32 month;
@ -1462,8 +1460,7 @@ namespace
[[nodiscard]]
static PosOrError jodaDayOfWeekText(size_t /*min_represent_digits*/, Pos cur, Pos end, const String & fragment, DateTime<error_handling> & date)
{
if (auto result= checkSpace(cur, end, 3, "jodaDayOfWeekText requires size >= 3", fragment); !result.has_value())
return tl::unexpected(result.error());
RETURN_ERROR_IF_FAILED(checkSpace(cur, end, 3, "jodaDayOfWeekText requires size >= 3", fragment))
String text1(cur, 3);
boost::to_lower(text1);
@ -1556,8 +1553,8 @@ namespace
Int32 day_of_month;
ASSIGN_RESULT_OR_RETURN_ERROR(cur, (readNumberWithVariableLength(
cur, end, false, false, false, repetitions, std::max(repetitions, 2uz), fragment, day_of_month)))
if (auto res = date.setDayOfMonth(day_of_month); !res.has_value())
return tl::unexpected(res.error());
RETURN_ERROR_IF_FAILED(date.setDayOfMonth(day_of_month))
return cur;
}

354
src/Functions/tests/gtest_ternary_logic.cpp
View File

@ -1,354 +0,0 @@
#include <algorithm>
#include <cstring>
#include <vector>
#include <string>
#include <type_traits>
#include <gtest/gtest.h>
#include <Columns/ColumnNothing.h>
#include <Columns/ColumnsNumber.h>
#include <Functions/FunctionsLogical.h>
// I know that inclusion of .cpp is not good at all
#include <Functions/FunctionsLogical.cpp> // NOLINT
using namespace DB;
using TernaryValues = std::vector<Ternary::ResultType>;
struct LinearCongruentialGenerator
{
/// Constants from `man lrand48_r`.
static constexpr UInt64 a = 0x5DEECE66D;
static constexpr UInt64 c = 0xB;
/// And this is from `head -c8 /dev/urandom | xxd -p`
UInt64 current = 0x09826f4a081cee35ULL;
UInt32 next()
{
current = current * a + c;
return static_cast<UInt32>(current >> 16);
}
};
void generateRandomTernaryValue(LinearCongruentialGenerator & gen, Ternary::ResultType * output, size_t size, double false_ratio, double null_ratio)
{
/// The LinearCongruentialGenerator generates nonnegative integers uniformly distributed over the interval [0, 2^32).
/// See https://linux.die.net/man/3/nrand48
double false_percentile = false_ratio;
double null_percentile = false_ratio + null_ratio;
false_percentile = false_percentile > 1 ? 1 : false_percentile;
null_percentile = null_percentile > 1 ? 1 : null_percentile;
UInt32 false_threshold = static_cast<UInt32>(static_cast<double>(std::numeric_limits<UInt32>::max()) * false_percentile);
UInt32 null_threshold = static_cast<UInt32>(static_cast<double>(std::numeric_limits<UInt32>::max()) * null_percentile);
for (Ternary::ResultType * end = output + size; output != end; ++output)
{
UInt32 val = gen.next();
*output = val < false_threshold ? Ternary::False : (val < null_threshold ? Ternary::Null : Ternary::True);
}
}
template<typename T>
ColumnPtr createColumnNullable(const Ternary::ResultType * ternary_values, size_t size)
{
auto nested_column = ColumnVector<T>::create(size);
auto null_map = ColumnUInt8::create(size);
auto & nested_column_data = nested_column->getData();
auto & null_map_data = null_map->getData();
for (size_t i = 0; i < size; ++i)
{
if (ternary_values[i] == Ternary::Null)
{
null_map_data[i] = 1;
nested_column_data[i] = 0;
}
else if (ternary_values[i] == Ternary::True)
{
null_map_data[i] = 0;
nested_column_data[i] = 100;
}
else
{
null_map_data[i] = 0;
nested_column_data[i] = 0;
}
}
return ColumnNullable::create(std::move(nested_column), std::move(null_map));
}
template<typename T>
ColumnPtr createColumnVector(const Ternary::ResultType * ternary_values, size_t size)
{
auto column = ColumnVector<T>::create(size);
auto & column_data = column->getData();
for (size_t i = 0; i < size; ++i)
{
if (ternary_values[i] == Ternary::True)
{
column_data[i] = 100;
}
else
{
column_data[i] = 0;
}
}
return column;
}
template<typename ColumnType, typename T>
ColumnPtr createRandomColumn(LinearCongruentialGenerator & gen, TernaryValues & ternary_values)
{
size_t size = ternary_values.size();
Ternary::ResultType * ternary_data = ternary_values.data();
if constexpr (std::is_same_v<ColumnType, ColumnNullable>)
{
generateRandomTernaryValue(gen, ternary_data, size, 0.3, 0.7);
return createColumnNullable<T>(ternary_data, size);
}
else if constexpr (std::is_same_v<ColumnType, ColumnVector<UInt8>>)
{
generateRandomTernaryValue(gen, ternary_data, size, 0.5, 0);
return createColumnVector<T>(ternary_data, size);
}
else
{
auto nested_col = ColumnNothing::create(size);
auto null_map = ColumnUInt8::create(size);
memset(ternary_data, Ternary::Null, size);
return ColumnNullable::create(std::move(nested_col), std::move(null_map));
}
}
/* The truth table of ternary And and Or operations:
* +-------+-------+---------+--------+
* | a | b | a And b | a Or b |
* +-------+-------+---------+--------+
* | False | False | False | False |
* | False | Null | False | Null |
* | False | True | False | True |
* | Null | False | False | Null |
* | Null | Null | Null | Null |
* | Null | True | Null | True |
* | True | False | False | True |
* | True | Null | Null | True |
* | True | True | True | True |
* +-------+-------+---------+--------+
*
* https://en.wikibooks.org/wiki/Structured_Query_Language/NULLs_and_the_Three_Valued_Logic
*/
template <typename Op, typename T>
bool testTernaryLogicTruthTable()
{
constexpr size_t size = 9;
Ternary::ResultType col_a_ternary[] = {Ternary::False, Ternary::False, Ternary::False, Ternary::Null, Ternary::Null, Ternary::Null, Ternary::True, Ternary::True, Ternary::True};
Ternary::ResultType col_b_ternary[] = {Ternary::False, Ternary::Null, Ternary::True, Ternary::False, Ternary::Null, Ternary::True,Ternary::False, Ternary::Null, Ternary::True};
Ternary::ResultType and_expected_ternary[] = {Ternary::False, Ternary::False, Ternary::False, Ternary::False, Ternary::Null, Ternary::Null,Ternary::False, Ternary::Null, Ternary::True};
Ternary::ResultType or_expected_ternary[] = {Ternary::False, Ternary::Null, Ternary::True, Ternary::Null, Ternary::Null, Ternary::True,Ternary::True, Ternary::True, Ternary::True};
Ternary::ResultType * expected_ternary;
if constexpr (std::is_same_v<Op, AndImpl>)
{
expected_ternary = and_expected_ternary;
}
else
{
expected_ternary = or_expected_ternary;
}
auto col_a = createColumnNullable<T>(col_a_ternary, size);
auto col_b = createColumnNullable<T>(col_b_ternary, size);
ColumnRawPtrs arguments = {col_a.get(), col_b.get()};
auto col_res = ColumnUInt8::create(size);
auto & col_res_data = col_res->getData();
OperationApplier<Op, AssociativeGenericApplierImpl>::apply(arguments, col_res->getData(), false);
for (size_t i = 0; i < size; ++i)
{
if (col_res_data[i] != expected_ternary[i]) return false;
}
return true;
}
template <typename Op, typename LeftColumn, typename RightColumn>
bool testTernaryLogicOfTwoColumns(size_t size)
{
LinearCongruentialGenerator gen;
TernaryValues left_column_ternary(size);
TernaryValues right_column_ternary(size);
TernaryValues expected_ternary(size);
ColumnPtr left = createRandomColumn<LeftColumn, UInt8>(gen, left_column_ternary);
ColumnPtr right = createRandomColumn<RightColumn, UInt8>(gen, right_column_ternary);
for (size_t i = 0; i < size; ++i)
{
/// Given that False is less than Null and Null is less than True, the And operation can be implemented
/// with std::min, and the Or operation can be implemented with std::max.
if constexpr (std::is_same_v<Op, AndImpl>)
{
expected_ternary[i] = std::min(left_column_ternary[i], right_column_ternary[i]);
}
else
{
expected_ternary[i] = std::max(left_column_ternary[i], right_column_ternary[i]);
}
}
ColumnRawPtrs arguments = {left.get(), right.get()};
auto col_res = ColumnUInt8::create(size);
auto & col_res_data = col_res->getData();
OperationApplier<Op, AssociativeGenericApplierImpl>::apply(arguments, col_res->getData(), false);
for (size_t i = 0; i < size; ++i)
{
if (col_res_data[i] != expected_ternary[i]) return false;
}
return true;
}
TEST(TernaryLogicTruthTable, NestedUInt8)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, UInt8>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, UInt8>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedUInt16)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, UInt16>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, UInt16>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedUInt32)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, UInt32>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, UInt32>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedUInt64)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, UInt64>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, UInt64>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedInt8)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Int8>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Int8>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedInt16)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Int16>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Int16>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedInt32)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Int32>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Int32>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedInt64)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Int64>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Int64>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedFloat32)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Float32>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Float32>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTruthTable, NestedFloat64)
{
bool test_1 = testTernaryLogicTruthTable<AndImpl, Float64>();
bool test_2 = testTernaryLogicTruthTable<OrImpl, Float64>();
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, TwoNullable)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnNullable, ColumnNullable>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnNullable, ColumnNullable>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, TwoVector)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnUInt8, ColumnUInt8>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnUInt8, ColumnUInt8>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, TwoNothing)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnNothing, ColumnNothing>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnNothing, ColumnNothing>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, NullableVector)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnNullable, ColumnUInt8>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnNullable, ColumnUInt8>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, NullableNothing)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnNullable, ColumnNothing>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnNullable, ColumnNothing>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}
TEST(TernaryLogicTwoColumns, VectorNothing)
{
bool test_1 = testTernaryLogicOfTwoColumns<AndImpl, ColumnUInt8, ColumnNothing>(100 /*size*/);
bool test_2 = testTernaryLogicOfTwoColumns<OrImpl, ColumnUInt8, ColumnNothing>(100 /*size*/);
ASSERT_EQ(test_1, true);
ASSERT_EQ(test_2, true);
}

12
src/Functions/tryBase64UrlDecode.cpp → src/Functions/tryBase64URLDecode.cpp
View File

@ -5,16 +5,16 @@
namespace DB
{
REGISTER_FUNCTION(TryBase64UrlDecode)
REGISTER_FUNCTION(TryBase64URLDecode)
{
FunctionDocumentation::Description description = R"(Decodes an URL from base64, like base64UrlDecode but returns an empty string in case of an error.)";
FunctionDocumentation::Syntax syntax = "tryBase64UrlDecode(encodedUrl)";
FunctionDocumentation::Arguments arguments = {{"encodedUrl", "String column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string."}};
FunctionDocumentation::Description description = R"(Decodes an URL from base64, like base64URLDecode but returns an empty string in case of an error.)";
FunctionDocumentation::Syntax syntax = "tryBase64URLDecode(encodedUrl)";
FunctionDocumentation::Arguments arguments = {{"encodedURL", "String column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string."}};
FunctionDocumentation::ReturnedValue returned_value = "A string containing the decoded value of the argument.";
FunctionDocumentation::Examples examples = {{"valid", "SELECT tryBase64UrlDecode('aHR0cHM6Ly9jbGlja2hvdXNlLmNvbQ')", "https://clickhouse.com"}, {"invalid", "SELECT tryBase64UrlDecode('aHR0cHM6Ly9jbGlja')", ""}};
FunctionDocumentation::Examples examples = {{"valid", "SELECT tryBase64URLDecode('aHR0cHM6Ly9jbGlja2hvdXNlLmNvbQ')", "https://clickhouse.com"}, {"invalid", "SELECT tryBase64UrlDecode('aHR0cHM6Ly9jbGlja')", ""}};
FunctionDocumentation::Categories categories = {"String encoding"};
factory.registerFunction<FunctionBase64Conversion<TryBase64Decode<Base64Variant::Url>>>({description, syntax, arguments, returned_value, examples, categories});
factory.registerFunction<FunctionBase64Conversion<TryBase64Decode<Base64Variant::URL>>>({description, syntax, arguments, returned_value, examples, categories});
}
}

14
src/IO/CascadeWriteBuffer.cpp
View File

@ -83,6 +83,20 @@ void CascadeWriteBuffer::finalizeImpl()
}
}
void CascadeWriteBuffer::cancelImpl() noexcept
{
if (curr_buffer)
curr_buffer->position() = position();
for (auto & buf : prepared_sources)
{
if (buf)
{
buf->cancel();
}
}
}
WriteBuffer * CascadeWriteBuffer::setNextBuffer()
{
if (first_lazy_source_num <= curr_buffer_num && curr_buffer_num < num_sources)

3
src/IO/CascadeWriteBuffer.h
View File

@ -16,7 +16,7 @@ namespace ErrorCodes
* (lazy_sources contains not pointers themself, but their delayed constructors)
*
* Firtly, CascadeWriteBuffer redirects data to first buffer of the sequence
* If current WriteBuffer cannot receive data anymore, it throws special exception MemoryWriteBuffer::CurrentBufferExhausted in nextImpl() body,
* If current WriteBuffer cannot receive data anymore, it throws special exception WriteBuffer::CurrentBufferExhausted in nextImpl() body,
* CascadeWriteBuffer prepare next buffer and continuously redirects data to it.
* If there are no buffers anymore CascadeWriteBuffer throws an exception.
*
@ -48,6 +48,7 @@ public:
private:
void finalizeImpl() override;
void cancelImpl() noexcept override;
WriteBuffer * setNextBuffer();

4
src/IO/MemoryReadWriteBuffer.h
View File

@ -16,11 +16,11 @@ namespace DB
class MemoryWriteBuffer : public WriteBuffer, public IReadableWriteBuffer, boost::noncopyable, private Allocator<false>
{
public:
/// Special exception to throw when the current WriteBuffer cannot receive data
/// Special exception to throw when the current MemoryWriteBuffer cannot receive data
class CurrentBufferExhausted : public std::exception
{
public:
const char * what() const noexcept override { return "MemoryWriteBuffer limit is exhausted"; }
const char * what() const noexcept override { return "WriteBuffer limit is exhausted"; }
};
/// Use max_total_size_ = 0 for unlimited storage

15
src/IO/S3/Credentials.cpp
View File

@ -9,6 +9,21 @@ namespace ErrorCodes
extern const int UNSUPPORTED_METHOD;
}
namespace S3
{
std::string tryGetRunningAvailabilityZone()
{
try
{
return getRunningAvailabilityZone();
}
catch (...)
{
tryLogCurrentException("tryGetRunningAvailabilityZone");
return "";
}
}
}
}
#if USE_AWS_S3

2
src/IO/S3/Credentials.h
View File

@ -24,6 +24,7 @@ static inline constexpr char GCP_METADATA_SERVICE_ENDPOINT[] = "http://metadata.
/// getRunningAvailabilityZone returns the availability zone of the underlying compute resources where the current process runs.
std::string getRunningAvailabilityZone();
std::string tryGetRunningAvailabilityZone();
class AWSEC2MetadataClient : public Aws::Internal::AWSHttpResourceClient
{
@ -195,6 +196,7 @@ namespace DB
namespace S3
{
std::string getRunningAvailabilityZone();
std::string tryGetRunningAvailabilityZone();
}
}

13
src/IO/WriteBuffer.cpp
View File

@ -11,7 +11,7 @@ namespace DB
WriteBuffer::~WriteBuffer()
{
// That destructor could be call with finalized=false in case of exceptions
if (count() > 0 && !finalized)
if (count() > 0 && !finalized && !canceled)
{
/// It is totally OK to destroy instance without finalization when an exception occurs
/// However it is suspicious to destroy instance without finalization at the green path
@ -20,7 +20,7 @@ WriteBuffer::~WriteBuffer()
LoggerPtr log = getLogger("WriteBuffer");
LOG_ERROR(
log,
"WriteBuffer is not finalized when destructor is called. "
"WriteBuffer is neither finalized nor canceled when destructor is called. "
"No exceptions in flight are detected. "
"The file might not be written at all or might be truncated. "
"Stack trace: {}",
@ -30,4 +30,13 @@ WriteBuffer::~WriteBuffer()
}
}
void WriteBuffer::cancel() noexcept
{
if (canceled || finalized)
return;
LockMemoryExceptionInThread lock(VariableContext::Global);
cancelImpl();
canceled = true;
}
}

16
src/IO/WriteBuffer.h
View File

@ -59,6 +59,7 @@ public:
*/
pos = working_buffer.begin();
bytes += bytes_in_buffer;
throw;
}
@ -75,7 +76,6 @@ public:
next();
}
void write(const char * from, size_t n)
{
if (finalized)
@ -121,6 +121,9 @@ public:
if (finalized)
return;
if (canceled)
throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot finalize buffer after cancellation.");
LockMemoryExceptionInThread lock(VariableContext::Global);
try
{
@ -130,11 +133,15 @@ public:
catch (...)
{
pos = working_buffer.begin();
finalized = true;
cancel();
throw;
}
}
void cancel() noexcept;
/// Wait for data to be reliably written. Mainly, call fsync for fd.
/// May be called after finalize() if needed.
virtual void sync()
@ -150,7 +157,12 @@ protected:
next();
}
virtual void cancelImpl() noexcept
{
}
bool finalized = false;
bool canceled = false;
private:
/** Write the data in the buffer (from the beginning of the buffer to the current position).

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