diff --git a/.gitignore b/.gitignore index 4bc162c1b0f..8a745655cbf 100644 --- a/.gitignore +++ b/.gitignore @@ -159,6 +159,7 @@ website/package-lock.json /programs/server/store /programs/server/uuid /programs/server/coordination +/programs/server/workload # temporary test files tests/queries/0_stateless/test_* diff --git a/.gitmodules b/.gitmodules index bbc8fc7d06c..a3b6450032a 100644 --- a/.gitmodules +++ b/.gitmodules @@ -332,7 +332,7 @@ url = https://github.com/ClickHouse/usearch.git [submodule "contrib/SimSIMD"] path = contrib/SimSIMD - url = https://github.com/ashvardanian/SimSIMD.git + url = https://github.com/ClickHouse/SimSIMD.git [submodule "contrib/FP16"] path = contrib/FP16 url = https://github.com/Maratyszcza/FP16.git diff --git a/CHANGELOG.md b/CHANGELOG.md index 6c0d21a4698..dacee73440f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,4 +1,5 @@ ### Table of Contents +**[ClickHouse release v24.10, 2024-10-31](#2410)**
**[ClickHouse release v24.9, 2024-09-26](#249)**
**[ClickHouse release v24.8 LTS, 2024-08-20](#248)**
**[ClickHouse release v24.7, 2024-07-30](#247)**
@@ -12,6 +13,165 @@ # 2024 Changelog +### ClickHouse release 24.10, 2024-10-31 + +#### Backward Incompatible Change +* Allow to write `SETTINGS` before `FORMAT` in a chain of queries with `UNION` when subqueries are inside parentheses. This closes [#39712](https://github.com/ClickHouse/ClickHouse/issues/39712). Change the behavior when a query has the SETTINGS clause specified twice in a sequence. The closest SETTINGS clause will have a preference for the corresponding subquery. In the previous versions, the outermost SETTINGS clause could take a preference over the inner one. [#68614](https://github.com/ClickHouse/ClickHouse/pull/68614) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Reordering of filter conditions from `[PRE]WHERE` clause is now allowed by default. It could be disabled by setting `allow_reorder_prewhere_conditions` to `false`. [#70657](https://github.com/ClickHouse/ClickHouse/pull/70657) ([Nikita Taranov](https://github.com/nickitat)). +* Remove the `idxd-config` library, which has an incompatible license. This also removes the experimental Intel DeflateQPL codec. [#70987](https://github.com/ClickHouse/ClickHouse/pull/70987) ([Alexey Milovidov](https://github.com/alexey-milovidov)). + +#### New Feature +* Allow to grant access to the wildcard prefixes. `GRANT SELECT ON db.table_pefix_* TO user`. [#65311](https://github.com/ClickHouse/ClickHouse/pull/65311) ([pufit](https://github.com/pufit)). +* If you press space bar during query runtime, the client will display a real-time table with detailed metrics. You can enable it globally with the new `--progress-table` option in clickhouse-client; a new `--enable-progress-table-toggle` is associated with the `--progress-table` option, and toggles the rendering of the progress table by pressing the control key (Space). [#63689](https://github.com/ClickHouse/ClickHouse/pull/63689) ([Maria Khristenko](https://github.com/mariaKhr)), [#70423](https://github.com/ClickHouse/ClickHouse/pull/70423) ([Julia Kartseva](https://github.com/jkartseva)). +* Allow to cache read files for object storage table engines and data lakes using hash from ETag + file path as cache key. [#70135](https://github.com/ClickHouse/ClickHouse/pull/70135) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Support creating a table with a query: `CREATE TABLE ... CLONE AS ...`. It clones the source table's schema and then attaches all partitions to the newly created table. This feature is only supported with tables of the `MergeTree` family Closes [#65015](https://github.com/ClickHouse/ClickHouse/issues/65015). [#69091](https://github.com/ClickHouse/ClickHouse/pull/69091) ([tuanpach](https://github.com/tuanpach)). +* Add a new system table, `system.query_metric_log` which contains history of memory and metric values from table system.events for individual queries, periodically flushed to disk. [#66532](https://github.com/ClickHouse/ClickHouse/pull/66532) ([Pablo Marcos](https://github.com/pamarcos)). +* A simple SELECT query can be written with implicit SELECT to enable calculator-style expressions, e.g., `ch "1 + 2"`. This is controlled by a new setting, `implicit_select`. [#68502](https://github.com/ClickHouse/ClickHouse/pull/68502) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Support the `--copy` mode for clickhouse local as a shortcut for format conversion [#68503](https://github.com/ClickHouse/ClickHouse/issues/68503). [#68583](https://github.com/ClickHouse/ClickHouse/pull/68583) ([Denis Hananein](https://github.com/denis-hananein)). +* Add a builtin HTML page for visualizing merges which is available at the `/merges` path. [#70821](https://github.com/ClickHouse/ClickHouse/pull/70821) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add support for `arrayUnion` function. [#68989](https://github.com/ClickHouse/ClickHouse/pull/68989) ([Peter Nguyen](https://github.com/petern48)). +* Allow parametrised SQL aliases. [#50665](https://github.com/ClickHouse/ClickHouse/pull/50665) ([Anton Kozlov](https://github.com/tonickkozlov)). +* A new aggregate function `quantileExactWeightedInterpolated`, which is a interpolated version based on quantileExactWeighted. Some people may wonder why we need a new `quantileExactWeightedInterpolated` since we already have `quantileExactInterpolatedWeighted`. The reason is the new one is more accurate than the old one. This is for spark compatibility. [#69619](https://github.com/ClickHouse/ClickHouse/pull/69619) ([李扬](https://github.com/taiyang-li)). +* A new function `arrayElementOrNull`. It returns `NULL` if the array index is out of range or a Map key not found. [#69646](https://github.com/ClickHouse/ClickHouse/pull/69646) ([李扬](https://github.com/taiyang-li)). +* Allows users to specify regular expressions through new `message_regexp` and `message_regexp_negative` fields in the `config.xml` file to filter out logging. The logging is applied to the formatted un-colored text for the most intuitive developer experience. [#69657](https://github.com/ClickHouse/ClickHouse/pull/69657) ([Peter Nguyen](https://github.com/petern48)). +* Added `RIPEMD160` function, which computes the RIPEMD-160 cryptographic hash of a string. Example: `SELECT HEX(RIPEMD160('The quick brown fox jumps over the lazy dog'))` returns `37F332F68DB77BD9D7EDD4969571AD671CF9DD3B`. [#70087](https://github.com/ClickHouse/ClickHouse/pull/70087) ([Dergousov Maxim](https://github.com/m7kss1)). +* Support reading `Iceberg` tables on `HDFS`. [#70268](https://github.com/ClickHouse/ClickHouse/pull/70268) ([flynn](https://github.com/ucasfl)). +* Support for CTE in the form of `WITH ... INSERT`, as previously we only supported `INSERT ... WITH ...`. [#70593](https://github.com/ClickHouse/ClickHouse/pull/70593) ([Shichao Jin](https://github.com/jsc0218)). +* MongoDB integration: support for all MongoDB types, support for WHERE and ORDER BY statements on MongoDB side, restriction for expressions unsupported by MongoDB. Note that the new inegration is disabled by default, to use it, please set `` to `false` in server config. [#63279](https://github.com/ClickHouse/ClickHouse/pull/63279) ([Kirill Nikiforov](https://github.com/allmazz)). +* A new function `getSettingOrDefault` added to return the default value and avoid exception if a custom setting is not found in the current profile. [#69917](https://github.com/ClickHouse/ClickHouse/pull/69917) ([Shankar](https://github.com/shiyer7474)). + +#### Experimental feature +* Refreshable materialized views are production ready. [#70550](https://github.com/ClickHouse/ClickHouse/pull/70550) ([Michael Kolupaev](https://github.com/al13n321)). Refreshable materialized views are now supported in Replicated databases. [#60669](https://github.com/ClickHouse/ClickHouse/pull/60669) ([Michael Kolupaev](https://github.com/al13n321)). +* Parallel replicas are moved from experimental to beta. Reworked settings that control the behavior of parallel replicas algorithms. A quick recap: ClickHouse has four different algorithms for parallel reading involving multiple replicas, which is reflected in the setting `parallel_replicas_mode`, the default value for it is `read_tasks` Additionally, the toggle-switch setting `enable_parallel_replicas` has been added. [#63151](https://github.com/ClickHouse/ClickHouse/pull/63151) ([Alexey Milovidov](https://github.com/alexey-milovidov)), ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Support for the `Dynamic` type in most functions by executing them on internal types inside `Dynamic`. [#69691](https://github.com/ClickHouse/ClickHouse/pull/69691) ([Pavel Kruglov](https://github.com/Avogar)). +* Allow to read/write the `JSON` type as a binary string in `RowBinary` format under settings `input_format_binary_read_json_as_string/output_format_binary_write_json_as_string`. [#70288](https://github.com/ClickHouse/ClickHouse/pull/70288) ([Pavel Kruglov](https://github.com/Avogar)). +* Allow to serialize/deserialize `JSON` column as single String column in the Native format. For output use setting `output_format_native_write_json_as_string`. For input, use serialization version `1` before the column data. [#70312](https://github.com/ClickHouse/ClickHouse/pull/70312) ([Pavel Kruglov](https://github.com/Avogar)). +* Introduced a special (experimental) mode of a merge selector for MergeTree tables which makes it more aggressive for the partitions that are close to the limit by the number of parts. It is controlled by the `merge_selector_use_blurry_base` MergeTree-level setting. [#70645](https://github.com/ClickHouse/ClickHouse/pull/70645) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Implement generic ser/de between Avro's `Union` and ClickHouse's `Variant` types. Resolves [#69713](https://github.com/ClickHouse/ClickHouse/issues/69713). [#69712](https://github.com/ClickHouse/ClickHouse/pull/69712) ([Jiří Kozlovský](https://github.com/jirislav)). + +#### Performance Improvement +* Refactor `IDisk` and `IObjectStorage` for better performance. Tables from `plain` and `plain_rewritable` object storages will initialize faster. [#68146](https://github.com/ClickHouse/ClickHouse/pull/68146) ([Alexey Milovidov](https://github.com/alexey-milovidov), [Julia Kartseva](https://github.com/jkartseva)). Do not call the LIST object storage API when determining if a file or directory exists on the plain rewritable disk, as it can be cost-inefficient. [#70852](https://github.com/ClickHouse/ClickHouse/pull/70852) ([Julia Kartseva](https://github.com/jkartseva)). Reduce the number of object storage HEAD API requests in the plain_rewritable disk. [#70915](https://github.com/ClickHouse/ClickHouse/pull/70915) ([Julia Kartseva](https://github.com/jkartseva)). +* Added an ability to parse data directly into sparse columns. [#69828](https://github.com/ClickHouse/ClickHouse/pull/69828) ([Anton Popov](https://github.com/CurtizJ)). +* Improved performance of parsing formats with high number of missed values (e.g. `JSONEachRow`). [#69875](https://github.com/ClickHouse/ClickHouse/pull/69875) ([Anton Popov](https://github.com/CurtizJ)). +* Supports parallel reading of parquet row groups and prefetching of row groups in single-threaded mode. [#69862](https://github.com/ClickHouse/ClickHouse/pull/69862) ([LiuNeng](https://github.com/liuneng1994)). +* Support minmax index for `pointInPolygon`. [#62085](https://github.com/ClickHouse/ClickHouse/pull/62085) ([JackyWoo](https://github.com/JackyWoo)). +* Use bloom filters when reading Parquet files. [#62966](https://github.com/ClickHouse/ClickHouse/pull/62966) ([Arthur Passos](https://github.com/arthurpassos)). +* Lock-free parts rename to avoid INSERT affect SELECT (due to parts lock) (under normal circumstances with `fsync_part_directory`, QPS of SELECT with INSERT in parallel, increased 2x, under heavy load the effect is even bigger). Note, this only includes `ReplicatedMergeTree` for now. [#64955](https://github.com/ClickHouse/ClickHouse/pull/64955) ([Azat Khuzhin](https://github.com/azat)). +* Respect `ttl_only_drop_parts` on `materialize ttl`; only read necessary columns to recalculate TTL and drop parts by replacing them with an empty one. [#65488](https://github.com/ClickHouse/ClickHouse/pull/65488) ([Andrey Zvonov](https://github.com/zvonand)). +* Optimized thread creation in the ThreadPool to minimize lock contention. Thread creation is now performed outside of the critical section to avoid delays in job scheduling and thread management under high load conditions. This leads to a much more responsive ClickHouse under heavy concurrent load. [#68694](https://github.com/ClickHouse/ClickHouse/pull/68694) ([filimonov](https://github.com/filimonov)). +* Enable reading `LowCardinality` string columns from `ORC`. [#69481](https://github.com/ClickHouse/ClickHouse/pull/69481) ([李扬](https://github.com/taiyang-li)). +* Use `LowCardinality` for `ProfileEvents` in system logs such as `part_log`, `query_views_log`, `filesystem_cache_log`. [#70152](https://github.com/ClickHouse/ClickHouse/pull/70152) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Improve performance of `fromUnixTimestamp`/`toUnixTimestamp` functions. [#71042](https://github.com/ClickHouse/ClickHouse/pull/71042) ([kevinyhzou](https://github.com/KevinyhZou)). +* Don't disable nonblocking read from page cache for the entire server when reading from a blocking I/O. This was leading to a poorer performance when a single filesystem (e.g., tmpfs) didn't support the `preadv2` syscall while others do. [#70299](https://github.com/ClickHouse/ClickHouse/pull/70299) ([Antonio Andelic](https://github.com/antonio2368)). +* `ALTER TABLE .. REPLACE PARTITION` doesn't wait anymore for mutations/merges that happen in other partitions. [#59138](https://github.com/ClickHouse/ClickHouse/pull/59138) ([Vasily Nemkov](https://github.com/Enmk)). +* Don't do validation when synchronizing ACL from Keeper. It's validating during creation. It shouldn't matter that much, but there are installations with tens of thousands or even more user created, and the unnecessary hash validation can take a long time to finish during server startup (it synchronizes everything from keeper). [#70644](https://github.com/ClickHouse/ClickHouse/pull/70644) ([Raúl Marín](https://github.com/Algunenano)). + +#### Improvement +* `CREATE TABLE AS` will copy `PRIMARY KEY`, `ORDER BY`, and similar clauses (of `MergeTree` tables). [#69739](https://github.com/ClickHouse/ClickHouse/pull/69739) ([sakulali](https://github.com/sakulali)). +* Support 64-bit XID in Keeper. It can be enabled with the `use_xid_64` configuration value. [#69908](https://github.com/ClickHouse/ClickHouse/pull/69908) ([Antonio Andelic](https://github.com/antonio2368)). +* Command-line arguments for Bool settings are set to true when no value is provided for the argument (e.g. `clickhouse-client --optimize_aggregation_in_order --query "SELECT 1"`). [#70459](https://github.com/ClickHouse/ClickHouse/pull/70459) ([davidtsuk](https://github.com/davidtsuk)). +* Added user-level settings `min_free_disk_bytes_to_throw_insert` and `min_free_disk_ratio_to_throw_insert` to prevent insertions on disks that are almost full. [#69755](https://github.com/ClickHouse/ClickHouse/pull/69755) ([Marco Vilas Boas](https://github.com/marco-vb)). +* Embedded documentation for settings will be strictly more detailed and complete than the documentation on the website. This is the first step before making the website documentation always auto-generated from the source code. This has long-standing implications: - it will be guaranteed to have every setting; - there is no chance of having default values obsolete; - we can generate this documentation for each ClickHouse version; - the documentation can be displayed by the server itself even without Internet access. Generate the docs on the website from the source code. [#70289](https://github.com/ClickHouse/ClickHouse/pull/70289) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Allow empty needle in the function `replace`, the same behavior with PostgreSQL. [#69918](https://github.com/ClickHouse/ClickHouse/pull/69918) ([zhanglistar](https://github.com/zhanglistar)). +* Allow empty needle in functions `replaceRegexp*`. [#70053](https://github.com/ClickHouse/ClickHouse/pull/70053) ([zhanglistar](https://github.com/zhanglistar)). +* Symbolic links for tables in the `data/database_name/` directory are created for the actual paths to the table's data, depending on the storage policy, instead of the `store/...` directory on the default disk. [#61777](https://github.com/ClickHouse/ClickHouse/pull/61777) ([Kirill](https://github.com/kirillgarbar)). +* While parsing an `Enum` field from `JSON`, a string containing an integer will be interpreted as the corresponding `Enum` element. This closes [#65119](https://github.com/ClickHouse/ClickHouse/issues/65119). [#66801](https://github.com/ClickHouse/ClickHouse/pull/66801) ([scanhex12](https://github.com/scanhex12)). +* Allow `TRIM` -ing `LEADING` or `TRAILING` empty string as a no-op. Closes [#67792](https://github.com/ClickHouse/ClickHouse/issues/67792). [#68455](https://github.com/ClickHouse/ClickHouse/pull/68455) ([Peter Nguyen](https://github.com/petern48)). +* Improve compatibility of `cast(timestamp as String)` with Spark. [#69179](https://github.com/ClickHouse/ClickHouse/pull/69179) ([Wenzheng Liu](https://github.com/lwz9103)). +* Always use the new analyzer to calculate constant expressions when `enable_analyzer` is set to `true`. Support calculation of `executable` table function arguments without using `SELECT` query for constant expressions. [#69292](https://github.com/ClickHouse/ClickHouse/pull/69292) ([Dmitry Novik](https://github.com/novikd)). +* Add a setting `enable_secure_identifiers` to disallow identifiers with special characters. [#69411](https://github.com/ClickHouse/ClickHouse/pull/69411) ([tuanpach](https://github.com/tuanpach)). +* Add `show_create_query_identifier_quoting_rule` to define identifier quoting behavior in the `SHOW CREATE TABLE` query result. Possible values: - `user_display`: When the identifiers is a keyword. - `when_necessary`: When the identifiers is one of `{"distinct", "all", "table"}` and when it could lead to ambiguity: column names, dictionary attribute names. - `always`: Always quote identifiers. [#69448](https://github.com/ClickHouse/ClickHouse/pull/69448) ([tuanpach](https://github.com/tuanpach)). +* Improve restoring of access entities' dependencies [#69563](https://github.com/ClickHouse/ClickHouse/pull/69563) ([Vitaly Baranov](https://github.com/vitlibar)). +* If you run `clickhouse-client` or other CLI application, and it starts up slowly due to an overloaded server, and you start typing your query, such as `SELECT`, the previous versions will display the remaining of the terminal echo contents before printing the greetings message, such as `SELECTClickHouse local version 24.10.1.1.` instead of `ClickHouse local version 24.10.1.1.`. Now it is fixed. This closes [#31696](https://github.com/ClickHouse/ClickHouse/issues/31696). [#69856](https://github.com/ClickHouse/ClickHouse/pull/69856) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add new column `readonly_duration` to the `system.replicas` table. Needed to be able to distinguish actual readonly replicas from sentinel ones in alerts. [#69871](https://github.com/ClickHouse/ClickHouse/pull/69871) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)). +* Change the type of `join_output_by_rowlist_perkey_rows_threshold` setting type to unsigned integer. [#69886](https://github.com/ClickHouse/ClickHouse/pull/69886) ([kevinyhzou](https://github.com/KevinyhZou)). +* Enhance OpenTelemetry span logging to include query settings. [#70011](https://github.com/ClickHouse/ClickHouse/pull/70011) ([sharathks118](https://github.com/sharathks118)). +* Add diagnostic info about higher-order array functions if lambda result type is unexpected. [#70093](https://github.com/ClickHouse/ClickHouse/pull/70093) ([ttanay](https://github.com/ttanay)). +* Keeper improvement: less locking during cluster changes. [#70275](https://github.com/ClickHouse/ClickHouse/pull/70275) ([Antonio Andelic](https://github.com/antonio2368)). +* Add `WITH IMPLICIT` and `FINAL` keywords to the `SHOW GRANTS` command. Fix a minor bug with implicit grants: [#70094](https://github.com/ClickHouse/ClickHouse/issues/70094). [#70293](https://github.com/ClickHouse/ClickHouse/pull/70293) ([pufit](https://github.com/pufit)). +* Respect `compatibility` for MergeTree settings. The `compatibility` value is taken from the `default` profile on server startup, and default MergeTree settings are changed accordingly. Further changes of the `compatibility` setting do not affect MergeTree settings. [#70322](https://github.com/ClickHouse/ClickHouse/pull/70322) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Avoid spamming the logs with large HTTP response bodies in case of errors during inter-server communication. [#70487](https://github.com/ClickHouse/ClickHouse/pull/70487) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Added a new setting `max_parts_to_move` to control the maximum number of parts that can be moved at once. [#70520](https://github.com/ClickHouse/ClickHouse/pull/70520) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Limit the frequency of certain log messages. [#70601](https://github.com/ClickHouse/ClickHouse/pull/70601) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* `CHECK TABLE` with `PART` qualifier was incorrectly formatted in the client. [#70660](https://github.com/ClickHouse/ClickHouse/pull/70660) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Support writing the column index and the offset index using parquet native writer. [#70669](https://github.com/ClickHouse/ClickHouse/pull/70669) ([LiuNeng](https://github.com/liuneng1994)). +* Support parsing `DateTime64` for microsecond and timezone in joda syntax ("joda" is a popular Java library for date and time, and the "joda syntax" is that library's style). [#70737](https://github.com/ClickHouse/ClickHouse/pull/70737) ([kevinyhzou](https://github.com/KevinyhZou)). +* Changed an approach to figure out if a cloud storage supports [batch delete](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html) or not. [#70786](https://github.com/ClickHouse/ClickHouse/pull/70786) ([Vitaly Baranov](https://github.com/vitlibar)). +* Support for Parquet page v2 in the native reader. [#70807](https://github.com/ClickHouse/ClickHouse/pull/70807) ([Arthur Passos](https://github.com/arthurpassos)). +* A check if table has both `storage_policy` and `disk` set. A check if a new storage policy is compatible with an old one when using `disk` setting is added. [#70839](https://github.com/ClickHouse/ClickHouse/pull/70839) ([Kirill](https://github.com/kirillgarbar)). +* Add `system.s3_queue_settings` and `system.azure_queue_settings`. [#70841](https://github.com/ClickHouse/ClickHouse/pull/70841) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Functions `base58Encode` and `base58Decode` now accept arguments of type `FixedString`. Example: `SELECT base58Encode(toFixedString('plaintext', 9));`. [#70846](https://github.com/ClickHouse/ClickHouse/pull/70846) ([Faizan Patel](https://github.com/faizan2786)). +* Add the `partition` column to every entry type of the part log. Previously, it was set only for some entries. This closes [#70819](https://github.com/ClickHouse/ClickHouse/issues/70819). [#70848](https://github.com/ClickHouse/ClickHouse/pull/70848) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add `MergeStart` and `MutateStart` events into `system.part_log` which helps with merges analysis and visualization. [#70850](https://github.com/ClickHouse/ClickHouse/pull/70850) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add a profile event about the number of merged source parts. It allows the monitoring of the fanout of the merge tree in production. [#70908](https://github.com/ClickHouse/ClickHouse/pull/70908) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Background downloads to the filesystem cache were enabled back. [#70929](https://github.com/ClickHouse/ClickHouse/pull/70929) ([Nikita Taranov](https://github.com/nickitat)). +* Add a new merge selector algorithm, named `Trivial`, for professional usage only. It is worse than the `Simple` merge selector. [#70969](https://github.com/ClickHouse/ClickHouse/pull/70969) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Support for atomic `CREATE OR REPLACE VIEW`. [#70536](https://github.com/ClickHouse/ClickHouse/pull/70536) ([tuanpach](https://github.com/tuanpach)) +* Added `strict_once` mode to aggregate function `windowFunnel` to avoid counting one event several times in case it matches multiple conditions, close [#21835](https://github.com/ClickHouse/ClickHouse/issues/21835). [#69738](https://github.com/ClickHouse/ClickHouse/pull/69738) ([Vladimir Cherkasov](https://github.com/vdimir)). + +#### Bug Fix (user-visible misbehavior in an official stable release) +* Apply configuration updates in global context object. It fixes issues like [#62308](https://github.com/ClickHouse/ClickHouse/issues/62308). [#62944](https://github.com/ClickHouse/ClickHouse/pull/62944) ([Amos Bird](https://github.com/amosbird)). +* Fix `ReadSettings` not using user set values, because defaults were only used. [#65625](https://github.com/ClickHouse/ClickHouse/pull/65625) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Fix type mismatch issue in `sumMapFiltered` when using signed arguments. [#58408](https://github.com/ClickHouse/ClickHouse/pull/58408) ([Chen768959](https://github.com/Chen768959)). +* Fix toHour-like conversion functions' monotonicity when optional time zone argument is passed. [#60264](https://github.com/ClickHouse/ClickHouse/pull/60264) ([Amos Bird](https://github.com/amosbird)). +* Relax `supportsPrewhere` check for `Merge` tables. This fixes [#61064](https://github.com/ClickHouse/ClickHouse/issues/61064). It was hardened unnecessarily in [#60082](https://github.com/ClickHouse/ClickHouse/issues/60082). [#61091](https://github.com/ClickHouse/ClickHouse/pull/61091) ([Amos Bird](https://github.com/amosbird)). +* Fix `use_concurrency_control` setting handling for proper `concurrent_threads_soft_limit_num` limit enforcing. This enables concurrency control by default because previously it was broken. [#61473](https://github.com/ClickHouse/ClickHouse/pull/61473) ([Sergei Trifonov](https://github.com/serxa)). +* Fix incorrect `JOIN ON` section optimization in case of `IS NULL` check under any other function (like `NOT`) that may lead to wrong results. Closes [#67915](https://github.com/ClickHouse/ClickHouse/issues/67915). [#68049](https://github.com/ClickHouse/ClickHouse/pull/68049) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Prevent `ALTER` queries that would make the `CREATE` query of tables invalid. [#68574](https://github.com/ClickHouse/ClickHouse/pull/68574) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)). +* Fix inconsistent AST formatting for `negate` (`-`) and `NOT` functions with tuples and arrays. [#68600](https://github.com/ClickHouse/ClickHouse/pull/68600) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix insertion of incomplete type into `Dynamic` during deserialization. It could lead to `Parameter out of bound` errors. [#69291](https://github.com/ClickHouse/ClickHouse/pull/69291) ([Pavel Kruglov](https://github.com/Avogar)). +* Zero-copy replication, which is experimental and should not be used in production: fix inf loop after `restore replica` in the replicated merge tree with zero copy. [#69293](https://github.com/CljmnickHouse/ClickHouse/pull/69293) ([MikhailBurdukov](https://github.com/MikhailBurdukov)). +* Return back default value of `processing_threads_num` as number of cpu cores in storage `S3Queue`. [#69384](https://github.com/ClickHouse/ClickHouse/pull/69384) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Bypass try/catch flow when de/serializing nested repeated protobuf to nested columns (fixes [#41971](https://github.com/ClickHouse/ClickHouse/issues/41971)). [#69556](https://github.com/ClickHouse/ClickHouse/pull/69556) ([Eliot Hautefeuille](https://github.com/hileef)). +* Fix crash during insertion into FixedString column in PostgreSQL engine. [#69584](https://github.com/ClickHouse/ClickHouse/pull/69584) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix crash when executing `create view t as (with recursive 42 as ttt select ttt);`. [#69676](https://github.com/ClickHouse/ClickHouse/pull/69676) ([Han Fei](https://github.com/hanfei1991)). +* Fixed `maxMapState` throwing 'Bad get' if value type is DateTime64. [#69787](https://github.com/ClickHouse/ClickHouse/pull/69787) ([Michael Kolupaev](https://github.com/al13n321)). +* Fix `getSubcolumn` with `LowCardinality` columns by overriding `useDefaultImplementationForLowCardinalityColumns` to return `true`. [#69831](https://github.com/ClickHouse/ClickHouse/pull/69831) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)). +* Fix permanent blocked distributed sends if a DROP of distributed table failed. [#69843](https://github.com/ClickHouse/ClickHouse/pull/69843) ([Azat Khuzhin](https://github.com/azat)). +* Fix non-cancellable queries containing WITH FILL with NaN keys. This closes [#69261](https://github.com/ClickHouse/ClickHouse/issues/69261). [#69845](https://github.com/ClickHouse/ClickHouse/pull/69845) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix analyzer default with old compatibility value. [#69895](https://github.com/ClickHouse/ClickHouse/pull/69895) ([Raúl Marín](https://github.com/Algunenano)). +* Don't check dependencies during CREATE OR REPLACE VIEW during DROP of old table. Previously CREATE OR REPLACE query failed when there are dependent tables of the recreated view. [#69907](https://github.com/ClickHouse/ClickHouse/pull/69907) ([Pavel Kruglov](https://github.com/Avogar)). +* Something for Decimal. Fixes [#69730](https://github.com/ClickHouse/ClickHouse/issues/69730). [#69978](https://github.com/ClickHouse/ClickHouse/pull/69978) ([Arthur Passos](https://github.com/arthurpassos)). +* Now DEFINER/INVOKER will work with parameterized views. [#69984](https://github.com/ClickHouse/ClickHouse/pull/69984) ([pufit](https://github.com/pufit)). +* Fix parsing for view's definers. [#69985](https://github.com/ClickHouse/ClickHouse/pull/69985) ([pufit](https://github.com/pufit)). +* Fixed a bug when the timezone could change the result of the query with a `Date` or `Date32` arguments. [#70036](https://github.com/ClickHouse/ClickHouse/pull/70036) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* Fixes `Block structure mismatch` for queries with nested views and `WHERE` condition. Fixes [#66209](https://github.com/ClickHouse/ClickHouse/issues/66209). [#70054](https://github.com/ClickHouse/ClickHouse/pull/70054) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Avoid reusing columns among different named tuples when evaluating `tuple` functions. This fixes [#70022](https://github.com/ClickHouse/ClickHouse/issues/70022). [#70103](https://github.com/ClickHouse/ClickHouse/pull/70103) ([Amos Bird](https://github.com/amosbird)). +* Fix wrong LOGICAL_ERROR when replacing literals in ranges. [#70122](https://github.com/ClickHouse/ClickHouse/pull/70122) ([Pablo Marcos](https://github.com/pamarcos)). +* Check for Nullable(Nothing) type during ALTER TABLE MODIFY COLUMN/QUERY to prevent tables with such data type. [#70123](https://github.com/ClickHouse/ClickHouse/pull/70123) ([Pavel Kruglov](https://github.com/Avogar)). +* Proper error message for illegal query `JOIN ... ON *` , close [#68650](https://github.com/ClickHouse/ClickHouse/issues/68650). [#70124](https://github.com/ClickHouse/ClickHouse/pull/70124) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix wrong result with skipping index. [#70127](https://github.com/ClickHouse/ClickHouse/pull/70127) ([Raúl Marín](https://github.com/Algunenano)). +* Fix data race in ColumnObject/ColumnTuple decompress method that could lead to heap use after free. [#70137](https://github.com/ClickHouse/ClickHouse/pull/70137) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix possible hung in ALTER COLUMN with Dynamic type. [#70144](https://github.com/ClickHouse/ClickHouse/pull/70144) ([Pavel Kruglov](https://github.com/Avogar)). +* Now ClickHouse will consider more errors as retriable and will not mark data parts as broken in case of such errors. [#70145](https://github.com/ClickHouse/ClickHouse/pull/70145) ([alesapin](https://github.com/alesapin)). +* Use correct `max_types` parameter during Dynamic type creation for JSON subcolumn. [#70147](https://github.com/ClickHouse/ClickHouse/pull/70147) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix the password being displayed in `system.query_log` for users with bcrypt password authentication method. [#70148](https://github.com/ClickHouse/ClickHouse/pull/70148) ([Nikolay Degterinsky](https://github.com/evillique)). +* Fix event counter for the native interface (InterfaceNativeSendBytes). [#70153](https://github.com/ClickHouse/ClickHouse/pull/70153) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)). +* Fix possible crash related to JSON columns. [#70172](https://github.com/ClickHouse/ClickHouse/pull/70172) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix multiple issues with arrayMin and arrayMax. [#70207](https://github.com/ClickHouse/ClickHouse/pull/70207) ([Raúl Marín](https://github.com/Algunenano)). +* Respect setting allow_simdjson in the JSON type parser. [#70218](https://github.com/ClickHouse/ClickHouse/pull/70218) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix a null pointer dereference on creating a materialized view with two selects and an `INTERSECT`, e.g. `CREATE MATERIALIZED VIEW v0 AS (SELECT 1) INTERSECT (SELECT 1);`. [#70264](https://github.com/ClickHouse/ClickHouse/pull/70264) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Don't modify global settings with startup scripts. Previously, changing a setting in a startup script would change it globally. [#70310](https://github.com/ClickHouse/ClickHouse/pull/70310) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix ALTER of `Dynamic` type with reducing max_types parameter that could lead to server crash. [#70328](https://github.com/ClickHouse/ClickHouse/pull/70328) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix crash when using WITH FILL incorrectly. [#70338](https://github.com/ClickHouse/ClickHouse/pull/70338) ([Raúl Marín](https://github.com/Algunenano)). +* Fix possible use-after-free in `SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf`. [#70358](https://github.com/ClickHouse/ClickHouse/pull/70358) ([Azat Khuzhin](https://github.com/azat)). +* Fix crash during GROUP BY JSON sub-object subcolumn. [#70374](https://github.com/ClickHouse/ClickHouse/pull/70374) ([Pavel Kruglov](https://github.com/Avogar)). +* Don't prefetch parts for vertical merges if part has no rows. [#70452](https://github.com/ClickHouse/ClickHouse/pull/70452) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix crash in WHERE with lambda functions. [#70464](https://github.com/ClickHouse/ClickHouse/pull/70464) ([Raúl Marín](https://github.com/Algunenano)). +* Fix table creation with `CREATE ... AS table_function(...)` with database `Replicated` and unavailable table function source on secondary replica. [#70511](https://github.com/ClickHouse/ClickHouse/pull/70511) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Ignore all output on async insert with `wait_for_async_insert=1`. Closes [#62644](https://github.com/ClickHouse/ClickHouse/issues/62644). [#70530](https://github.com/ClickHouse/ClickHouse/pull/70530) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Ignore frozen_metadata.txt while traversing shadow directory from system.remote_data_paths. [#70590](https://github.com/ClickHouse/ClickHouse/pull/70590) ([Aleksei Filatov](https://github.com/aalexfvk)). +* Fix creation of stateful window functions on misaligned memory. [#70631](https://github.com/ClickHouse/ClickHouse/pull/70631) ([Raúl Marín](https://github.com/Algunenano)). +* Fixed rare crashes in `SELECT`-s and merges after adding a column of `Array` type with non-empty default expression. [#70695](https://github.com/ClickHouse/ClickHouse/pull/70695) ([Anton Popov](https://github.com/CurtizJ)). +* Insert into table function s3 will respect query settings. [#70696](https://github.com/ClickHouse/ClickHouse/pull/70696) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix infinite recursion when inferring a protobuf schema when skipping unsupported fields is enabled. [#70697](https://github.com/ClickHouse/ClickHouse/pull/70697) ([Raúl Marín](https://github.com/Algunenano)). +* Disable enable_named_columns_in_function_tuple by default. [#70833](https://github.com/ClickHouse/ClickHouse/pull/70833) ([Raúl Marín](https://github.com/Algunenano)). +* Fix S3Queue table engine setting processing_threads_num not being effective in case it was deduced from the number of cpu cores on the server. [#70837](https://github.com/ClickHouse/ClickHouse/pull/70837) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Normalize named tuple arguments in aggregation states. This fixes [#69732](https://github.com/ClickHouse/ClickHouse/issues/69732) . [#70853](https://github.com/ClickHouse/ClickHouse/pull/70853) ([Amos Bird](https://github.com/amosbird)). +* Fix a logical error due to negative zeros in the two-level hash table. This closes [#70973](https://github.com/ClickHouse/ClickHouse/issues/70973). [#70979](https://github.com/ClickHouse/ClickHouse/pull/70979) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix `limit by`, `limit with ties` for distributed and parallel replicas. [#70880](https://github.com/ClickHouse/ClickHouse/pull/70880) ([Nikita Taranov](https://github.com/nickitat)). + + ### ClickHouse release 24.9, 2024-09-26 #### Backward Incompatible Change @@ -328,6 +488,7 @@ * Remove `is_deterministic` field from the `system.functions` table. [#66630](https://github.com/ClickHouse/ClickHouse/pull/66630) ([Alexey Milovidov](https://github.com/alexey-milovidov)). * Function `tuple` will now try to construct named tuples in query (controlled by `enable_named_columns_in_function_tuple`). Introduce function `tupleNames` to extract names from tuples. [#54881](https://github.com/ClickHouse/ClickHouse/pull/54881) ([Amos Bird](https://github.com/amosbird)). * Change how deduplication for Materialized Views works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)). +* Functions `bitShiftLeft` and `bitShitfRight` return an error for out of bounds shift positions [#65838](https://github.com/ClickHouse/ClickHouse/pull/65838) ([Pablo Marcos](https://github.com/pamarcos)). #### New Feature * Add `ASOF JOIN` support for `full_sorting_join` algorithm. [#55051](https://github.com/ClickHouse/ClickHouse/pull/55051) ([vdimir](https://github.com/vdimir)). @@ -439,7 +600,6 @@ * Functions `bitTest`, `bitTestAll`, and `bitTestAny` now return an error if the specified bit index is out-of-bounds [#65818](https://github.com/ClickHouse/ClickHouse/pull/65818) ([Pablo Marcos](https://github.com/pamarcos)). * Setting `join_any_take_last_row` is supported in any query with hash join. [#65820](https://github.com/ClickHouse/ClickHouse/pull/65820) ([vdimir](https://github.com/vdimir)). * Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)). -* Functions `bitShiftLeft` and `bitShitfRight` return an error for out of bounds shift positions [#65838](https://github.com/ClickHouse/ClickHouse/pull/65838) ([Pablo Marcos](https://github.com/pamarcos)). * Fix growing memory usage in S3Queue. [#65839](https://github.com/ClickHouse/ClickHouse/pull/65839) ([Kseniia Sumarokova](https://github.com/kssenii)). * Fix tie handling in `arrayAUC` to match sklearn. [#65840](https://github.com/ClickHouse/ClickHouse/pull/65840) ([gabrielmcg44](https://github.com/gabrielmcg44)). * Fix possible issues with MySQL server protocol TLS connections. [#65917](https://github.com/ClickHouse/ClickHouse/pull/65917) ([Azat Khuzhin](https://github.com/azat)). diff --git a/CMakeLists.txt b/CMakeLists.txt index f0965530739..a165be799c0 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -88,6 +88,7 @@ string (TOUPPER ${CMAKE_BUILD_TYPE} CMAKE_BUILD_TYPE_UC) list(REVERSE CMAKE_FIND_LIBRARY_SUFFIXES) option (ENABLE_FUZZING "Fuzzy testing using libfuzzer" OFF) +option (ENABLE_FUZZER_TEST "Build testing fuzzers in order to test libFuzzer functionality" OFF) if (ENABLE_FUZZING) # Also set WITH_COVERAGE=1 for better fuzzing process diff --git a/README.md b/README.md index 3b5209dcbe9..dcaeda13acd 100644 --- a/README.md +++ b/README.md @@ -42,31 +42,19 @@ Keep an eye out for upcoming meetups and events around the world. Somewhere else Upcoming meetups -* [Jakarta Meetup](https://www.meetup.com/clickhouse-indonesia-user-group/events/303191359/) - October 1 -* [Singapore Meetup](https://www.meetup.com/clickhouse-singapore-meetup-group/events/303212064/) - October 3 -* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22 -* [Oslo Meetup](https://www.meetup.com/open-source-real-time-data-warehouse-real-time-analytics/events/302938622) - October 31 * [Barcelona Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096876/) - November 12 * [Ghent Meetup](https://www.meetup.com/clickhouse-belgium-user-group/events/303049405/) - November 19 * [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - November 21 * [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/303096434) - November 26 +* [Amsterdam Meetup](https://www.meetup.com/clickhouse-netherlands-user-group/events/303638814) - December 3 +* [New York Meetup](https://www.meetup.com/clickhouse-new-york-user-group/events/304268174) - December 9 +* [San Francisco Meetup](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/304286951/) - December 12 Recently completed meetups -* [ClickHouse Guangzhou User Group Meetup](https://mp.weixin.qq.com/s/GSvo-7xUoVzCsuUvlLTpCw) - August 25 -* [Seattle Meetup (Statsig)](https://www.meetup.com/clickhouse-seattle-user-group/events/302518075/) - August 27 -* [Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302732666/) - August 27 -* [Sydney Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302862966/) - September 5 -* [Zurich Meetup](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/302267429/) - September 5 -* [San Francisco Meetup (Cloudflare)](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/302540575) - September 5 -* [Raleigh Meetup (Deutsche Bank)](https://www.meetup.com/triangletechtalks/events/302723486/) - September 9 -* [New York Meetup (Rokt)](https://www.meetup.com/clickhouse-new-york-user-group/events/302575342) - September 10 -* [Toronto Meetup (Shopify)](https://www.meetup.com/clickhouse-toronto-user-group/events/301490855/) - September 10 -* [Chicago Meetup (Jump Capital)](https://lu.ma/43tvmrfw) - September 12 -* [London Meetup](https://www.meetup.com/clickhouse-london-user-group/events/302977267) - September 17 -* [Austin Meetup](https://www.meetup.com/clickhouse-austin-user-group/events/302558689/) - September 17 -* [Bangalore Meetup](https://www.meetup.com/clickhouse-bangalore-user-group/events/303208274/) - September 18 -* [Tel Aviv Meetup](https://www.meetup.com/clickhouse-meetup-israel/events/303095121) - September 22 +* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22 +* [Singapore Meetup](https://www.meetup.com/clickhouse-singapore-meetup-group/events/303212064/) - October 3 +* [Jakarta Meetup](https://www.meetup.com/clickhouse-indonesia-user-group/events/303191359/) - October 1 ## Recent Recordings * **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments" diff --git a/SECURITY.md b/SECURITY.md index db302da8ecd..1b0648dc489 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -14,9 +14,10 @@ The following versions of ClickHouse server are currently supported with securit | Version | Supported | |:-|:-| +| 24.10 | ✔️ | | 24.9 | ✔️ | | 24.8 | ✔️ | -| 24.7 | ✔️ | +| 24.7 | ❌ | | 24.6 | ❌ | | 24.5 | ❌ | | 24.4 | ❌ | diff --git a/base/base/StringRef.h b/base/base/StringRef.h index aa2bce71032..74878b50545 100644 --- a/base/base/StringRef.h +++ b/base/base/StringRef.h @@ -86,7 +86,7 @@ using StringRefs = std::vector; * For more information, see hash_map_string_2.cpp */ -inline bool compare8(const char * p1, const char * p2) +inline bool compare16(const char * p1, const char * p2) { return 0xFFFF == _mm_movemask_epi8(_mm_cmpeq_epi8( _mm_loadu_si128(reinterpret_cast(p1)), @@ -115,7 +115,7 @@ inline bool compare64(const char * p1, const char * p2) #elif defined(__aarch64__) && defined(__ARM_NEON) -inline bool compare8(const char * p1, const char * p2) +inline bool compare16(const char * p1, const char * p2) { uint64_t mask = getNibbleMask(vceqq_u8( vld1q_u8(reinterpret_cast(p1)), vld1q_u8(reinterpret_cast(p2)))); @@ -185,13 +185,22 @@ inline bool memequalWide(const char * p1, const char * p2, size_t size) switch (size / 16) // NOLINT(bugprone-switch-missing-default-case) { - case 3: if (!compare8(p1 + 32, p2 + 32)) return false; [[fallthrough]]; - case 2: if (!compare8(p1 + 16, p2 + 16)) return false; [[fallthrough]]; - case 1: if (!compare8(p1, p2)) return false; [[fallthrough]]; + case 3: + if (!compare16(p1 + 32, p2 + 32)) + return false; + [[fallthrough]]; + case 2: + if (!compare16(p1 + 16, p2 + 16)) + return false; + [[fallthrough]]; + case 1: + if (!compare16(p1, p2)) + return false; + [[fallthrough]]; default: ; } - return compare8(p1 + size - 16, p2 + size - 16); + return compare16(p1 + size - 16, p2 + size - 16); } #endif diff --git a/base/base/chrono_io.h b/base/base/chrono_io.h index 4ee8dec6634..d55aa11bc1d 100644 --- a/base/base/chrono_io.h +++ b/base/base/chrono_io.h @@ -4,6 +4,7 @@ #include #include #include +#include inline std::string to_string(const std::time_t & time) @@ -11,18 +12,6 @@ inline std::string to_string(const std::time_t & time) return cctz::format("%Y-%m-%d %H:%M:%S", std::chrono::system_clock::from_time_t(time), cctz::local_time_zone()); } -template -std::string to_string(const std::chrono::time_point & tp) -{ - // Don't use DateLUT because it shows weird characters for - // TimePoint::max(). I wish we could use C++20 format, but it's not - // there yet. - // return DateLUT::instance().timeToString(std::chrono::system_clock::to_time_t(tp)); - - auto in_time_t = std::chrono::system_clock::to_time_t(tp); - return to_string(in_time_t); -} - template > std::string to_string(const std::chrono::duration & duration) { @@ -33,6 +22,20 @@ std::string to_string(const std::chrono::duration & duration) return std::to_string(seconds_as_double.count()) + "s"; } +template +std::string to_string(const std::chrono::time_point & tp) +{ + // Don't use DateLUT because it shows weird characters for + // TimePoint::max(). I wish we could use C++20 format, but it's not + // there yet. + // return DateLUT::instance().timeToString(std::chrono::system_clock::to_time_t(tp)); + + if constexpr (std::is_same_v) + return to_string(std::chrono::system_clock::to_time_t(tp)); + else + return to_string(tp.time_since_epoch()); +} + template std::ostream & operator<<(std::ostream & o, const std::chrono::time_point & tp) { @@ -44,3 +47,23 @@ std::ostream & operator<<(std::ostream & o, const std::chrono::duration +struct fmt::formatter> : fmt::formatter +{ + template + auto format(const std::chrono::time_point & tp, FormatCtx & ctx) const + { + return fmt::formatter::format(::to_string(tp), ctx); + } +}; + +template +struct fmt::formatter> : fmt::formatter +{ + template + auto format(const std::chrono::duration & duration, FormatCtx & ctx) const + { + return fmt::formatter::format(::to_string(duration), ctx); + } +}; diff --git a/base/glibc-compatibility/musl/getauxval.c b/base/glibc-compatibility/musl/getauxval.c index ec2cce1e4aa..cc0cdf25b03 100644 --- a/base/glibc-compatibility/musl/getauxval.c +++ b/base/glibc-compatibility/musl/getauxval.c @@ -25,9 +25,10 @@ // We don't have libc struct available here. // Compute aux vector manually (from /proc/self/auxv). // -// Right now there is only 51 AT_* constants, -// so 64 should be enough until this implementation will be replaced with musl. -static unsigned long __auxv_procfs[64]; +// Right now there are 51 AT_* constants. Custom kernels have been encountered +// making use of up to 71. 128 should be enough until this implementation is +// replaced with musl. +static unsigned long __auxv_procfs[128]; static unsigned long __auxv_secure = 0; // Common static unsigned long * __auxv_environ = NULL; diff --git a/ci/docker/fasttest/Dockerfile b/ci/docker/fasttest/Dockerfile index 02595ad0d0a..66e48b163b8 100644 --- a/ci/docker/fasttest/Dockerfile +++ b/ci/docker/fasttest/Dockerfile @@ -33,6 +33,8 @@ RUN apt-get update \ # moreutils - provides ts fo FT # expect, bzip2 - requried by FT # bsdmainutils - provides hexdump for FT +# nasm - nasm copiler for one of submodules, required from normal build +# yasm - asssembler for libhdfs3, required from normal build RUN apt-get update \ && apt-get install \ @@ -53,6 +55,8 @@ RUN apt-get update \ pv \ jq \ bzip2 \ + nasm \ + yasm \ --yes --no-install-recommends \ && apt-get clean \ && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/* diff --git a/ci/jobs/build_clickhouse.py b/ci/jobs/build_clickhouse.py new file mode 100644 index 00000000000..21ed8091608 --- /dev/null +++ b/ci/jobs/build_clickhouse.py @@ -0,0 +1,102 @@ +import argparse + +from praktika.result import Result +from praktika.settings import Settings +from praktika.utils import MetaClasses, Shell, Utils + + +class JobStages(metaclass=MetaClasses.WithIter): + CHECKOUT_SUBMODULES = "checkout" + CMAKE = "cmake" + BUILD = "build" + + +def parse_args(): + parser = argparse.ArgumentParser(description="ClickHouse Build Job") + parser.add_argument("BUILD_TYPE", help="Type: ") + parser.add_argument("--param", help="Optional custom job start stage", default=None) + return parser.parse_args() + + +def main(): + + args = parse_args() + + stop_watch = Utils.Stopwatch() + + stages = list(JobStages) + stage = args.param or JobStages.CHECKOUT_SUBMODULES + if stage: + assert stage in JobStages, f"--param must be one of [{list(JobStages)}]" + print(f"Job will start from stage [{stage}]") + while stage in stages: + stages.pop(0) + stages.insert(0, stage) + + cmake_build_type = "Release" + sanitizer = "" + + if "debug" in args.BUILD_TYPE.lower(): + print("Build type set: debug") + cmake_build_type = "Debug" + + if "asan" in args.BUILD_TYPE.lower(): + print("Sanitizer set: address") + sanitizer = "address" + + # if Environment.is_local_run(): + # build_cache_type = "disabled" + # else: + build_cache_type = "sccache" + + current_directory = Utils.cwd() + build_dir = f"{Settings.TEMP_DIR}/build" + + res = True + results = [] + + if res and JobStages.CHECKOUT_SUBMODULES in stages: + Shell.check(f"rm -rf {build_dir} && mkdir -p {build_dir}") + results.append( + Result.create_from_command_execution( + name="Checkout Submodules", + command=f"git submodule sync --recursive && git submodule init && git submodule update --depth 1 --recursive --jobs {min([Utils.cpu_count(), 20])}", + ) + ) + res = results[-1].is_ok() + + if res and JobStages.CMAKE in stages: + results.append( + Result.create_from_command_execution( + name="Cmake configuration", + command=f"cmake --debug-trycompile -DCMAKE_VERBOSE_MAKEFILE=1 -LA -DCMAKE_BUILD_TYPE={cmake_build_type} \ + -DSANITIZE={sanitizer} -DENABLE_CHECK_HEAVY_BUILDS=1 -DENABLE_CLICKHOUSE_SELF_EXTRACTING=1 -DENABLE_TESTS=0 \ + -DENABLE_UTILS=0 -DCMAKE_FIND_PACKAGE_NO_PACKAGE_REGISTRY=ON -DCMAKE_INSTALL_PREFIX=/usr \ + -DCMAKE_INSTALL_SYSCONFDIR=/etc -DCMAKE_INSTALL_LOCALSTATEDIR=/var -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=ON \ + -DCMAKE_C_COMPILER=clang-18 -DCMAKE_CXX_COMPILER=clang++-18 -DCOMPILER_CACHE={build_cache_type} -DENABLE_TESTS=1 \ + -DENABLE_BUILD_PROFILING=1 {current_directory}", + workdir=build_dir, + with_log=True, + ) + ) + res = results[-1].is_ok() + + if res and JobStages.BUILD in stages: + Shell.check("sccache --show-stats") + results.append( + Result.create_from_command_execution( + name="Build ClickHouse", + command="ninja clickhouse-bundle clickhouse-odbc-bridge clickhouse-library-bridge", + workdir=build_dir, + with_log=True, + ) + ) + Shell.check("sccache --show-stats") + Shell.check(f"ls -l {build_dir}/programs/") + res = results[-1].is_ok() + + Result.create_from(results=results, stopwatch=stop_watch).finish_job_accordingly() + + +if __name__ == "__main__": + main() diff --git a/ci/jobs/check_style.py b/ci/jobs/check_style.py index 1b1b0bf689b..f9cdc76302d 100644 --- a/ci/jobs/check_style.py +++ b/ci/jobs/check_style.py @@ -68,7 +68,7 @@ def check_duplicate_includes(file_path): def check_whitespaces(file_paths): for file in file_paths: exit_code, out, err = Shell.get_res_stdout_stderr( - f'./ci_v2/jobs/scripts/check_style/double_whitespaces.pl "{file}"', + f'./ci/jobs/scripts/check_style/double_whitespaces.pl "{file}"', verbose=False, ) if out or err: @@ -174,7 +174,7 @@ def check_broken_links(path, exclude_paths): def check_cpp_code(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check_cpp.sh" + "./ci/jobs/scripts/check_style/check_cpp.sh" ) if err: out += err @@ -183,7 +183,7 @@ def check_cpp_code(): def check_repo_submodules(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check_submodules.sh" + "./ci/jobs/scripts/check_style/check_submodules.sh" ) if err: out += err @@ -192,7 +192,7 @@ def check_repo_submodules(): def check_other(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/checks_to_refactor.sh" + "./ci/jobs/scripts/check_style/checks_to_refactor.sh" ) if err: out += err @@ -201,7 +201,7 @@ def check_other(): def check_codespell(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check_typos.sh" + "./ci/jobs/scripts/check_style/check_typos.sh" ) if err: out += err @@ -210,7 +210,7 @@ def check_codespell(): def check_aspell(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check_aspell.sh" + "./ci/jobs/scripts/check_style/check_aspell.sh" ) if err: out += err @@ -219,7 +219,7 @@ def check_aspell(): def check_mypy(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check-mypy" + "./ci/jobs/scripts/check_style/check-mypy" ) if err: out += err @@ -228,7 +228,7 @@ def check_mypy(): def check_pylint(): res, out, err = Shell.get_res_stdout_stderr( - "./ci_v2/jobs/scripts/check_style/check-pylint" + "./ci/jobs/scripts/check_style/check-pylint" ) if err: out += err diff --git a/ci/jobs/fast_test.py b/ci/jobs/fast_test.py index b82c17aa42c..1dcd65b6ed2 100644 --- a/ci/jobs/fast_test.py +++ b/ci/jobs/fast_test.py @@ -1,12 +1,13 @@ +import argparse import threading from pathlib import Path -from ci_v2.jobs.scripts.functional_tests_results import FTResultsProcessor -from praktika.environment import Environment from praktika.result import Result from praktika.settings import Settings from praktika.utils import MetaClasses, Shell, Utils +from ci.jobs.scripts.functional_tests_results import FTResultsProcessor + class ClickHouseProc: def __init__(self): @@ -208,11 +209,18 @@ class JobStages(metaclass=MetaClasses.WithIter): TEST = "test" +def parse_args(): + parser = argparse.ArgumentParser(description="ClickHouse Fast Test Job") + parser.add_argument("--param", help="Optional custom job start stage", default=None) + return parser.parse_args() + + def main(): + args = parse_args() stop_watch = Utils.Stopwatch() stages = list(JobStages) - stage = Environment.LOCAL_RUN_PARAM or JobStages.CHECKOUT_SUBMODULES + stage = args.param or JobStages.CHECKOUT_SUBMODULES if stage: assert stage in JobStages, f"--param must be one of [{list(JobStages)}]" print(f"Job will start from stage [{stage}]") diff --git a/ci/jobs/scripts/check_style/check_cpp.sh b/ci/jobs/scripts/check_style/check_cpp.sh index 7963bf982af..2e47b253bac 100755 --- a/ci/jobs/scripts/check_style/check_cpp.sh +++ b/ci/jobs/scripts/check_style/check_cpp.sh @@ -52,26 +52,6 @@ find $ROOT_PATH/{src,base,programs,utils} -name '*.h' -or -name '*.cpp' 2>/dev/n # Broken symlinks find -L $ROOT_PATH -type l 2>/dev/null | grep -v contrib && echo "^ Broken symlinks found" -# Duplicated or incorrect setting declarations -SETTINGS_FILE=$(mktemp) -ALL_DECLARATION_FILES=" - $ROOT_PATH/src/Core/Settings.cpp - $ROOT_PATH/src/Storages/MergeTree/MergeTreeSettings.cpp - $ROOT_PATH/src/Core/FormatFactorySettingsDeclaration.h" - -cat $ROOT_PATH/src/Core/Settings.cpp $ROOT_PATH/src/Core/FormatFactorySettingsDeclaration.h | grep "M(" | awk '{print substr($2, 0, length($2) - 1) " Settings" substr($1, 3, length($1) - 3) " SettingsDeclaration" }' | sort | uniq > ${SETTINGS_FILE} -cat $ROOT_PATH/src/Storages/MergeTree/MergeTreeSettings.cpp | grep "M(" | awk '{print substr($2, 0, length($2) - 1) " MergeTreeSettings" substr($1, 3, length($1) - 3) " SettingsDeclaration" }' | sort | uniq >> ${SETTINGS_FILE} - -# Check that if there are duplicated settings (declared in different objects) they all have the same type (it's simpler to validate style with that assert) -for setting in $(awk '{print $1 " " $2}' ${SETTINGS_FILE} | sed -e 's/MergeTreeSettings//g' -e 's/Settings//g' | sort | uniq | awk '{ print $1 }' | uniq -d); -do - echo "# Found multiple definitions of setting ${setting} with different types: " - grep --line-number " ${setting}," ${ALL_DECLARATION_FILES} | awk '{print " > " $0 }' -done - -# We append all uses of extern found in implementation files to validate them in a single pass and avoid reading the same files over and over -find $ROOT_PATH/{src,base,programs,utils} -name '*.h' -or -name '*.cpp' | xargs grep -e "^\s*extern const Settings" -e "^\s**extern const MergeTreeSettings" -T | awk '{print substr($5, 0, length($5) -1) " " $4 " " substr($1, 0, length($1) - 1)}' >> ${SETTINGS_FILE} - # Duplicated or incorrect setting declarations bash $ROOT_PATH/utils/check-style/check-settings-style diff --git a/ci/praktika/_environment.py b/ci/praktika/_environment.py index ca84def1d29..ce9c6f5b486 100644 --- a/ci/praktika/_environment.py +++ b/ci/praktika/_environment.py @@ -29,9 +29,9 @@ class _Environment(MetaClasses.Serializable): INSTANCE_TYPE: str INSTANCE_ID: str INSTANCE_LIFE_CYCLE: str + LOCAL_RUN: bool = False PARAMETER: Any = None REPORT_INFO: List[str] = dataclasses.field(default_factory=list) - LOCAL_RUN_PARAM: str = "" name = "environment" @classmethod @@ -185,6 +185,9 @@ class _Environment(MetaClasses.Serializable): REPORT_URL = f"https://{path}/{Path(Settings.HTML_PAGE_FILE).name}?PR={self.PR_NUMBER}&sha={self.SHA}&name_0={urllib.parse.quote(self.WORKFLOW_NAME, safe='')}&name_1={urllib.parse.quote(self.JOB_NAME, safe='')}" return REPORT_URL + def is_local_run(self): + return self.LOCAL_RUN + def _to_object(data): if isinstance(data, dict): diff --git a/ci/praktika/_settings.py b/ci/praktika/_settings.py index bfd7ba6c1be..3052d8ef877 100644 --- a/ci/praktika/_settings.py +++ b/ci/praktika/_settings.py @@ -8,11 +8,7 @@ class _Settings: ###################################### # Pipeline generation settings # ###################################### - if Path("./ci_v2").is_dir(): - # TODO: hack for CH, remove - CI_PATH = "./ci_v2" - else: - CI_PATH = "./ci" + CI_PATH = "./ci" WORKFLOW_PATH_PREFIX: str = "./.github/workflows" WORKFLOWS_DIRECTORY: str = f"{CI_PATH}/workflows" SETTINGS_DIRECTORY: str = f"{CI_PATH}/settings" diff --git a/ci/praktika/digest.py b/ci/praktika/digest.py index 44317d5249e..93b62b13dc0 100644 --- a/ci/praktika/digest.py +++ b/ci/praktika/digest.py @@ -1,6 +1,8 @@ import dataclasses import hashlib +import os from hashlib import md5 +from pathlib import Path from typing import List from praktika import Job @@ -37,7 +39,9 @@ class Digest: sorted=True, ) - print(f"calc digest: hash_key [{cache_key}], include [{included_files}] files") + print( + f"calc digest for job [{job_config.name}]: hash_key [{cache_key}], include [{len(included_files)}] files" + ) # Sort files to ensure consistent hash calculation included_files.sort() @@ -91,10 +95,18 @@ class Digest: @staticmethod def _calc_file_digest(file_path, hash_md5): - # Calculate MD5 hash - with open(file_path, "rb") as f: + # Resolve file path if it's a symbolic link + resolved_path = file_path + if Path(file_path).is_symlink(): + resolved_path = os.path.realpath(file_path) + if not Path(resolved_path).is_file(): + print( + f"WARNING: No valid file resolved by link {file_path} -> {resolved_path} - skipping digest calculation" + ) + return hash_md5.hexdigest()[: Settings.CACHE_DIGEST_LEN] + + with open(resolved_path, "rb") as f: for chunk in iter(lambda: f.read(4096), b""): hash_md5.update(chunk) - res = hash_md5.hexdigest()[: Settings.CACHE_DIGEST_LEN] - return res + return hash_md5.hexdigest()[: Settings.CACHE_DIGEST_LEN] diff --git a/ci/praktika/hook_html.py b/ci/praktika/hook_html.py index c998e817fe7..f4bd4435511 100644 --- a/ci/praktika/hook_html.py +++ b/ci/praktika/hook_html.py @@ -1,5 +1,8 @@ +import dataclasses +import json import urllib.parse from pathlib import Path +from typing import List from praktika._environment import _Environment from praktika.gh import GH @@ -8,12 +11,50 @@ from praktika.result import Result, ResultInfo from praktika.runtime import RunConfig from praktika.s3 import S3 from praktika.settings import Settings -from praktika.utils import Utils +from praktika.utils import Shell, Utils + + +@dataclasses.dataclass +class GitCommit: + date: str + message: str + sha: str + + @staticmethod + def from_json(json_data: str) -> List["GitCommit"]: + commits = [] + try: + data = json.loads(json_data) + + commits = [ + GitCommit( + message=commit["messageHeadline"], + sha=commit["oid"], + date=commit["committedDate"], + ) + for commit in data.get("commits", []) + ] + except Exception as e: + print( + f"ERROR: Failed to deserialize commit's data: [{json_data}], ex: [{e}]" + ) + + return commits class HtmlRunnerHooks: @classmethod def configure(cls, _workflow): + + def _get_pr_commits(pr_number): + res = [] + if not pr_number: + return res + output = Shell.get_output(f"gh pr view {pr_number} --json commits") + if output: + res = GitCommit.from_json(output) + return res + # generate pending Results for all jobs in the workflow if _workflow.enable_cache: skip_jobs = RunConfig.from_fs(_workflow.name).cache_success @@ -62,10 +103,14 @@ class HtmlRunnerHooks: or_update_comment_with_substring=f"Workflow [", ) if not (res1 or res2): - print( - "ERROR: Failed to set both GH commit status and PR comment with Workflow Status, cannot proceed" + Utils.raise_with_error( + "Failed to set both GH commit status and PR comment with Workflow Status, cannot proceed" ) - raise + + if env.PR_NUMBER: + commits = _get_pr_commits(env.PR_NUMBER) + # TODO: upload commits data to s3 to visualise it on a report page + print(commits) @classmethod def pre_run(cls, _workflow, _job): diff --git a/ci/praktika/json.html b/ci/praktika/json.html index fe7b65a5ec5..2f8c3e45d0b 100644 --- a/ci/praktika/json.html +++ b/ci/praktika/json.html @@ -24,13 +24,15 @@ margin: 0; display: flex; flex-direction: column; - font-family: monospace, sans-serif; + font-family: 'IBM Plex Mono Condensed', monospace, sans-serif; + --header-background-color: #f4f4f4; } body.night-theme { --background-color: #1F1F1C; --text-color: #fff; --tile-background: black; + --header-background-color: #1F1F1C; } #info-container { @@ -50,27 +52,41 @@ background-color: var(--tile-background); padding: 20px; box-sizing: border-box; - text-align: left; font-size: 18px; + margin: 0; + } + + #status-container a { + color: #007bff; + text-decoration: underline; font-weight: bold; - margin: 0; /* Remove margin */ - } - - #status-container button { - display: block; /* Stack buttons vertically */ - width: 100%; /* Full width of container */ - padding: 10px; - margin-bottom: 10px; /* Space between buttons */ - background-color: #4CAF50; /* Green background color */ - color: white; - border: none; - border-radius: 5px; - font-size: 16px; cursor: pointer; + display: inline-block; + margin-top: 5px; + margin-left: 20px; + padding: 2px 0; + font-size: 0.8em; } - #status-container button:hover { - background-color: #45a049; /* Darker green on hover */ + #status-container a:hover { + color: #0056b3; + text-decoration: none; + } + + .key-value-pair { + display: flex; /* Enable Flexbox for alignment */ + justify-content: space-between; /* Distribute space between key and value */ + margin-bottom: 20px; /* Add space between each pair */ + } + + .json-key { + font-weight: bold; + } + + .json-value { + font-weight: normal; + font-family: 'Source Code Pro', monospace, sans-serif; + letter-spacing: -0.5px; } #result-container { @@ -203,7 +219,7 @@ } th { - background-color: #f4f4f4; + background-color: var(--header-background-color); } .status-success { @@ -240,23 +256,6 @@ color: grey; font-weight: bold; } - - .json-key { - font-weight: bold; - margin-top: 10px; - } - - .json-value { - margin-left: 20px; - } - - .json-value a { - color: #007bff; - } - - .json-value a:hover { - text-decoration: underline; - } @@ -286,7 +285,6 @@ // Attach the toggle function to the click event of the icon document.getElementById('theme-toggle').addEventListener('click', toggleTheme); - // Function to format timestamp to "DD-mmm-YYYY HH:MM:SS.MM" function formatTimestamp(timestamp, showDate = true) { const date = new Date(timestamp * 1000); const day = String(date.getDate()).padStart(2, '0'); @@ -304,6 +302,38 @@ : `${hours}:${minutes}:${seconds}`; } + function formatDuration(durationInSeconds, detailed = false) { + // Check if the duration is empty, null, or not a number + if (!durationInSeconds || isNaN(durationInSeconds)) { + return ''; + } + + // Ensure duration is a floating-point number + const duration = parseFloat(durationInSeconds); + + if (detailed) { + // Format in the detailed format with hours, minutes, and seconds + const hours = Math.floor(duration / 3600); + const minutes = Math.floor((duration % 3600) / 60); + const seconds = Math.floor(duration % 60); + + const formattedHours = hours > 0 ? `${hours}h ` : ''; + const formattedMinutes = minutes > 0 ? `${minutes}m ` : ''; + const formattedSeconds = `${String(seconds).padStart(2, '0')}s`; + + return `${formattedHours}${formattedMinutes}${formattedSeconds}`.trim(); + } else { + // Format in the default format with seconds and milliseconds + const seconds = Math.floor(duration); + const milliseconds = Math.floor((duration % 1) * 1000); + + const formattedSeconds = String(seconds); + const formattedMilliseconds = String(milliseconds).padStart(3, '0'); + + return `${formattedSeconds}.${formattedMilliseconds}`; + } + } + // Function to determine status class based on value function getStatusClass(status) { const lowerStatus = status.toLowerCase(); @@ -316,32 +346,13 @@ return 'status-other'; } - // Function to format duration from seconds to "HH:MM:SS" - function formatDuration(durationInSeconds) { - // Check if the duration is empty, null, or not a number - if (!durationInSeconds || isNaN(durationInSeconds)) { - return ''; - } - - // Ensure duration is a floating-point number - const duration = parseFloat(durationInSeconds); - - // Calculate seconds and milliseconds - const seconds = Math.floor(duration); // Whole seconds - const milliseconds = Math.floor((duration % 1) * 1000); // Convert fraction to milliseconds - - // Format seconds and milliseconds with leading zeros where needed - const formattedSeconds = String(seconds); - const formattedMilliseconds = String(milliseconds).padStart(3, '0'); - - // Return the formatted duration as seconds.milliseconds - return `${formattedSeconds}.${formattedMilliseconds}`; - } - function addKeyValueToStatus(key, value) { const statusContainer = document.getElementById('status-container'); + let keyValuePair = document.createElement('div'); + keyValuePair.className = 'key-value-pair'; + const keyElement = document.createElement('div'); keyElement.className = 'json-key'; keyElement.textContent = key + ':'; @@ -350,8 +361,9 @@ valueElement.className = 'json-value'; valueElement.textContent = value; - statusContainer.appendChild(keyElement); - statusContainer.appendChild(valueElement); + keyValuePair.appendChild(keyElement) + keyValuePair.appendChild(valueElement) + statusContainer.appendChild(keyValuePair); } function addFileButtonToStatus(key, links) { @@ -364,64 +376,68 @@ const keyElement = document.createElement('div'); keyElement.className = 'json-key'; - keyElement.textContent = key + ':'; + keyElement.textContent = columnSymbols[key] + ':' || key; statusContainer.appendChild(keyElement); if (Array.isArray(links) && links.length > 0) { links.forEach(link => { - // const a = document.createElement('a'); - // a.href = link; - // a.textContent = link.split('/').pop(); - // a.target = '_blank'; - // statusContainer.appendChild(a); - const button = document.createElement('button'); - button.textContent = link.split('/').pop(); - button.addEventListener('click', function () { - window.location.href = link; - }); - statusContainer.appendChild(button); + const textLink = document.createElement('a'); + textLink.href = link; + textLink.textContent = link.split('/').pop(); + textLink.target = '_blank'; + statusContainer.appendChild(textLink); + statusContainer.appendChild(document.createElement('br')); }); } } function addStatusToStatus(status, start_time, duration) { - const statusContainer = document.getElementById('status-container'); + const statusContainer = document.getElementById('status-container') + let keyValuePair = document.createElement('div'); + keyValuePair.className = 'key-value-pair'; let keyElement = document.createElement('div'); let valueElement = document.createElement('div'); keyElement.className = 'json-key'; valueElement.className = 'json-value'; - keyElement.textContent = 'status:'; + keyElement.textContent = columnSymbols['status'] + ':' || 'status:'; valueElement.classList.add('status-value'); valueElement.classList.add(getStatusClass(status)); valueElement.textContent = status; - statusContainer.appendChild(keyElement); - statusContainer.appendChild(valueElement); + keyValuePair.appendChild(keyElement); + keyValuePair.appendChild(valueElement); + statusContainer.appendChild(keyValuePair); + keyValuePair = document.createElement('div'); + keyValuePair.className = 'key-value-pair'; keyElement = document.createElement('div'); valueElement = document.createElement('div'); keyElement.className = 'json-key'; valueElement.className = 'json-value'; - keyElement.textContent = 'start_time:'; + keyElement.textContent = columnSymbols['start_time'] + ':' || 'start_time:'; valueElement.textContent = formatTimestamp(start_time); - statusContainer.appendChild(keyElement); - statusContainer.appendChild(valueElement); + keyValuePair.appendChild(keyElement); + keyValuePair.appendChild(valueElement); + statusContainer.appendChild(keyValuePair); + keyValuePair = document.createElement('div'); + keyValuePair.className = 'key-value-pair'; keyElement = document.createElement('div'); valueElement = document.createElement('div'); keyElement.className = 'json-key'; valueElement.className = 'json-value'; - keyElement.textContent = 'duration:'; + keyElement.textContent = columnSymbols['duration'] + ':' || 'duration:'; if (duration === null) { // Set initial value to 0 and add a unique ID or data attribute to identify the duration element valueElement.textContent = '00:00:00'; valueElement.setAttribute('id', 'duration-value'); } else { // Format the duration if it's a valid number - valueElement.textContent = formatDuration(duration); + valueElement.textContent = formatDuration(duration, true); } - statusContainer.appendChild(keyElement); - statusContainer.appendChild(valueElement); + keyValuePair.appendChild(keyElement); + keyValuePair.appendChild(valueElement); + statusContainer.appendChild(keyValuePair); } function navigatePath(jsonObj, nameArray) { @@ -470,11 +486,12 @@ const columns = ['name', 'status', 'start_time', 'duration', 'info']; const columnSymbols = { - name: '👤', + name: '📂', status: '✔️', start_time: '🕒', duration: '⏳', - info: '⚠️' + info: 'ℹ️', + files: '📄' }; function createResultsTable(results, nest_level) { @@ -626,6 +643,7 @@ footerRight.appendChild(a); }); } + addStatusToStatus(targetData.status, targetData.start_time, targetData.duration) // Handle links @@ -639,7 +657,7 @@ const intervalId = setInterval(() => { duration++; - durationElement.textContent = formatDuration(duration); + durationElement.textContent = formatDuration(duration, true); }, 1000); } diff --git a/ci/praktika/runner.py b/ci/praktika/runner.py index 15e759397ec..797a799a74d 100644 --- a/ci/praktika/runner.py +++ b/ci/praktika/runner.py @@ -42,6 +42,7 @@ class Runner: INSTANCE_ID="", INSTANCE_TYPE="", INSTANCE_LIFE_CYCLE="", + LOCAL_RUN=True, ).dump() workflow_config = RunConfig( name=workflow.name, @@ -76,9 +77,6 @@ class Runner: os.environ[key] = value print(f"Set environment variable {key}.") - # TODO: remove - os.environ["PYTHONPATH"] = os.getcwd() - print("Read GH Environment") env = _Environment.from_env() env.JOB_NAME = job.name @@ -132,9 +130,7 @@ class Runner: f"Custom param for local tests must be of type str, got [{type(param)}]" ) env = _Environment.get() - env.LOCAL_RUN_PARAM = param env.dump() - print(f"Custom param for local tests [{param}] dumped into Environment") if job.run_in_docker and not no_docker: # TODO: add support for any image, including not from ci config (e.g. ubuntu:latest) @@ -142,9 +138,13 @@ class Runner: job.run_in_docker ] docker = docker or f"{job.run_in_docker}:{docker_tag}" - cmd = f"docker run --rm --user \"$(id -u):$(id -g)\" -e PYTHONPATH='{Settings.DOCKER_WD}' --volume ./:{Settings.DOCKER_WD} --volume {Settings.TEMP_DIR}:{Settings.TEMP_DIR} --workdir={Settings.DOCKER_WD} {docker} {job.command}" + cmd = f"docker run --rm --user \"$(id -u):$(id -g)\" -e PYTHONPATH='{Settings.DOCKER_WD}:{Settings.DOCKER_WD}/ci' --volume ./:{Settings.DOCKER_WD} --volume {Settings.TEMP_DIR}:{Settings.TEMP_DIR} --workdir={Settings.DOCKER_WD} {docker} {job.command}" else: cmd = job.command + + if param: + print(f"Custom --param [{param}] will be passed to job's script") + cmd += f" --param {param}" print(f"--- Run command [{cmd}]") with TeePopen(cmd, timeout=job.timeout) as process: diff --git a/ci/praktika/utils.py b/ci/praktika/utils.py index 1983ce274a3..b96c78e4fa7 100644 --- a/ci/praktika/utils.py +++ b/ci/praktika/utils.py @@ -348,9 +348,9 @@ class Utils: return multiprocessing.cpu_count() @staticmethod - def raise_with_error(error_message, stdout="", stderr=""): + def raise_with_error(error_message, stdout="", stderr="", ex=None): Utils.print_formatted_error(error_message, stdout, stderr) - raise + raise ex or RuntimeError() @staticmethod def timestamp(): diff --git a/ci/praktika/yaml_generator.py b/ci/praktika/yaml_generator.py index 9c61b5e2f79..00c469fec0c 100644 --- a/ci/praktika/yaml_generator.py +++ b/ci/praktika/yaml_generator.py @@ -83,8 +83,8 @@ jobs: {JOB_ADDONS} - name: Prepare env script run: | - export PYTHONPATH=.:$PYTHONPATH cat > {ENV_SETUP_SCRIPT} << 'ENV_SETUP_SCRIPT_EOF' + export PYTHONPATH=./ci:. {SETUP_ENVS} cat > {WORKFLOW_CONFIG_FILE} << 'EOF' ${{{{ needs.{WORKFLOW_CONFIG_JOB_NAME}.outputs.data }}}} @@ -100,6 +100,7 @@ jobs: - name: Run id: run run: | + . /tmp/praktika_setup_env.sh set -o pipefail {PYTHON} -m praktika run --job '''{JOB_NAME}''' --workflow "{WORKFLOW_NAME}" --ci |& tee {RUN_LOG} {UPLOADS_GITHUB}\ diff --git a/ci/settings/definitions.py b/ci/settings/definitions.py index 4e6a7f213f0..176e865e6f3 100644 --- a/ci/settings/definitions.py +++ b/ci/settings/definitions.py @@ -30,133 +30,133 @@ SECRETS = [ DOCKERS = [ # Docker.Config( # name="clickhouse/binary-builder", - # path="./ci_v2/docker/packager/binary-builder", + # path="./ci/docker/packager/binary-builder", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), # Docker.Config( # name="clickhouse/cctools", - # path="./ci_v2/docker/packager/cctools", + # path="./ci/docker/packager/cctools", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), # Docker.Config( # name="clickhouse/test-old-centos", - # path="./ci_v2/docker/test/compatibility/centos", + # path="./ci/docker/test/compatibility/centos", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), # Docker.Config( # name="clickhouse/test-old-ubuntu", - # path="./ci_v2/docker/test/compatibility/ubuntu", + # path="./ci/docker/test/compatibility/ubuntu", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), # Docker.Config( # name="clickhouse/test-util", - # path="./ci_v2/docker/test/util", + # path="./ci/docker/test/util", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), # Docker.Config( # name="clickhouse/integration-test", - # path="./ci_v2/docker/test/integration/base", + # path="./ci/docker/test/integration/base", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/fuzzer", - # path="./ci_v2/docker/test/fuzzer", + # path="./ci/docker/test/fuzzer", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/performance-comparison", - # path="./ci_v2/docker/test/performance-comparison", + # path="./ci/docker/test/performance-comparison", # platforms=Docker.Platforms.arm_amd, # depends_on=[], # ), Docker.Config( name="clickhouse/fasttest", - path="./ci_v2/docker/fasttest", + path="./ci/docker/fasttest", platforms=Docker.Platforms.arm_amd, depends_on=[], ), # Docker.Config( # name="clickhouse/test-base", - # path="./ci_v2/docker/test/base", + # path="./ci/docker/test/base", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-util"], # ), # Docker.Config( # name="clickhouse/clickbench", - # path="./ci_v2/docker/test/clickbench", + # path="./ci/docker/test/clickbench", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/keeper-jepsen-test", - # path="./ci_v2/docker/test/keeper-jepsen", + # path="./ci/docker/test/keeper-jepsen", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/server-jepsen-test", - # path="./ci_v2/docker/test/server-jepsen", + # path="./ci/docker/test/server-jepsen", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/sqllogic-test", - # path="./ci_v2/docker/test/sqllogic", + # path="./ci/docker/test/sqllogic", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/sqltest", - # path="./ci_v2/docker/test/sqltest", + # path="./ci/docker/test/sqltest", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/stateless-test", - # path="./ci_v2/docker/test/stateless", + # path="./ci/docker/test/stateless", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/stateful-test", - # path="./ci_v2/docker/test/stateful", + # path="./ci/docker/test/stateful", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/stateless-test"], # ), # Docker.Config( # name="clickhouse/stress-test", - # path="./ci_v2/docker/test/stress", + # path="./ci/docker/test/stress", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/stateful-test"], # ), # Docker.Config( # name="clickhouse/unit-test", - # path="./ci_v2/docker/test/unit", + # path="./ci/docker/test/unit", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), # Docker.Config( # name="clickhouse/integration-tests-runner", - # path="./ci_v2/docker/test/integration/runner", + # path="./ci/docker/test/integration/runner", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), Docker.Config( name="clickhouse/style-test", - path="./ci_v2/docker/style-test", + path="./ci/docker/style-test", platforms=Docker.Platforms.arm_amd, depends_on=[], ), # Docker.Config( # name="clickhouse/docs-builder", - # path="./ci_v2/docker/docs/builder", + # path="./ci/docker/docs/builder", # platforms=Docker.Platforms.arm_amd, # depends_on=["clickhouse/test-base"], # ), @@ -230,3 +230,4 @@ DOCKERS = [ class JobNames: STYLE_CHECK = "Style Check" FAST_TEST = "Fast test" + BUILD_AMD_DEBUG = "Build amd64 debug" diff --git a/ci/settings/settings.py b/ci/settings/settings.py index 153aab93506..8d5e7bc3c87 100644 --- a/ci/settings/settings.py +++ b/ci/settings/settings.py @@ -1,4 +1,4 @@ -from ci_v2.settings.definitions import ( +from ci.settings.definitions import ( S3_BUCKET_HTTP_ENDPOINT, S3_BUCKET_NAME, RunnerLabels, diff --git a/ci/workflows/pull_request.py b/ci/workflows/pull_request.py index 0e96329788b..74129177efb 100644 --- a/ci/workflows/pull_request.py +++ b/ci/workflows/pull_request.py @@ -1,26 +1,62 @@ from typing import List -from ci_v2.settings.definitions import ( +from praktika import Artifact, Job, Workflow +from praktika.settings import Settings + +from ci.settings.definitions import ( BASE_BRANCH, DOCKERS, SECRETS, JobNames, RunnerLabels, ) -from praktika import Job, Workflow + + +class ArtifactNames: + ch_debug_binary = "clickhouse_debug_binary" + style_check_job = Job.Config( name=JobNames.STYLE_CHECK, runs_on=[RunnerLabels.CI_SERVICES], - command="python3 ./ci_v2/jobs/check_style.py", + command="python3 ./ci/jobs/check_style.py", run_in_docker="clickhouse/style-test", ) fast_test_job = Job.Config( name=JobNames.FAST_TEST, runs_on=[RunnerLabels.BUILDER], - command="python3 ./ci_v2/jobs/fast_test.py", + command="python3 ./ci/jobs/fast_test.py", run_in_docker="clickhouse/fasttest", + digest_config=Job.CacheDigestConfig( + include_paths=[ + "./ci/jobs/fast_test.py", + "./tests/queries/0_stateless/", + "./src", + ], + ), +) + +job_build_amd_debug = Job.Config( + name=JobNames.BUILD_AMD_DEBUG, + runs_on=[RunnerLabels.BUILDER], + command="python3 ./ci/jobs/build_clickhouse.py amd_debug", + run_in_docker="clickhouse/fasttest", + digest_config=Job.CacheDigestConfig( + include_paths=[ + "./src", + "./contrib/", + "./CMakeLists.txt", + "./PreLoad.cmake", + "./cmake", + "./base", + "./programs", + "./docker/packager/packager", + "./rust", + "./tests/ci/version_helper.py", + ], + ), + provides=[ArtifactNames.ch_debug_binary], ) workflow = Workflow.Config( @@ -30,6 +66,14 @@ workflow = Workflow.Config( jobs=[ style_check_job, fast_test_job, + job_build_amd_debug, + ], + artifacts=[ + Artifact.Config( + name=ArtifactNames.ch_debug_binary, + type=Artifact.Type.S3, + path=f"{Settings.TEMP_DIR}/build/programs/clickhouse", + ) ], dockers=DOCKERS, secrets=SECRETS, diff --git a/cmake/autogenerated_versions.txt b/cmake/autogenerated_versions.txt index 91a7e976aaf..99141510248 100644 --- a/cmake/autogenerated_versions.txt +++ b/cmake/autogenerated_versions.txt @@ -2,11 +2,11 @@ # NOTE: VERSION_REVISION has nothing common with DBMS_TCP_PROTOCOL_VERSION, # only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes. -SET(VERSION_REVISION 54491) +SET(VERSION_REVISION 54492) SET(VERSION_MAJOR 24) -SET(VERSION_MINOR 10) +SET(VERSION_MINOR 11) SET(VERSION_PATCH 1) -SET(VERSION_GITHASH b12a367741812f9e5fe754d19ebae600e2a2614c) -SET(VERSION_DESCRIBE v24.10.1.1-testing) -SET(VERSION_STRING 24.10.1.1) +SET(VERSION_GITHASH c82cf25b3e5864bcc153cbe45adb8c6527e1ec6e) +SET(VERSION_DESCRIBE v24.11.1.1-testing) +SET(VERSION_STRING 24.11.1.1) # end of autochange diff --git a/contrib/SimSIMD b/contrib/SimSIMD index ff51434d90c..ee3c9c9c00b 160000 --- a/contrib/SimSIMD +++ b/contrib/SimSIMD @@ -1 +1 @@ -Subproject commit ff51434d90c66f916e94ff05b24530b127aa4cff +Subproject commit ee3c9c9c00b51645f62a1a9e99611b78c0052a21 diff --git a/contrib/SimSIMD-cmake/CMakeLists.txt b/contrib/SimSIMD-cmake/CMakeLists.txt index f5dc4d63604..8350417479a 100644 --- a/contrib/SimSIMD-cmake/CMakeLists.txt +++ b/contrib/SimSIMD-cmake/CMakeLists.txt @@ -1,4 +1,8 @@ -set(SIMSIMD_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/SimSIMD") - -add_library(_simsimd INTERFACE) -target_include_directories(_simsimd SYSTEM INTERFACE "${SIMSIMD_PROJECT_DIR}/include") +# See contrib/usearch-cmake/CMakeLists.txt, why only enabled on x86 +if (ARCH_AMD64) + set(SIMSIMD_PROJECT_DIR "${ClickHouse_SOURCE_DIR}/contrib/SimSIMD") + set(SIMSIMD_SRCS ${SIMSIMD_PROJECT_DIR}/c/lib.c) + add_library(_simsimd ${SIMSIMD_SRCS}) + target_include_directories(_simsimd SYSTEM PUBLIC "${SIMSIMD_PROJECT_DIR}/include") + target_compile_definitions(_simsimd PUBLIC SIMSIMD_DYNAMIC_DISPATCH) +endif() diff --git a/contrib/arrow b/contrib/arrow index 5cfccd8ea65..6e2574f5013 160000 --- a/contrib/arrow +++ b/contrib/arrow @@ -1 +1 @@ -Subproject commit 5cfccd8ea65f33d4517e7409815d761c7650b45d +Subproject commit 6e2574f5013a005c050c9a7787d341aef09d0063 diff --git a/contrib/arrow-cmake/CMakeLists.txt b/contrib/arrow-cmake/CMakeLists.txt index 96d1f4adda7..208d48df178 100644 --- a/contrib/arrow-cmake/CMakeLists.txt +++ b/contrib/arrow-cmake/CMakeLists.txt @@ -213,13 +213,19 @@ target_include_directories(_orc SYSTEM PRIVATE set(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src/arrow") # arrow/cpp/src/arrow/CMakeLists.txt (ARROW_SRCS + ARROW_COMPUTE + ARROW_IPC) +# find . \( -iname \*.cc -o -iname \*.cpp -o -iname \*.c \) | sort | awk '{print "\"${LIBRARY_DIR}" substr($1,2) "\"" }' | grep -v 'test.cc' | grep -v 'json' | grep -v 'flight' \| +# grep -v 'csv' | grep -v 'acero' | grep -v 'dataset' | grep -v 'testing' | grep -v 'gpu' | grep -v 'engine' | grep -v 'filesystem' | grep -v 'benchmark.cc' set(ARROW_SRCS + "${LIBRARY_DIR}/adapters/orc/adapter.cc" + "${LIBRARY_DIR}/adapters/orc/options.cc" + "${LIBRARY_DIR}/adapters/orc/util.cc" "${LIBRARY_DIR}/array/array_base.cc" "${LIBRARY_DIR}/array/array_binary.cc" "${LIBRARY_DIR}/array/array_decimal.cc" "${LIBRARY_DIR}/array/array_dict.cc" "${LIBRARY_DIR}/array/array_nested.cc" "${LIBRARY_DIR}/array/array_primitive.cc" + "${LIBRARY_DIR}/array/array_run_end.cc" "${LIBRARY_DIR}/array/builder_adaptive.cc" "${LIBRARY_DIR}/array/builder_base.cc" "${LIBRARY_DIR}/array/builder_binary.cc" @@ -227,124 +233,26 @@ set(ARROW_SRCS "${LIBRARY_DIR}/array/builder_dict.cc" "${LIBRARY_DIR}/array/builder_nested.cc" "${LIBRARY_DIR}/array/builder_primitive.cc" - "${LIBRARY_DIR}/array/builder_union.cc" "${LIBRARY_DIR}/array/builder_run_end.cc" - "${LIBRARY_DIR}/array/array_run_end.cc" + "${LIBRARY_DIR}/array/builder_union.cc" "${LIBRARY_DIR}/array/concatenate.cc" "${LIBRARY_DIR}/array/data.cc" "${LIBRARY_DIR}/array/diff.cc" "${LIBRARY_DIR}/array/util.cc" "${LIBRARY_DIR}/array/validate.cc" - "${LIBRARY_DIR}/builder.cc" "${LIBRARY_DIR}/buffer.cc" - "${LIBRARY_DIR}/chunked_array.cc" - "${LIBRARY_DIR}/chunk_resolver.cc" - "${LIBRARY_DIR}/compare.cc" - "${LIBRARY_DIR}/config.cc" - "${LIBRARY_DIR}/datum.cc" - "${LIBRARY_DIR}/device.cc" - "${LIBRARY_DIR}/extension_type.cc" - "${LIBRARY_DIR}/memory_pool.cc" - "${LIBRARY_DIR}/pretty_print.cc" - "${LIBRARY_DIR}/record_batch.cc" - "${LIBRARY_DIR}/result.cc" - "${LIBRARY_DIR}/scalar.cc" - "${LIBRARY_DIR}/sparse_tensor.cc" - "${LIBRARY_DIR}/status.cc" - "${LIBRARY_DIR}/table.cc" - "${LIBRARY_DIR}/table_builder.cc" - "${LIBRARY_DIR}/tensor.cc" - "${LIBRARY_DIR}/tensor/coo_converter.cc" - "${LIBRARY_DIR}/tensor/csf_converter.cc" - "${LIBRARY_DIR}/tensor/csx_converter.cc" - "${LIBRARY_DIR}/type.cc" - "${LIBRARY_DIR}/visitor.cc" + "${LIBRARY_DIR}/builder.cc" "${LIBRARY_DIR}/c/bridge.cc" - "${LIBRARY_DIR}/io/buffered.cc" - "${LIBRARY_DIR}/io/caching.cc" - "${LIBRARY_DIR}/io/compressed.cc" - "${LIBRARY_DIR}/io/file.cc" - "${LIBRARY_DIR}/io/hdfs.cc" - "${LIBRARY_DIR}/io/hdfs_internal.cc" - "${LIBRARY_DIR}/io/interfaces.cc" - "${LIBRARY_DIR}/io/memory.cc" - "${LIBRARY_DIR}/io/slow.cc" - "${LIBRARY_DIR}/io/stdio.cc" - "${LIBRARY_DIR}/io/transform.cc" - "${LIBRARY_DIR}/util/async_util.cc" - "${LIBRARY_DIR}/util/basic_decimal.cc" - "${LIBRARY_DIR}/util/bit_block_counter.cc" - "${LIBRARY_DIR}/util/bit_run_reader.cc" - "${LIBRARY_DIR}/util/bit_util.cc" - "${LIBRARY_DIR}/util/bitmap.cc" - "${LIBRARY_DIR}/util/bitmap_builders.cc" - "${LIBRARY_DIR}/util/bitmap_ops.cc" - "${LIBRARY_DIR}/util/bpacking.cc" - "${LIBRARY_DIR}/util/cancel.cc" - "${LIBRARY_DIR}/util/compression.cc" - "${LIBRARY_DIR}/util/counting_semaphore.cc" - "${LIBRARY_DIR}/util/cpu_info.cc" - "${LIBRARY_DIR}/util/decimal.cc" - "${LIBRARY_DIR}/util/delimiting.cc" - "${LIBRARY_DIR}/util/formatting.cc" - "${LIBRARY_DIR}/util/future.cc" - "${LIBRARY_DIR}/util/int_util.cc" - "${LIBRARY_DIR}/util/io_util.cc" - "${LIBRARY_DIR}/util/logging.cc" - "${LIBRARY_DIR}/util/key_value_metadata.cc" - "${LIBRARY_DIR}/util/memory.cc" - "${LIBRARY_DIR}/util/mutex.cc" - "${LIBRARY_DIR}/util/string.cc" - "${LIBRARY_DIR}/util/string_builder.cc" - "${LIBRARY_DIR}/util/task_group.cc" - "${LIBRARY_DIR}/util/tdigest.cc" - "${LIBRARY_DIR}/util/thread_pool.cc" - "${LIBRARY_DIR}/util/time.cc" - "${LIBRARY_DIR}/util/trie.cc" - "${LIBRARY_DIR}/util/unreachable.cc" - "${LIBRARY_DIR}/util/uri.cc" - "${LIBRARY_DIR}/util/utf8.cc" - "${LIBRARY_DIR}/util/value_parsing.cc" - "${LIBRARY_DIR}/util/byte_size.cc" - "${LIBRARY_DIR}/util/debug.cc" - "${LIBRARY_DIR}/util/tracing.cc" - "${LIBRARY_DIR}/util/atfork_internal.cc" - "${LIBRARY_DIR}/util/crc32.cc" - "${LIBRARY_DIR}/util/hashing.cc" - "${LIBRARY_DIR}/util/ree_util.cc" - "${LIBRARY_DIR}/util/union_util.cc" - "${LIBRARY_DIR}/vendored/base64.cpp" - "${LIBRARY_DIR}/vendored/datetime/tz.cpp" - "${LIBRARY_DIR}/vendored/musl/strptime.c" - "${LIBRARY_DIR}/vendored/uriparser/UriCommon.c" - "${LIBRARY_DIR}/vendored/uriparser/UriCompare.c" - "${LIBRARY_DIR}/vendored/uriparser/UriEscape.c" - "${LIBRARY_DIR}/vendored/uriparser/UriFile.c" - "${LIBRARY_DIR}/vendored/uriparser/UriIp4Base.c" - "${LIBRARY_DIR}/vendored/uriparser/UriIp4.c" - "${LIBRARY_DIR}/vendored/uriparser/UriMemory.c" - "${LIBRARY_DIR}/vendored/uriparser/UriNormalizeBase.c" - "${LIBRARY_DIR}/vendored/uriparser/UriNormalize.c" - "${LIBRARY_DIR}/vendored/uriparser/UriParseBase.c" - "${LIBRARY_DIR}/vendored/uriparser/UriParse.c" - "${LIBRARY_DIR}/vendored/uriparser/UriQuery.c" - "${LIBRARY_DIR}/vendored/uriparser/UriRecompose.c" - "${LIBRARY_DIR}/vendored/uriparser/UriResolve.c" - "${LIBRARY_DIR}/vendored/uriparser/UriShorten.c" - "${LIBRARY_DIR}/vendored/double-conversion/bignum.cc" - "${LIBRARY_DIR}/vendored/double-conversion/bignum-dtoa.cc" - "${LIBRARY_DIR}/vendored/double-conversion/cached-powers.cc" - "${LIBRARY_DIR}/vendored/double-conversion/double-to-string.cc" - "${LIBRARY_DIR}/vendored/double-conversion/fast-dtoa.cc" - "${LIBRARY_DIR}/vendored/double-conversion/fixed-dtoa.cc" - "${LIBRARY_DIR}/vendored/double-conversion/string-to-double.cc" - "${LIBRARY_DIR}/vendored/double-conversion/strtod.cc" - + "${LIBRARY_DIR}/c/dlpack.cc" + "${LIBRARY_DIR}/chunk_resolver.cc" + "${LIBRARY_DIR}/chunked_array.cc" + "${LIBRARY_DIR}/compare.cc" "${LIBRARY_DIR}/compute/api_aggregate.cc" "${LIBRARY_DIR}/compute/api_scalar.cc" "${LIBRARY_DIR}/compute/api_vector.cc" "${LIBRARY_DIR}/compute/cast.cc" "${LIBRARY_DIR}/compute/exec.cc" + "${LIBRARY_DIR}/compute/expression.cc" "${LIBRARY_DIR}/compute/function.cc" "${LIBRARY_DIR}/compute/function_internal.cc" "${LIBRARY_DIR}/compute/kernel.cc" @@ -355,6 +263,7 @@ set(ARROW_SRCS "${LIBRARY_DIR}/compute/kernels/aggregate_var_std.cc" "${LIBRARY_DIR}/compute/kernels/codegen_internal.cc" "${LIBRARY_DIR}/compute/kernels/hash_aggregate.cc" + "${LIBRARY_DIR}/compute/kernels/ree_util_internal.cc" "${LIBRARY_DIR}/compute/kernels/row_encoder.cc" "${LIBRARY_DIR}/compute/kernels/scalar_arithmetic.cc" "${LIBRARY_DIR}/compute/kernels/scalar_boolean.cc" @@ -382,30 +291,139 @@ set(ARROW_SRCS "${LIBRARY_DIR}/compute/kernels/vector_cumulative_ops.cc" "${LIBRARY_DIR}/compute/kernels/vector_hash.cc" "${LIBRARY_DIR}/compute/kernels/vector_nested.cc" + "${LIBRARY_DIR}/compute/kernels/vector_pairwise.cc" "${LIBRARY_DIR}/compute/kernels/vector_rank.cc" "${LIBRARY_DIR}/compute/kernels/vector_replace.cc" + "${LIBRARY_DIR}/compute/kernels/vector_run_end_encode.cc" "${LIBRARY_DIR}/compute/kernels/vector_select_k.cc" "${LIBRARY_DIR}/compute/kernels/vector_selection.cc" - "${LIBRARY_DIR}/compute/kernels/vector_sort.cc" - "${LIBRARY_DIR}/compute/kernels/vector_selection_internal.cc" "${LIBRARY_DIR}/compute/kernels/vector_selection_filter_internal.cc" + "${LIBRARY_DIR}/compute/kernels/vector_selection_internal.cc" "${LIBRARY_DIR}/compute/kernels/vector_selection_take_internal.cc" - "${LIBRARY_DIR}/compute/light_array.cc" - "${LIBRARY_DIR}/compute/registry.cc" - "${LIBRARY_DIR}/compute/expression.cc" + "${LIBRARY_DIR}/compute/kernels/vector_sort.cc" + "${LIBRARY_DIR}/compute/key_hash_internal.cc" + "${LIBRARY_DIR}/compute/key_map_internal.cc" + "${LIBRARY_DIR}/compute/light_array_internal.cc" "${LIBRARY_DIR}/compute/ordering.cc" + "${LIBRARY_DIR}/compute/registry.cc" "${LIBRARY_DIR}/compute/row/compare_internal.cc" "${LIBRARY_DIR}/compute/row/encode_internal.cc" "${LIBRARY_DIR}/compute/row/grouper.cc" "${LIBRARY_DIR}/compute/row/row_internal.cc" - + "${LIBRARY_DIR}/compute/util.cc" + "${LIBRARY_DIR}/config.cc" + "${LIBRARY_DIR}/datum.cc" + "${LIBRARY_DIR}/device.cc" + "${LIBRARY_DIR}/extension_type.cc" + "${LIBRARY_DIR}/integration/c_data_integration_internal.cc" + "${LIBRARY_DIR}/io/buffered.cc" + "${LIBRARY_DIR}/io/caching.cc" + "${LIBRARY_DIR}/io/compressed.cc" + "${LIBRARY_DIR}/io/file.cc" + "${LIBRARY_DIR}/io/hdfs.cc" + "${LIBRARY_DIR}/io/hdfs_internal.cc" + "${LIBRARY_DIR}/io/interfaces.cc" + "${LIBRARY_DIR}/io/memory.cc" + "${LIBRARY_DIR}/io/slow.cc" + "${LIBRARY_DIR}/io/stdio.cc" + "${LIBRARY_DIR}/io/transform.cc" "${LIBRARY_DIR}/ipc/dictionary.cc" "${LIBRARY_DIR}/ipc/feather.cc" + "${LIBRARY_DIR}/ipc/file_to_stream.cc" "${LIBRARY_DIR}/ipc/message.cc" "${LIBRARY_DIR}/ipc/metadata_internal.cc" "${LIBRARY_DIR}/ipc/options.cc" "${LIBRARY_DIR}/ipc/reader.cc" + "${LIBRARY_DIR}/ipc/stream_to_file.cc" "${LIBRARY_DIR}/ipc/writer.cc" + "${LIBRARY_DIR}/memory_pool.cc" + "${LIBRARY_DIR}/pretty_print.cc" + "${LIBRARY_DIR}/record_batch.cc" + "${LIBRARY_DIR}/result.cc" + "${LIBRARY_DIR}/scalar.cc" + "${LIBRARY_DIR}/sparse_tensor.cc" + "${LIBRARY_DIR}/status.cc" + "${LIBRARY_DIR}/table.cc" + "${LIBRARY_DIR}/table_builder.cc" + "${LIBRARY_DIR}/tensor.cc" + "${LIBRARY_DIR}/tensor/coo_converter.cc" + "${LIBRARY_DIR}/tensor/csf_converter.cc" + "${LIBRARY_DIR}/tensor/csx_converter.cc" + "${LIBRARY_DIR}/type.cc" + "${LIBRARY_DIR}/type_traits.cc" + "${LIBRARY_DIR}/util/align_util.cc" + "${LIBRARY_DIR}/util/async_util.cc" + "${LIBRARY_DIR}/util/atfork_internal.cc" + "${LIBRARY_DIR}/util/basic_decimal.cc" + "${LIBRARY_DIR}/util/bit_block_counter.cc" + "${LIBRARY_DIR}/util/bit_run_reader.cc" + "${LIBRARY_DIR}/util/bit_util.cc" + "${LIBRARY_DIR}/util/bitmap.cc" + "${LIBRARY_DIR}/util/bitmap_builders.cc" + "${LIBRARY_DIR}/util/bitmap_ops.cc" + "${LIBRARY_DIR}/util/bpacking.cc" + "${LIBRARY_DIR}/util/byte_size.cc" + "${LIBRARY_DIR}/util/cancel.cc" + "${LIBRARY_DIR}/util/compression.cc" + "${LIBRARY_DIR}/util/counting_semaphore.cc" + "${LIBRARY_DIR}/util/cpu_info.cc" + "${LIBRARY_DIR}/util/crc32.cc" + "${LIBRARY_DIR}/util/debug.cc" + "${LIBRARY_DIR}/util/decimal.cc" + "${LIBRARY_DIR}/util/delimiting.cc" + "${LIBRARY_DIR}/util/dict_util.cc" + "${LIBRARY_DIR}/util/float16.cc" + "${LIBRARY_DIR}/util/formatting.cc" + "${LIBRARY_DIR}/util/future.cc" + "${LIBRARY_DIR}/util/hashing.cc" + "${LIBRARY_DIR}/util/int_util.cc" + "${LIBRARY_DIR}/util/io_util.cc" + "${LIBRARY_DIR}/util/key_value_metadata.cc" + "${LIBRARY_DIR}/util/list_util.cc" + "${LIBRARY_DIR}/util/logging.cc" + "${LIBRARY_DIR}/util/memory.cc" + "${LIBRARY_DIR}/util/mutex.cc" + "${LIBRARY_DIR}/util/ree_util.cc" + "${LIBRARY_DIR}/util/string.cc" + "${LIBRARY_DIR}/util/string_builder.cc" + "${LIBRARY_DIR}/util/task_group.cc" + "${LIBRARY_DIR}/util/tdigest.cc" + "${LIBRARY_DIR}/util/thread_pool.cc" + "${LIBRARY_DIR}/util/time.cc" + "${LIBRARY_DIR}/util/tracing.cc" + "${LIBRARY_DIR}/util/trie.cc" + "${LIBRARY_DIR}/util/union_util.cc" + "${LIBRARY_DIR}/util/unreachable.cc" + "${LIBRARY_DIR}/util/uri.cc" + "${LIBRARY_DIR}/util/utf8.cc" + "${LIBRARY_DIR}/util/value_parsing.cc" + "${LIBRARY_DIR}/vendored/base64.cpp" + "${LIBRARY_DIR}/vendored/datetime/tz.cpp" + "${LIBRARY_DIR}/vendored/double-conversion/bignum-dtoa.cc" + "${LIBRARY_DIR}/vendored/double-conversion/bignum.cc" + "${LIBRARY_DIR}/vendored/double-conversion/cached-powers.cc" + "${LIBRARY_DIR}/vendored/double-conversion/double-to-string.cc" + "${LIBRARY_DIR}/vendored/double-conversion/fast-dtoa.cc" + "${LIBRARY_DIR}/vendored/double-conversion/fixed-dtoa.cc" + "${LIBRARY_DIR}/vendored/double-conversion/string-to-double.cc" + "${LIBRARY_DIR}/vendored/double-conversion/strtod.cc" + "${LIBRARY_DIR}/vendored/musl/strptime.c" + "${LIBRARY_DIR}/vendored/uriparser/UriCommon.c" + "${LIBRARY_DIR}/vendored/uriparser/UriCompare.c" + "${LIBRARY_DIR}/vendored/uriparser/UriEscape.c" + "${LIBRARY_DIR}/vendored/uriparser/UriFile.c" + "${LIBRARY_DIR}/vendored/uriparser/UriIp4.c" + "${LIBRARY_DIR}/vendored/uriparser/UriIp4Base.c" + "${LIBRARY_DIR}/vendored/uriparser/UriMemory.c" + "${LIBRARY_DIR}/vendored/uriparser/UriNormalize.c" + "${LIBRARY_DIR}/vendored/uriparser/UriNormalizeBase.c" + "${LIBRARY_DIR}/vendored/uriparser/UriParse.c" + "${LIBRARY_DIR}/vendored/uriparser/UriParseBase.c" + "${LIBRARY_DIR}/vendored/uriparser/UriQuery.c" + "${LIBRARY_DIR}/vendored/uriparser/UriRecompose.c" + "${LIBRARY_DIR}/vendored/uriparser/UriResolve.c" + "${LIBRARY_DIR}/vendored/uriparser/UriShorten.c" + "${LIBRARY_DIR}/visitor.cc" "${ARROW_SRC_DIR}/arrow/adapters/orc/adapter.cc" "${ARROW_SRC_DIR}/arrow/adapters/orc/util.cc" @@ -465,22 +483,38 @@ set(PARQUET_SRCS "${LIBRARY_DIR}/arrow/schema.cc" "${LIBRARY_DIR}/arrow/schema_internal.cc" "${LIBRARY_DIR}/arrow/writer.cc" + "${LIBRARY_DIR}/benchmark_util.cc" "${LIBRARY_DIR}/bloom_filter.cc" + "${LIBRARY_DIR}/bloom_filter_reader.cc" "${LIBRARY_DIR}/column_reader.cc" "${LIBRARY_DIR}/column_scanner.cc" "${LIBRARY_DIR}/column_writer.cc" "${LIBRARY_DIR}/encoding.cc" + "${LIBRARY_DIR}/encryption/crypto_factory.cc" "${LIBRARY_DIR}/encryption/encryption.cc" "${LIBRARY_DIR}/encryption/encryption_internal.cc" + "${LIBRARY_DIR}/encryption/encryption_internal_nossl.cc" + "${LIBRARY_DIR}/encryption/file_key_unwrapper.cc" + "${LIBRARY_DIR}/encryption/file_key_wrapper.cc" + "${LIBRARY_DIR}/encryption/file_system_key_material_store.cc" "${LIBRARY_DIR}/encryption/internal_file_decryptor.cc" "${LIBRARY_DIR}/encryption/internal_file_encryptor.cc" + "${LIBRARY_DIR}/encryption/key_material.cc" + "${LIBRARY_DIR}/encryption/key_metadata.cc" + "${LIBRARY_DIR}/encryption/key_toolkit.cc" + "${LIBRARY_DIR}/encryption/key_toolkit_internal.cc" + "${LIBRARY_DIR}/encryption/kms_client.cc" + "${LIBRARY_DIR}/encryption/local_wrap_kms_client.cc" + "${LIBRARY_DIR}/encryption/openssl_internal.cc" "${LIBRARY_DIR}/exception.cc" "${LIBRARY_DIR}/file_reader.cc" "${LIBRARY_DIR}/file_writer.cc" - "${LIBRARY_DIR}/page_index.cc" - "${LIBRARY_DIR}/level_conversion.cc" "${LIBRARY_DIR}/level_comparison.cc" + "${LIBRARY_DIR}/level_comparison_avx2.cc" + "${LIBRARY_DIR}/level_conversion.cc" + "${LIBRARY_DIR}/level_conversion_bmi2.cc" "${LIBRARY_DIR}/metadata.cc" + "${LIBRARY_DIR}/page_index.cc" "${LIBRARY_DIR}/platform.cc" "${LIBRARY_DIR}/printer.cc" "${LIBRARY_DIR}/properties.cc" @@ -489,7 +523,6 @@ set(PARQUET_SRCS "${LIBRARY_DIR}/stream_reader.cc" "${LIBRARY_DIR}/stream_writer.cc" "${LIBRARY_DIR}/types.cc" - "${LIBRARY_DIR}/bloom_filter_reader.cc" "${LIBRARY_DIR}/xxhasher.cc" "${GEN_LIBRARY_DIR}/parquet_constants.cpp" @@ -520,6 +553,9 @@ endif () add_definitions(-DPARQUET_THRIFT_VERSION_MAJOR=0) add_definitions(-DPARQUET_THRIFT_VERSION_MINOR=16) +# As per https://github.com/apache/arrow/pull/35672 you need to enable it explicitly. +add_definitions(-DARROW_ENABLE_THREADING) + # === tools set(TOOLS_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/tools/parquet") diff --git a/contrib/flatbuffers b/contrib/flatbuffers index eb3f8279482..0100f6a5779 160000 --- a/contrib/flatbuffers +++ b/contrib/flatbuffers @@ -1 +1 @@ -Subproject commit eb3f827948241ce0e701516f16cd67324802bce9 +Subproject commit 0100f6a5779831fa7a651e4b67ef389a8752bd9b diff --git a/contrib/krb5 b/contrib/krb5 index 71b06c22760..c5b4b994c18 160000 --- a/contrib/krb5 +++ b/contrib/krb5 @@ -1 +1 @@ -Subproject commit 71b06c2276009ae649c7703019f3b4605f66fd3d +Subproject commit c5b4b994c18db86933255907a97eee5993fd18fe diff --git a/contrib/numactl b/contrib/numactl index 8d13d63a05f..ff32c618d63 160000 --- a/contrib/numactl +++ b/contrib/numactl @@ -1 +1 @@ -Subproject commit 8d13d63a05f0c3cd88bf777cbb61541202b7da08 +Subproject commit ff32c618d63ca7ac48cce366c5a04bb3563683a0 diff --git a/contrib/usearch b/contrib/usearch index 1706420acaf..7efe8b710c9 160000 --- a/contrib/usearch +++ b/contrib/usearch @@ -1 +1 @@ -Subproject commit 1706420acafbd83d852c512dcf343af0a4059e48 +Subproject commit 7efe8b710c9831bfe06573b1df0fad001b04a2b5 diff --git a/contrib/usearch-cmake/CMakeLists.txt b/contrib/usearch-cmake/CMakeLists.txt index 25f6ca82a74..fda061bf467 100644 --- a/contrib/usearch-cmake/CMakeLists.txt +++ b/contrib/usearch-cmake/CMakeLists.txt @@ -6,12 +6,63 @@ target_include_directories(_usearch SYSTEM INTERFACE ${USEARCH_PROJECT_DIR}/incl target_link_libraries(_usearch INTERFACE _fp16) target_compile_definitions(_usearch INTERFACE USEARCH_USE_FP16LIB) -# target_compile_definitions(_usearch INTERFACE USEARCH_USE_SIMSIMD) -# ^^ simsimd is not enabled at the moment. Reasons: -# - Vectorization is important for raw scans but not so much for HNSW. We use usearch only for HNSW. -# - Simsimd does compile-time dispatch (choice of SIMD kernels determined by capabilities of the build machine) or dynamic dispatch (SIMD -# kernels chosen at runtime based on cpuid instruction). Since current builds are limited to SSE 4.2 (x86) and NEON (ARM), the speedup of -# the former would be moderate compared to AVX-512 / SVE. The latter is at the moment too fragile with respect to portability across x86 -# and ARM machines ... certain conbinations of quantizations / distance functions / SIMD instructions are not implemented at the moment. +# Only x86 for now. On ARM, the linker goes down in flames. To make SimSIMD compile, I had to remove a macro checks in SimSIMD +# for AVX512 (x86, worked nicely) and __ARM_BF16_FORMAT_ALTERNATIVE. It is probably because of that. +if (ARCH_AMD64) + target_link_libraries(_usearch INTERFACE _simsimd) + target_compile_definitions(_usearch INTERFACE USEARCH_USE_SIMSIMD) + + target_compile_definitions(_usearch INTERFACE USEARCH_CAN_COMPILE_FLOAT16) + target_compile_definitions(_usearch INTERFACE USEARCH_CAN_COMPILE_BF16) +endif () add_library(ch_contrib::usearch ALIAS _usearch) + + +# Cf. https://github.com/llvm/llvm-project/issues/107810 (though it is not 100% the same stack) +# +# LLVM ERROR: Cannot select: 0x7996e7a73150: f32,ch = load<(load (s16) from %ir.22, !tbaa !54231), anyext from bf16> 0x79961cb737c0, 0x7996e7a1a500, undef:i64, ./contrib/SimSIMD/include/simsimd/dot.h:215:1 +# 0x7996e7a1a500: i64 = add 0x79961e770d00, Constant:i64<-16>, ./contrib/SimSIMD/include/simsimd/dot.h:215:1 +# 0x79961e770d00: i64,ch = CopyFromReg 0x79961cb737c0, Register:i64 %4, ./contrib/SimSIMD/include/simsimd/dot.h:215:1 +# 0x7996e7a1ae10: i64 = Register %4 +# 0x7996e7a1b5f0: i64 = Constant<-16> +# 0x7996e7a1a730: i64 = undef +# In function: _ZL23simsimd_dot_bf16_serialPKu6__bf16S0_yPd +# PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace. +# Stack dump: +# 0. Running pass 'Function Pass Manager' on module 'src/libdbms.a(MergeTreeIndexVectorSimilarity.cpp.o at 2312737440)'. +# 1. Running pass 'AArch64 Instruction Selection' on function '@_ZL23simsimd_dot_bf16_serialPKu6__bf16S0_yPd' +# #0 0x00007999e83a63bf llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xda63bf) +# #1 0x00007999e83a44f9 llvm::sys::RunSignalHandlers() (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xda44f9) +# #2 0x00007999e83a6b00 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xda6b00) +# #3 0x00007999e6e45320 (/lib/x86_64-linux-gnu/libc.so.6+0x45320) +# #4 0x00007999e6e9eb1c pthread_kill (/lib/x86_64-linux-gnu/libc.so.6+0x9eb1c) +# #5 0x00007999e6e4526e raise (/lib/x86_64-linux-gnu/libc.so.6+0x4526e) +# #6 0x00007999e6e288ff abort (/lib/x86_64-linux-gnu/libc.so.6+0x288ff) +# #7 0x00007999e82fe0c2 llvm::report_fatal_error(llvm::Twine const&, bool) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xcfe0c2) +# #8 0x00007999e8c2f8e3 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x162f8e3) +# #9 0x00007999e8c2ed76 llvm::SelectionDAGISel::SelectCodeCommon(llvm::SDNode*, unsigned char const*, unsigned int) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x162ed76) +# #10 0x00007999ea1adbcb (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x2badbcb) +# #11 0x00007999e8c2611f llvm::SelectionDAGISel::DoInstructionSelection() (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x162611f) +# #12 0x00007999e8c25790 llvm::SelectionDAGISel::CodeGenAndEmitDAG() (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x1625790) +# #13 0x00007999e8c248de llvm::SelectionDAGISel::SelectAllBasicBlocks(llvm::Function const&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x16248de) +# #14 0x00007999e8c22934 llvm::SelectionDAGISel::runOnMachineFunction(llvm::MachineFunction&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x1622934) +# #15 0x00007999e87826b9 llvm::MachineFunctionPass::runOnFunction(llvm::Function&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x11826b9) +# #16 0x00007999e84f7772 llvm::FPPassManager::runOnFunction(llvm::Function&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xef7772) +# #17 0x00007999e84fd2f4 llvm::FPPassManager::runOnModule(llvm::Module&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xefd2f4) +# #18 0x00007999e84f7e9f llvm::legacy::PassManagerImpl::run(llvm::Module&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xef7e9f) +# #19 0x00007999e99f7d61 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x23f7d61) +# #20 0x00007999e99f8c91 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x23f8c91) +# #21 0x00007999e99f8b10 llvm::lto::thinBackend(llvm::lto::Config const&, unsigned int, std::function>> (unsigned int, llvm::Twine const&)>, llvm::Module&, llvm::ModuleSummaryIndex const&, llvm::DenseMap, std::equal_to, std::allocator>, llvm::DenseMapInfo, llvm::detail::DenseMapPair, std::equal_to, std::allocator>>> const&, llvm::DenseMap, llvm::detail::DenseMapPair> const&, llvm::MapVector, llvm::detail::DenseMapPair>, llvm::SmallVector, 0u>>*, std::vector> const&) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x23f8b10) +# #22 0x00007999e99f248d (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x23f248d) +# #23 0x00007999e99f1cd6 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0x23f1cd6) +# #24 0x00007999e82c9beb (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xcc9beb) +# #25 0x00007999e834ebe3 llvm::ThreadPool::processTasks(llvm::ThreadPoolTaskGroup*) (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xd4ebe3) +# #26 0x00007999e834f704 (/usr/lib/llvm-18/bin/../lib/libLLVM.so.18.1+0xd4f704) +# #27 0x00007999e6e9ca94 (/lib/x86_64-linux-gnu/libc.so.6+0x9ca94) +# #28 0x00007999e6f29c3c (/lib/x86_64-linux-gnu/libc.so.6+0x129c3c) +# clang++-18: error: unable to execute command: Aborted (core dumped) +# clang++-18: error: linker command failed due to signal (use -v to see invocation) +# ^[[A^Cninja: build stopped: interrupted by user. diff --git a/docker/keeper/Dockerfile b/docker/keeper/Dockerfile index dfe6a420260..4ecc087afb4 100644 --- a/docker/keeper/Dockerfile +++ b/docker/keeper/Dockerfile @@ -1,7 +1,7 @@ # The Dockerfile.ubuntu exists for the tests/ci/docker_server.py script # If the image is built from Dockerfile.alpine, then the `-alpine` suffix is added automatically, # so the only purpose of Dockerfile.ubuntu is to push `latest`, `head` and so on w/o suffixes -FROM ubuntu:20.04 AS glibc-donor +FROM ubuntu:22.04 AS glibc-donor ARG TARGETARCH RUN arch=${TARGETARCH:-amd64} \ @@ -9,7 +9,11 @@ RUN arch=${TARGETARCH:-amd64} \ amd64) rarch=x86_64 ;; \ arm64) rarch=aarch64 ;; \ esac \ - && ln -s "${rarch}-linux-gnu" /lib/linux-gnu + && ln -s "${rarch}-linux-gnu" /lib/linux-gnu \ + && case $arch in \ + amd64) ln /lib/linux-gnu/ld-linux-x86-64.so.2 /lib/linux-gnu/ld-2.35.so ;; \ + arm64) ln /lib/linux-gnu/ld-linux-aarch64.so.1 /lib/linux-gnu/ld-2.35.so ;; \ + esac FROM alpine @@ -20,7 +24,7 @@ ENV LANG=en_US.UTF-8 \ TZ=UTC \ CLICKHOUSE_CONFIG=/etc/clickhouse-server/config.xml -COPY --from=glibc-donor /lib/linux-gnu/libc.so.6 /lib/linux-gnu/libdl.so.2 /lib/linux-gnu/libm.so.6 /lib/linux-gnu/libpthread.so.0 /lib/linux-gnu/librt.so.1 /lib/linux-gnu/libnss_dns.so.2 /lib/linux-gnu/libnss_files.so.2 /lib/linux-gnu/libresolv.so.2 /lib/linux-gnu/ld-2.31.so /lib/ +COPY --from=glibc-donor /lib/linux-gnu/libc.so.6 /lib/linux-gnu/libdl.so.2 /lib/linux-gnu/libm.so.6 /lib/linux-gnu/libpthread.so.0 /lib/linux-gnu/librt.so.1 /lib/linux-gnu/libnss_dns.so.2 /lib/linux-gnu/libnss_files.so.2 /lib/linux-gnu/libresolv.so.2 /lib/linux-gnu/ld-2.35.so /lib/ COPY --from=glibc-donor /etc/nsswitch.conf /etc/ COPY entrypoint.sh /entrypoint.sh @@ -34,7 +38,7 @@ RUN arch=${TARGETARCH:-amd64} \ # lts / testing / prestable / etc ARG REPO_CHANNEL="stable" ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}" -ARG VERSION="24.9.2.42" +ARG VERSION="24.10.1.2812" ARG PACKAGES="clickhouse-keeper" ARG DIRECT_DOWNLOAD_URLS="" diff --git a/docker/server/Dockerfile.alpine b/docker/server/Dockerfile.alpine index 991c25ad142..93acf1a5773 100644 --- a/docker/server/Dockerfile.alpine +++ b/docker/server/Dockerfile.alpine @@ -35,7 +35,7 @@ RUN arch=${TARGETARCH:-amd64} \ # lts / testing / prestable / etc ARG REPO_CHANNEL="stable" ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}" -ARG VERSION="24.9.2.42" +ARG VERSION="24.10.1.2812" ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static" ARG DIRECT_DOWNLOAD_URLS="" diff --git a/docker/server/Dockerfile.ubuntu b/docker/server/Dockerfile.ubuntu index 5dc88b49e31..0d5c983f5e6 100644 --- a/docker/server/Dockerfile.ubuntu +++ b/docker/server/Dockerfile.ubuntu @@ -1,4 +1,4 @@ -FROM ubuntu:20.04 +FROM ubuntu:22.04 # see https://github.com/moby/moby/issues/4032#issuecomment-192327844 # It could be removed after we move on a version 23:04+ @@ -28,7 +28,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list ARG REPO_CHANNEL="stable" ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main" -ARG VERSION="24.9.2.42" +ARG VERSION="24.10.1.2812" ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static" #docker-official-library:off diff --git a/docker/server/README.md b/docker/server/README.md index 65239126790..1dc636414ac 100644 --- a/docker/server/README.md +++ b/docker/server/README.md @@ -20,6 +20,7 @@ For more information and documentation see https://clickhouse.com/. - The amd64 image requires support for [SSE3 instructions](https://en.wikipedia.org/wiki/SSE3). Virtually all x86 CPUs after 2005 support SSE3. - The arm64 image requires support for the [ARMv8.2-A architecture](https://en.wikipedia.org/wiki/AArch64#ARMv8.2-A) and additionally the Load-Acquire RCpc register. The register is optional in version ARMv8.2-A and mandatory in [ARMv8.3-A](https://en.wikipedia.org/wiki/AArch64#ARMv8.3-A). Supported in Graviton >=2, Azure and GCP instances. Examples for unsupported devices are Raspberry Pi 4 (ARMv8.0-A) and Jetson AGX Xavier/Orin (ARMv8.2-A). +- Since the Clickhouse 24.11 Ubuntu images started using `ubuntu:22.04` as its base image. It requires docker version >= `20.10.10` containing [patch](https://github.com/moby/moby/commit/977283509f75303bc6612665a04abf76ff1d2468). As a workaround you could use `docker run [--privileged | --security-opt seccomp=unconfined]` instead, however that has security implications. ## How to use this image diff --git a/docker/test/base/setup_export_logs.sh b/docker/test/base/setup_export_logs.sh index a39f96867be..12f1cc4d357 100755 --- a/docker/test/base/setup_export_logs.sh +++ b/docker/test/base/setup_export_logs.sh @@ -25,7 +25,7 @@ EXTRA_COLUMNS_EXPRESSION_TRACE_LOG="${EXTRA_COLUMNS_EXPRESSION}, arrayMap(x -> d # coverage_log needs more columns for symbolization, but only symbol names (the line numbers are too heavy to calculate) EXTRA_COLUMNS_COVERAGE_LOG="${EXTRA_COLUMNS} symbols Array(LowCardinality(String)), " -EXTRA_COLUMNS_EXPRESSION_COVERAGE_LOG="${EXTRA_COLUMNS_EXPRESSION}, arrayMap(x -> demangle(addressToSymbol(x)), coverage)::Array(LowCardinality(String)) AS symbols" +EXTRA_COLUMNS_EXPRESSION_COVERAGE_LOG="${EXTRA_COLUMNS_EXPRESSION}, arrayDistinct(arrayMap(x -> demangle(addressToSymbol(x)), coverage))::Array(LowCardinality(String)) AS symbols" function __set_connection_args diff --git a/docker/test/libfuzzer/Dockerfile b/docker/test/libfuzzer/Dockerfile index 3ffae0cd921..46e305c90ab 100644 --- a/docker/test/libfuzzer/Dockerfile +++ b/docker/test/libfuzzer/Dockerfile @@ -33,8 +33,6 @@ RUN apt-get update \ COPY requirements.txt / RUN pip3 install --no-cache-dir -r /requirements.txt -ENV FUZZER_ARGS="-max_total_time=60" - SHELL ["/bin/bash", "-c"] # docker run --network=host --volume :/workspace -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/libfuzzer diff --git a/docker/test/stateless/clickhouse-statelest-test-runner.Dockerfile b/docker/test/stateless/clickhouse-statelest-test-runner.Dockerfile deleted file mode 100644 index a9802f6f1da..00000000000 --- a/docker/test/stateless/clickhouse-statelest-test-runner.Dockerfile +++ /dev/null @@ -1,16 +0,0 @@ -# Since right now we can't set volumes to the docker during build, we split building container in stages: -# 1. build base container -# 2. run base conatiner with mounted volumes -# 3. commit container as image -FROM ubuntu:20.04 as clickhouse-test-runner-base - -# A volume where directory with clickhouse packages to be mounted, -# for later installing. -VOLUME /packages - -CMD apt-get update ;\ - DEBIAN_FRONTEND=noninteractive \ - apt install -y /packages/clickhouse-common-static_*.deb \ - /packages/clickhouse-client_*.deb \ - && apt-get clean \ - && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/* diff --git a/docker/test/style/Dockerfile b/docker/test/style/Dockerfile index fa6b087eb7d..564301f447c 100644 --- a/docker/test/style/Dockerfile +++ b/docker/test/style/Dockerfile @@ -28,7 +28,7 @@ COPY requirements.txt / RUN pip3 install --no-cache-dir -r requirements.txt RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && locale-gen en_US.UTF-8 -ENV LC_ALL en_US.UTF-8 +ENV LC_ALL=en_US.UTF-8 # Architecture of the image when BuildKit/buildx is used ARG TARGETARCH diff --git a/docker/test/style/requirements.txt b/docker/test/style/requirements.txt index cc87f6e548d..aab20b5bee0 100644 --- a/docker/test/style/requirements.txt +++ b/docker/test/style/requirements.txt @@ -12,6 +12,7 @@ charset-normalizer==3.3.2 click==8.1.7 codespell==2.2.1 cryptography==43.0.1 +datacompy==0.7.3 Deprecated==1.2.14 dill==0.3.8 flake8==4.0.1 @@ -23,6 +24,7 @@ mccabe==0.6.1 multidict==6.0.5 mypy==1.8.0 mypy-extensions==1.0.0 +pandas==2.2.3 packaging==24.1 pathspec==0.9.0 pip==24.1.1 diff --git a/docs/changelogs/v24.10.1.2812-stable.md b/docs/changelogs/v24.10.1.2812-stable.md new file mode 100644 index 00000000000..c26bbf706ff --- /dev/null +++ b/docs/changelogs/v24.10.1.2812-stable.md @@ -0,0 +1,412 @@ +--- +sidebar_position: 1 +sidebar_label: 2024 +--- + +# 2024 Changelog + +### ClickHouse release v24.10.1.2812-stable (9cd0a3738d5) FIXME as compared to v24.10.1.1-new (b12a3677418) + +#### Backward Incompatible Change +* Allow to write `SETTINGS` before `FORMAT` in a chain of queries with `UNION` when subqueries are inside parentheses. This closes [#39712](https://github.com/ClickHouse/ClickHouse/issues/39712). Change the behavior when a query has the SETTINGS clause specified twice in a sequence. The closest SETTINGS clause will have a preference for the corresponding subquery. In the previous versions, the outermost SETTINGS clause could take a preference over the inner one. [#68614](https://github.com/ClickHouse/ClickHouse/pull/68614) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Reordering of filter conditions from `[PRE]WHERE` clause is now allowed by default. It could be disabled by setting `allow_reorder_prewhere_conditions` to `false`. [#70657](https://github.com/ClickHouse/ClickHouse/pull/70657) ([Nikita Taranov](https://github.com/nickitat)). +* Fix `optimize_functions_to_subcolumns` optimization (previously could lead to `Invalid column type for ColumnUnique::insertRangeFrom. Expected String, got LowCardinality(String)` error), by preserving `LowCardinality` type in `mapKeys`/`mapValues`. [#70716](https://github.com/ClickHouse/ClickHouse/pull/70716) ([Azat Khuzhin](https://github.com/azat)). +* Remove the `idxd-config` library, which has an incompatible license. This also removes the experimental Intel DeflateQPL codec. [#70987](https://github.com/ClickHouse/ClickHouse/pull/70987) ([Alexey Milovidov](https://github.com/alexey-milovidov)). + +#### New Feature +* MongoDB integration refactored: migration to new driver mongocxx from deprecated Poco::MongoDB, remove support for deprecated old protocol, support for connection by URI, support for all MongoDB types, support for WHERE and ORDER BY statements on MongoDB side, restriction for expression unsupported by MongoDB. [#63279](https://github.com/ClickHouse/ClickHouse/pull/63279) ([Kirill Nikiforov](https://github.com/allmazz)). +* A new `--progress-table` option in clickhouse-client prints a table with metrics changing during query execution; a new `--enable-progress-table-toggle` is associated with the `--progress-table` option, and toggles the rendering of the progress table by pressing the control key (Space). [#63689](https://github.com/ClickHouse/ClickHouse/pull/63689) ([Maria Khristenko](https://github.com/mariaKhr)). +* This allows to grant access to the wildcard prefixes. `GRANT SELECT ON db.table_pefix_* TO user`. [#65311](https://github.com/ClickHouse/ClickHouse/pull/65311) ([pufit](https://github.com/pufit)). +* Add system.query_metric_log which contains history of memory and metric values from table system.events for individual queries, periodically flushed to disk. [#66532](https://github.com/ClickHouse/ClickHouse/pull/66532) ([Pablo Marcos](https://github.com/pamarcos)). +* A simple SELECT query can be written with implicit SELECT to enable calculator-style expressions, e.g., `ch "1 + 2"`. This is controlled by a new setting, `implicit_select`. [#68502](https://github.com/ClickHouse/ClickHouse/pull/68502) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Support --copy mode for clickhouse local as a shortcut for format conversion [#68503](https://github.com/ClickHouse/ClickHouse/issues/68503). [#68583](https://github.com/ClickHouse/ClickHouse/pull/68583) ([Denis Hananein](https://github.com/denis-hananein)). +* Add support for `arrayUnion` function. [#68989](https://github.com/ClickHouse/ClickHouse/pull/68989) ([Peter Nguyen](https://github.com/petern48)). +* Support aggreate function `quantileExactWeightedInterpolated`, which is a interpolated version based on quantileExactWeighted. Some people may wonder why we need a new `quantileExactWeightedInterpolated` since we already have `quantileExactInterpolatedWeighted`. The reason is the new one is more accurate than the old one. BTW, it is for spark compatiability in Apache Gluten. [#69619](https://github.com/ClickHouse/ClickHouse/pull/69619) ([李扬](https://github.com/taiyang-li)). +* Support function arrayElementOrNull. It returns null if array index is out of range or map key not found. [#69646](https://github.com/ClickHouse/ClickHouse/pull/69646) ([李扬](https://github.com/taiyang-li)). +* Allows users to specify regular expressions through new `message_regexp` and `message_regexp_negative` fields in the `config.xml` file to filter out logging. The logging is applied to the formatted un-colored text for the most intuitive developer experience. [#69657](https://github.com/ClickHouse/ClickHouse/pull/69657) ([Peter Nguyen](https://github.com/petern48)). +* Support Dynamic type in most functions by executing them on internal types inside Dynamic. [#69691](https://github.com/ClickHouse/ClickHouse/pull/69691) ([Pavel Kruglov](https://github.com/Avogar)). +* Re-added `RIPEMD160` function, which computes the RIPEMD-160 cryptographic hash of a string. Example: `SELECT HEX(RIPEMD160('The quick brown fox jumps over the lazy dog'))` returns `37F332F68DB77BD9D7EDD4969571AD671CF9DD3B`. [#70087](https://github.com/ClickHouse/ClickHouse/pull/70087) ([Dergousov Maxim](https://github.com/m7kss1)). +* Allow to cache read files for object storage table engines and data lakes using hash from ETag + file path as cache key. [#70135](https://github.com/ClickHouse/ClickHouse/pull/70135) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Support reading Iceberg tables on HDFS. [#70268](https://github.com/ClickHouse/ClickHouse/pull/70268) ([flynn](https://github.com/ucasfl)). +* Allow to read/write JSON type as binary string in RowBinary format under settings `input_format_binary_read_json_as_string/output_format_binary_write_json_as_string`. [#70288](https://github.com/ClickHouse/ClickHouse/pull/70288) ([Pavel Kruglov](https://github.com/Avogar)). +* Allow to serialize/deserialize JSON column as single String column in Native format. For output use setting `output_format_native_write_json_as_string`. For input, use serialization version `1` before the column data. [#70312](https://github.com/ClickHouse/ClickHouse/pull/70312) ([Pavel Kruglov](https://github.com/Avogar)). +* Supports standard CTE, `with insert`, as previously only supports `insert ... with ...`. [#70593](https://github.com/ClickHouse/ClickHouse/pull/70593) ([Shichao Jin](https://github.com/jsc0218)). + +#### Performance Improvement +* Support minmax index for `pointInPolygon`. [#62085](https://github.com/ClickHouse/ClickHouse/pull/62085) ([JackyWoo](https://github.com/JackyWoo)). +* Add support for parquet bloom filters. [#62966](https://github.com/ClickHouse/ClickHouse/pull/62966) ([Arthur Passos](https://github.com/arthurpassos)). +* Lock-free parts rename to avoid INSERT affect SELECT (due to parts lock) (under normal circumstances with `fsync_part_directory`, QPS of SELECT with INSERT in parallel, increased 2x, under heavy load the effect is even bigger). Note, this only includes `ReplicatedMergeTree` for now. [#64955](https://github.com/ClickHouse/ClickHouse/pull/64955) ([Azat Khuzhin](https://github.com/azat)). +* Respect `ttl_only_drop_parts` on `materialize ttl`; only read necessary columns to recalculate TTL and drop parts by replacing them with an empty one. [#65488](https://github.com/ClickHouse/ClickHouse/pull/65488) ([Andrey Zvonov](https://github.com/zvonand)). +* Refactor `IDisk` and `IObjectStorage` for better performance. Tables from `plain` and `plain_rewritable` object storages will initialize faster. [#68146](https://github.com/ClickHouse/ClickHouse/pull/68146) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Optimized thread creation in the ThreadPool to minimize lock contention. Thread creation is now performed outside of the critical section to avoid delays in job scheduling and thread management under high load conditions. This leads to a much more responsive ClickHouse under heavy concurrent load. [#68694](https://github.com/ClickHouse/ClickHouse/pull/68694) ([filimonov](https://github.com/filimonov)). +* Enable reading LowCardinality string columns from ORC. [#69481](https://github.com/ClickHouse/ClickHouse/pull/69481) ([李扬](https://github.com/taiyang-li)). +* Added an ability to parse data directly into sparse columns. [#69828](https://github.com/ClickHouse/ClickHouse/pull/69828) ([Anton Popov](https://github.com/CurtizJ)). +* Supports parallel reading of parquet row groups and prefetching of row groups in single-threaded mode. [#69862](https://github.com/ClickHouse/ClickHouse/pull/69862) ([LiuNeng](https://github.com/liuneng1994)). +* Improved performance of parsing formats with high number of missed values (e.g. `JSONEachRow`). [#69875](https://github.com/ClickHouse/ClickHouse/pull/69875) ([Anton Popov](https://github.com/CurtizJ)). +* Use `LowCardinality` for `ProfileEvents` in system logs such as `part_log`, `query_views_log`, `filesystem_cache_log`. [#70152](https://github.com/ClickHouse/ClickHouse/pull/70152) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Improve performance of FromUnixTimestamp/ToUnixTimestamp functions. [#71042](https://github.com/ClickHouse/ClickHouse/pull/71042) ([kevinyhzou](https://github.com/KevinyhZou)). + +#### Improvement +* Allow parametrised SQL aliases. [#50665](https://github.com/ClickHouse/ClickHouse/pull/50665) ([Anton Kozlov](https://github.com/tonickkozlov)). +* Fixed [#57616](https://github.com/ClickHouse/ClickHouse/issues/57616) this problem occurs because all positive number arguments are automatically identified as `uint64` type, leading to an inability to match int type data in `summapfiltered`. the issue of non-matching is indeed confusing, as the `uint64` parameters are not specified by the user. additionally, if the arguments are `[1,2,3,toint8(-3)]`, due to the `getleastsupertype()`, these parameters will be uniformly treated as `int` type, causing `'1,2,3'` to also fail in matching the `uint` type data in `summapfiltered`. [#58408](https://github.com/ClickHouse/ClickHouse/pull/58408) ([Chen768959](https://github.com/Chen768959)). +* `ALTER TABLE .. REPLACE PARTITION` doesn't wait anymore for mutations/merges that happen in other partitions. [#59138](https://github.com/ClickHouse/ClickHouse/pull/59138) ([Vasily Nemkov](https://github.com/Enmk)). +* Refreshable materialized views are now supported in Replicated databases. [#60669](https://github.com/ClickHouse/ClickHouse/pull/60669) ([Michael Kolupaev](https://github.com/al13n321)). +* Symbolic links for tables in the `data/database_name/` directory are created for the actual paths to the table's data, depending on the storage policy, instead of the `store/...` directory on the default disk. [#61777](https://github.com/ClickHouse/ClickHouse/pull/61777) ([Kirill](https://github.com/kirillgarbar)). +* Apply configuration updates in global context object. It fixes issues like [#62308](https://github.com/ClickHouse/ClickHouse/issues/62308). [#62944](https://github.com/ClickHouse/ClickHouse/pull/62944) ([Amos Bird](https://github.com/amosbird)). +* Reworked settings that control the behavior of parallel replicas algorithms. A quick recap: ClickHouse has four different algorithms for parallel reading involving multiple replicas, which is reflected in the setting `parallel_replicas_mode`, the default value for it is `read_tasks` Additionally, the toggle-switch setting `enable_parallel_replicas` has been added. [#63151](https://github.com/ClickHouse/ClickHouse/pull/63151) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix `ReadSettings` not using user set values, because defaults were only used. [#65625](https://github.com/ClickHouse/ClickHouse/pull/65625) ([Kseniia Sumarokova](https://github.com/kssenii)). +* While parsing an Enum field from JSON, a string containing an integer will be interpreted as the corresponding Enum element. This closes [#65119](https://github.com/ClickHouse/ClickHouse/issues/65119). [#66801](https://github.com/ClickHouse/ClickHouse/pull/66801) ([scanhex12](https://github.com/scanhex12)). +* Allow `TRIM` -ing `LEADING` or `TRAILING` empty string as a no-op. Closes [#67792](https://github.com/ClickHouse/ClickHouse/issues/67792). [#68455](https://github.com/ClickHouse/ClickHouse/pull/68455) ([Peter Nguyen](https://github.com/petern48)). +* Support creating a table with a query: `CREATE TABLE ... CLONE AS ...`. It clones the source table's schema and then attaches all partitions to the newly created table. This feature is only supported with tables of the `MergeTree` family Closes [#65015](https://github.com/ClickHouse/ClickHouse/issues/65015). [#69091](https://github.com/ClickHouse/ClickHouse/pull/69091) ([tuanpach](https://github.com/tuanpach)). +* In Gluten ClickHouse, Spark's timestamp type is mapped to ClickHouse's datetime64(6) type. When casting timestamp '2012-01-01 00:11:22' as a string, Spark returns '2012-01-01 00:11:22', while Gluten ClickHouse returns '2012-01-01 00:11:22.000000'. [#69179](https://github.com/ClickHouse/ClickHouse/pull/69179) ([Wenzheng Liu](https://github.com/lwz9103)). +* Always use the new analyzer to calculate constant expressions when `enable_analyzer` is set to `true`. Support calculation of `executable()` table function arguments without using `SELECT` query for constant expression. [#69292](https://github.com/ClickHouse/ClickHouse/pull/69292) ([Dmitry Novik](https://github.com/novikd)). +* Add `enable_secure_identifiers` to disallow insecure identifiers. [#69411](https://github.com/ClickHouse/ClickHouse/pull/69411) ([tuanpach](https://github.com/tuanpach)). +* Add `show_create_query_identifier_quoting_rule` to define identifier quoting behavior of the show create query result. Possible values: - `user_display`: When the identifiers is a keyword. - `when_necessary`: When the identifiers is one of `{"distinct", "all", "table"}`, or it can cause ambiguity: column names, dictionary attribute names. - `always`: Always quote identifiers. [#69448](https://github.com/ClickHouse/ClickHouse/pull/69448) ([tuanpach](https://github.com/tuanpach)). +* Follow-up to https://github.com/ClickHouse/ClickHouse/pull/69346 Point 4 described there will work now as well:. [#69563](https://github.com/ClickHouse/ClickHouse/pull/69563) ([Vitaly Baranov](https://github.com/vitlibar)). +* Implement generic SerDe between Avro Union and ClickHouse Variant type. Resolves [#69713](https://github.com/ClickHouse/ClickHouse/issues/69713). [#69712](https://github.com/ClickHouse/ClickHouse/pull/69712) ([Jiří Kozlovský](https://github.com/jirislav)). +* 1. CREATE TABLE AS will copy PRIMARY KEY, ORDER BY, and similar clauses. Now it is supported only for the MergeTree family of table engines. 2. For example, the follow SQL statements will trigger exception in the past, but this PR fixes it: if the destination table do not provide an `ORDER BY` or `PRIMARY KEY` expression in the table definition, we will copy that from source table. [#69739](https://github.com/ClickHouse/ClickHouse/pull/69739) ([sakulali](https://github.com/sakulali)). +* Added user-level settings `min_free_disk_bytes_to_throw_insert` and `min_free_disk_ratio_to_throw_insert` to prevent insertions on disks that are almost full. [#69755](https://github.com/ClickHouse/ClickHouse/pull/69755) ([Marco Vilas Boas](https://github.com/marco-vb)). +* If you run `clickhouse-client` or other CLI application and it starts up slowly due to an overloaded server, and you start typing your query, such as `SELECT`, the previous versions will display the remaining of the terminal echo contents before printing the greetings message, such as `SELECTClickHouse local version 24.10.1.1.` instead of `ClickHouse local version 24.10.1.1.`. Now it is fixed. This closes [#31696](https://github.com/ClickHouse/ClickHouse/issues/31696). [#69856](https://github.com/ClickHouse/ClickHouse/pull/69856) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add new column readonly_duration to the system.replicas table. Needed to be able to distinguish actual readonly replicas from sentinel ones in alerts. [#69871](https://github.com/ClickHouse/ClickHouse/pull/69871) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)). +* Change the join to sort settings type to unsigned int. [#69886](https://github.com/ClickHouse/ClickHouse/pull/69886) ([kevinyhzou](https://github.com/KevinyhZou)). +* Support 64-bit XID in Keeper. It can be enabled with `use_xid_64` config. [#69908](https://github.com/ClickHouse/ClickHouse/pull/69908) ([Antonio Andelic](https://github.com/antonio2368)). +* New function getSettingOrDefault() added to return the default value and avoid exception if a custom setting is not found in the current profile. [#69917](https://github.com/ClickHouse/ClickHouse/pull/69917) ([Shankar](https://github.com/shiyer7474)). +* Allow empty needle in function replace, the same behavior with PostgreSQL. [#69918](https://github.com/ClickHouse/ClickHouse/pull/69918) ([zhanglistar](https://github.com/zhanglistar)). +* Enhance OpenTelemetry span logging to include query settings. [#70011](https://github.com/ClickHouse/ClickHouse/pull/70011) ([sharathks118](https://github.com/sharathks118)). +* Allow empty needle in functions replaceRegexp*, like https://github.com/ClickHouse/ClickHouse/pull/69918. [#70053](https://github.com/ClickHouse/ClickHouse/pull/70053) ([zhanglistar](https://github.com/zhanglistar)). +* Add info to higher-order array functions if lambda result type is unexpected. [#70093](https://github.com/ClickHouse/ClickHouse/pull/70093) ([ttanay](https://github.com/ttanay)). +* Keeper improvement: less blocking during cluster changes. [#70275](https://github.com/ClickHouse/ClickHouse/pull/70275) ([Antonio Andelic](https://github.com/antonio2368)). +* Embedded documentation for settings will be strictly more detailed and complete than the documentation on the website. This is the first step before making the website documentation always auto-generated from the source code. This has long-standing implications: - it will be guaranteed to have every setting; - there is no chance of having default values obsolete; - we can generate this documentation for each ClickHouse version; - the documentation can be displayed by the server itself even without Internet access. Generate the docs on the website from the source code. [#70289](https://github.com/ClickHouse/ClickHouse/pull/70289) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add `WITH IMPLICIT` and `FINAL` keywords to the `SHOW GRANTS` command. Fix a minor bug with implicit grants: [#70094](https://github.com/ClickHouse/ClickHouse/issues/70094). [#70293](https://github.com/ClickHouse/ClickHouse/pull/70293) ([pufit](https://github.com/pufit)). +* Don't disable nonblocking read from page cache for the entire server when reading from a blocking I/O. [#70299](https://github.com/ClickHouse/ClickHouse/pull/70299) ([Antonio Andelic](https://github.com/antonio2368)). +* Respect `compatibility` for MergeTree settings. The `compatibility` value is taken from the `default` profile on server startup, and default MergeTree settings are changed accordingly. Further changes of the `compatibility` setting do not affect MergeTree settings. [#70322](https://github.com/ClickHouse/ClickHouse/pull/70322) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Clickhouse-client realtime metrics follow-up: restore cursor when ctrl-c cancels query; immediately stop intercepting keystrokes when the query is canceled; display the metrics table if `--progress-table` is on, and toggling is disabled. [#70423](https://github.com/ClickHouse/ClickHouse/pull/70423) ([Julia Kartseva](https://github.com/jkartseva)). +* Command-line arguments for Bool settings are set to true when no value is provided for the argument (e.g. `clickhouse-client --optimize_aggregation_in_order --query "SELECT 1"`). [#70459](https://github.com/ClickHouse/ClickHouse/pull/70459) ([davidtsuk](https://github.com/davidtsuk)). +* Avoid spamming the logs with large HTTP response bodies in case of errors during inter-server communication. [#70487](https://github.com/ClickHouse/ClickHouse/pull/70487) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Added a new setting `max_parts_to_move` to control the maximum number of parts that can be moved at once. [#70520](https://github.com/ClickHouse/ClickHouse/pull/70520) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Limit the frequency of certain log messages. [#70601](https://github.com/ClickHouse/ClickHouse/pull/70601) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Don't do validation when synchronizing user_directories from keeper. [#70644](https://github.com/ClickHouse/ClickHouse/pull/70644) ([Raúl Marín](https://github.com/Algunenano)). +* Introduced a special (experimental) mode of a merge selector for MergeTree tables which makes it more aggressive for the partitions that are close to the limit by the number of parts. It is controlled by the `merge_selector_use_blurry_base` MergeTree-level setting. [#70645](https://github.com/ClickHouse/ClickHouse/pull/70645) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* `CHECK TABLE` with `PART` qualifier was incorrectly formatted in the client. [#70660](https://github.com/ClickHouse/ClickHouse/pull/70660) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Support write column index and offset index using parquet native writer. [#70669](https://github.com/ClickHouse/ClickHouse/pull/70669) ([LiuNeng](https://github.com/liuneng1994)). +* Support parse `DateTime64` for microseond and timezone in joda syntax. [#70737](https://github.com/ClickHouse/ClickHouse/pull/70737) ([kevinyhzou](https://github.com/KevinyhZou)). +* Changed an approach to figure out if a cloud storage supports [batch delete](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html) or not. [#70786](https://github.com/ClickHouse/ClickHouse/pull/70786) ([Vitaly Baranov](https://github.com/vitlibar)). +* Support for Parquet page V2 on native reader. [#70807](https://github.com/ClickHouse/ClickHouse/pull/70807) ([Arthur Passos](https://github.com/arthurpassos)). +* Add an HTML page for visualizing merges. [#70821](https://github.com/ClickHouse/ClickHouse/pull/70821) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Backported in [#71234](https://github.com/ClickHouse/ClickHouse/issues/71234): Do not call the object storage API when listing directories, as this may be cost-inefficient. Instead, store the list of filenames in the memory. The trade-offs are increased initial load time and memory required to store filenames. [#70823](https://github.com/ClickHouse/ClickHouse/pull/70823) ([Julia Kartseva](https://github.com/jkartseva)). +* A check if table has both `storage_policy` and `disk` set after alter query is added. A check if a new storage policy is compatible with an old one when using `disk` setting is added. [#70839](https://github.com/ClickHouse/ClickHouse/pull/70839) ([Kirill](https://github.com/kirillgarbar)). +* Add system.s3_queue_settings and system.azure_queue_settings. [#70841](https://github.com/ClickHouse/ClickHouse/pull/70841) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Functions `base58Encode` and `base58Decode` now accept arguments of type `FixedString`. Example: `SELECT base58Encode(toFixedString('plaintext', 9));`. [#70846](https://github.com/ClickHouse/ClickHouse/pull/70846) ([Faizan Patel](https://github.com/faizan2786)). +* Add the `partition` column to every entry type of the part log. Previously, it was set only for some entries. This closes [#70819](https://github.com/ClickHouse/ClickHouse/issues/70819). [#70848](https://github.com/ClickHouse/ClickHouse/pull/70848) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add merge start and mutate start events into `system.part_log` which helps with merges analysis and visualization. [#70850](https://github.com/ClickHouse/ClickHouse/pull/70850) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Do not call the LIST object storage API when determining if a file or directory exists on the plain rewritable disk, as it can be cost-inefficient. [#70852](https://github.com/ClickHouse/ClickHouse/pull/70852) ([Julia Kartseva](https://github.com/jkartseva)). +* Add a profile event about the number of merged source parts. It allows the monitoring of the fanout of the merge tree in production. [#70908](https://github.com/ClickHouse/ClickHouse/pull/70908) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Reduce the number of object storage HEAD API requests in the plain_rewritable disk. [#70915](https://github.com/ClickHouse/ClickHouse/pull/70915) ([Julia Kartseva](https://github.com/jkartseva)). +* Background downloads to filesystem cache was enabled back. [#70929](https://github.com/ClickHouse/ClickHouse/pull/70929) ([Nikita Taranov](https://github.com/nickitat)). +* Add a new merge selector algorithm, named `Trivial`, for professional usage only. It is worse than the `Simple` merge selector. [#70969](https://github.com/ClickHouse/ClickHouse/pull/70969) ([Alexey Milovidov](https://github.com/alexey-milovidov)). + +#### Bug Fix (user-visible misbehavior in an official stable release) +* Fix toHour-like conversion functions' monotonicity when optional time zone argument is passed. [#60264](https://github.com/ClickHouse/ClickHouse/pull/60264) ([Amos Bird](https://github.com/amosbird)). +* Relax `supportsPrewhere` check for StorageMerge. This fixes [#61064](https://github.com/ClickHouse/ClickHouse/issues/61064). It was hardened unnecessarily in [#60082](https://github.com/ClickHouse/ClickHouse/issues/60082). [#61091](https://github.com/ClickHouse/ClickHouse/pull/61091) ([Amos Bird](https://github.com/amosbird)). +* Fix `use_concurrency_control` setting handling for proper `concurrent_threads_soft_limit_num` limit enforcing. This enables concurrency control by default because previously it was broken. [#61473](https://github.com/ClickHouse/ClickHouse/pull/61473) ([Sergei Trifonov](https://github.com/serxa)). +* Fix incorrect JOIN ON section optimization in case of `IS NULL` check under any other function (like `NOT`) that may lead to wrong results. Closes [#67915](https://github.com/ClickHouse/ClickHouse/issues/67915). [#68049](https://github.com/ClickHouse/ClickHouse/pull/68049) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Prevent `ALTER` queries that would make the `CREATE` query of tables invalid. [#68574](https://github.com/ClickHouse/ClickHouse/pull/68574) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)). +* Fix inconsistent AST formatting for `negate` (`-`) and `NOT` functions with tuples and arrays. [#68600](https://github.com/ClickHouse/ClickHouse/pull/68600) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix insertion of incomplete type into Dynamic during deserialization. It could lead to `Parameter out of bound` errors. [#69291](https://github.com/ClickHouse/ClickHouse/pull/69291) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix inf loop after `restore replica` in the replicated merge tree with zero copy. [#69293](https://github.com/ClickHouse/ClickHouse/pull/69293) ([MikhailBurdukov](https://github.com/MikhailBurdukov)). +* Return back default value of `processing_threads_num` as number of cpu cores in storage `S3Queue`. [#69384](https://github.com/ClickHouse/ClickHouse/pull/69384) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Bypass try/catch flow when de/serializing nested repeated protobuf to nested columns ( fixes [#41971](https://github.com/ClickHouse/ClickHouse/issues/41971) ). [#69556](https://github.com/ClickHouse/ClickHouse/pull/69556) ([Eliot Hautefeuille](https://github.com/hileef)). +* Fix vrash during insertion into FixedString column in PostgreSQL engine. [#69584](https://github.com/ClickHouse/ClickHouse/pull/69584) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix crash when executing `create view t as (with recursive 42 as ttt select ttt);`. [#69676](https://github.com/ClickHouse/ClickHouse/pull/69676) ([Han Fei](https://github.com/hanfei1991)). +* Added `strict_once` mode to aggregate function `windowFunnel` to avoid counting one event several times in case it matches multiple conditions, close [#21835](https://github.com/ClickHouse/ClickHouse/issues/21835). [#69738](https://github.com/ClickHouse/ClickHouse/pull/69738) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fixed `maxMapState` throwing 'Bad get' if value type is DateTime64. [#69787](https://github.com/ClickHouse/ClickHouse/pull/69787) ([Michael Kolupaev](https://github.com/al13n321)). +* Fix `getSubcolumn` with `LowCardinality` columns by overriding `useDefaultImplementationForLowCardinalityColumns` to return `true`. [#69831](https://github.com/ClickHouse/ClickHouse/pull/69831) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)). +* Fix permanent blocked distributed sends if DROP of distributed table fails. [#69843](https://github.com/ClickHouse/ClickHouse/pull/69843) ([Azat Khuzhin](https://github.com/azat)). +* Fix non-cancellable queries containing WITH FILL with NaN keys. This closes [#69261](https://github.com/ClickHouse/ClickHouse/issues/69261). [#69845](https://github.com/ClickHouse/ClickHouse/pull/69845) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix analyzer default with old compatibility value. [#69895](https://github.com/ClickHouse/ClickHouse/pull/69895) ([Raúl Marín](https://github.com/Algunenano)). +* Don't check dependencies during CREATE OR REPLACE VIEW during DROP of old table. Previously CREATE OR REPLACE query failed when there are dependent tables of the recreated view. [#69907](https://github.com/ClickHouse/ClickHouse/pull/69907) ([Pavel Kruglov](https://github.com/Avogar)). +* Implement missing decimal cases for `zeroField`. Fixes [#69730](https://github.com/ClickHouse/ClickHouse/issues/69730). [#69978](https://github.com/ClickHouse/ClickHouse/pull/69978) ([Arthur Passos](https://github.com/arthurpassos)). +* Now SQL security will work with parameterized views correctly. [#69984](https://github.com/ClickHouse/ClickHouse/pull/69984) ([pufit](https://github.com/pufit)). +* Closes [#69752](https://github.com/ClickHouse/ClickHouse/issues/69752). [#69985](https://github.com/ClickHouse/ClickHouse/pull/69985) ([pufit](https://github.com/pufit)). +* Fixed a bug when the timezone could change the result of the query with a `Date` or `Date32` arguments. [#70036](https://github.com/ClickHouse/ClickHouse/pull/70036) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* Fixes `Block structure mismatch` for queries with nested views and `WHERE` condition. Fixes [#66209](https://github.com/ClickHouse/ClickHouse/issues/66209). [#70054](https://github.com/ClickHouse/ClickHouse/pull/70054) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Avoid reusing columns among different named tuples when evaluating `tuple` functions. This fixes [#70022](https://github.com/ClickHouse/ClickHouse/issues/70022). [#70103](https://github.com/ClickHouse/ClickHouse/pull/70103) ([Amos Bird](https://github.com/amosbird)). +* Fix wrong LOGICAL_ERROR when replacing literals in ranges. [#70122](https://github.com/ClickHouse/ClickHouse/pull/70122) ([Pablo Marcos](https://github.com/pamarcos)). +* Check for Nullable(Nothing) type during ALTER TABLE MODIFY COLUMN/QUERY to prevent tables with such data type. [#70123](https://github.com/ClickHouse/ClickHouse/pull/70123) ([Pavel Kruglov](https://github.com/Avogar)). +* Proper error message for illegal query `JOIN ... ON *` , close [#68650](https://github.com/ClickHouse/ClickHouse/issues/68650). [#70124](https://github.com/ClickHouse/ClickHouse/pull/70124) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix wrong result with skipping index. [#70127](https://github.com/ClickHouse/ClickHouse/pull/70127) ([Raúl Marín](https://github.com/Algunenano)). +* Fix data race in ColumnObject/ColumnTuple decompress method that could lead to heap use after free. [#70137](https://github.com/ClickHouse/ClickHouse/pull/70137) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix possible hung in ALTER COLUMN with Dynamic type. [#70144](https://github.com/ClickHouse/ClickHouse/pull/70144) ([Pavel Kruglov](https://github.com/Avogar)). +* Now ClickHouse will consider more errors as retriable and will not mark data parts as broken in case of such errors. [#70145](https://github.com/ClickHouse/ClickHouse/pull/70145) ([alesapin](https://github.com/alesapin)). +* Use correct `max_types` parameter during Dynamic type creation for JSON subcolumn. [#70147](https://github.com/ClickHouse/ClickHouse/pull/70147) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix the password being displayed in `system.query_log` for users with bcrypt password authentication method. [#70148](https://github.com/ClickHouse/ClickHouse/pull/70148) ([Nikolay Degterinsky](https://github.com/evillique)). +* Fix event counter for native interface (InterfaceNativeSendBytes). [#70153](https://github.com/ClickHouse/ClickHouse/pull/70153) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)). +* Fix possible crash in JSON column. [#70172](https://github.com/ClickHouse/ClickHouse/pull/70172) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix multiple issues with arrayMin and arrayMax. [#70207](https://github.com/ClickHouse/ClickHouse/pull/70207) ([Raúl Marín](https://github.com/Algunenano)). +* Respect setting allow_simdjson in JSON type parser. [#70218](https://github.com/ClickHouse/ClickHouse/pull/70218) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix server segfault on creating a materialized view with two selects and an `INTERSECT`, e.g. `CREATE MATERIALIZED VIEW v0 AS (SELECT 1) INTERSECT (SELECT 1);`. [#70264](https://github.com/ClickHouse/ClickHouse/pull/70264) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Don't modify global settings with startup scripts. Previously, changing a setting in a startup script would change it globally. [#70310](https://github.com/ClickHouse/ClickHouse/pull/70310) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix ALTER of Dynamic type with reducing max_types parameter that could lead to server crash. [#70328](https://github.com/ClickHouse/ClickHouse/pull/70328) ([Pavel Kruglov](https://github.com/Avogar)). +* Fix crash when using WITH FILL incorrectly. [#70338](https://github.com/ClickHouse/ClickHouse/pull/70338) ([Raúl Marín](https://github.com/Algunenano)). +* Fix possible use-after-free in `SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf`. [#70358](https://github.com/ClickHouse/ClickHouse/pull/70358) ([Azat Khuzhin](https://github.com/azat)). +* Fix crash during GROUP BY JSON sub-object subcolumn. [#70374](https://github.com/ClickHouse/ClickHouse/pull/70374) ([Pavel Kruglov](https://github.com/Avogar)). +* Don't prefetch parts for vertical merges if part has no rows. [#70452](https://github.com/ClickHouse/ClickHouse/pull/70452) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix crash in WHERE with lambda functions. [#70464](https://github.com/ClickHouse/ClickHouse/pull/70464) ([Raúl Marín](https://github.com/Algunenano)). +* Fix table creation with `CREATE ... AS table_function()` with database `Replicated` and unavailable table function source on secondary replica. [#70511](https://github.com/ClickHouse/ClickHouse/pull/70511) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Ignore all output on async insert with `wait_for_async_insert=1`. Closes [#62644](https://github.com/ClickHouse/ClickHouse/issues/62644). [#70530](https://github.com/ClickHouse/ClickHouse/pull/70530) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Ignore frozen_metadata.txt while traversing shadow directory from system.remote_data_paths. [#70590](https://github.com/ClickHouse/ClickHouse/pull/70590) ([Aleksei Filatov](https://github.com/aalexfvk)). +* Fix creation of stateful window functions on misaligned memory. [#70631](https://github.com/ClickHouse/ClickHouse/pull/70631) ([Raúl Marín](https://github.com/Algunenano)). +* Fixed rare crashes in `SELECT`-s and merges after adding a column of `Array` type with non-empty default expression. [#70695](https://github.com/ClickHouse/ClickHouse/pull/70695) ([Anton Popov](https://github.com/CurtizJ)). +* Insert into table function s3 respect query settings. [#70696](https://github.com/ClickHouse/ClickHouse/pull/70696) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix infinite recursion when infering a proto schema with skip unsupported fields enabled. [#70697](https://github.com/ClickHouse/ClickHouse/pull/70697) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71122](https://github.com/ClickHouse/ClickHouse/issues/71122): `GroupArraySortedData` uses a PODArray with non-POD elements, manually calling constructors and destructors for the elements as needed. But it wasn't careful enough: in two places it forgot to call destructor, in one place it left elements uninitialized if an exception is thrown when deserializing previous elements. Then `GroupArraySortedData`'s destructor called destructors on uninitialized elements and crashed: ``` 2024.10.17 22:58:23.523790 [ 5233 ] {} BaseDaemon: ########## Short fault info ############ 2024.10.17 22:58:23.523834 [ 5233 ] {} BaseDaemon: (version 24.6.1.4609 (official build), build id: 5423339A6571004018D55BBE05D464AFA35E6718, git hash: fa6cdfda8a94890eb19bc7f22f8b0b56292f7a26) (from thread 682) Received signal 11 2024.10.17 22:58:23.523862 [ 5233 ] {} BaseDaemon: Signal description: Segmentation fault 2024.10.17 22:58:23.523883 [ 5233 ] {} BaseDaemon: Address: 0x8f. Access: . Address not mapped to object. 2024.10.17 22:58:23.523908 [ 5233 ] {} BaseDaemon: Stack trace: 0x0000aaaac4b78308 0x0000ffffb7701850 0x0000aaaac0104855 0x0000aaaac01048a0 0x0000aaaac501e84c 0x0000aaaac7c510d0 0x0000aaaac7c4ba20 0x0000aaaac968bbfc 0x0000aaaac968fab0 0x0000aaaac969bf50 0x0000aaaac9b7520c 0x0000aaaac9b74c74 0x0000aaaac9b8a150 0x0000aaaac9b809f0 0x0000aaaac9b80574 0x0000aaaac9b8e364 0x0000aaaac9b8e4fc 0x0000aaaac94f4328 0x0000aaaac94f428c 0x0000aaaac94f7df0 0x0000aaaac98b5a3c 0x0000aaaac950b234 0x0000aaaac49ae264 0x0000aaaac49b1dd0 0x0000aaaac49b0a80 0x0000ffffb755d5c8 0x0000ffffb75c5edc 2024.10.17 22:58:23.523936 [ 5233 ] {} BaseDaemon: ######################################## 2024.10.17 22:58:23.523959 [ 5233 ] {} BaseDaemon: (version 24.6.1.4609 (official build), build id: 5423339A6571004018D55BBE05D464AFA35E6718, git hash: fa6cdfda8a94890eb19bc7f22f8b0b56292f7a26) (from thread 682) (query_id: 6c8a33a2-f45a-4a3b-bd71-ded6a1c9ccd3::202410_534066_534078_2) (query: ) Received signal Segmentation fault (11) 2024.10.17 22:58:23.523977 [ 5233 ] {} BaseDaemon: Address: 0x8f. Access: . Address not mapped to object. 2024.10.17 22:58:23.523993 [ 5233 ] {} BaseDaemon: Stack trace: 0x0000aaaac4b78308 0x0000ffffb7701850 0x0000aaaac0104855 0x0000aaaac01048a0 0x0000aaaac501e84c 0x0000aaaac7c510d0 0x0000aaaac7c4ba20 0x0000aaaac968bbfc 0x0000aaaac968fab0 0x0000aaaac969bf50 0x0000aaaac9b7520c 0x0000aaaac9b74c74 0x0000aaaac9b8a150 0x0000aaaac9b809f0 0x0000aaaac9b80574 0x0000aaaac9b8e364 0x0000aaaac9b8e4fc 0x0000aaaac94f4328 0x0000aaaac94f428c 0x0000aaaac94f7df0 0x0000aaaac98b5a3c 0x0000aaaac950b234 0x0000aaaac49ae264 0x0000aaaac49b1dd0 0x0000aaaac49b0a80 0x0000ffffb755d5c8 0x0000ffffb75c5edc 2024.10.17 22:58:23.524817 [ 5233 ] {} BaseDaemon: 0. signalHandler(int, siginfo_t*, void*) @ 0x000000000c6f8308 2024.10.17 22:58:23.524917 [ 5233 ] {} BaseDaemon: 1. ? @ 0x0000ffffb7701850 2024.10.17 22:58:23.524962 [ 5233 ] {} BaseDaemon: 2. DB::Field::~Field() @ 0x0000000007c84855 2024.10.17 22:58:23.525012 [ 5233 ] {} BaseDaemon: 3. DB::Field::~Field() @ 0x0000000007c848a0 2024.10.17 22:58:23.526626 [ 5233 ] {} BaseDaemon: 4. DB::IAggregateFunctionDataHelper, DB::(anonymous namespace)::GroupArraySorted, DB::Field>>::destroy(char*) const (.5a6a451027f732f9fd91c13f4a13200c) @ 0x000000000cb9e84c 2024.10.17 22:58:23.527322 [ 5233 ] {} BaseDaemon: 5. DB::SerializationAggregateFunction::deserializeBinaryBulk(DB::IColumn&, DB::ReadBuffer&, unsigned long, double) const @ 0x000000000f7d10d0 2024.10.17 22:58:23.528470 [ 5233 ] {} BaseDaemon: 6. DB::ISerialization::deserializeBinaryBulkWithMultipleStreams(COW::immutable_ptr&, unsigned long, DB::ISerialization::DeserializeBinaryBulkSettings&, std::shared_ptr&, std::unordered_map::immutable_ptr, std::hash, std::equal_to, std::allocator::immutable_ptr>>>*) const @ 0x000000000f7cba20 2024.10.17 22:58:23.529213 [ 5233 ] {} BaseDaemon: 7. DB::MergeTreeReaderCompact::readData(DB::NameAndTypePair const&, COW::immutable_ptr&, unsigned long, std::function const&) @ 0x000000001120bbfc 2024.10.17 22:58:23.529277 [ 5233 ] {} BaseDaemon: 8. DB::MergeTreeReaderCompactSingleBuffer::readRows(unsigned long, unsigned long, bool, unsigned long, std::vector::immutable_ptr, std::allocator::immutable_ptr>>&) @ 0x000000001120fab0 2024.10.17 22:58:23.529319 [ 5233 ] {} BaseDaemon: 9. DB::MergeTreeSequentialSource::generate() @ 0x000000001121bf50 2024.10.17 22:58:23.529346 [ 5233 ] {} BaseDaemon: 10. DB::ISource::tryGenerate() @ 0x00000000116f520c 2024.10.17 22:58:23.529653 [ 5233 ] {} BaseDaemon: 11. DB::ISource::work() @ 0x00000000116f4c74 2024.10.17 22:58:23.529679 [ 5233 ] {} BaseDaemon: 12. DB::ExecutionThreadContext::executeTask() @ 0x000000001170a150 2024.10.17 22:58:23.529733 [ 5233 ] {} BaseDaemon: 13. DB::PipelineExecutor::executeStepImpl(unsigned long, std::atomic*) @ 0x00000000117009f0 2024.10.17 22:58:23.529763 [ 5233 ] {} BaseDaemon: 14. DB::PipelineExecutor::executeStep(std::atomic*) @ 0x0000000011700574 2024.10.17 22:58:23.530089 [ 5233 ] {} BaseDaemon: 15. DB::PullingPipelineExecutor::pull(DB::Chunk&) @ 0x000000001170e364 2024.10.17 22:58:23.530277 [ 5233 ] {} BaseDaemon: 16. DB::PullingPipelineExecutor::pull(DB::Block&) @ 0x000000001170e4fc 2024.10.17 22:58:23.530295 [ 5233 ] {} BaseDaemon: 17. DB::MergeTask::ExecuteAndFinalizeHorizontalPart::executeImpl() @ 0x0000000011074328 2024.10.17 22:58:23.530318 [ 5233 ] {} BaseDaemon: 18. DB::MergeTask::ExecuteAndFinalizeHorizontalPart::execute() @ 0x000000001107428c 2024.10.17 22:58:23.530339 [ 5233 ] {} BaseDaemon: 19. DB::MergeTask::execute() @ 0x0000000011077df0 2024.10.17 22:58:23.530362 [ 5233 ] {} BaseDaemon: 20. DB::SharedMergeMutateTaskBase::executeStep() @ 0x0000000011435a3c 2024.10.17 22:58:23.530384 [ 5233 ] {} BaseDaemon: 21. DB::MergeTreeBackgroundExecutor::threadFunction() @ 0x000000001108b234 2024.10.17 22:58:23.530410 [ 5233 ] {} BaseDaemon: 22. ThreadPoolImpl>::worker(std::__list_iterator, void*>) @ 0x000000000c52e264 2024.10.17 22:58:23.530448 [ 5233 ] {} BaseDaemon: 23. void std::__function::__policy_invoker::__call_impl::ThreadFromGlobalPoolImpl>::scheduleImpl(std::function, Priority, std::optional, bool)::'lambda0'()>(void&&)::'lambda'(), void ()>>(std::__function::__policy_storage const*) @ 0x000000000c531dd0 2024.10.17 22:58:23.530476 [ 5233 ] {} BaseDaemon: 24. void* std::__thread_proxy[abi:v15000]>, void ThreadPoolImpl::scheduleImpl(std::function, Priority, std::optional, bool)::'lambda0'()>>(void*) @ 0x000000000c530a80 2024.10.17 22:58:23.530514 [ 5233 ] {} BaseDaemon: 25. ? @ 0x000000000007d5c8 2024.10.17 22:58:23.530534 [ 5233 ] {} BaseDaemon: 26. ? @ 0x00000000000e5edc 2024.10.17 22:58:23.530551 [ 5233 ] {} BaseDaemon: Integrity check of the executable skipped because the reference checksum could not be read. 2024.10.17 22:58:23.531083 [ 5233 ] {} BaseDaemon: Report this error to https://github.com/ClickHouse/ClickHouse/issues 2024.10.17 22:58:23.531294 [ 5233 ] {} BaseDaemon: Changed settings: max_insert_threads = 4, max_threads = 42, use_hedged_requests = false, distributed_foreground_insert = true, alter_sync = 0, enable_memory_bound_merging_of_aggregation_results = true, cluster_for_parallel_replicas = 'default', do_not_merge_across_partitions_select_final = false, log_queries = true, log_queries_probability = 1., max_http_get_redirects = 10, enable_deflate_qpl_codec = false, enable_zstd_qat_codec = false, query_profiler_real_time_period_ns = 0, query_profiler_cpu_time_period_ns = 0, max_bytes_before_external_group_by = 90194313216, max_bytes_before_external_sort = 90194313216, max_memory_usage = 180388626432, backup_restore_keeper_retry_max_backoff_ms = 60000, cancel_http_readonly_queries_on_client_close = true, max_table_size_to_drop = 1000000000000, max_partition_size_to_drop = 1000000000000, default_table_engine = 'ReplicatedMergeTree', mutations_sync = 0, optimize_trivial_insert_select = false, database_replicated_allow_only_replicated_engine = true, cloud_mode = true, cloud_mode_engine = 2, distributed_ddl_output_mode = 'none_only_active', distributed_ddl_entry_format_version = 6, async_insert_max_data_size = 10485760, async_insert_busy_timeout_max_ms = 1000, enable_filesystem_cache_on_write_operations = true, load_marks_asynchronously = true, allow_prefetched_read_pool_for_remote_filesystem = true, filesystem_prefetch_max_memory_usage = 18038862643, filesystem_prefetches_limit = 200, compatibility = '24.6', insert_keeper_max_retries = 20, allow_experimental_materialized_postgresql_table = false, date_time_input_format = 'best_effort' ```. [#70820](https://github.com/ClickHouse/ClickHouse/pull/70820) ([Michael Kolupaev](https://github.com/al13n321)). +* Disable enable_named_columns_in_function_tuple by default. [#70833](https://github.com/ClickHouse/ClickHouse/pull/70833) ([Raúl Marín](https://github.com/Algunenano)). +* Fix S3Queue table engine setting processing_threads_num not being effective in case it was deduced from the number of cpu cores on the server. [#70837](https://github.com/ClickHouse/ClickHouse/pull/70837) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Normalize named tuple arguments in aggregation states. This fixes [#69732](https://github.com/ClickHouse/ClickHouse/issues/69732) . [#70853](https://github.com/ClickHouse/ClickHouse/pull/70853) ([Amos Bird](https://github.com/amosbird)). +* Fix a logical error due to negative zeros in the two-level hash table. This closes [#70973](https://github.com/ClickHouse/ClickHouse/issues/70973). [#70979](https://github.com/ClickHouse/ClickHouse/pull/70979) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Backported in [#71214](https://github.com/ClickHouse/ClickHouse/issues/71214): Fix logical error in `StorageS3Queue` "Cannot create a persistent node in /processed since it already exists". [#70984](https://github.com/ClickHouse/ClickHouse/pull/70984) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Backported in [#71243](https://github.com/ClickHouse/ClickHouse/issues/71243): Fixed named sessions not being closed and hanging on forever under certain circumstances. [#70998](https://github.com/ClickHouse/ClickHouse/pull/70998) ([Márcio Martins](https://github.com/marcio-absmartly)). +* Backported in [#71157](https://github.com/ClickHouse/ClickHouse/issues/71157): Fix the bug that didn't consider _row_exists column in rebuild option of projection lightweight delete. [#71089](https://github.com/ClickHouse/ClickHouse/pull/71089) ([Shichao Jin](https://github.com/jsc0218)). +* Backported in [#71265](https://github.com/ClickHouse/ClickHouse/issues/71265): Fix wrong value in system.query_metric_log due to unexpected race condition. [#71124](https://github.com/ClickHouse/ClickHouse/pull/71124) ([Pablo Marcos](https://github.com/pamarcos)). +* Backported in [#71331](https://github.com/ClickHouse/ClickHouse/issues/71331): Fix async inserts with empty blocks via native protocol. [#71312](https://github.com/ClickHouse/ClickHouse/pull/71312) ([Anton Popov](https://github.com/CurtizJ)). + +#### Build/Testing/Packaging Improvement +* Docker in integration tests runner is updated to latest version. It was previously pinned u until patch release 24.0.3 was out. https://github.com/moby/moby/issues/45770#issuecomment-1618255130. - HDFS image was deprecated and not running with current docker version. Switched to newer version of a derivative image based on ubuntu. - HDFS tests were hardened to allow them to run with python-repeat. [#66867](https://github.com/ClickHouse/ClickHouse/pull/66867) ([Ilya Yatsishin](https://github.com/qoega)). +* Alpine docker images now use ubuntu 22.04 as glibc donor, results in upgrade of glibc version delivered with alpine images from 2.31 to 2.35. [#69033](https://github.com/ClickHouse/ClickHouse/pull/69033) ([filimonov](https://github.com/filimonov)). +* Makes dbms independent from clickhouse_functions. [#69914](https://github.com/ClickHouse/ClickHouse/pull/69914) ([Raúl Marín](https://github.com/Algunenano)). +* Fix FreeBSD compilation of the MariaDB connector. [#70007](https://github.com/ClickHouse/ClickHouse/pull/70007) ([Raúl Marín](https://github.com/Algunenano)). +* Building on Apple Mac OS X Darwin does not produce strange warnings anymore. [#70411](https://github.com/ClickHouse/ClickHouse/pull/70411) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix building with ARCH_NATIVE CMake flag. [#70585](https://github.com/ClickHouse/ClickHouse/pull/70585) ([Daniil Gentili](https://github.com/danog)). +* The universal installer will download Musl build on Alpine Linux. Some Docker containers are using Alpine Linux, but it was not possible to install ClickHouse there with `curl https://clickhouse.com/ | sh`. [#70767](https://github.com/ClickHouse/ClickHouse/pull/70767) ([Alexey Milovidov](https://github.com/alexey-milovidov)). + +#### NO CL CATEGORY + +* Backported in [#71259](https://github.com/ClickHouse/ClickHouse/issues/71259):. [#71220](https://github.com/ClickHouse/ClickHouse/pull/71220) ([Raúl Marín](https://github.com/Algunenano)). + +#### NO CL ENTRY + +* NO CL ENTRY: 'Revert "JSONCompactWithProgress query output format"'. [#69989](https://github.com/ClickHouse/ClickHouse/pull/69989) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* NO CL ENTRY: 'Revert "Support CREATE OR REPLACE VIEW atomically"'. [#70535](https://github.com/ClickHouse/ClickHouse/pull/70535) ([Raúl Marín](https://github.com/Algunenano)). +* NO CL ENTRY: 'Revert "Revert "Support CREATE OR REPLACE VIEW atomically""'. [#70536](https://github.com/ClickHouse/ClickHouse/pull/70536) ([Raúl Marín](https://github.com/Algunenano)). +* NO CL ENTRY: 'Revert "Add projections size to system.projections"'. [#70858](https://github.com/ClickHouse/ClickHouse/pull/70858) ([Alexey Milovidov](https://github.com/alexey-milovidov)). + +#### NOT FOR CHANGELOG / INSIGNIFICANT + +* Allow writing argument of `has` or `hasAny` or `hasAll` as string values if array element type is `Enum`. [#56555](https://github.com/ClickHouse/ClickHouse/pull/56555) ([Duc Canh Le](https://github.com/canhld94)). +* Rename FileSegmentKind::Ephemeral and other changes. [#66600](https://github.com/ClickHouse/ClickHouse/pull/66600) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Closes [#67345](https://github.com/ClickHouse/ClickHouse/issues/67345). [#67346](https://github.com/ClickHouse/ClickHouse/pull/67346) ([KrJin](https://github.com/jincong8973)). +* Because it is too complicated to support. [#68410](https://github.com/ClickHouse/ClickHouse/pull/68410) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix 01600_parts_states_metrics_long flakiness. [#68521](https://github.com/ClickHouse/ClickHouse/pull/68521) ([Azat Khuzhin](https://github.com/azat)). +* Reduce client start time in debug/sanitizer mode. [#68980](https://github.com/ClickHouse/ClickHouse/pull/68980) ([Raúl Marín](https://github.com/Algunenano)). +* Closes [#69038](https://github.com/ClickHouse/ClickHouse/issues/69038). [#69040](https://github.com/ClickHouse/ClickHouse/pull/69040) ([Nikolay Degterinsky](https://github.com/evillique)). +* Better exception for unsupported full_text index with non-full parts. [#69067](https://github.com/ClickHouse/ClickHouse/pull/69067) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Catch additional zk connection erros while creating table and make sure to cleanup dirs if necessary for retries. [#69093](https://github.com/ClickHouse/ClickHouse/pull/69093) ([Sumit](https://github.com/sum12)). +* Update version_date.tsv and changelog after v24.7.5.37-stable. [#69185](https://github.com/ClickHouse/ClickHouse/pull/69185) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* DOCS: Replace live view with refreshable since the former is deprecated. [#69392](https://github.com/ClickHouse/ClickHouse/pull/69392) ([Damian Kula](https://github.com/heavelock)). +* Update ORC to the current HEAD. [#69473](https://github.com/ClickHouse/ClickHouse/pull/69473) ([Nikita Taranov](https://github.com/nickitat)). +* Make a test ready for flaky check. [#69586](https://github.com/ClickHouse/ClickHouse/pull/69586) ([Alexander Tokmakov](https://github.com/tavplubix)). +* Support antlr parser to parse sql with some keywords as alias, make the behaviour same as the clickhouse-server - remove redundant `for` in the `keyword` field. [#69614](https://github.com/ClickHouse/ClickHouse/pull/69614) ([Z.H.](https://github.com/onlyacat)). +* Allow default implementations for null in function mapFromArrays for spark compatiability in apache gluten. Current change doesn't have any side effects on clickhouse in theory. [#69715](https://github.com/ClickHouse/ClickHouse/pull/69715) ([李扬](https://github.com/taiyang-li)). +* Fix exception message in AzureBlobStorage. [#69728](https://github.com/ClickHouse/ClickHouse/pull/69728) ([Pavel Kruglov](https://github.com/Avogar)). +* Add test parsing s3 URL with a bucket name including a dot. [#69743](https://github.com/ClickHouse/ClickHouse/pull/69743) ([Kaushik Iska](https://github.com/iskakaushik)). +* Make `clang-tidy` happy. [#69765](https://github.com/ClickHouse/ClickHouse/pull/69765) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Prepare to enable `clang-tidy` `readability-else-after-return`. [#69768](https://github.com/ClickHouse/ClickHouse/pull/69768) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* S3Queue: support having deprecated settings to not fail server startup. [#69769](https://github.com/ClickHouse/ClickHouse/pull/69769) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Use only adaptive heuristic to choose task sizes for remote reading. [#69778](https://github.com/ClickHouse/ClickHouse/pull/69778) ([Nikita Taranov](https://github.com/nickitat)). +* Remove unused buggy code. [#69780](https://github.com/ClickHouse/ClickHouse/pull/69780) ([Raúl Marín](https://github.com/Algunenano)). +* Fix bugfix check. [#69789](https://github.com/ClickHouse/ClickHouse/pull/69789) ([Antonio Andelic](https://github.com/antonio2368)). +* Followup for [#63279](https://github.com/ClickHouse/ClickHouse/issues/63279). [#69790](https://github.com/ClickHouse/ClickHouse/pull/69790) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Update version after release. [#69816](https://github.com/ClickHouse/ClickHouse/pull/69816) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* Update ext-dict-functions.md. [#69819](https://github.com/ClickHouse/ClickHouse/pull/69819) ([kurikuQwQ](https://github.com/kurikuQwQ)). +* Allow cyrillic characters in generated contributor names. [#69820](https://github.com/ClickHouse/ClickHouse/pull/69820) ([Raúl Marín](https://github.com/Algunenano)). +* CI: praktika integration 1. [#69822](https://github.com/ClickHouse/ClickHouse/pull/69822) ([Max Kainov](https://github.com/maxknv)). +* Fix `test_delayed_replica_failover`. [#69826](https://github.com/ClickHouse/ClickHouse/pull/69826) ([Antonio Andelic](https://github.com/antonio2368)). +* minor change, less conflicts. [#69830](https://github.com/ClickHouse/ClickHouse/pull/69830) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Improve error message DDLWorker.cpp. [#69835](https://github.com/ClickHouse/ClickHouse/pull/69835) ([Denny Crane](https://github.com/den-crane)). +* Fix typo in description: mutation_sync -> mutations_sync. [#69838](https://github.com/ClickHouse/ClickHouse/pull/69838) ([Alexander Gololobov](https://github.com/davenger)). +* Fix changelog. [#69841](https://github.com/ClickHouse/ClickHouse/pull/69841) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* This closes [#49940](https://github.com/ClickHouse/ClickHouse/issues/49940). [#69842](https://github.com/ClickHouse/ClickHouse/pull/69842) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* This closes [#51036](https://github.com/ClickHouse/ClickHouse/issues/51036). [#69844](https://github.com/ClickHouse/ClickHouse/pull/69844) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update README.md - Update meetups. [#69849](https://github.com/ClickHouse/ClickHouse/pull/69849) ([Tanya Bragin](https://github.com/tbragin)). +* Revert [#69790](https://github.com/ClickHouse/ClickHouse/issues/69790) and [#63279](https://github.com/ClickHouse/ClickHouse/issues/63279). [#69850](https://github.com/ClickHouse/ClickHouse/pull/69850) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* See [#63279](https://github.com/ClickHouse/ClickHouse/issues/63279). [#69851](https://github.com/ClickHouse/ClickHouse/pull/69851) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add a test for [#50928](https://github.com/ClickHouse/ClickHouse/issues/50928). [#69852](https://github.com/ClickHouse/ClickHouse/pull/69852) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add a test for [#55981](https://github.com/ClickHouse/ClickHouse/issues/55981). [#69853](https://github.com/ClickHouse/ClickHouse/pull/69853) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add a test for [#56823](https://github.com/ClickHouse/ClickHouse/issues/56823). [#69854](https://github.com/ClickHouse/ClickHouse/pull/69854) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* This closes [#62350](https://github.com/ClickHouse/ClickHouse/issues/62350). [#69855](https://github.com/ClickHouse/ClickHouse/pull/69855) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Refactor functions and variables in statistics code. [#69860](https://github.com/ClickHouse/ClickHouse/pull/69860) ([Robert Schulze](https://github.com/rschu1ze)). +* Resubmit [#63279](https://github.com/ClickHouse/ClickHouse/issues/63279). [#69861](https://github.com/ClickHouse/ClickHouse/pull/69861) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Improve stateless test runner. [#69864](https://github.com/ClickHouse/ClickHouse/pull/69864) ([Alexey Katsman](https://github.com/alexkats)). +* Adjust fast test time limit a bit. [#69874](https://github.com/ClickHouse/ClickHouse/pull/69874) ([Raúl Marín](https://github.com/Algunenano)). +* Add initial 24.9 CHANGELOG. [#69876](https://github.com/ClickHouse/ClickHouse/pull/69876) ([Raúl Marín](https://github.com/Algunenano)). +* Fix test `01278_random_string_utf8`. [#69878](https://github.com/ClickHouse/ClickHouse/pull/69878) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Fix minor fuzzer issue with experimental statistics. [#69881](https://github.com/ClickHouse/ClickHouse/pull/69881) ([Robert Schulze](https://github.com/rschu1ze)). +* Fix linking after settings refactoring. [#69882](https://github.com/ClickHouse/ClickHouse/pull/69882) ([Robert Schulze](https://github.com/rschu1ze)). +* Add Proj Obsolete Setting. [#69883](https://github.com/ClickHouse/ClickHouse/pull/69883) ([Shichao Jin](https://github.com/jsc0218)). +* Improve remote queries startup time. [#69884](https://github.com/ClickHouse/ClickHouse/pull/69884) ([Igor Nikonov](https://github.com/devcrafter)). +* Revert "Merge pull request [#69032](https://github.com/ClickHouse/ClickHouse/issues/69032) from alexon1234/include_real_time_execution_in_http_header". [#69885](https://github.com/ClickHouse/ClickHouse/pull/69885) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* A dedicated commits from https://github.com/ClickHouse/ClickHouse/pull/61473. [#69896](https://github.com/ClickHouse/ClickHouse/pull/69896) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Added aliases `time_bucket`(from TimescaleDB) and `date_bin`(from PostgreSQL) for `toStartOfInterval`. [#69900](https://github.com/ClickHouse/ClickHouse/pull/69900) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* RIPE is an acronym and thus should be capital. RIPE stands for **R**ACE **I**ntegrity **P**rimitives **E**valuation and RACE stands for **R**esearch and Development in **A**dvanced **C**ommunications **T**echnologies in **E**urope. [#69901](https://github.com/ClickHouse/ClickHouse/pull/69901) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Replace error codes with error names in stateless tests. [#69906](https://github.com/ClickHouse/ClickHouse/pull/69906) ([Dmitry Novik](https://github.com/novikd)). +* Move setting to 24.10. [#69913](https://github.com/ClickHouse/ClickHouse/pull/69913) ([Raúl Marín](https://github.com/Algunenano)). +* Minor: Reduce diff between public and private repo. [#69928](https://github.com/ClickHouse/ClickHouse/pull/69928) ([Robert Schulze](https://github.com/rschu1ze)). +* Followup for [#69861](https://github.com/ClickHouse/ClickHouse/issues/69861). [#69930](https://github.com/ClickHouse/ClickHouse/pull/69930) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix test_dictionaries_all_layouts_separate_sources. [#69962](https://github.com/ClickHouse/ClickHouse/pull/69962) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Fix test_keeper_mntr_data_size. [#69965](https://github.com/ClickHouse/ClickHouse/pull/69965) ([Antonio Andelic](https://github.com/antonio2368)). +* This closes [#49823](https://github.com/ClickHouse/ClickHouse/issues/49823). [#69981](https://github.com/ClickHouse/ClickHouse/pull/69981) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add changelog for 24.9. [#69982](https://github.com/ClickHouse/ClickHouse/pull/69982) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add a test for [#45303](https://github.com/ClickHouse/ClickHouse/issues/45303). [#69987](https://github.com/ClickHouse/ClickHouse/pull/69987) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update CHANGELOG.md. [#69988](https://github.com/ClickHouse/ClickHouse/pull/69988) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update README.md. [#69991](https://github.com/ClickHouse/ClickHouse/pull/69991) ([Tyler Hannan](https://github.com/tylerhannan)). +* Disable `03215_parallel_replicas_crash_after_refactoring.sql` for Azure. [#69992](https://github.com/ClickHouse/ClickHouse/pull/69992) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Update CHANGELOG.md. [#69993](https://github.com/ClickHouse/ClickHouse/pull/69993) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update CHANGELOG.md. [#70004](https://github.com/ClickHouse/ClickHouse/pull/70004) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Revert "Add RIPEMD160 function". [#70005](https://github.com/ClickHouse/ClickHouse/pull/70005) ([Robert Schulze](https://github.com/rschu1ze)). +* Update CHANGELOG.md. [#70009](https://github.com/ClickHouse/ClickHouse/pull/70009) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update CHANGELOG.md. [#70010](https://github.com/ClickHouse/ClickHouse/pull/70010) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Make the pylint stricter. [#70013](https://github.com/ClickHouse/ClickHouse/pull/70013) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Added a setting `restore_replace_external_dictionary_source_to_null` which enables replacing dictionary source with Null on restore for external dictionaries (useful for testing). [#70032](https://github.com/ClickHouse/ClickHouse/pull/70032) ([Alexander Tokmakov](https://github.com/tavplubix)). +* `isort` is a simple import sorter for the python to comply [pep-8](https://peps.python.org/pep-0008/#imports) requirements. It will allow to decrease conflicts during sync and beautify the code. The import block is divided into three sub-blocks: `standard library` -> `third-party libraries` -> `local imports` -> `.local imports`. Each sub-block is ordered alphabetically with sub-sub-blocks `import X` -> `from X import Y`. [#70038](https://github.com/ClickHouse/ClickHouse/pull/70038) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Update version_date.tsv and changelog after v24.9.1.3278-stable. [#70049](https://github.com/ClickHouse/ClickHouse/pull/70049) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* Despite the fact that we set the org-level workflow parameter `PYTHONUNBUFFERED`, it's not inherited in workflows. [#70050](https://github.com/ClickHouse/ClickHouse/pull/70050) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Fix ubsan issue in function sqid. [#70061](https://github.com/ClickHouse/ClickHouse/pull/70061) ([Robert Schulze](https://github.com/rschu1ze)). +* Delete a setting change. [#70071](https://github.com/ClickHouse/ClickHouse/pull/70071) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fix `test_distributed_ddl`. [#70075](https://github.com/ClickHouse/ClickHouse/pull/70075) ([Alexander Tokmakov](https://github.com/tavplubix)). +* Remove unused placeholder from exception message string. [#70086](https://github.com/ClickHouse/ClickHouse/pull/70086) ([Alsu Giliazova](https://github.com/alsugiliazova)). +* Better exception message when some of the permission is missing. [#70088](https://github.com/ClickHouse/ClickHouse/pull/70088) ([pufit](https://github.com/pufit)). +* Make vector similarity indexes work with adaptive granularity. [#70101](https://github.com/ClickHouse/ClickHouse/pull/70101) ([Robert Schulze](https://github.com/rschu1ze)). +* Add missing columns `total_rows`, `data_compressed_bytes`, and `data_uncompressed_bytes` to `system.projections`. Part of https://github.com/ClickHouse/ClickHouse/pull/68901. [#70106](https://github.com/ClickHouse/ClickHouse/pull/70106) ([Jordi Villar](https://github.com/jrdi)). +* Make `00938_fix_rwlock_segfault_long` non flaky. [#70109](https://github.com/ClickHouse/ClickHouse/pull/70109) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Remove TODO. [#70110](https://github.com/ClickHouse/ClickHouse/pull/70110) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Change the default threshold to enable hyper threading. [#70111](https://github.com/ClickHouse/ClickHouse/pull/70111) ([Jiebin Sun](https://github.com/jiebinn)). +* Fixed [#69092](https://github.com/ClickHouse/ClickHouse/issues/69092): if `materialized_postgresql_tables_list=table1(id, code),table(id,name)` (`table1` has name that is a substring for `table`) `getTableAllowedColumns` method returns `[id, code]` for `table` before this fix. [#70114](https://github.com/ClickHouse/ClickHouse/pull/70114) ([Kruglov Kirill](https://github.com/1on)). +* Reduce log level. [#70117](https://github.com/ClickHouse/ClickHouse/pull/70117) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Rename `getNumberOfPhysicalCPUCores` and fix its decription. [#70130](https://github.com/ClickHouse/ClickHouse/pull/70130) ([Nikita Taranov](https://github.com/nickitat)). +* Adding 24.10. [#70132](https://github.com/ClickHouse/ClickHouse/pull/70132) ([Tyler Hannan](https://github.com/tylerhannan)). +* (Re?)-enable libcxx asserts for debug builds. [#70134](https://github.com/ClickHouse/ClickHouse/pull/70134) ([Robert Schulze](https://github.com/rschu1ze)). +* Refactor reading from object storage. [#70141](https://github.com/ClickHouse/ClickHouse/pull/70141) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Silence UBSAN for integer overflows in some datetime functions. [#70142](https://github.com/ClickHouse/ClickHouse/pull/70142) ([Michael Kolupaev](https://github.com/al13n321)). +* Improve pipdeptree generator for docker images. - Update requirements.txt for the integration tests runner container - Remove some small dependencies, improve `helpers/retry_decorator.py` - Upgrade docker-compose from EOL version 1 to version 2. [#70146](https://github.com/ClickHouse/ClickHouse/pull/70146) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Fix 'QueryPlan was not initialized' in 'loop' with empty MergeTree. [#70149](https://github.com/ClickHouse/ClickHouse/pull/70149) ([Michael Kolupaev](https://github.com/al13n321)). +* Remove QueryPlan DataStream. [#70158](https://github.com/ClickHouse/ClickHouse/pull/70158) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Update test_storage_s3_queue/test.py. [#70159](https://github.com/ClickHouse/ClickHouse/pull/70159) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Small docs fix. [#70160](https://github.com/ClickHouse/ClickHouse/pull/70160) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* Test: PR local plan, non-constant in source stream. [#70173](https://github.com/ClickHouse/ClickHouse/pull/70173) ([Igor Nikonov](https://github.com/devcrafter)). +* Fix performance checks. [#70175](https://github.com/ClickHouse/ClickHouse/pull/70175) ([Antonio Andelic](https://github.com/antonio2368)). +* Simplify test 03246_range_literal_replacement_works. [#70176](https://github.com/ClickHouse/ClickHouse/pull/70176) ([Pablo Marcos](https://github.com/pamarcos)). +* Update 01079_parallel_alter_add_drop_column_zookeeper.sh. [#70196](https://github.com/ClickHouse/ClickHouse/pull/70196) ([Alexander Tokmakov](https://github.com/tavplubix)). +* Require bugfix job for a set of labels. [#70197](https://github.com/ClickHouse/ClickHouse/pull/70197) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* CI: Praktika integration, fast test. [#70239](https://github.com/ClickHouse/ClickHouse/pull/70239) ([Max Kainov](https://github.com/maxknv)). +* Avoid `Cannot schedule a task` error when loading parts. [#70257](https://github.com/ClickHouse/ClickHouse/pull/70257) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Bump usearch to v2.15.2 and SimSIMD to v5.0.0. [#70270](https://github.com/ClickHouse/ClickHouse/pull/70270) ([Robert Schulze](https://github.com/rschu1ze)). +* Instead of balancing tests by `crc32(file_name)` we'll use `add tests to a group with a minimal number of tests`. [#70272](https://github.com/ClickHouse/ClickHouse/pull/70272) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Closes [#70263](https://github.com/ClickHouse/ClickHouse/issues/70263). [#70273](https://github.com/ClickHouse/ClickHouse/pull/70273) ([flynn](https://github.com/ucasfl)). +* Hide MergeTreeSettings implementation. [#70285](https://github.com/ClickHouse/ClickHouse/pull/70285) ([Raúl Marín](https://github.com/Algunenano)). +* CI: Remove await feature from release branches. [#70294](https://github.com/ClickHouse/ClickHouse/pull/70294) ([Max Kainov](https://github.com/maxknv)). +* Fix `test_keeper_four_word_command`. [#70298](https://github.com/ClickHouse/ClickHouse/pull/70298) ([Antonio Andelic](https://github.com/antonio2368)). +* Update version_date.tsv and changelog after v24.9.2.42-stable. [#70301](https://github.com/ClickHouse/ClickHouse/pull/70301) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* Synchronize settings with private. [#70320](https://github.com/ClickHouse/ClickHouse/pull/70320) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Add Ignore Option In DeduplicateMergeProjectionMode. [#70327](https://github.com/ClickHouse/ClickHouse/pull/70327) ([Shichao Jin](https://github.com/jsc0218)). +* CI: Enable Integration Tests for backport PRs. [#70329](https://github.com/ClickHouse/ClickHouse/pull/70329) ([Max Kainov](https://github.com/maxknv)). +* There is [a failed CI job](https://s3.amazonaws.com/clickhouse-test-reports/69778/2d81c38874958bd9d54a25524173bdb1ddf2b75c/stateless_tests__release_.html) which is triggered by [03237_create_or_replace_view_atomically_with_atomic_engine](https://github.com/ClickHouse/ClickHouse/blob/master/tests/queries/0_stateless/03237_create_or_replace_view_atomically_with_atomic_engine.sh). [#70330](https://github.com/ClickHouse/ClickHouse/pull/70330) ([tuanpach](https://github.com/tuanpach)). +* Fix flaky test `03237_insert_sparse_columns_mem`. [#70333](https://github.com/ClickHouse/ClickHouse/pull/70333) ([Anton Popov](https://github.com/CurtizJ)). +* Rename enable_secure_identifiers -> enforce_strict_identifier_format. [#70335](https://github.com/ClickHouse/ClickHouse/pull/70335) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Attempt to fix flaky RabbitMQ tests. Maybe closes [#45160](https://github.com/ClickHouse/ClickHouse/issues/45160). [#70336](https://github.com/ClickHouse/ClickHouse/pull/70336) ([filimonov](https://github.com/filimonov)). +* Don't fail the stateless check script if we can't collect minio logs. [#70350](https://github.com/ClickHouse/ClickHouse/pull/70350) ([Raúl Marín](https://github.com/Algunenano)). +* Fix tiny mistake, responsible for some of kafka test flaps. Example [report](https://s3.amazonaws.com/clickhouse-test-reports/0/3198aafac59c368993e7b5f49d95674cc1b1be18/integration_tests__release__[2_4].html). [#70352](https://github.com/ClickHouse/ClickHouse/pull/70352) ([filimonov](https://github.com/filimonov)). +* Closes [#69634](https://github.com/ClickHouse/ClickHouse/issues/69634). [#70354](https://github.com/ClickHouse/ClickHouse/pull/70354) ([pufit](https://github.com/pufit)). +* Fix 02346_fulltext_index_bug52019. [#70357](https://github.com/ClickHouse/ClickHouse/pull/70357) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Use new JSON for collecting minio logs. [#70359](https://github.com/ClickHouse/ClickHouse/pull/70359) ([Antonio Andelic](https://github.com/antonio2368)). +* Update comments in VectorSimilarityCondition (WHERE is not supported). [#70360](https://github.com/ClickHouse/ClickHouse/pull/70360) ([Azat Khuzhin](https://github.com/azat)). +* Remove 02492_clickhouse_local_context_uaf test. [#70363](https://github.com/ClickHouse/ClickHouse/pull/70363) ([Azat Khuzhin](https://github.com/azat)). +* Fix `clang-19` build issues. [#70412](https://github.com/ClickHouse/ClickHouse/pull/70412) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Ignore "Invalid multibyte data detected" error during completion. [#70422](https://github.com/ClickHouse/ClickHouse/pull/70422) ([Azat Khuzhin](https://github.com/azat)). +* Make QueryPlan explain methods const. [#70444](https://github.com/ClickHouse/ClickHouse/pull/70444) ([Alexander Gololobov](https://github.com/davenger)). +* Fix 0.1 second delay for interactive queries (due to keystroke interceptor). [#70445](https://github.com/ClickHouse/ClickHouse/pull/70445) ([Azat Khuzhin](https://github.com/azat)). +* Increase lock timeout in attempt to fix 02125_many_mutations. [#70448](https://github.com/ClickHouse/ClickHouse/pull/70448) ([Azat Khuzhin](https://github.com/azat)). +* Fix order in 03249_dynamic_alter_consistency. [#70453](https://github.com/ClickHouse/ClickHouse/pull/70453) ([Alexander Gololobov](https://github.com/davenger)). +* Fix refreshable MV in system database breaking server startup. [#70460](https://github.com/ClickHouse/ClickHouse/pull/70460) ([Michael Kolupaev](https://github.com/al13n321)). +* Fix flaky test_refreshable_mv_in_replicated_db. [#70462](https://github.com/ClickHouse/ClickHouse/pull/70462) ([Michael Kolupaev](https://github.com/al13n321)). +* Update version_date.tsv and changelog after v24.8.5.115-lts. [#70463](https://github.com/ClickHouse/ClickHouse/pull/70463) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* Decrease probability of "Server died" due to 00913_many_threads. [#70473](https://github.com/ClickHouse/ClickHouse/pull/70473) ([Azat Khuzhin](https://github.com/azat)). +* Fixes for killing leftovers in clikhouse-test. [#70474](https://github.com/ClickHouse/ClickHouse/pull/70474) ([Azat Khuzhin](https://github.com/azat)). +* Update version_date.tsv and changelog after v24.3.12.75-lts. [#70485](https://github.com/ClickHouse/ClickHouse/pull/70485) ([robot-clickhouse](https://github.com/robot-clickhouse)). +* Use logging instead of print. [#70505](https://github.com/ClickHouse/ClickHouse/pull/70505) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)). +* Remove slow poll() logs in keeper. [#70508](https://github.com/ClickHouse/ClickHouse/pull/70508) ([Raúl Marín](https://github.com/Algunenano)). +* Add timeouts for retry loops in test_storage_rabbitmq. It should prevent cascading failures of the whole test suite caused by deadloop in one of the test scenarios. Also added small sleeps in a 'tight' loops to make retries bit less agressive. [#70510](https://github.com/ClickHouse/ClickHouse/pull/70510) ([filimonov](https://github.com/filimonov)). +* CI: Fix for canceled Sync workflow. [#70521](https://github.com/ClickHouse/ClickHouse/pull/70521) ([Max Kainov](https://github.com/maxknv)). +* Debug build faild with clang-18 after https://github.com/ClickHouse/ClickHouse/pull/70412, don't know why it's ok in release build, simply changing `_` to `_1` is ok for both release and debug build. [#70532](https://github.com/ClickHouse/ClickHouse/pull/70532) ([Chang chen](https://github.com/baibaichen)). +* Refreshable materialized views are not experimental anymore. [#70550](https://github.com/ClickHouse/ClickHouse/pull/70550) ([Michael Kolupaev](https://github.com/al13n321)). +* Fix 24.9 setting compatibility `database_replicated_allow_explicit_uuid`. [#70565](https://github.com/ClickHouse/ClickHouse/pull/70565) ([Nikita Fomichev](https://github.com/fm4v)). +* Fix typos. [#70588](https://github.com/ClickHouse/ClickHouse/pull/70588) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Vector search: allow to specify HNSW parameter `ef_search` at query time. [#70616](https://github.com/ClickHouse/ClickHouse/pull/70616) ([Robert Schulze](https://github.com/rschu1ze)). +* Increase max_rows_to_read limit in some tests. [#70617](https://github.com/ClickHouse/ClickHouse/pull/70617) ([Raúl Marín](https://github.com/Algunenano)). +* Reduce sync efforts with private. [#70634](https://github.com/ClickHouse/ClickHouse/pull/70634) ([Raúl Marín](https://github.com/Algunenano)). +* Fix parsing of some formats into sparse columns. [#70635](https://github.com/ClickHouse/ClickHouse/pull/70635) ([Anton Popov](https://github.com/CurtizJ)). +* Fix typos. [#70637](https://github.com/ClickHouse/ClickHouse/pull/70637) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Try fix 00180_no_seek_avoiding_when_reading_from_cache. [#70640](https://github.com/ClickHouse/ClickHouse/pull/70640) ([Kseniia Sumarokova](https://github.com/kssenii)). +* When the `PR Check` status is set, it's a valid RunConfig job failure. [#70643](https://github.com/ClickHouse/ClickHouse/pull/70643) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Fix timeout in materialized pg tests. [#70646](https://github.com/ClickHouse/ClickHouse/pull/70646) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Introduced MergeTree setting which allow to change merge selecting algorithm. However we still have only one algorithm and it's mostly for future experiments. [#70647](https://github.com/ClickHouse/ClickHouse/pull/70647) ([alesapin](https://github.com/alesapin)). +* Docs: Follow-up for [#70585](https://github.com/ClickHouse/ClickHouse/issues/70585). [#70654](https://github.com/ClickHouse/ClickHouse/pull/70654) ([Robert Schulze](https://github.com/rschu1ze)). +* Remove strange file. [#70662](https://github.com/ClickHouse/ClickHouse/pull/70662) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Locally I had lots of errors like `'AllocList' does not refer to a value` around places which used `offsetof`. Changing it to `__builtin_offsetof ` helped and I didn't debug any further. [#70671](https://github.com/ClickHouse/ClickHouse/pull/70671) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Adding the report link to a test result and files' list. [#70677](https://github.com/ClickHouse/ClickHouse/pull/70677) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* materialized postgres: minor fixes. [#70710](https://github.com/ClickHouse/ClickHouse/pull/70710) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Probably fix flaky test_refreshable_mv_in_replicated_db. [#70714](https://github.com/ClickHouse/ClickHouse/pull/70714) ([Michael Kolupaev](https://github.com/al13n321)). +* Move more setting structs to pImpl. [#70739](https://github.com/ClickHouse/ClickHouse/pull/70739) ([Raúl Marín](https://github.com/Algunenano)). +* Reduce sync effort. [#70747](https://github.com/ClickHouse/ClickHouse/pull/70747) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71198](https://github.com/ClickHouse/ClickHouse/issues/71198): Check number of arguments for function with Dynamic argument. [#70749](https://github.com/ClickHouse/ClickHouse/pull/70749) ([Nikita Taranov](https://github.com/nickitat)). +* Add s3queue settings check for cloud. [#70750](https://github.com/ClickHouse/ClickHouse/pull/70750) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Fix readiness/health check for OpenLDAP container. [#70755](https://github.com/ClickHouse/ClickHouse/pull/70755) ([Julian Maicher](https://github.com/jmaicher)). +* Allow update plan headers for all the steps. [#70761](https://github.com/ClickHouse/ClickHouse/pull/70761) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Autogenerate documentation for settings. [#70768](https://github.com/ClickHouse/ClickHouse/pull/70768) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Not a logical error. [#70770](https://github.com/ClickHouse/ClickHouse/pull/70770) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* CI: Aarch64 build with Asan. [#70778](https://github.com/ClickHouse/ClickHouse/pull/70778) ([Max Kainov](https://github.com/maxknv)). +* Minor fix. [#70783](https://github.com/ClickHouse/ClickHouse/pull/70783) ([Anton Popov](https://github.com/CurtizJ)). +* The docs for settings should be located in the source code. Now, the CI supports that. [#70784](https://github.com/ClickHouse/ClickHouse/pull/70784) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Update style-test image. [#70785](https://github.com/ClickHouse/ClickHouse/pull/70785) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Avoid double finalization of `WriteBuffer` in library bridge. [#70799](https://github.com/ClickHouse/ClickHouse/pull/70799) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Make Array Field serialization consistent. [#70803](https://github.com/ClickHouse/ClickHouse/pull/70803) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* A follow-up for [#70785](https://github.com/ClickHouse/ClickHouse/issues/70785), [jwt](https://pypi.org/project/jwt/#history) looks very outdated, and we have issue with conflicting paths. [#70815](https://github.com/ClickHouse/ClickHouse/pull/70815) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Remove inneficient code. [#70816](https://github.com/ClickHouse/ClickHouse/pull/70816) ([Raúl Marín](https://github.com/Algunenano)). +* Allow large object files if OMIT_HEAVY_DEBUG_SYMBOLS = 0. [#70818](https://github.com/ClickHouse/ClickHouse/pull/70818) ([Michael Kolupaev](https://github.com/al13n321)). +* Add test with distributed queries for 15768. [#70834](https://github.com/ClickHouse/ClickHouse/pull/70834) ([Nikita Taranov](https://github.com/nickitat)). +* More setting structs to pImpl and reuse code. [#70840](https://github.com/ClickHouse/ClickHouse/pull/70840) ([Raúl Marín](https://github.com/Algunenano)). +* Update default HNSW parameter settings. [#70873](https://github.com/ClickHouse/ClickHouse/pull/70873) ([Robert Schulze](https://github.com/rschu1ze)). +* Limiting logging some lines about configs. [#70879](https://github.com/ClickHouse/ClickHouse/pull/70879) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* Fix `limit by`, `limit with ties` for distributed and parallel replicas. [#70880](https://github.com/ClickHouse/ClickHouse/pull/70880) ([Nikita Taranov](https://github.com/nickitat)). +* Fix darwin build. [#70894](https://github.com/ClickHouse/ClickHouse/pull/70894) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Add dots for consistency. [#70909](https://github.com/ClickHouse/ClickHouse/pull/70909) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Logical error fix for substrings, found by fuzzer. [#70914](https://github.com/ClickHouse/ClickHouse/pull/70914) ([Yarik Briukhovetskyi](https://github.com/yariks5s)). +* More setting structs to pImpl. [#70942](https://github.com/ClickHouse/ClickHouse/pull/70942) ([Raúl Marín](https://github.com/Algunenano)). +* Add logging for mock HTTP servers used in minio integration tests. [#70943](https://github.com/ClickHouse/ClickHouse/pull/70943) ([Vitaly Baranov](https://github.com/vitlibar)). +* Minor fixups of [#70011](https://github.com/ClickHouse/ClickHouse/issues/70011) and [#69918](https://github.com/ClickHouse/ClickHouse/issues/69918). [#70959](https://github.com/ClickHouse/ClickHouse/pull/70959) ([Robert Schulze](https://github.com/rschu1ze)). +* CI: Do not skip Build report and status fix. [#70965](https://github.com/ClickHouse/ClickHouse/pull/70965) ([Max Kainov](https://github.com/maxknv)). +* Fix Keeper entry serialization compatibility. [#70972](https://github.com/ClickHouse/ClickHouse/pull/70972) ([Antonio Andelic](https://github.com/antonio2368)). +* Update exception message. [#70975](https://github.com/ClickHouse/ClickHouse/pull/70975) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Fix `utils/c++expr` option `-b`. [#70978](https://github.com/ClickHouse/ClickHouse/pull/70978) ([Sergei Trifonov](https://github.com/serxa)). +* Fix `test_keeper_broken_logs`. [#70982](https://github.com/ClickHouse/ClickHouse/pull/70982) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix `01039_test_setting_parse`. [#70986](https://github.com/ClickHouse/ClickHouse/pull/70986) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Tests for languages support for Embedded Dictionaries. [#71004](https://github.com/ClickHouse/ClickHouse/pull/71004) ([Max Vostrikov](https://github.com/max-vostrikov)). +* Required for internal test runs with the same image build in public CI. [#71008](https://github.com/ClickHouse/ClickHouse/pull/71008) ([Ilya Yatsishin](https://github.com/qoega)). +* Move remaining settings objects to pImpl and start simplification. [#71019](https://github.com/ClickHouse/ClickHouse/pull/71019) ([Raúl Marín](https://github.com/Algunenano)). +* CI: Rearrange directories for praktika ci. [#71029](https://github.com/ClickHouse/ClickHouse/pull/71029) ([Max Kainov](https://github.com/maxknv)). +* Fix assert in RemoteSource::onAsyncJobReady(). [#71034](https://github.com/ClickHouse/ClickHouse/pull/71034) ([Igor Nikonov](https://github.com/devcrafter)). +* Fix showing error message in ReadBufferFromS3 when retrying. Without this PR information about a retryable failure in `ReadBufferFromS3` could look like this:. [#71038](https://github.com/ClickHouse/ClickHouse/pull/71038) ([Vitaly Baranov](https://github.com/vitlibar)). +* Fix `test_truncate_database`. [#71057](https://github.com/ClickHouse/ClickHouse/pull/71057) ([Antonio Andelic](https://github.com/antonio2368)). +* Fix clickhouse-test useless 5 second delay in case of multiple threads are used. [#71069](https://github.com/ClickHouse/ClickHouse/pull/71069) ([Azat Khuzhin](https://github.com/azat)). +* Backported in [#71142](https://github.com/ClickHouse/ClickHouse/issues/71142): Followup [#70520](https://github.com/ClickHouse/ClickHouse/issues/70520). [#71129](https://github.com/ClickHouse/ClickHouse/pull/71129) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Backported in [#71189](https://github.com/ClickHouse/ClickHouse/issues/71189): Update compatibility setting for `hnsw_candidate_list_size_for_search`. [#71133](https://github.com/ClickHouse/ClickHouse/pull/71133) ([Robert Schulze](https://github.com/rschu1ze)). +* Backported in [#71222](https://github.com/ClickHouse/ClickHouse/issues/71222): Fixes for interactive metrics. [#71173](https://github.com/ClickHouse/ClickHouse/pull/71173) ([Julia Kartseva](https://github.com/jkartseva)). +* Backported in [#71205](https://github.com/ClickHouse/ClickHouse/issues/71205): Maybe not GWPAsan by default. [#71174](https://github.com/ClickHouse/ClickHouse/pull/71174) ([Antonio Andelic](https://github.com/antonio2368)). +* Backported in [#71277](https://github.com/ClickHouse/ClickHouse/issues/71277): Fix LOGICAL_ERROR on wrong scalar subquery argument to table functions. [#71216](https://github.com/ClickHouse/ClickHouse/pull/71216) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71253](https://github.com/ClickHouse/ClickHouse/issues/71253): Disable enable_named_columns_in_function_tuple for 24.10. [#71219](https://github.com/ClickHouse/ClickHouse/pull/71219) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71303](https://github.com/ClickHouse/ClickHouse/issues/71303): Improve system.query_metric_log to remove flakiness. [#71295](https://github.com/ClickHouse/ClickHouse/pull/71295) ([Pablo Marcos](https://github.com/pamarcos)). +* Backported in [#71317](https://github.com/ClickHouse/ClickHouse/issues/71317): Fix debug log timestamp. [#71311](https://github.com/ClickHouse/ClickHouse/pull/71311) ([Pablo Marcos](https://github.com/pamarcos)). + +#### Not for changeling + +* Reverted. [#69812](https://github.com/ClickHouse/ClickHouse/pull/69812) ([tuanpach](https://github.com/tuanpach)). + diff --git a/docs/changelogs/v24.8.6.70-lts.md b/docs/changelogs/v24.8.6.70-lts.md new file mode 100644 index 00000000000..81fa4db1458 --- /dev/null +++ b/docs/changelogs/v24.8.6.70-lts.md @@ -0,0 +1,50 @@ +--- +sidebar_position: 1 +sidebar_label: 2024 +--- + +# 2024 Changelog + +### ClickHouse release v24.8.6.70-lts (ddb8c219771) FIXME as compared to v24.8.5.115-lts (8c4cb00a384) + +#### Backward Incompatible Change +* Backported in [#71359](https://github.com/ClickHouse/ClickHouse/issues/71359): Fix possible error `No such file or directory` due to unescaped special symbols in files for JSON subcolumns. [#71182](https://github.com/ClickHouse/ClickHouse/pull/71182) ([Pavel Kruglov](https://github.com/Avogar)). + +#### Improvement +* Backported in [#70680](https://github.com/ClickHouse/ClickHouse/issues/70680): Don't do validation when synchronizing user_directories from keeper. [#70644](https://github.com/ClickHouse/ClickHouse/pull/70644) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71395](https://github.com/ClickHouse/ClickHouse/issues/71395): Do not call the object storage API when listing directories, as this may be cost-inefficient. Instead, store the list of filenames in the memory. The trade-offs are increased initial load time and memory required to store filenames. [#70823](https://github.com/ClickHouse/ClickHouse/pull/70823) ([Julia Kartseva](https://github.com/jkartseva)). +* Backported in [#71287](https://github.com/ClickHouse/ClickHouse/issues/71287): Reduce the number of object storage HEAD API requests in the plain_rewritable disk. [#70915](https://github.com/ClickHouse/ClickHouse/pull/70915) ([Julia Kartseva](https://github.com/jkartseva)). + +#### Bug Fix (user-visible misbehavior in an official stable release) +* Backported in [#70934](https://github.com/ClickHouse/ClickHouse/issues/70934): Fix incorrect JOIN ON section optimization in case of `IS NULL` check under any other function (like `NOT`) that may lead to wrong results. Closes [#67915](https://github.com/ClickHouse/ClickHouse/issues/67915). [#68049](https://github.com/ClickHouse/ClickHouse/pull/68049) ([Vladimir Cherkasov](https://github.com/vdimir)). +* Backported in [#70735](https://github.com/ClickHouse/ClickHouse/issues/70735): Fix unexpected exception when passing empty tuple in array. This fixes [#68618](https://github.com/ClickHouse/ClickHouse/issues/68618). [#68848](https://github.com/ClickHouse/ClickHouse/pull/68848) ([Amos Bird](https://github.com/amosbird)). +* Backported in [#71138](https://github.com/ClickHouse/ClickHouse/issues/71138): Fix propogating structure argument in s3Cluster. Previously the `DEFAULT` expression of the column could be lost when sending the query to the replicas in s3Cluster. [#69147](https://github.com/ClickHouse/ClickHouse/pull/69147) ([Pavel Kruglov](https://github.com/Avogar)). +* Backported in [#70561](https://github.com/ClickHouse/ClickHouse/issues/70561): Fix `getSubcolumn` with `LowCardinality` columns by overriding `useDefaultImplementationForLowCardinalityColumns` to return `true`. [#69831](https://github.com/ClickHouse/ClickHouse/pull/69831) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)). +* Backported in [#70903](https://github.com/ClickHouse/ClickHouse/issues/70903): Avoid reusing columns among different named tuples when evaluating `tuple` functions. This fixes [#70022](https://github.com/ClickHouse/ClickHouse/issues/70022). [#70103](https://github.com/ClickHouse/ClickHouse/pull/70103) ([Amos Bird](https://github.com/amosbird)). +* Backported in [#70623](https://github.com/ClickHouse/ClickHouse/issues/70623): Fix server segfault on creating a materialized view with two selects and an `INTERSECT`, e.g. `CREATE MATERIALIZED VIEW v0 AS (SELECT 1) INTERSECT (SELECT 1);`. [#70264](https://github.com/ClickHouse/ClickHouse/pull/70264) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Backported in [#70688](https://github.com/ClickHouse/ClickHouse/issues/70688): Fix possible use-after-free in `SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf`. [#70358](https://github.com/ClickHouse/ClickHouse/pull/70358) ([Azat Khuzhin](https://github.com/azat)). +* Backported in [#70494](https://github.com/ClickHouse/ClickHouse/issues/70494): Fix crash during GROUP BY JSON sub-object subcolumn. [#70374](https://github.com/ClickHouse/ClickHouse/pull/70374) ([Pavel Kruglov](https://github.com/Avogar)). +* Backported in [#70482](https://github.com/ClickHouse/ClickHouse/issues/70482): Don't prefetch parts for vertical merges if part has no rows. [#70452](https://github.com/ClickHouse/ClickHouse/pull/70452) ([Antonio Andelic](https://github.com/antonio2368)). +* Backported in [#70556](https://github.com/ClickHouse/ClickHouse/issues/70556): Fix crash in WHERE with lambda functions. [#70464](https://github.com/ClickHouse/ClickHouse/pull/70464) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#70878](https://github.com/ClickHouse/ClickHouse/issues/70878): Fix table creation with `CREATE ... AS table_function()` with database `Replicated` and unavailable table function source on secondary replica. [#70511](https://github.com/ClickHouse/ClickHouse/pull/70511) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Backported in [#70575](https://github.com/ClickHouse/ClickHouse/issues/70575): Ignore all output on async insert with `wait_for_async_insert=1`. Closes [#62644](https://github.com/ClickHouse/ClickHouse/issues/62644). [#70530](https://github.com/ClickHouse/ClickHouse/pull/70530) ([Konstantin Bogdanov](https://github.com/thevar1able)). +* Backported in [#71052](https://github.com/ClickHouse/ClickHouse/issues/71052): Ignore frozen_metadata.txt while traversing shadow directory from system.remote_data_paths. [#70590](https://github.com/ClickHouse/ClickHouse/pull/70590) ([Aleksei Filatov](https://github.com/aalexfvk)). +* Backported in [#70651](https://github.com/ClickHouse/ClickHouse/issues/70651): Fix creation of stateful window functions on misaligned memory. [#70631](https://github.com/ClickHouse/ClickHouse/pull/70631) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#70757](https://github.com/ClickHouse/ClickHouse/issues/70757): Fixed rare crashes in `SELECT`-s and merges after adding a column of `Array` type with non-empty default expression. [#70695](https://github.com/ClickHouse/ClickHouse/pull/70695) ([Anton Popov](https://github.com/CurtizJ)). +* Backported in [#70763](https://github.com/ClickHouse/ClickHouse/issues/70763): Fix infinite recursion when infering a proto schema with skip unsupported fields enabled. [#70697](https://github.com/ClickHouse/ClickHouse/pull/70697) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#71118](https://github.com/ClickHouse/ClickHouse/issues/71118): `GroupArraySortedData` uses a PODArray with non-POD elements, manually calling constructors and destructors for the elements as needed. But it wasn't careful enough: in two places it forgot to call destructor, in one place it left elements uninitialized if an exception is thrown when deserializing previous elements. Then `GroupArraySortedData`'s destructor called destructors on uninitialized elements and crashed: ``` 2024.10.17 22:58:23.523790 [ 5233 ] {} BaseDaemon: ########## Short fault info ############ 2024.10.17 22:58:23.523834 [ 5233 ] {} BaseDaemon: (version 24.6.1.4609 (official build), build id: 5423339A6571004018D55BBE05D464AFA35E6718, git hash: fa6cdfda8a94890eb19bc7f22f8b0b56292f7a26) (from thread 682) Received signal 11 2024.10.17 22:58:23.523862 [ 5233 ] {} BaseDaemon: Signal description: Segmentation fault 2024.10.17 22:58:23.523883 [ 5233 ] {} BaseDaemon: Address: 0x8f. Access: . Address not mapped to object. 2024.10.17 22:58:23.523908 [ 5233 ] {} BaseDaemon: Stack trace: 0x0000aaaac4b78308 0x0000ffffb7701850 0x0000aaaac0104855 0x0000aaaac01048a0 0x0000aaaac501e84c 0x0000aaaac7c510d0 0x0000aaaac7c4ba20 0x0000aaaac968bbfc 0x0000aaaac968fab0 0x0000aaaac969bf50 0x0000aaaac9b7520c 0x0000aaaac9b74c74 0x0000aaaac9b8a150 0x0000aaaac9b809f0 0x0000aaaac9b80574 0x0000aaaac9b8e364 0x0000aaaac9b8e4fc 0x0000aaaac94f4328 0x0000aaaac94f428c 0x0000aaaac94f7df0 0x0000aaaac98b5a3c 0x0000aaaac950b234 0x0000aaaac49ae264 0x0000aaaac49b1dd0 0x0000aaaac49b0a80 0x0000ffffb755d5c8 0x0000ffffb75c5edc 2024.10.17 22:58:23.523936 [ 5233 ] {} BaseDaemon: ######################################## 2024.10.17 22:58:23.523959 [ 5233 ] {} BaseDaemon: (version 24.6.1.4609 (official build), build id: 5423339A6571004018D55BBE05D464AFA35E6718, git hash: fa6cdfda8a94890eb19bc7f22f8b0b56292f7a26) (from thread 682) (query_id: 6c8a33a2-f45a-4a3b-bd71-ded6a1c9ccd3::202410_534066_534078_2) (query: ) Received signal Segmentation fault (11) 2024.10.17 22:58:23.523977 [ 5233 ] {} BaseDaemon: Address: 0x8f. Access: . Address not mapped to object. 2024.10.17 22:58:23.523993 [ 5233 ] {} BaseDaemon: Stack trace: 0x0000aaaac4b78308 0x0000ffffb7701850 0x0000aaaac0104855 0x0000aaaac01048a0 0x0000aaaac501e84c 0x0000aaaac7c510d0 0x0000aaaac7c4ba20 0x0000aaaac968bbfc 0x0000aaaac968fab0 0x0000aaaac969bf50 0x0000aaaac9b7520c 0x0000aaaac9b74c74 0x0000aaaac9b8a150 0x0000aaaac9b809f0 0x0000aaaac9b80574 0x0000aaaac9b8e364 0x0000aaaac9b8e4fc 0x0000aaaac94f4328 0x0000aaaac94f428c 0x0000aaaac94f7df0 0x0000aaaac98b5a3c 0x0000aaaac950b234 0x0000aaaac49ae264 0x0000aaaac49b1dd0 0x0000aaaac49b0a80 0x0000ffffb755d5c8 0x0000ffffb75c5edc 2024.10.17 22:58:23.524817 [ 5233 ] {} BaseDaemon: 0. signalHandler(int, siginfo_t*, void*) @ 0x000000000c6f8308 2024.10.17 22:58:23.524917 [ 5233 ] {} BaseDaemon: 1. ? @ 0x0000ffffb7701850 2024.10.17 22:58:23.524962 [ 5233 ] {} BaseDaemon: 2. DB::Field::~Field() @ 0x0000000007c84855 2024.10.17 22:58:23.525012 [ 5233 ] {} BaseDaemon: 3. DB::Field::~Field() @ 0x0000000007c848a0 2024.10.17 22:58:23.526626 [ 5233 ] {} BaseDaemon: 4. DB::IAggregateFunctionDataHelper, DB::(anonymous namespace)::GroupArraySorted, DB::Field>>::destroy(char*) const (.5a6a451027f732f9fd91c13f4a13200c) @ 0x000000000cb9e84c 2024.10.17 22:58:23.527322 [ 5233 ] {} BaseDaemon: 5. DB::SerializationAggregateFunction::deserializeBinaryBulk(DB::IColumn&, DB::ReadBuffer&, unsigned long, double) const @ 0x000000000f7d10d0 2024.10.17 22:58:23.528470 [ 5233 ] {} BaseDaemon: 6. DB::ISerialization::deserializeBinaryBulkWithMultipleStreams(COW::immutable_ptr&, unsigned long, DB::ISerialization::DeserializeBinaryBulkSettings&, std::shared_ptr&, std::unordered_map::immutable_ptr, std::hash, std::equal_to, std::allocator::immutable_ptr>>>*) const @ 0x000000000f7cba20 2024.10.17 22:58:23.529213 [ 5233 ] {} BaseDaemon: 7. DB::MergeTreeReaderCompact::readData(DB::NameAndTypePair const&, COW::immutable_ptr&, unsigned long, std::function const&) @ 0x000000001120bbfc 2024.10.17 22:58:23.529277 [ 5233 ] {} BaseDaemon: 8. DB::MergeTreeReaderCompactSingleBuffer::readRows(unsigned long, unsigned long, bool, unsigned long, std::vector::immutable_ptr, std::allocator::immutable_ptr>>&) @ 0x000000001120fab0 2024.10.17 22:58:23.529319 [ 5233 ] {} BaseDaemon: 9. DB::MergeTreeSequentialSource::generate() @ 0x000000001121bf50 2024.10.17 22:58:23.529346 [ 5233 ] {} BaseDaemon: 10. DB::ISource::tryGenerate() @ 0x00000000116f520c 2024.10.17 22:58:23.529653 [ 5233 ] {} BaseDaemon: 11. DB::ISource::work() @ 0x00000000116f4c74 2024.10.17 22:58:23.529679 [ 5233 ] {} BaseDaemon: 12. DB::ExecutionThreadContext::executeTask() @ 0x000000001170a150 2024.10.17 22:58:23.529733 [ 5233 ] {} BaseDaemon: 13. DB::PipelineExecutor::executeStepImpl(unsigned long, std::atomic*) @ 0x00000000117009f0 2024.10.17 22:58:23.529763 [ 5233 ] {} BaseDaemon: 14. DB::PipelineExecutor::executeStep(std::atomic*) @ 0x0000000011700574 2024.10.17 22:58:23.530089 [ 5233 ] {} BaseDaemon: 15. DB::PullingPipelineExecutor::pull(DB::Chunk&) @ 0x000000001170e364 2024.10.17 22:58:23.530277 [ 5233 ] {} BaseDaemon: 16. DB::PullingPipelineExecutor::pull(DB::Block&) @ 0x000000001170e4fc 2024.10.17 22:58:23.530295 [ 5233 ] {} BaseDaemon: 17. DB::MergeTask::ExecuteAndFinalizeHorizontalPart::executeImpl() @ 0x0000000011074328 2024.10.17 22:58:23.530318 [ 5233 ] {} BaseDaemon: 18. DB::MergeTask::ExecuteAndFinalizeHorizontalPart::execute() @ 0x000000001107428c 2024.10.17 22:58:23.530339 [ 5233 ] {} BaseDaemon: 19. DB::MergeTask::execute() @ 0x0000000011077df0 2024.10.17 22:58:23.530362 [ 5233 ] {} BaseDaemon: 20. DB::SharedMergeMutateTaskBase::executeStep() @ 0x0000000011435a3c 2024.10.17 22:58:23.530384 [ 5233 ] {} BaseDaemon: 21. DB::MergeTreeBackgroundExecutor::threadFunction() @ 0x000000001108b234 2024.10.17 22:58:23.530410 [ 5233 ] {} BaseDaemon: 22. ThreadPoolImpl>::worker(std::__list_iterator, void*>) @ 0x000000000c52e264 2024.10.17 22:58:23.530448 [ 5233 ] {} BaseDaemon: 23. void std::__function::__policy_invoker::__call_impl::ThreadFromGlobalPoolImpl>::scheduleImpl(std::function, Priority, std::optional, bool)::'lambda0'()>(void&&)::'lambda'(), void ()>>(std::__function::__policy_storage const*) @ 0x000000000c531dd0 2024.10.17 22:58:23.530476 [ 5233 ] {} BaseDaemon: 24. void* std::__thread_proxy[abi:v15000]>, void ThreadPoolImpl::scheduleImpl(std::function, Priority, std::optional, bool)::'lambda0'()>>(void*) @ 0x000000000c530a80 2024.10.17 22:58:23.530514 [ 5233 ] {} BaseDaemon: 25. ? @ 0x000000000007d5c8 2024.10.17 22:58:23.530534 [ 5233 ] {} BaseDaemon: 26. ? @ 0x00000000000e5edc 2024.10.17 22:58:23.530551 [ 5233 ] {} BaseDaemon: Integrity check of the executable skipped because the reference checksum could not be read. 2024.10.17 22:58:23.531083 [ 5233 ] {} BaseDaemon: Report this error to https://github.com/ClickHouse/ClickHouse/issues 2024.10.17 22:58:23.531294 [ 5233 ] {} BaseDaemon: Changed settings: max_insert_threads = 4, max_threads = 42, use_hedged_requests = false, distributed_foreground_insert = true, alter_sync = 0, enable_memory_bound_merging_of_aggregation_results = true, cluster_for_parallel_replicas = 'default', do_not_merge_across_partitions_select_final = false, log_queries = true, log_queries_probability = 1., max_http_get_redirects = 10, enable_deflate_qpl_codec = false, enable_zstd_qat_codec = false, query_profiler_real_time_period_ns = 0, query_profiler_cpu_time_period_ns = 0, max_bytes_before_external_group_by = 90194313216, max_bytes_before_external_sort = 90194313216, max_memory_usage = 180388626432, backup_restore_keeper_retry_max_backoff_ms = 60000, cancel_http_readonly_queries_on_client_close = true, max_table_size_to_drop = 1000000000000, max_partition_size_to_drop = 1000000000000, default_table_engine = 'ReplicatedMergeTree', mutations_sync = 0, optimize_trivial_insert_select = false, database_replicated_allow_only_replicated_engine = true, cloud_mode = true, cloud_mode_engine = 2, distributed_ddl_output_mode = 'none_only_active', distributed_ddl_entry_format_version = 6, async_insert_max_data_size = 10485760, async_insert_busy_timeout_max_ms = 1000, enable_filesystem_cache_on_write_operations = true, load_marks_asynchronously = true, allow_prefetched_read_pool_for_remote_filesystem = true, filesystem_prefetch_max_memory_usage = 18038862643, filesystem_prefetches_limit = 200, compatibility = '24.6', insert_keeper_max_retries = 20, allow_experimental_materialized_postgresql_table = false, date_time_input_format = 'best_effort' ```. [#70820](https://github.com/ClickHouse/ClickHouse/pull/70820) ([Michael Kolupaev](https://github.com/al13n321)). +* Backported in [#70896](https://github.com/ClickHouse/ClickHouse/issues/70896): Disable enable_named_columns_in_function_tuple by default. [#70833](https://github.com/ClickHouse/ClickHouse/pull/70833) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#70994](https://github.com/ClickHouse/ClickHouse/issues/70994): Fix a logical error due to negative zeros in the two-level hash table. This closes [#70973](https://github.com/ClickHouse/ClickHouse/issues/70973). [#70979](https://github.com/ClickHouse/ClickHouse/pull/70979) ([Alexey Milovidov](https://github.com/alexey-milovidov)). +* Backported in [#71210](https://github.com/ClickHouse/ClickHouse/issues/71210): Fix logical error in `StorageS3Queue` "Cannot create a persistent node in /processed since it already exists". [#70984](https://github.com/ClickHouse/ClickHouse/pull/70984) ([Kseniia Sumarokova](https://github.com/kssenii)). +* Backported in [#71248](https://github.com/ClickHouse/ClickHouse/issues/71248): Fixed named sessions not being closed and hanging on forever under certain circumstances. [#70998](https://github.com/ClickHouse/ClickHouse/pull/70998) ([Márcio Martins](https://github.com/marcio-absmartly)). +* Backported in [#71375](https://github.com/ClickHouse/ClickHouse/issues/71375): Add try/catch to data parts destructors to avoid terminate. [#71364](https://github.com/ClickHouse/ClickHouse/pull/71364) ([alesapin](https://github.com/alesapin)). + +#### NOT FOR CHANGELOG / INSIGNIFICANT + +* Backported in [#71026](https://github.com/ClickHouse/ClickHouse/issues/71026): Fix dropping of file cache in CHECK query in case of enabled transactions. [#69256](https://github.com/ClickHouse/ClickHouse/pull/69256) ([Anton Popov](https://github.com/CurtizJ)). +* Backported in [#70388](https://github.com/ClickHouse/ClickHouse/issues/70388): CI: Enable Integration Tests for backport PRs. [#70329](https://github.com/ClickHouse/ClickHouse/pull/70329) ([Max Kainov](https://github.com/maxknv)). +* Backported in [#70701](https://github.com/ClickHouse/ClickHouse/issues/70701): Fix order in 03249_dynamic_alter_consistency. [#70453](https://github.com/ClickHouse/ClickHouse/pull/70453) ([Alexander Gololobov](https://github.com/davenger)). +* Backported in [#70542](https://github.com/ClickHouse/ClickHouse/issues/70542): Remove slow poll() logs in keeper. [#70508](https://github.com/ClickHouse/ClickHouse/pull/70508) ([Raúl Marín](https://github.com/Algunenano)). +* Backported in [#70804](https://github.com/ClickHouse/ClickHouse/issues/70804): When the `PR Check` status is set, it's a valid RunConfig job failure. [#70643](https://github.com/ClickHouse/ClickHouse/pull/70643) ([Mikhail f. Shiryaev](https://github.com/Felixoid)). +* Backported in [#71229](https://github.com/ClickHouse/ClickHouse/issues/71229): Maybe not GWPAsan by default. [#71174](https://github.com/ClickHouse/ClickHouse/pull/71174) ([Antonio Andelic](https://github.com/antonio2368)). + diff --git a/docs/en/engines/table-engines/integrations/embedded-rocksdb.md b/docs/en/engines/table-engines/integrations/embedded-rocksdb.md index 1958250ed73..41c4e8fc4a9 100644 --- a/docs/en/engines/table-engines/integrations/embedded-rocksdb.md +++ b/docs/en/engines/table-engines/integrations/embedded-rocksdb.md @@ -4,9 +4,13 @@ sidebar_position: 50 sidebar_label: EmbeddedRocksDB --- +import CloudNotSupportedBadge from '@theme/badges/CloudNotSupportedBadge'; + # EmbeddedRocksDB Engine -This engine allows integrating ClickHouse with [rocksdb](http://rocksdb.org/). + + +This engine allows integrating ClickHouse with [RocksDB](http://rocksdb.org/). ## Creating a Table {#creating-a-table} diff --git a/docs/en/engines/table-engines/integrations/s3.md b/docs/en/engines/table-engines/integrations/s3.md index fb759b948a5..fd27d4b6ed9 100644 --- a/docs/en/engines/table-engines/integrations/s3.md +++ b/docs/en/engines/table-engines/integrations/s3.md @@ -290,6 +290,7 @@ The following settings can be specified in configuration file for given endpoint - `expiration_window_seconds` — Grace period for checking if expiration-based credentials have expired. Optional, default value is `120`. - `no_sign_request` - Ignore all the credentials so requests are not signed. Useful for accessing public buckets. - `header` — Adds specified HTTP header to a request to given endpoint. Optional, can be specified multiple times. +- `access_header` - Adds specified HTTP header to a request to given endpoint, in cases where there are no other credentials from another source. - `server_side_encryption_customer_key_base64` — If specified, required headers for accessing S3 objects with SSE-C encryption will be set. Optional. - `server_side_encryption_kms_key_id` - If specified, required headers for accessing S3 objects with [SSE-KMS encryption](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingKMSEncryption.html) will be set. If an empty string is specified, the AWS managed S3 key will be used. Optional. - `server_side_encryption_kms_encryption_context` - If specified alongside `server_side_encryption_kms_key_id`, the given encryption context header for SSE-KMS will be set. Optional. @@ -320,6 +321,32 @@ The following settings can be specified in configuration file for given endpoint ``` +## Working with archives + +Suppose that we have several archive files with following URIs on S3: + +- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-10.csv.zip' +- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-11.csv.zip' +- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-12.csv.zip' + +Extracting data from these archives is possible using ::. Globs can be used both in the url part as well as in the part after :: (responsible for the name of a file inside the archive). + +``` sql +SELECT * +FROM s3( + 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-1{0..2}.csv.zip :: *.csv' +); +``` + +:::note +ClickHouse supports three archive formats: +ZIP +TAR +7Z +While ZIP and TAR archives can be accessed from any supported storage location, 7Z archives can only be read from the local filesystem where ClickHouse is installed. +::: + + ## Accessing public buckets ClickHouse tries to fetch credentials from many different types of sources. @@ -331,6 +358,10 @@ CREATE TABLE big_table (name String, value UInt32) ENGINE = S3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/aapl_stock.csv', NOSIGN, 'CSVWithNames'); ``` +## Optimizing performance + +For details on optimizing the performance of the s3 function see [our detailed guide](/docs/en/integrations/s3/performance). + ## See also - [s3 table function](../../../sql-reference/table-functions/s3.md) diff --git a/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md index 5a0a2691a9e..3670c763da6 100644 --- a/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md @@ -12,6 +12,10 @@ Data deduplication occurs only during a merge. Merging occurs in the background Thus, `ReplacingMergeTree` is suitable for clearing out duplicate data in the background in order to save space, but it does not guarantee the absence of duplicates. +:::note +A detailed guide on ReplacingMergeTree, including best practices and how to optimize performance, is available [here](/docs/en/guides/replacing-merge-tree). +::: + ## Creating a Table {#creating-a-table} ``` sql @@ -162,3 +166,51 @@ All of the parameters excepting `ver` have the same meaning as in `MergeTree`. - `ver` - column with the version. Optional parameter. For a description, see the text above. + +## Query time de-duplication & FINAL + +At merge time, the ReplacingMergeTree identifies duplicate rows, using the values of the `ORDER BY` columns (used to create the table) as a unique identifier, and retains only the highest version. This, however, offers eventual correctness only - it does not guarantee rows will be deduplicated, and you should not rely on it. Queries can, therefore, produce incorrect answers due to update and delete rows being considered in queries. + +To obtain correct answers, users will need to complement background merges with query time deduplication and deletion removal. This can be achieved using the `FINAL` operator. For example, consider the following example: + +```sql +CREATE TABLE rmt_example +( + `number` UInt16 +) +ENGINE = ReplacingMergeTree +ORDER BY number + +INSERT INTO rmt_example SELECT floor(randUniform(0, 100)) AS number +FROM numbers(1000000000) + +0 rows in set. Elapsed: 19.958 sec. Processed 1.00 billion rows, 8.00 GB (50.11 million rows/s., 400.84 MB/s.) +``` +Querying without `FINAL` produces an incorrect count (exact result will vary depending on merges): + +```sql +SELECT count() +FROM rmt_example + +┌─count()─┐ +│ 200 │ +└─────────┘ + +1 row in set. Elapsed: 0.002 sec. +``` + +Adding final produces a correct result: + +```sql +SELECT count() +FROM rmt_example +FINAL + +┌─count()─┐ +│ 100 │ +└─────────┘ + +1 row in set. Elapsed: 0.002 sec. +``` + +For further details on `FINAL`, including how to optimize `FINAL` performance, we recommend reading our [detailed guide on ReplacingMergeTree](/docs/en/guides/replacing-merge-tree). diff --git a/docs/en/getting-started/index.md b/docs/en/getting-started/index.md index b520220984c..7898ca01129 100644 --- a/docs/en/getting-started/index.md +++ b/docs/en/getting-started/index.md @@ -23,6 +23,7 @@ functions in ClickHouse. The sample datasets include: - The [NYPD Complaint Data](../getting-started/example-datasets/nypd_complaint_data.md) demonstrates how to use data inference to simplify creating tables - The ["What's on the Menu?" dataset](../getting-started/example-datasets/menus.md) has an example of denormalizing data - The [Laion dataset](../getting-started/example-datasets/laion.md) has an example of [Approximate nearest neighbor search indexes](../engines/table-engines/mergetree-family/annindexes.md) usage +- The [TPC-H](../getting-started/example-datasets/tpch.md), [TPC-DS](../getting-started/example-datasets/tpcds.md), and [Star Schema (SSB)](../getting-started/example-datasets/star-schema.md) industry benchmarks for analytics databases - [Getting Data Into ClickHouse - Part 1](https://clickhouse.com/blog/getting-data-into-clickhouse-part-1) provides examples of defining a schema and loading a small Hacker News dataset - [Getting Data Into ClickHouse - Part 3 - Using S3](https://clickhouse.com/blog/getting-data-into-clickhouse-part-3-s3) has examples of loading data from s3 - [Generating random data in ClickHouse](https://clickhouse.com/blog/generating-random-test-distribution-data-for-clickhouse) shows how to generate random data if none of the above fit your needs. diff --git a/docs/en/interfaces/cli.md b/docs/en/interfaces/cli.md index 66291014ed7..504f6eec6de 100644 --- a/docs/en/interfaces/cli.md +++ b/docs/en/interfaces/cli.md @@ -190,6 +190,7 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va - `--config-file` – The name of the configuration file. - `--secure` – If specified, will connect to server over secure connection (TLS). You might need to configure your CA certificates in the [configuration file](#configuration_files). The available configuration settings are the same as for [server-side TLS configuration](../operations/server-configuration-parameters/settings.md#openssl). - `--history_file` — Path to a file containing command history. +- `--history_max_entries` — Maximum number of entries in the history file. Default value: 1 000 000. - `--param_` — Value for a [query with parameters](#cli-queries-with-parameters). - `--hardware-utilization` — Print hardware utilization information in progress bar. - `--print-profile-events` – Print `ProfileEvents` packets. diff --git a/docs/en/interfaces/prometheus.md b/docs/en/interfaces/prometheus.md index 8e7023cc51f..11f503b54d7 100644 --- a/docs/en/interfaces/prometheus.md +++ b/docs/en/interfaces/prometheus.md @@ -9,7 +9,7 @@ sidebar_label: Prometheus protocols ## Exposing metrics {#expose} :::note -ClickHouse Cloud does not currently support connecting to Prometheus. To be notified when this feature is supported, please contact support@clickhouse.com. +If you are using ClickHouse Cloud, you can expose metrics to Prometheus using the [Prometheus Integration](/en/integrations/prometheus). ::: ClickHouse can expose its own metrics for scraping from Prometheus: diff --git a/docs/en/operations/_troubleshooting.md b/docs/en/operations/_troubleshooting.md index 77389782675..f0ee1ca1d29 100644 --- a/docs/en/operations/_troubleshooting.md +++ b/docs/en/operations/_troubleshooting.md @@ -65,6 +65,34 @@ sudo rm -f /etc/yum.repos.d/clickhouse.repo After that follow the [install guide](../getting-started/install.md#from-rpm-packages) +### You Can't Run Docker Container + +You are running a simple `docker run clickhouse/clickhouse-server` and it crashes with a stack trace similar to following: + +``` +$ docker run -it clickhouse/clickhouse-server +........ +2024.11.06 21:04:48.912036 [ 1 ] {} SentryWriter: Sending crash reports is disabled +Poco::Exception. Code: 1000, e.code() = 0, System exception: cannot start thread, Stack trace (when copying this message, always include the lines below): + +0. Poco::ThreadImpl::startImpl(Poco::SharedPtr>) @ 0x00000000157c7b34 +1. Poco::Thread::start(Poco::Runnable&) @ 0x00000000157c8a0e +2. BaseDaemon::initializeTerminationAndSignalProcessing() @ 0x000000000d267a14 +3. BaseDaemon::initialize(Poco::Util::Application&) @ 0x000000000d2652cb +4. DB::Server::initialize(Poco::Util::Application&) @ 0x000000000d128b38 +5. Poco::Util::Application::run() @ 0x000000001581cfda +6. DB::Server::run() @ 0x000000000d1288f0 +7. Poco::Util::ServerApplication::run(int, char**) @ 0x0000000015825e27 +8. mainEntryClickHouseServer(int, char**) @ 0x000000000d125b38 +9. main @ 0x0000000007ea4eee +10. ? @ 0x00007f67ff946d90 +11. ? @ 0x00007f67ff946e40 +12. _start @ 0x00000000062e802e + (version 24.10.1.2812 (official build)) +``` + +The reason is an old docker daemon with version lower than `20.10.10`. A way to fix it either upgrading it, or running `docker run [--privileged | --security-opt seccomp=unconfined]`. The latter has security implications. + ## Connecting to the Server {#troubleshooting-accepts-no-connections} Possible issues: diff --git a/docs/en/operations/server-configuration-parameters/settings.md b/docs/en/operations/server-configuration-parameters/settings.md index b6238487725..02fa5a8ca58 100644 --- a/docs/en/operations/server-configuration-parameters/settings.md +++ b/docs/en/operations/server-configuration-parameters/settings.md @@ -1975,6 +1975,22 @@ The default is `false`. true ``` +## async_load_system_database {#async_load_system_database} + +Asynchronous loading of system tables. Helpful if there is a high amount of log tables and parts in the `system` database. Independent of the `async_load_databases` setting. + +If set to `true`, all system databases with `Ordinary`, `Atomic`, and `Replicated` engines will be loaded asynchronously after the ClickHouse server starts. See `system.asynchronous_loader` table, `tables_loader_background_pool_size` and `tables_loader_foreground_pool_size` server settings. Any query that tries to access a system table, that is not yet loaded, will wait for exactly this table to be started up. The table that is waited for by at least one query will be loaded with higher priority. Also consider setting the `max_waiting_queries` setting to limit the total number of waiting queries. + +If `false`, system database loads before server start. + +The default is `false`. + +**Example** + +``` xml +true +``` + ## tables_loader_foreground_pool_size {#tables_loader_foreground_pool_size} Sets the number of threads performing load jobs in foreground pool. The foreground pool is used for loading table synchronously before server start listening on a port and for loading tables that are waited for. Foreground pool has higher priority than background pool. It means that no job starts in background pool while there are jobs running in foreground pool. @@ -2217,6 +2233,39 @@ If the table does not exist, ClickHouse will create it. If the structure of the ``` +# query_metric_log {#query_metric_log} + +It is disabled by default. + +**Enabling** + +To manually turn on metrics history collection [`system.query_metric_log`](../../operations/system-tables/query_metric_log.md), create `/etc/clickhouse-server/config.d/query_metric_log.xml` with the following content: + +``` xml + + + system + query_metric_log
+ 7500 + 1000 + 1048576 + 8192 + 524288 + false + + +``` + +**Disabling** + +To disable `query_metric_log` setting, you should create the following file `/etc/clickhouse-server/config.d/disable_query_metric_log.xml` with the following content: + +``` xml + + + +``` + ## query_cache {#server_configuration_parameters_query-cache} [Query cache](../query-cache.md) configuration. @@ -3109,7 +3158,7 @@ By default, tunneling (i.e, `HTTP CONNECT`) is used to make `HTTPS` requests ove ### no_proxy By default, all requests will go through the proxy. In order to disable it for specific hosts, the `no_proxy` variable must be set. -It can be set inside the `` clause for list and remote resolvers and as an environment variable for environment resolver. +It can be set inside the `` clause for list and remote resolvers and as an environment variable for environment resolver. It supports IP addresses, domains, subdomains and `'*'` wildcard for full bypass. Leading dots are stripped just like curl does. Example: @@ -3175,6 +3224,34 @@ Default value: "default" **See Also** - [Workload Scheduling](/docs/en/operations/workload-scheduling.md) +## workload_path {#workload_path} + +The directory used as a storage for all `CREATE WORKLOAD` and `CREATE RESOURCE` queries. By default `/workload/` folder under server working directory is used. + +**Example** + +``` xml +/var/lib/clickhouse/workload/ +``` + +**See Also** +- [Workload Hierarchy](/docs/en/operations/workload-scheduling.md#workloads) +- [workload_zookeeper_path](#workload_zookeeper_path) + +## workload_zookeeper_path {#workload_zookeeper_path} + +The path to a ZooKeeper node, which is used as a storage for all `CREATE WORKLOAD` and `CREATE RESOURCE` queries. For consistency all SQL definitions are stored as a value of this single znode. By default ZooKeeper is not used and definitions are stored on [disk](#workload_path). + +**Example** + +``` xml +/clickhouse/workload/definitions.sql +``` + +**See Also** +- [Workload Hierarchy](/docs/en/operations/workload-scheduling.md#workloads) +- [workload_path](#workload_path) + ## max_authentication_methods_per_user {#max_authentication_methods_per_user} The maximum number of authentication methods a user can be created with or altered to. diff --git a/docs/en/operations/system-tables/grants.md b/docs/en/operations/system-tables/grants.md index 262a53a87a5..debc3146008 100644 --- a/docs/en/operations/system-tables/grants.md +++ b/docs/en/operations/system-tables/grants.md @@ -19,7 +19,7 @@ Columns: - `column` ([Nullable](../../sql-reference/data-types/nullable.md)([String](../../sql-reference/data-types/string.md))) — Name of a column to which access is granted. - `is_partial_revoke` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Logical value. It shows whether some privileges have been revoked. Possible values: -- `0` — The row describes a partial revoke. -- `1` — The row describes a grant. +- `0` — The row describes a grant. +- `1` — The row describes a partial revoke. - `grant_option` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Permission is granted `WITH GRANT OPTION`, see [GRANT](../../sql-reference/statements/grant.md#granting-privilege-syntax). diff --git a/docs/en/operations/system-tables/merge_tree_settings.md b/docs/en/operations/system-tables/merge_tree_settings.md index 48217d63f9d..473315d3941 100644 --- a/docs/en/operations/system-tables/merge_tree_settings.md +++ b/docs/en/operations/system-tables/merge_tree_settings.md @@ -18,6 +18,11 @@ Columns: - `1` — Current user can’t change the setting. - `type` ([String](../../sql-reference/data-types/string.md)) — Setting type (implementation specific string value). - `is_obsolete` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) - Shows whether a setting is obsolete. +- `tier` ([Enum8](../../sql-reference/data-types/enum.md)) — Support level for this feature. ClickHouse features are organized in tiers, varying depending on the current status of their development and the expectations one might have when using them. Values: + - `'Production'` — The feature is stable, safe to use and does not have issues interacting with other **production** features. . + - `'Beta'` — The feature is stable and safe. The outcome of using it together with other features is unknown and correctness is not guaranteed. Testing and reports are welcome. + - `'Experimental'` — The feature is under development. Only intended for developers and ClickHouse enthusiasts. The feature might or might not work and could be removed at any time. + - `'Obsolete'` — No longer supported. Either it is already removed or it will be removed in future releases. **Example** ```sql diff --git a/docs/en/operations/system-tables/query_metric_log.md b/docs/en/operations/system-tables/query_metric_log.md new file mode 100644 index 00000000000..38d44c0e19a --- /dev/null +++ b/docs/en/operations/system-tables/query_metric_log.md @@ -0,0 +1,49 @@ +--- +slug: /en/operations/system-tables/query_metric_log +--- +# query_metric_log + +Contains history of memory and metric values from table `system.events` for individual queries, periodically flushed to disk. + +Once a query starts, data is collected at periodic intervals of `query_metric_log_interval` milliseconds (which is set to 1000 +by default). The data is also collected when the query finishes if the query takes longer than `query_metric_log_interval`. + +Columns: +- `query_id` ([String](../../sql-reference/data-types/string.md)) — ID of the query. +- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query. +- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date. +- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time. +- `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Event time with microseconds resolution. + +**Example** + +``` sql +SELECT * FROM system.query_metric_log LIMIT 1 FORMAT Vertical; +``` + +``` text +Row 1: +────── +query_id: 97c8ba04-b6d4-4bd7-b13e-6201c5c6e49d +hostname: clickhouse.eu-central1.internal +event_date: 2020-09-05 +event_time: 2020-09-05 16:22:33 +event_time_microseconds: 2020-09-05 16:22:33.196807 +memory_usage: 313434219 +peak_memory_usage: 598951986 +ProfileEvent_Query: 0 +ProfileEvent_SelectQuery: 0 +ProfileEvent_InsertQuery: 0 +ProfileEvent_FailedQuery: 0 +ProfileEvent_FailedSelectQuery: 0 +... +``` + +**See also** + +- [query_metric_log setting](../../operations/server-configuration-parameters/settings.md#query_metric_log) — Enabling and disabling the setting. +- [query_metric_log_interval](../../operations/settings/settings.md#query_metric_log_interval) +- [system.asynchronous_metrics](../../operations/system-tables/asynchronous_metrics.md) — Contains periodically calculated metrics. +- [system.events](../../operations/system-tables/events.md#system_tables-events) — Contains a number of events that occurred. +- [system.metrics](../../operations/system-tables/metrics.md) — Contains instantly calculated metrics. +- [Monitoring](../../operations/monitoring.md) — Base concepts of ClickHouse monitoring. diff --git a/docs/en/operations/system-tables/resources.md b/docs/en/operations/system-tables/resources.md new file mode 100644 index 00000000000..6329f05f610 --- /dev/null +++ b/docs/en/operations/system-tables/resources.md @@ -0,0 +1,37 @@ +--- +slug: /en/operations/system-tables/resources +--- +# resources + +Contains information for [resources](/docs/en/operations/workload-scheduling.md#workload_entity_storage) residing on the local server. The table contains a row for every resource. + +Example: + +``` sql +SELECT * +FROM system.resources +FORMAT Vertical +``` + +``` text +Row 1: +────── +name: io_read +read_disks: ['s3'] +write_disks: [] +create_query: CREATE RESOURCE io_read (READ DISK s3) + +Row 2: +────── +name: io_write +read_disks: [] +write_disks: ['s3'] +create_query: CREATE RESOURCE io_write (WRITE DISK s3) +``` + +Columns: + +- `name` (`String`) - Resource name. +- `read_disks` (`Array(String)`) - The array of disk names that uses this resource for read operations. +- `write_disks` (`Array(String)`) - The array of disk names that uses this resource for write operations. +- `create_query` (`String`) - The definition of the resource. diff --git a/docs/en/operations/system-tables/settings.md b/docs/en/operations/system-tables/settings.md index a04e095e990..1cfee0ba5f4 100644 --- a/docs/en/operations/system-tables/settings.md +++ b/docs/en/operations/system-tables/settings.md @@ -18,6 +18,11 @@ Columns: - `1` — Current user can’t change the setting. - `default` ([String](../../sql-reference/data-types/string.md)) — Setting default value. - `is_obsolete` ([UInt8](../../sql-reference/data-types/int-uint.md#uint-ranges)) - Shows whether a setting is obsolete. +- `tier` ([Enum8](../../sql-reference/data-types/enum.md)) — Support level for this feature. ClickHouse features are organized in tiers, varying depending on the current status of their development and the expectations one might have when using them. Values: + - `'Production'` — The feature is stable, safe to use and does not have issues interacting with other **production** features. . + - `'Beta'` — The feature is stable and safe. The outcome of using it together with other features is unknown and correctness is not guaranteed. Testing and reports are welcome. + - `'Experimental'` — The feature is under development. Only intended for developers and ClickHouse enthusiasts. The feature might or might not work and could be removed at any time. + - `'Obsolete'` — No longer supported. Either it is already removed or it will be removed in future releases. **Example** @@ -26,19 +31,99 @@ The following example shows how to get information about settings which name con ``` sql SELECT * FROM system.settings -WHERE name LIKE '%min_i%' +WHERE name LIKE '%min_insert_block_size_%' +FORMAT Vertical ``` ``` text -┌─name───────────────────────────────────────────────_─value─────_─changed─_─description───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────_─min──_─max──_─readonly─_─type─────────_─default───_─alias_for─_─is_obsolete─┐ -│ min_insert_block_size_rows │ 1048449 │ 0 │ Squash blocks passed to INSERT query to specified size in rows, if blocks are not big enough. │ ____ │ ____ │ 0 │ UInt64 │ 1048449 │ │ 0 │ -│ min_insert_block_size_bytes │ 268402944 │ 0 │ Squash blocks passed to INSERT query to specified size in bytes, if blocks are not big enough. │ ____ │ ____ │ 0 │ UInt64 │ 268402944 │ │ 0 │ -│ min_insert_block_size_rows_for_materialized_views │ 0 │ 0 │ Like min_insert_block_size_rows, but applied only during pushing to MATERIALIZED VIEW (default: min_insert_block_size_rows) │ ____ │ ____ │ 0 │ UInt64 │ 0 │ │ 0 │ -│ min_insert_block_size_bytes_for_materialized_views │ 0 │ 0 │ Like min_insert_block_size_bytes, but applied only during pushing to MATERIALIZED VIEW (default: min_insert_block_size_bytes) │ ____ │ ____ │ 0 │ UInt64 │ 0 │ │ 0 │ -│ read_backoff_min_interval_between_events_ms │ 1000 │ 0 │ Settings to reduce the number of threads in case of slow reads. Do not pay attention to the event, if the previous one has passed less than a certain amount of time. │ ____ │ ____ │ 0 │ Milliseconds │ 1000 │ │ 0 │ -└────────────────────────────────────────────────────┴───────────┴─────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────── -──────────────────────────────────────────────────────┴──────┴──────┴──────────┴──────────────┴───────────┴───────────┴─────────────┘ -``` +Row 1: +────── +name: min_insert_block_size_rows +value: 1048449 +changed: 0 +description: Sets the minimum number of rows in the block that can be inserted into a table by an `INSERT` query. Smaller-sized blocks are squashed into bigger ones. + +Possible values: + +- Positive integer. +- 0 — Squashing disabled. +min: ᴺᵁᴸᴸ +max: ᴺᵁᴸᴸ +readonly: 0 +type: UInt64 +default: 1048449 +alias_for: +is_obsolete: 0 +tier: Production + +Row 2: +────── +name: min_insert_block_size_bytes +value: 268402944 +changed: 0 +description: Sets the minimum number of bytes in the block which can be inserted into a table by an `INSERT` query. Smaller-sized blocks are squashed into bigger ones. + +Possible values: + +- Positive integer. +- 0 — Squashing disabled. +min: ᴺᵁᴸᴸ +max: ᴺᵁᴸᴸ +readonly: 0 +type: UInt64 +default: 268402944 +alias_for: +is_obsolete: 0 +tier: Production + +Row 3: +────── +name: min_insert_block_size_rows_for_materialized_views +value: 0 +changed: 0 +description: Sets the minimum number of rows in the block which can be inserted into a table by an `INSERT` query. Smaller-sized blocks are squashed into bigger ones. This setting is applied only for blocks inserted into [materialized view](../../sql-reference/statements/create/view.md). By adjusting this setting, you control blocks squashing while pushing to materialized view and avoid excessive memory usage. + +Possible values: + +- Any positive integer. +- 0 — Squashing disabled. + +**See Also** + +- [min_insert_block_size_rows](#min-insert-block-size-rows) +min: ᴺᵁᴸᴸ +max: ᴺᵁᴸᴸ +readonly: 0 +type: UInt64 +default: 0 +alias_for: +is_obsolete: 0 +tier: Production + +Row 4: +────── +name: min_insert_block_size_bytes_for_materialized_views +value: 0 +changed: 0 +description: Sets the minimum number of bytes in the block which can be inserted into a table by an `INSERT` query. Smaller-sized blocks are squashed into bigger ones. This setting is applied only for blocks inserted into [materialized view](../../sql-reference/statements/create/view.md). By adjusting this setting, you control blocks squashing while pushing to materialized view and avoid excessive memory usage. + +Possible values: + +- Any positive integer. +- 0 — Squashing disabled. + +**See also** + +- [min_insert_block_size_bytes](#min-insert-block-size-bytes) +min: ᴺᵁᴸᴸ +max: ᴺᵁᴸᴸ +readonly: 0 +type: UInt64 +default: 0 +alias_for: +is_obsolete: 0 +tier: Production + ``` Using of `WHERE changed` can be useful, for example, when you want to check: diff --git a/docs/en/operations/system-tables/workloads.md b/docs/en/operations/system-tables/workloads.md new file mode 100644 index 00000000000..d9c62372044 --- /dev/null +++ b/docs/en/operations/system-tables/workloads.md @@ -0,0 +1,40 @@ +--- +slug: /en/operations/system-tables/workloads +--- +# workloads + +Contains information for [workloads](/docs/en/operations/workload-scheduling.md#workload_entity_storage) residing on the local server. The table contains a row for every workload. + +Example: + +``` sql +SELECT * +FROM system.workloads +FORMAT Vertical +``` + +``` text +Row 1: +────── +name: production +parent: all +create_query: CREATE WORKLOAD production IN `all` SETTINGS weight = 9 + +Row 2: +────── +name: development +parent: all +create_query: CREATE WORKLOAD development IN `all` + +Row 3: +────── +name: all +parent: +create_query: CREATE WORKLOAD `all` +``` + +Columns: + +- `name` (`String`) - Workload name. +- `parent` (`String`) - Parent workload name. +- `create_query` (`String`) - The definition of the workload. diff --git a/docs/en/operations/workload-scheduling.md b/docs/en/operations/workload-scheduling.md index 08629492ec6..a43bea7a5b1 100644 --- a/docs/en/operations/workload-scheduling.md +++ b/docs/en/operations/workload-scheduling.md @@ -43,6 +43,20 @@ Example: ``` +An alternative way to express which disks are used by a resource is SQL syntax: + +```sql +CREATE RESOURCE resource_name (WRITE DISK disk1, READ DISK disk2) +``` + +Resource could be used for any number of disk for READ or WRITE or both for READ and WRITE. There a syntax allowing to use a resource for all the disks: + +```sql +CREATE RESOURCE all_io (READ ANY DISK, WRITE ANY DISK); +``` + +Note that server configuration options have priority over SQL way to define resources. + ## Workload markup {#workload_markup} Queries can be marked with setting `workload` to distinguish different workloads. If `workload` is not set, than value "default" is used. Note that you are able to specify the other value using settings profiles. Setting constraints can be used to make `workload` constant if you want all queries from the user to be marked with fixed value of `workload` setting. @@ -153,9 +167,48 @@ Example: ``` +## Workload hierarchy (SQL only) {#workloads} + +Defining resources and classifiers in XML could be challenging. ClickHouse provides SQL syntax that is much more convenient. All resources that were created with `CREATE RESOURCE` share the same structure of the hierarchy, but could differ in some aspects. Every workload created with `CREATE WORKLOAD` maintains a few automatically created scheduling nodes for every resource. A child workload can be created inside another parent workload. Here is the example that defines exactly the same hierarchy as XML configuration above: + +```sql +CREATE RESOURCE network_write (WRITE DISK s3) +CREATE RESOURCE network_read (READ DISK s3) +CREATE WORKLOAD all SETTINGS max_requests = 100 +CREATE WORKLOAD development IN all +CREATE WORKLOAD production IN all SETTINGS weight = 3 +``` + +The name of a leaf workload without children could be used in query settings `SETTINGS workload = 'name'`. Note that workload classifiers are also created automatically when using SQL syntax. + +To customize workload the following settings could be used: +* `priority` - sibling workloads are served according to static priority values (lower value means higher priority). +* `weight` - sibling workloads having the same static priority share resources according to weights. +* `max_requests` - the limit on the number of concurrent resource requests in this workload. +* `max_cost` - the limit on the total inflight bytes count of concurrent resource requests in this workload. +* `max_speed` - the limit on byte processing rate of this workload (the limit is independent for every resource). +* `max_burst` - maximum number of bytes that could be processed by the workload without being throttled (for every resource independently). + +Note that workload settings are translated into a proper set of scheduling nodes. For more details, see the description of the scheduling node [types and options](#hierarchy). + +There is no way to specify different hierarchies of workloads for different resources. But there is a way to specify different workload setting value for a specific resource: + +```sql +CREATE OR REPLACE WORKLOAD all SETTINGS max_requests = 100, max_speed = 1000000 FOR network_read, max_speed = 2000000 FOR network_write +``` + +Also note that workload or resource could not be dropped if it is referenced from another workload. To update a definition of a workload use `CREATE OR REPLACE WORKLOAD` query. + +## Workloads and resources storage {#workload_entity_storage} +Definitions of all workloads and resources in the form of `CREATE WORKLOAD` and `CREATE RESOURCE` queries are stored persistently either on disk at `workload_path` or in ZooKeeper at `workload_zookeeper_path`. ZooKeeper storage is recommended to achieve consistency between nodes. Alternatively `ON CLUSTER` clause could be used along with disk storage. + ## See also - [system.scheduler](/docs/en/operations/system-tables/scheduler.md) + - [system.workloads](/docs/en/operations/system-tables/workloads.md) + - [system.resources](/docs/en/operations/system-tables/resources.md) - [merge_workload](/docs/en/operations/settings/merge-tree-settings.md#merge_workload) merge tree setting - [merge_workload](/docs/en/operations/server-configuration-parameters/settings.md#merge_workload) global server setting - [mutation_workload](/docs/en/operations/settings/merge-tree-settings.md#mutation_workload) merge tree setting - [mutation_workload](/docs/en/operations/server-configuration-parameters/settings.md#mutation_workload) global server setting + - [workload_path](/docs/en/operations/server-configuration-parameters/settings.md#workload_path) global server setting + - [workload_zookeeper_path](/docs/en/operations/server-configuration-parameters/settings.md#workload_zookeeper_path) global server setting diff --git a/docs/en/sql-reference/aggregate-functions/reference/anylast.md b/docs/en/sql-reference/aggregate-functions/reference/anylast.md index 202d2e9fb10..4fe21531c76 100644 --- a/docs/en/sql-reference/aggregate-functions/reference/anylast.md +++ b/docs/en/sql-reference/aggregate-functions/reference/anylast.md @@ -17,7 +17,7 @@ anyLast(column) [RESPECT NULLS] - `column`: The column name. :::note -Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the first value passed, regardless of whether it is `NULL` or not. +Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the last value passed, regardless of whether it is `NULL` or not. ::: **Returned value** @@ -40,4 +40,4 @@ SELECT anyLast(city) FROM any_last_nulls; ┌─anyLast(city)─┐ │ Valencia │ └───────────────┘ -``` \ No newline at end of file +``` diff --git a/docs/en/sql-reference/aggregate-functions/reference/quantileexactweighted.md b/docs/en/sql-reference/aggregate-functions/reference/quantileexactweighted.md index 4ce212888c4..6004e8392f1 100644 --- a/docs/en/sql-reference/aggregate-functions/reference/quantileexactweighted.md +++ b/docs/en/sql-reference/aggregate-functions/reference/quantileexactweighted.md @@ -23,7 +23,7 @@ Alias: `medianExactWeighted`. - `level` — Level of quantile. Optional parameter. Constant floating-point number from 0 to 1. We recommend using a `level` value in the range of `[0.01, 0.99]`. Default value: 0.5. At `level=0.5` the function calculates [median](https://en.wikipedia.org/wiki/Median). - `expr` — Expression over the column values resulting in numeric [data types](../../../sql-reference/data-types/index.md#data_types), [Date](../../../sql-reference/data-types/date.md) or [DateTime](../../../sql-reference/data-types/datetime.md). -- `weight` — Column with weights of sequence members. Weight is a number of value occurrences. +- `weight` — Column with weights of sequence members. Weight is a number of value occurrences with [Unsigned integer types](../../../sql-reference/data-types/int-uint.md). **Returned value** diff --git a/docs/en/sql-reference/aggregate-functions/reference/quantileexactweightedinterpolated.md b/docs/en/sql-reference/aggregate-functions/reference/quantileexactweightedinterpolated.md new file mode 100644 index 00000000000..6b38e130cb2 --- /dev/null +++ b/docs/en/sql-reference/aggregate-functions/reference/quantileexactweightedinterpolated.md @@ -0,0 +1,77 @@ +--- +slug: /en/sql-reference/aggregate-functions/reference/quantileExactWeightedInterpolated +sidebar_position: 176 +--- + +# quantileExactWeightedInterpolated + +Computes [quantile](https://en.wikipedia.org/wiki/Quantile) of a numeric data sequence using linear interpolation, taking into account the weight of each element. + +To get the interpolated value, all the passed values are combined into an array, which are then sorted by their corresponding weights. Quantile interpolation is then performed using the [weighted percentile method](https://en.wikipedia.org/wiki/Percentile#The_weighted_percentile_method) by building a cumulative distribution based on weights and then a linear interpolation is performed using the weights and the values to compute the quantiles. + +When using multiple `quantile*` functions with different levels in a query, the internal states are not combined (that is, the query works less efficiently than it could). In this case, use the [quantiles](../../../sql-reference/aggregate-functions/reference/quantiles.md#quantiles) function. + +We strongly recommend using `quantileExactWeightedInterpolated` instead of `quantileInterpolatedWeighted` because `quantileExactWeightedInterpolated` is more accurate than `quantileInterpolatedWeighted`. Here is an example: + +``` sql +SELECT + quantileExactWeightedInterpolated(0.99)(number, 1), + quantile(0.99)(number), + quantileInterpolatedWeighted(0.99)(number, 1) +FROM numbers(9) + + +┌─quantileExactWeightedInterpolated(0.99)(number, 1)─┬─quantile(0.99)(number)─┬─quantileInterpolatedWeighted(0.99)(number, 1)─┐ +│ 7.92 │ 7.92 │ 8 │ +└────────────────────────────────────────────────────┴────────────────────────┴───────────────────────────────────────────────┘ +``` + +**Syntax** + +``` sql +quantileExactWeightedInterpolated(level)(expr, weight) +``` + +Alias: `medianExactWeightedInterpolated`. + +**Arguments** + +- `level` — Level of quantile. Optional parameter. Constant floating-point number from 0 to 1. We recommend using a `level` value in the range of `[0.01, 0.99]`. Default value: 0.5. At `level=0.5` the function calculates [median](https://en.wikipedia.org/wiki/Median). +- `expr` — Expression over the column values resulting in numeric [data types](../../../sql-reference/data-types/index.md#data_types), [Date](../../../sql-reference/data-types/date.md) or [DateTime](../../../sql-reference/data-types/datetime.md). +- `weight` — Column with weights of sequence members. Weight is a number of value occurrences with [Unsigned integer types](../../../sql-reference/data-types/int-uint.md). + +**Returned value** + +- Quantile of the specified level. + +Type: + +- [Float64](../../../sql-reference/data-types/float.md) for numeric data type input. +- [Date](../../../sql-reference/data-types/date.md) if input values have the `Date` type. +- [DateTime](../../../sql-reference/data-types/datetime.md) if input values have the `DateTime` type. + +**Example** + +Input table: + +``` text +┌─n─┬─val─┐ +│ 0 │ 3 │ +│ 1 │ 2 │ +│ 2 │ 1 │ +│ 5 │ 4 │ +└───┴─────┘ +``` + +Result: + +``` text +┌─quantileExactWeightedInterpolated(n, val)─┐ +│ 1.5 │ +└───────────────────────────────────────────┘ +``` + +**See Also** + +- [median](../../../sql-reference/aggregate-functions/reference/median.md#median) +- [quantiles](../../../sql-reference/aggregate-functions/reference/quantiles.md#quantiles) diff --git a/docs/en/sql-reference/aggregate-functions/reference/quantiles.md b/docs/en/sql-reference/aggregate-functions/reference/quantiles.md index e2c3295221d..aed017d295f 100644 --- a/docs/en/sql-reference/aggregate-functions/reference/quantiles.md +++ b/docs/en/sql-reference/aggregate-functions/reference/quantiles.md @@ -9,7 +9,7 @@ sidebar_position: 177 Syntax: `quantiles(level1, level2, ...)(x)` -All the quantile functions also have corresponding quantiles functions: `quantiles`, `quantilesDeterministic`, `quantilesTiming`, `quantilesTimingWeighted`, `quantilesExact`, `quantilesExactWeighted`, `quantileInterpolatedWeighted`, `quantilesTDigest`, `quantilesBFloat16`, `quantilesDD`. These functions calculate all the quantiles of the listed levels in one pass, and return an array of the resulting values. +All the quantile functions also have corresponding quantiles functions: `quantiles`, `quantilesDeterministic`, `quantilesTiming`, `quantilesTimingWeighted`, `quantilesExact`, `quantilesExactWeighted`, `quantileExactWeightedInterpolated`, `quantileInterpolatedWeighted`, `quantilesTDigest`, `quantilesBFloat16`, `quantilesDD`. These functions calculate all the quantiles of the listed levels in one pass, and return an array of the resulting values. ## quantilesExactExclusive diff --git a/docs/en/sql-reference/data-types/dynamic.md b/docs/en/sql-reference/data-types/dynamic.md index 5fbf47f7ef2..aa7455c8f68 100644 --- a/docs/en/sql-reference/data-types/dynamic.md +++ b/docs/en/sql-reference/data-types/dynamic.md @@ -512,6 +512,8 @@ The result of operator `<` for values `d1` with underlying type `T1` and `d2` wi - If `T1 = T2 = T`, the result will be `d1.T < d2.T` (underlying values will be compared). - If `T1 != T2`, the result will be `T1 < T2` (type names will be compared). +By default `Dynamic` type is not allowed in `GROUP BY`/`ORDER BY` keys, if you want to use it consider its special comparison rule and enable `allow_suspicious_types_in_group_by`/`allow_suspicious_types_in_order_by` settings. + Examples: ```sql CREATE TABLE test (d Dynamic) ENGINE=Memory; @@ -535,7 +537,7 @@ SELECT d, dynamicType(d) FROM test; ``` ```sql -SELECT d, dynamicType(d) FROM test ORDER BY d; +SELECT d, dynamicType(d) FROM test ORDER BY d SETTINGS allow_suspicious_types_in_order_by=1; ``` ```sql @@ -557,7 +559,7 @@ Example: ```sql CREATE TABLE test (d Dynamic) ENGINE=Memory; INSERT INTO test VALUES (1::UInt32), (1::Int64), (100::UInt32), (100::Int64); -SELECT d, dynamicType(d) FROM test ORDER by d; +SELECT d, dynamicType(d) FROM test ORDER BY d SETTINGS allow_suspicious_types_in_order_by=1; ``` ```text @@ -570,7 +572,7 @@ SELECT d, dynamicType(d) FROM test ORDER by d; ``` ```sql -SELECT d, dynamicType(d) FROM test GROUP by d; +SELECT d, dynamicType(d) FROM test GROUP by d SETTINGS allow_suspicious_types_in_group_by=1; ``` ```text @@ -582,7 +584,7 @@ SELECT d, dynamicType(d) FROM test GROUP by d; └─────┴────────────────┘ ``` -**Note**: the described comparison rule is not applied during execution of comparison functions like `<`/`>`/`=` and others because of [special work](#using-dynamic-type-in-functions) of functions with `Dynamic` type +**Note:** the described comparison rule is not applied during execution of comparison functions like `<`/`>`/`=` and others because of [special work](#using-dynamic-type-in-functions) of functions with `Dynamic` type ## Reaching the limit in number of different data types stored inside Dynamic diff --git a/docs/en/sql-reference/data-types/newjson.md b/docs/en/sql-reference/data-types/newjson.md index 68952590eb9..abb32388b7a 100644 --- a/docs/en/sql-reference/data-types/newjson.md +++ b/docs/en/sql-reference/data-types/newjson.md @@ -5,7 +5,7 @@ sidebar_label: JSON keywords: [json, data type] --- -# JSON +# JSON Data Type Stores JavaScript Object Notation (JSON) documents in a single column. @@ -58,10 +58,10 @@ SELECT json FROM test; └───────────────────────────────────┘ ``` -Using CAST from 'String': +Using CAST from `String`: ```sql -SELECT '{"a" : {"b" : 42},"c" : [1, 2, 3], "d" : "Hello, World!"}'::JSON as json; +SELECT '{"a" : {"b" : 42},"c" : [1, 2, 3], "d" : "Hello, World!"}'::JSON AS json; ``` ```text @@ -70,7 +70,47 @@ SELECT '{"a" : {"b" : 42},"c" : [1, 2, 3], "d" : "Hello, World!"}'::JSON as json └────────────────────────────────────────────────┘ ``` -CAST from `JSON`, named `Tuple`, `Map` and `Object('json')` to `JSON` type will be supported later. +Using CAST from `Tuple`: + +```sql +SELECT (tuple(42 AS b) AS a, [1, 2, 3] AS c, 'Hello, World!' AS d)::JSON AS json; +``` + +```text +┌─json───────────────────────────────────────────┐ +│ {"a":{"b":42},"c":[1,2,3],"d":"Hello, World!"} │ +└────────────────────────────────────────────────┘ +``` + +Using CAST from `Map`: + +```sql +SELECT map('a', map('b', 42), 'c', [1,2,3], 'd', 'Hello, World!')::JSON AS json; +``` + +```text +┌─json───────────────────────────────────────────┐ +│ {"a":{"b":42},"c":[1,2,3],"d":"Hello, World!"} │ +└────────────────────────────────────────────────┘ +``` + +Using CAST from deprecated `Object('json')`: + +```sql + SELECT '{"a" : {"b" : 42},"c" : [1, 2, 3], "d" : "Hello, World!"}'::Object('json')::JSON AS json; + ``` + +```text +┌─json───────────────────────────────────────────┐ +│ {"a":{"b":42},"c":[1,2,3],"d":"Hello, World!"} │ +└────────────────────────────────────────────────┘ +``` + +:::note +CAST from `Tuple`/`Map`/`Object('json')` to `JSON` is implemented via serializing the column into `String` column containing JSON objects and deserializing it back to `JSON` type column. +::: + +CAST between `JSON` types with different arguments will be supported later. ## Reading JSON paths as subcolumns diff --git a/docs/en/sql-reference/data-types/variant.md b/docs/en/sql-reference/data-types/variant.md index 3c2b6e0a362..7cb0f4ad4ea 100644 --- a/docs/en/sql-reference/data-types/variant.md +++ b/docs/en/sql-reference/data-types/variant.md @@ -441,6 +441,8 @@ SELECT v, variantType(v) FROM test ORDER by v; └─────┴────────────────┘ ``` +**Note** by default `Variant` type is not allowed in `GROUP BY`/`ORDER BY` keys, if you want to use it consider its special comparison rule and enable `allow_suspicious_types_in_group_by`/`allow_suspicious_types_in_order_by` settings. + ## JSONExtract functions with Variant All `JSONExtract*` functions support `Variant` type: diff --git a/docs/en/sql-reference/functions/type-conversion-functions.md b/docs/en/sql-reference/functions/type-conversion-functions.md index 5c39f880a0e..91bae2fe9da 100644 --- a/docs/en/sql-reference/functions/type-conversion-functions.md +++ b/docs/en/sql-reference/functions/type-conversion-functions.md @@ -6867,6 +6867,18 @@ Same as for [parseDateTimeInJodaSyntax](#parsedatetimeinjodasyntax) except that Same as for [parseDateTimeInJodaSyntax](#parsedatetimeinjodasyntax) except that it returns `NULL` when it encounters a date format that cannot be processed. +## parseDateTime64InJodaSyntax + +Similar to [parseDateTimeInJodaSyntax](#parsedatetimeinjodasyntax). Differently, it returns a value of type [DateTime64](../data-types/datetime64.md). + +## parseDateTime64InJodaSyntaxOrZero + +Same as for [parseDateTime64InJodaSyntax](#parsedatetime64injodasyntax) except that it returns zero date when it encounters a date format that cannot be processed. + +## parseDateTime64InJodaSyntaxOrNull + +Same as for [parseDateTime64InJodaSyntax](#parsedatetime64injodasyntax) except that it returns `NULL` when it encounters a date format that cannot be processed. + ## parseDateTimeBestEffort ## parseDateTime32BestEffort diff --git a/docs/en/sql-reference/statements/alter/user.md b/docs/en/sql-reference/statements/alter/user.md index a56532e2ab0..1514b16a657 100644 --- a/docs/en/sql-reference/statements/alter/user.md +++ b/docs/en/sql-reference/statements/alter/user.md @@ -12,7 +12,7 @@ Syntax: ``` sql ALTER USER [IF EXISTS] name1 [RENAME TO new_name |, name2 [,...]] [ON CLUSTER cluster_name] - [NOT IDENTIFIED | RESET AUTHENTICATION METHODS TO NEW | {IDENTIFIED | ADD IDENTIFIED} {[WITH {plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | WITH NO_PASSWORD | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'} | {WITH ssh_key BY KEY 'public_key' TYPE 'ssh-rsa|...'} | {WITH http SERVER 'server_name' [SCHEME 'Basic']} + [NOT IDENTIFIED | RESET AUTHENTICATION METHODS TO NEW | {IDENTIFIED | ADD IDENTIFIED} {[WITH {plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | WITH NO_PASSWORD | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'} | {WITH ssh_key BY KEY 'public_key' TYPE 'ssh-rsa|...'} | {WITH http SERVER 'server_name' [SCHEME 'Basic']} [VALID UNTIL datetime] [, {[{plaintext_password | sha256_password | sha256_hash | ...}] BY {'password' | 'hash'}} | {ldap SERVER 'server_name'} | {...} | ... [,...]]] [[ADD | DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] [VALID UNTIL datetime] @@ -91,3 +91,15 @@ Reset authentication methods and keep the most recent added one: ``` sql ALTER USER user1 RESET AUTHENTICATION METHODS TO NEW ``` + +## VALID UNTIL Clause + +Allows you to specify the expiration date and, optionally, the time for an authentication method. It accepts a string as a parameter. It is recommended to use the `YYYY-MM-DD [hh:mm:ss] [timezone]` format for datetime. By default, this parameter equals `'infinity'`. +The `VALID UNTIL` clause can only be specified along with an authentication method, except for the case where no authentication method has been specified in the query. In this scenario, the `VALID UNTIL` clause will be applied to all existing authentication methods. + +Examples: + +- `ALTER USER name1 VALID UNTIL '2025-01-01'` +- `ALTER USER name1 VALID UNTIL '2025-01-01 12:00:00 UTC'` +- `ALTER USER name1 VALID UNTIL 'infinity'` +- `ALTER USER name1 IDENTIFIED WITH plaintext_password BY 'no_expiration', bcrypt_password BY 'expiration_set' VALID UNTIL'2025-01-01''` diff --git a/docs/en/sql-reference/statements/create/user.md b/docs/en/sql-reference/statements/create/user.md index a018e28306c..03d93fc3365 100644 --- a/docs/en/sql-reference/statements/create/user.md +++ b/docs/en/sql-reference/statements/create/user.md @@ -11,7 +11,7 @@ Syntax: ``` sql CREATE USER [IF NOT EXISTS | OR REPLACE] name1 [, name2 [,...]] [ON CLUSTER cluster_name] - [NOT IDENTIFIED | IDENTIFIED {[WITH {plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | WITH NO_PASSWORD | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'} | {WITH ssh_key BY KEY 'public_key' TYPE 'ssh-rsa|...'} | {WITH http SERVER 'server_name' [SCHEME 'Basic']} + [NOT IDENTIFIED | IDENTIFIED {[WITH {plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | WITH NO_PASSWORD | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'} | {WITH ssh_key BY KEY 'public_key' TYPE 'ssh-rsa|...'} | {WITH http SERVER 'server_name' [SCHEME 'Basic']} [VALID UNTIL datetime] [, {[{plaintext_password | sha256_password | sha256_hash | ...}] BY {'password' | 'hash'}} | {ldap SERVER 'server_name'} | {...} | ... [,...]]] [HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE] [VALID UNTIL datetime] @@ -178,13 +178,16 @@ ClickHouse treats `user_name@'address'` as a username as a whole. Thus, technica ## VALID UNTIL Clause -Allows you to specify the expiration date and, optionally, the time for user credentials. It accepts a string as a parameter. It is recommended to use the `YYYY-MM-DD [hh:mm:ss] [timezone]` format for datetime. By default, this parameter equals `'infinity'`. +Allows you to specify the expiration date and, optionally, the time for an authentication method. It accepts a string as a parameter. It is recommended to use the `YYYY-MM-DD [hh:mm:ss] [timezone]` format for datetime. By default, this parameter equals `'infinity'`. +The `VALID UNTIL` clause can only be specified along with an authentication method, except for the case where no authentication method has been specified in the query. In this scenario, the `VALID UNTIL` clause will be applied to all existing authentication methods. Examples: - `CREATE USER name1 VALID UNTIL '2025-01-01'` - `CREATE USER name1 VALID UNTIL '2025-01-01 12:00:00 UTC'` - `CREATE USER name1 VALID UNTIL 'infinity'` +- ```CREATE USER name1 VALID UNTIL '2025-01-01 12:00:00 `Asia/Tokyo`'``` +- `CREATE USER name1 IDENTIFIED WITH plaintext_password BY 'no_expiration', bcrypt_password BY 'expiration_set' VALID UNTIL '2025-01-01''` ## GRANTEES Clause diff --git a/docs/en/sql-reference/statements/create/view.md b/docs/en/sql-reference/statements/create/view.md index 0e5d5250e0f..c770348bce0 100644 --- a/docs/en/sql-reference/statements/create/view.md +++ b/docs/en/sql-reference/statements/create/view.md @@ -55,7 +55,7 @@ SELECT * FROM view(column1=value1, column2=value2 ...) ## Materialized View ``` sql -CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER] [TO[db.]name] [ENGINE = engine] [POPULATE] +CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster_name] [TO[db.]name] [ENGINE = engine] [POPULATE] [DEFINER = { user | CURRENT_USER }] [SQL SECURITY { DEFINER | INVOKER | NONE }] AS SELECT ... [COMMENT 'comment'] diff --git a/docs/en/sql-reference/statements/grant.md b/docs/en/sql-reference/statements/grant.md index c11299baf38..6decaf19d5b 100644 --- a/docs/en/sql-reference/statements/grant.md +++ b/docs/en/sql-reference/statements/grant.md @@ -78,6 +78,10 @@ Specifying privileges you can use asterisk (`*`) instead of a table or a databas Also, you can omit database name. In this case privileges are granted for current database. For example, `GRANT SELECT ON * TO john` grants the privilege on all the tables in the current database, `GRANT SELECT ON mytable TO john` grants the privilege on the `mytable` table in the current database. +:::note +The feature described below is available starting with the 24.10 ClickHouse version. +::: + You can also put asterisks at the end of a table or a database name. This feature allows you to grant privileges on an abstract prefix of the table's path. Example: `GRANT SELECT ON db.my_tables* TO john`. This query allows `john` to execute the `SELECT` query over all the `db` database tables with the prefix `my_tables*`. @@ -113,6 +117,7 @@ GRANT SELECT ON db*.* TO john -- correct GRANT SELECT ON *.my_table TO john -- wrong GRANT SELECT ON foo*bar TO john -- wrong GRANT SELECT ON *suffix TO john -- wrong +GRANT SELECT(foo) ON db.table* TO john -- wrong ``` ## Privileges @@ -238,10 +243,13 @@ Hierarchy of privileges: - `HDFS` - `HIVE` - `JDBC` + - `KAFKA` - `MONGO` - `MYSQL` + - `NATS` - `ODBC` - `POSTGRES` + - `RABBITMQ` - `REDIS` - `REMOTE` - `S3` @@ -520,10 +528,13 @@ Allows using external data sources. Applies to [table engines](../../engines/tab - `HDFS`. Level: `GLOBAL` - `HIVE`. Level: `GLOBAL` - `JDBC`. Level: `GLOBAL` + - `KAFKA`. Level: `GLOBAL` - `MONGO`. Level: `GLOBAL` - `MYSQL`. Level: `GLOBAL` + - `NATS`. Level: `GLOBAL` - `ODBC`. Level: `GLOBAL` - `POSTGRES`. Level: `GLOBAL` + - `RABBITMQ`. Level: `GLOBAL` - `REDIS`. Level: `GLOBAL` - `REMOTE`. Level: `GLOBAL` - `S3`. Level: `GLOBAL` diff --git a/docs/en/sql-reference/statements/kill.md b/docs/en/sql-reference/statements/kill.md index 667a5b51f5c..ff6f64a97fe 100644 --- a/docs/en/sql-reference/statements/kill.md +++ b/docs/en/sql-reference/statements/kill.md @@ -83,7 +83,7 @@ The presence of long-running or incomplete mutations often indicates that a Clic - Or manually kill some of these mutations by sending a `KILL` command. ``` sql -KILL MUTATION [ON CLUSTER cluster] +KILL MUTATION WHERE [TEST] [FORMAT format] @@ -135,7 +135,6 @@ KILL MUTATION WHERE database = 'default' AND table = 'table' -- Cancel the specific mutation: KILL MUTATION WHERE database = 'default' AND table = 'table' AND mutation_id = 'mutation_3.txt' ``` -:::tip If you are killing a mutation in ClickHouse Cloud or in a self-managed cluster, then be sure to use the ```ON CLUSTER [cluster-name]``` option, in order to ensure the mutation is killed on all replicas::: The query is useful when a mutation is stuck and cannot finish (e.g. if some function in the mutation query throws an exception when applied to the data contained in the table). diff --git a/docs/en/sql-reference/statements/select/order-by.md b/docs/en/sql-reference/statements/select/order-by.md index 512a58d7cd9..25d2e7123fd 100644 --- a/docs/en/sql-reference/statements/select/order-by.md +++ b/docs/en/sql-reference/statements/select/order-by.md @@ -291,7 +291,7 @@ All missed values of `expr` column will be filled sequentially and other columns To fill multiple columns, add `WITH FILL` modifier with optional parameters after each field name in `ORDER BY` section. ``` sql -ORDER BY expr [WITH FILL] [FROM const_expr] [TO const_expr] [STEP const_numeric_expr], ... exprN [WITH FILL] [FROM expr] [TO expr] [STEP numeric_expr] +ORDER BY expr [WITH FILL] [FROM const_expr] [TO const_expr] [STEP const_numeric_expr] [STALENESS const_numeric_expr], ... exprN [WITH FILL] [FROM expr] [TO expr] [STEP numeric_expr] [STALENESS numeric_expr] [INTERPOLATE [(col [AS expr], ... colN [AS exprN])]] ``` @@ -300,6 +300,7 @@ When `FROM const_expr` not defined sequence of filling use minimal `expr` field When `TO const_expr` not defined sequence of filling use maximum `expr` field value from `ORDER BY`. When `STEP const_numeric_expr` defined then `const_numeric_expr` interprets `as is` for numeric types, as `days` for Date type, as `seconds` for DateTime type. It also supports [INTERVAL](https://clickhouse.com/docs/en/sql-reference/data-types/special-data-types/interval/) data type representing time and date intervals. When `STEP const_numeric_expr` omitted then sequence of filling use `1.0` for numeric type, `1 day` for Date type and `1 second` for DateTime type. +When `STALENESS const_numeric_expr` is defined, the query will generate rows until the difference from the previous row in the original data exceeds `const_numeric_expr`. `INTERPOLATE` can be applied to columns not participating in `ORDER BY WITH FILL`. Such columns are filled based on previous fields values by applying `expr`. If `expr` is not present will repeat previous value. Omitted list will result in including all allowed columns. Example of a query without `WITH FILL`: @@ -497,6 +498,64 @@ Result: └────────────┴────────────┴──────────┘ ``` +Example of a query without `STALENESS`: + +``` sql +SELECT number as key, 5 * number value, 'original' AS source +FROM numbers(16) WHERE key % 5 == 0 +ORDER BY key WITH FILL; +``` + +Result: + +``` text + ┌─key─┬─value─┬─source───┐ + 1. │ 0 │ 0 │ original │ + 2. │ 1 │ 0 │ │ + 3. │ 2 │ 0 │ │ + 4. │ 3 │ 0 │ │ + 5. │ 4 │ 0 │ │ + 6. │ 5 │ 25 │ original │ + 7. │ 6 │ 0 │ │ + 8. │ 7 │ 0 │ │ + 9. │ 8 │ 0 │ │ +10. │ 9 │ 0 │ │ +11. │ 10 │ 50 │ original │ +12. │ 11 │ 0 │ │ +13. │ 12 │ 0 │ │ +14. │ 13 │ 0 │ │ +15. │ 14 │ 0 │ │ +16. │ 15 │ 75 │ original │ + └─────┴───────┴──────────┘ +``` + +Same query after applying `STALENESS 3`: + +``` sql +SELECT number as key, 5 * number value, 'original' AS source +FROM numbers(16) WHERE key % 5 == 0 +ORDER BY key WITH FILL STALENESS 3; +``` + +Result: + +``` text + ┌─key─┬─value─┬─source───┐ + 1. │ 0 │ 0 │ original │ + 2. │ 1 │ 0 │ │ + 3. │ 2 │ 0 │ │ + 4. │ 5 │ 25 │ original │ + 5. │ 6 │ 0 │ │ + 6. │ 7 │ 0 │ │ + 7. │ 10 │ 50 │ original │ + 8. │ 11 │ 0 │ │ + 9. │ 12 │ 0 │ │ +10. │ 15 │ 75 │ original │ +11. │ 16 │ 0 │ │ +12. │ 17 │ 0 │ │ + └─────┴───────┴──────────┘ +``` + Example of a query without `INTERPOLATE`: ``` sql diff --git a/docs/en/sql-reference/table-functions/s3.md b/docs/en/sql-reference/table-functions/s3.md index 181c92b92d4..b14eb84392f 100644 --- a/docs/en/sql-reference/table-functions/s3.md +++ b/docs/en/sql-reference/table-functions/s3.md @@ -93,7 +93,6 @@ LIMIT 5; ClickHouse also can determine the compression method of the file. For example, if the file was zipped up with a `.csv.gz` extension, ClickHouse would decompress the file automatically. ::: - ## Usage Suppose that we have several files with following URIs on S3: @@ -248,6 +247,25 @@ FROM s3( LIMIT 5; ``` +## Using S3 credentials (ClickHouse Cloud) + +For non-public buckets, users can pass an `aws_access_key_id` and `aws_secret_access_key` to the function. For example: + +```sql +SELECT count() FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/mta/*.tsv', '', '','TSVWithNames') +``` + +This is appropriate for one-off accesses or in cases where credentials can easily be rotated. However, this is not recommended as a long-term solution for repeated access or where credentials are sensitive. In this case, we recommend users rely on role-based access. + +Role-based access for S3 in ClickHouse Cloud is documented [here](/docs/en/cloud/security/secure-s3#access-your-s3-bucket-with-the-clickhouseaccess-role). + +Once configured, a `roleARN` can be passed to the s3 function via an `extra_credentials` parameter. For example: + +```sql +SELECT count() FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/mta/*.tsv','CSVWithNames',extra_credentials(role_arn = 'arn:aws:iam::111111111111:role/ClickHouseAccessRole-001')) +``` + +Further examples can be found [here](/docs/en/cloud/security/secure-s3#access-your-s3-bucket-with-the-clickhouseaccess-role) ## Working with archives @@ -266,6 +284,14 @@ FROM s3( ); ``` +:::note +ClickHouse supports three archive formats: +ZIP +TAR +7Z +While ZIP and TAR archives can be accessed from any supported storage location, 7Z archives can only be read from the local filesystem where ClickHouse is installed. +::: + ## Virtual Columns {#virtual-columns} diff --git a/docs/en/sql-reference/table-functions/s3Cluster.md b/docs/en/sql-reference/table-functions/s3Cluster.md index 9bf5a6b4da6..0aa4784d27a 100644 --- a/docs/en/sql-reference/table-functions/s3Cluster.md +++ b/docs/en/sql-reference/table-functions/s3Cluster.md @@ -70,6 +70,15 @@ SELECT count(*) FROM s3Cluster( ) ``` +## Accessing private and public buckets + +Users can use the same approaches as document for the s3 function [here](/docs/en/sql-reference/table-functions/s3#accessing-public-buckets). + +## Optimizing performance + +For details on optimizing the performance of the s3 function see [our detailed guide](/docs/en/integrations/s3/performance). + + **See Also** - [S3 engine](../../engines/table-engines/integrations/s3.md) diff --git a/docs/ru/engines/table-engines/integrations/s3.md b/docs/ru/engines/table-engines/integrations/s3.md index a1c69df4d0a..2bab78c0612 100644 --- a/docs/ru/engines/table-engines/integrations/s3.md +++ b/docs/ru/engines/table-engines/integrations/s3.md @@ -138,6 +138,7 @@ CREATE TABLE table_with_asterisk (name String, value UInt32) - `use_insecure_imds_request` — признак использования менее безопасного соединения при выполнении запроса к IMDS при получении учётных данных из метаданных Amazon EC2. Значение по умолчанию — `false`. - `region` — название региона S3. - `header` — добавляет указанный HTTP-заголовок к запросу на заданную точку приема запроса. Может быть определен несколько раз. +- `access_header` - добавляет указанный HTTP-заголовок к запросу на заданную точку приема запроса, в случая если не указаны другие способы авторизации. - `server_side_encryption_customer_key_base64` — устанавливает необходимые заголовки для доступа к объектам S3 с шифрованием SSE-C. - `single_read_retries` — Максимальное количество попыток запроса при единичном чтении. Значение по умолчанию — `4`. diff --git a/docs/ru/getting-started/install.md b/docs/ru/getting-started/install.md index f8a660fbec9..083ddc8c39c 100644 --- a/docs/ru/getting-started/install.md +++ b/docs/ru/getting-started/install.md @@ -95,7 +95,7 @@ sudo yum install -y clickhouse-server clickhouse-client sudo systemctl enable clickhouse-server sudo systemctl start clickhouse-server sudo systemctl status clickhouse-server -clickhouse-client # илм "clickhouse-client --password" если установлен пароль +clickhouse-client # или "clickhouse-client --password" если установлен пароль ``` Для использования наиболее свежих версий нужно заменить `stable` на `testing` (рекомендуется для тестовых окружений). Также иногда доступен `prestable`. diff --git a/docs/ru/sql-reference/statements/create/view.md b/docs/ru/sql-reference/statements/create/view.md index 8fa30446bb3..5dbffd90205 100644 --- a/docs/ru/sql-reference/statements/create/view.md +++ b/docs/ru/sql-reference/statements/create/view.md @@ -39,7 +39,7 @@ SELECT a, b, c FROM (SELECT ...) ## Материализованные представления {#materialized} ``` sql -CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER] [TO[db.]name] [ENGINE = engine] [POPULATE] +CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster_name] [TO[db.]name] [ENGINE = engine] [POPULATE] [DEFINER = { user | CURRENT_USER }] [SQL SECURITY { DEFINER | INVOKER | NONE }] AS SELECT ... ``` diff --git a/docs/ru/sql-reference/statements/grant.md b/docs/ru/sql-reference/statements/grant.md index 2ccc2d05452..79682dc42cd 100644 --- a/docs/ru/sql-reference/statements/grant.md +++ b/docs/ru/sql-reference/statements/grant.md @@ -192,14 +192,23 @@ GRANT SELECT(x,y) ON db.table TO john WITH GRANT OPTION - `addressToSymbol` - `demangle` - [SOURCES](#grant-sources) + - `AZURE` - `FILE` - - `URL` - - `REMOTE` - - `MYSQL` - - `ODBC` - - `JDBC` - `HDFS` + - `HIVE` + - `JDBC` + - `KAFKA` + - `MONGO` + - `MYSQL` + - `NATS` + - `ODBC` + - `POSTGRES` + - `RABBITMQ` + - `REDIS` + - `REMOTE` - `S3` + - `SQLITE` + - `URL` - [dictGet](#grant-dictget) Примеры того, как трактуется данная иерархия: @@ -461,14 +470,23 @@ GRANT INSERT(x,y) ON db.table TO john Разрешает использовать внешние источники данных. Применяется к [движкам таблиц](../../engines/table-engines/index.md) и [табличным функциям](../table-functions/index.md#table-functions). - `SOURCES`. Уровень: `GROUP` + - `AZURE`. Уровень: `GLOBAL` - `FILE`. Уровень: `GLOBAL` - - `URL`. Уровень: `GLOBAL` - - `REMOTE`. Уровень: `GLOBAL` - - `MYSQL`. Уровень: `GLOBAL` - - `ODBC`. Уровень: `GLOBAL` - - `JDBC`. Уровень: `GLOBAL` - `HDFS`. Уровень: `GLOBAL` + - `HIVE`. Уровень: `GLOBAL` + - `JDBC`. Уровень: `GLOBAL` + - `KAFKA`. Уровень: `GLOBAL` + - `MONGO`. Уровень: `GLOBAL` + - `MYSQL`. Уровень: `GLOBAL` + - `NATS`. Уровень: `GLOBAL` + - `ODBC`. Уровень: `GLOBAL` + - `POSTGRES`. Уровень: `GLOBAL` + - `RABBITMQ`. Уровень: `GLOBAL` + - `REDIS`. Уровень: `GLOBAL` + - `REMOTE`. Уровень: `GLOBAL` - `S3`. Уровень: `GLOBAL` + - `SQLITE`. Уровень: `GLOBAL` + - `URL`. Уровень: `GLOBAL` Привилегия `SOURCES` разрешает использование всех источников. Также вы можете присвоить привилегию для каждого источника отдельно. Для использования источников необходимы дополнительные привилегии. diff --git a/docs/zh/sql-reference/statements/create/view.md b/docs/zh/sql-reference/statements/create/view.md index 49a1d66bdf1..6c93240644d 100644 --- a/docs/zh/sql-reference/statements/create/view.md +++ b/docs/zh/sql-reference/statements/create/view.md @@ -39,7 +39,7 @@ SELECT a, b, c FROM (SELECT ...) ## Materialized {#materialized} ``` sql -CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER] [TO[db.]name] [ENGINE = engine] [POPULATE] AS SELECT ... +CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster_name] [TO[db.]name] [ENGINE = engine] [POPULATE] AS SELECT ... ``` 物化视图存储由相应的[SELECT](../../../sql-reference/statements/select/index.md)管理. diff --git a/docs/zh/sql-reference/statements/grant.md b/docs/zh/sql-reference/statements/grant.md index fea51d590d5..3fd314c791f 100644 --- a/docs/zh/sql-reference/statements/grant.md +++ b/docs/zh/sql-reference/statements/grant.md @@ -170,14 +170,23 @@ GRANT SELECT(x,y) ON db.table TO john WITH GRANT OPTION - `addressToSymbol` - `demangle` - [SOURCES](#grant-sources) + - `AZURE` - `FILE` - - `URL` - - `REMOTE` - - `YSQL` - - `ODBC` - - `JDBC` - `HDFS` + - `HIVE` + - `JDBC` + - `KAFKA` + - `MONGO` + - `MYSQL` + - `NATS` + - `ODBC` + - `POSTGRES` + - `RABBITMQ` + - `REDIS` + - `REMOTE` - `S3` + - `SQLITE` + - `URL` - [dictGet](#grant-dictget) 如何对待该层级的示例： @@ -428,14 +437,23 @@ GRANT INSERT(x,y) ON db.table TO john 允许在 [table engines](../../engines/table-engines/index.md) 和 [table functions](../../sql-reference/table-functions/index.md#table-functions)中使用外部数据源。 - `SOURCES`. 级别: `GROUP` + - `AZURE`. 级别: `GLOBAL` - `FILE`. 级别: `GLOBAL` - - `URL`. 级别: `GLOBAL` - - `REMOTE`. 级别: `GLOBAL` - - `YSQL`. 级别: `GLOBAL` - - `ODBC`. 级别: `GLOBAL` - - `JDBC`. 级别: `GLOBAL` - `HDFS`. 级别: `GLOBAL` + - `HIVE`. 级别: `GLOBAL` + - `JDBC`. 级别: `GLOBAL` + - `KAFKA`. 级别: `GLOBAL` + - `MONGO`. 级别: `GLOBAL` + - `MYSQL`. 级别: `GLOBAL` + - `NATS`. 级别: `GLOBAL` + - `ODBC`. 级别: `GLOBAL` + - `POSTGRES`. 级别: `GLOBAL` + - `RABBITMQ`. 级别: `GLOBAL` + - `REDIS`. 级别: `GLOBAL` + - `REMOTE`. 级别: `GLOBAL` - `S3`. 级别: `GLOBAL` + - `SQLITE`. 级别: `GLOBAL` + - `URL`. 级别: `GLOBAL` `SOURCES` 权限允许使用所有数据源。当然也可以单独对每个数据源进行授权。要使用数据源时，还需要额外的权限。 diff --git a/programs/client/Client.cpp b/programs/client/Client.cpp index 4aab7fcae14..d7190444f0b 100644 --- a/programs/client/Client.cpp +++ b/programs/client/Client.cpp @@ -192,6 +192,10 @@ void Client::parseConnectionsCredentials(Poco::Util::AbstractConfiguration & con history_file = home_path + "/" + history_file.substr(1); config.setString("history_file", history_file); } + if (config.has(prefix + ".history_max_entries")) + { + config.setUInt("history_max_entries", history_max_entries); + } if (config.has(prefix + ".accept-invalid-certificate")) config.setBool("accept-invalid-certificate", config.getBool(prefix + ".accept-invalid-certificate")); } diff --git a/programs/disks/DisksApp.cpp b/programs/disks/DisksApp.cpp index 5fddfce0678..610d8eaa638 100644 --- a/programs/disks/DisksApp.cpp +++ b/programs/disks/DisksApp.cpp @@ -236,6 +236,7 @@ void DisksApp::runInteractiveReplxx() ReplxxLineReader lr( suggest, history_file, + history_max_entries, /* multiline= */ false, /* ignore_shell_suspend= */ false, query_extenders, @@ -398,6 +399,8 @@ void DisksApp::initializeHistoryFile() throw; } } + + history_max_entries = config().getUInt("history-max-entries", 1000000); } void DisksApp::init(const std::vector & common_arguments) diff --git a/programs/disks/DisksApp.h b/programs/disks/DisksApp.h index 5b240648508..4f2bd7fcad6 100644 --- a/programs/disks/DisksApp.h +++ b/programs/disks/DisksApp.h @@ -62,6 +62,8 @@ private: // Fields responsible for the REPL work String history_file; + UInt32 history_max_entries = 0; /// Maximum number of entries in the history file. Needs to be initialized to 0 since we don't have a proper constructor. Worry not, actual value is set within the initializeHistoryFile method. + LineReader::Suggest suggest; static LineReader::Patterns query_extenders; static LineReader::Patterns query_delimiters; diff --git a/programs/keeper-client/KeeperClient.cpp b/programs/keeper-client/KeeperClient.cpp index 97caa142124..2a426fad7ac 100644 --- a/programs/keeper-client/KeeperClient.cpp +++ b/programs/keeper-client/KeeperClient.cpp @@ -163,6 +163,10 @@ void KeeperClient::defineOptions(Poco::Util::OptionSet & options) .argument("") .binding("operation-timeout")); + options.addOption( + Poco::Util::Option("use-xid-64", "", "use 64-bit XID. default false.") + .binding("use-xid-64")); + options.addOption( Poco::Util::Option("config-file", "c", "if set, will try to get a connection string from clickhouse config. default `config.xml`") .argument("") @@ -239,6 +243,8 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */) } } + history_max_entries = config().getUInt("history-max-entries", 1000000); + String default_log_level; if (config().has("query")) /// We don't want to see any information log in query mode, unless it was set explicitly @@ -315,6 +321,7 @@ void KeeperClient::runInteractiveReplxx() ReplxxLineReader lr( suggest, history_file, + history_max_entries, /* multiline= */ false, /* ignore_shell_suspend= */ false, query_extenders, @@ -411,6 +418,7 @@ int KeeperClient::main(const std::vector & /* args */) 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; + zk_args.use_xid_64 = config().hasOption("use-xid-64"); zookeeper = zkutil::ZooKeeper::createWithoutKillingPreviousSessions(zk_args); if (config().has("no-confirmation") || config().has("query")) diff --git a/programs/keeper-client/KeeperClient.h b/programs/keeper-client/KeeperClient.h index 0d3db3c2f02..359663c6a13 100644 --- a/programs/keeper-client/KeeperClient.h +++ b/programs/keeper-client/KeeperClient.h @@ -59,6 +59,8 @@ protected: std::vector getCompletions(const String & prefix) const; String history_file; + UInt32 history_max_entries; /// Maximum number of entries in the history file. + LineReader::Suggest suggest; zkutil::ZooKeeperArgs zk_args; diff --git a/programs/keeper/Keeper.cpp b/programs/keeper/Keeper.cpp index 3007df60765..74af9950e13 100644 --- a/programs/keeper/Keeper.cpp +++ b/programs/keeper/Keeper.cpp @@ -590,6 +590,7 @@ try #if USE_SSL CertificateReloader::instance().tryLoad(*config); + CertificateReloader::instance().tryLoadClient(*config); #endif }); diff --git a/programs/local/LocalServer.cpp b/programs/local/LocalServer.cpp index b6b67724b0a..1dcef5eb25e 100644 --- a/programs/local/LocalServer.cpp +++ b/programs/local/LocalServer.cpp @@ -821,11 +821,11 @@ void LocalServer::processConfig() status.emplace(fs::path(path) / "status", StatusFile::write_full_info); LOG_DEBUG(log, "Loading metadata from {}", path); - auto startup_system_tasks = loadMetadataSystem(global_context); + auto load_system_metadata_tasks = loadMetadataSystem(global_context); 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)); - waitLoad(TablesLoaderForegroundPoolId, startup_system_tasks); + waitLoad(TablesLoaderForegroundPoolId, load_system_metadata_tasks); if (!getClientConfiguration().has("only-system-tables")) { diff --git a/programs/server/Server.cpp b/programs/server/Server.cpp index 35dae614d87..5159f95419e 100644 --- a/programs/server/Server.cpp +++ b/programs/server/Server.cpp @@ -86,7 +86,7 @@ #include #include #include -#include +#include #include #include #include "MetricsTransmitter.h" @@ -168,9 +168,11 @@ namespace ServerSetting { extern const ServerSettingsUInt32 asynchronous_heavy_metrics_update_period_s; extern const ServerSettingsUInt32 asynchronous_metrics_update_period_s; + extern const ServerSettingsBool asynchronous_metrics_enable_heavy_metrics; extern const ServerSettingsBool async_insert_queue_flush_on_shutdown; extern const ServerSettingsUInt64 async_insert_threads; extern const ServerSettingsBool async_load_databases; + extern const ServerSettingsBool async_load_system_database; extern const ServerSettingsUInt64 background_buffer_flush_schedule_pool_size; extern const ServerSettingsUInt64 background_common_pool_size; extern const ServerSettingsUInt64 background_distributed_schedule_pool_size; @@ -205,7 +207,6 @@ namespace ServerSetting extern const ServerSettingsBool format_alter_operations_with_parentheses; extern const ServerSettingsUInt64 global_profiler_cpu_time_period_ns; extern const ServerSettingsUInt64 global_profiler_real_time_period_ns; - extern const ServerSettingsDouble gwp_asan_force_sample_probability; extern const ServerSettingsUInt64 http_connections_soft_limit; extern const ServerSettingsUInt64 http_connections_store_limit; extern const ServerSettingsUInt64 http_connections_warn_limit; @@ -620,7 +621,7 @@ void sanityChecks(Server & server) #if defined(OS_LINUX) try { - const std::unordered_set fastClockSources = { + const std::unordered_set fast_clock_sources = { // ARM clock "arch_sys_counter", // KVM guest clock @@ -629,7 +630,7 @@ void sanityChecks(Server & server) "tsc", }; const char * filename = "/sys/devices/system/clocksource/clocksource0/current_clocksource"; - if (!fastClockSources.contains(readLine(filename))) + if (!fast_clock_sources.contains(readLine(filename))) server.context()->addWarningMessage("Linux is not using a fast clock source. Performance can be degraded. Check " + String(filename)); } catch (...) // NOLINT(bugprone-empty-catch) @@ -919,7 +920,6 @@ try registerFormats(); registerRemoteFileMetadatas(); registerSchedulerNodes(); - registerResourceManagers(); CurrentMetrics::set(CurrentMetrics::Revision, ClickHouseRevision::getVersionRevision()); CurrentMetrics::set(CurrentMetrics::VersionInteger, ClickHouseRevision::getVersionInteger()); @@ -1060,6 +1060,7 @@ try ServerAsynchronousMetrics async_metrics( global_context, server_settings[ServerSetting::asynchronous_metrics_update_period_s], + server_settings[ServerSetting::asynchronous_metrics_enable_heavy_metrics], server_settings[ServerSetting::asynchronous_heavy_metrics_update_period_s], [&]() -> std::vector { @@ -1352,9 +1353,11 @@ try } FailPointInjection::enableFromGlobalConfig(config()); +#endif memory_worker.start(); +#if defined(OS_LINUX) int default_oom_score = 0; #if !defined(NDEBUG) @@ -1927,10 +1930,6 @@ try if (global_context->isServerCompletelyStarted()) CannotAllocateThreadFaultInjector::setFaultProbability(new_server_settings[ServerSetting::cannot_allocate_thread_fault_injection_probability]); -#if USE_GWP_ASAN - GWPAsan::setForceSampleProbability(new_server_settings[ServerSetting::gwp_asan_force_sample_probability]); -#endif - ProfileEvents::increment(ProfileEvents::MainConfigLoads); /// Must be the last. @@ -2199,6 +2198,7 @@ try LOG_INFO(log, "Loading metadata from {}", path_str); + LoadTaskPtrs load_system_metadata_tasks; LoadTaskPtrs load_metadata_tasks; // Make sure that if exception is thrown during startup async, new async loading jobs are not going to be called. @@ -2222,12 +2222,8 @@ try auto & database_catalog = DatabaseCatalog::instance(); /// We load temporary database first, because projections need it. database_catalog.initializeAndLoadTemporaryDatabase(); - auto system_startup_tasks = loadMetadataSystem(global_context); - maybeConvertSystemDatabase(global_context, system_startup_tasks); - /// This has to be done before the initialization of system logs, - /// otherwise there is a race condition between the system database initialization - /// and creation of new tables in the database. - waitLoad(TablesLoaderForegroundPoolId, system_startup_tasks); + load_system_metadata_tasks = loadMetadataSystem(global_context, server_settings[ServerSetting::async_load_system_database]); + maybeConvertSystemDatabase(global_context, load_system_metadata_tasks); /// Startup scripts can depend on the system log tables. if (config().has("startup_scripts") && !server_settings[ServerSetting::prepare_system_log_tables_on_startup].changed) @@ -2258,6 +2254,8 @@ try database_catalog.assertDatabaseExists(default_database); /// Load user-defined SQL functions. global_context->getUserDefinedSQLObjectsStorage().loadObjects(); + /// Load WORKLOADs and RESOURCEs. + global_context->getWorkloadEntityStorage().loadEntities(); global_context->getRefreshSet().setRefreshesStopped(false); } @@ -2267,6 +2265,30 @@ try throw; } + bool found_stop_flag = false; + + if (has_zookeeper && global_context->getMacros()->getMacroMap().contains("replica")) + { + try + { + auto zookeeper = global_context->getZooKeeper(); + String stop_flag_path = "/clickhouse/stop_replicated_ddl_queries/{replica}"; + stop_flag_path = global_context->getMacros()->expand(stop_flag_path); + found_stop_flag = zookeeper->exists(stop_flag_path); + } + catch (const Coordination::Exception & e) + { + if (e.code != Coordination::Error::ZCONNECTIONLOSS) + throw; + tryLogCurrentException(log); + } + } + + if (found_stop_flag) + LOG_INFO(log, "Found a stop flag for replicated DDL queries. They will be disabled"); + else + DatabaseCatalog::instance().startReplicatedDDLQueries(); + LOG_DEBUG(log, "Loaded metadata."); if (has_trace_collector) @@ -2321,6 +2343,7 @@ try #if USE_SSL CertificateReloader::instance().tryLoad(config()); + CertificateReloader::instance().tryLoadClient(config()); #endif /// Must be done after initialization of `servers`, because async_metrics will access `servers` variable from its thread. @@ -2369,17 +2392,28 @@ try if (has_zookeeper && config().has("distributed_ddl")) { /// DDL worker should be started after all tables were loaded - String ddl_zookeeper_path = config().getString("distributed_ddl.path", "/clickhouse/task_queue/ddl/"); + String ddl_queue_path = config().getString("distributed_ddl.path", "/clickhouse/task_queue/ddl/"); + String ddl_replicas_path = config().getString("distributed_ddl.replicas_path", "/clickhouse/task_queue/replicas/"); int pool_size = config().getInt("distributed_ddl.pool_size", 1); if (pool_size < 1) throw Exception(ErrorCodes::ARGUMENT_OUT_OF_BOUND, "distributed_ddl.pool_size should be greater then 0"); - global_context->setDDLWorker(std::make_unique(pool_size, ddl_zookeeper_path, global_context, &config(), - "distributed_ddl", "DDLWorker", - &CurrentMetrics::MaxDDLEntryID, &CurrentMetrics::MaxPushedDDLEntryID), - load_metadata_tasks); + global_context->setDDLWorker( + std::make_unique( + pool_size, + ddl_queue_path, + ddl_replicas_path, + global_context, + &config(), + "distributed_ddl", + "DDLWorker", + &CurrentMetrics::MaxDDLEntryID, + &CurrentMetrics::MaxPushedDDLEntryID), + joinTasks(load_system_metadata_tasks, load_metadata_tasks)); } /// Do not keep tasks in server, they should be kept inside databases. Used here to make dependent tasks only. + load_system_metadata_tasks.clear(); + load_system_metadata_tasks.shrink_to_fit(); load_metadata_tasks.clear(); load_metadata_tasks.shrink_to_fit(); @@ -2405,7 +2439,6 @@ try #if USE_GWP_ASAN GWPAsan::initFinished(); - GWPAsan::setForceSampleProbability(server_settings[ServerSetting::gwp_asan_force_sample_probability]); #endif try @@ -2999,7 +3032,7 @@ void Server::updateServers( for (auto * server : all_servers) { - if (!server->isStopping()) + if (server->supportsRuntimeReconfiguration() && !server->isStopping()) { std::string port_name = server->getPortName(); bool has_host = false; diff --git a/programs/server/config.xml b/programs/server/config.xml index 10ad831465a..9807f8c0d5a 100644 --- a/programs/server/config.xml +++ b/programs/server/config.xml @@ -1195,6 +1195,19 @@ false + + + system + query_metric_log
+ 7500 + 1048576 + 8192 + 524288 + 1000 + false + + + + + @@ -1437,6 +1454,8 @@ /clickhouse/task_queue/ddl + + /clickhouse/task_queue/replicas diff --git a/programs/server/config.yaml.example b/programs/server/config.yaml.example index 5d5499f876c..5b0330df572 100644 --- a/programs/server/config.yaml.example +++ b/programs/server/config.yaml.example @@ -743,6 +743,13 @@ error_log: flush_interval_milliseconds: 7500 collect_interval_milliseconds: 1000 +# Query metric log contains history of memory and metric values from table system.events for individual queries, periodically flushed to disk. +query_metric_log: + database: system + table: query_metric_log + flush_interval_milliseconds: 7500 + collect_interval_milliseconds: 1000 + # Asynchronous metric log contains values of metrics from # system.asynchronous_metrics. asynchronous_metric_log: diff --git a/programs/static-files-disk-uploader/static-files-disk-uploader.cpp b/programs/static-files-disk-uploader/static-files-disk-uploader.cpp index f7696dd37f1..590e0364040 100644 --- a/programs/static-files-disk-uploader/static-files-disk-uploader.cpp +++ b/programs/static-files-disk-uploader/static-files-disk-uploader.cpp @@ -4,6 +4,7 @@ #include #include +#include #include #include #include diff --git a/src/Access/AccessControl.cpp b/src/Access/AccessControl.cpp index e8ee363be1a..9b3b8d2a977 100644 --- a/src/Access/AccessControl.cpp +++ b/src/Access/AccessControl.cpp @@ -608,7 +608,7 @@ AuthResult AccessControl::authenticate(const Credentials & credentials, const Po } catch (...) { - tryLogCurrentException(getLogger(), "from: " + address.toString() + ", user: " + credentials.getUserName() + ": Authentication failed"); + tryLogCurrentException(getLogger(), "from: " + address.toString() + ", user: " + credentials.getUserName() + ": Authentication failed", LogsLevel::information); WriteBufferFromOwnString message; message << credentials.getUserName() << ": Authentication failed: password is incorrect, or there is no user with such name."; @@ -622,8 +622,9 @@ AuthResult AccessControl::authenticate(const Credentials & credentials, const Po << "and deleting this file will reset the password.\n" << "See also /etc/clickhouse-server/users.xml on the server where ClickHouse is installed.\n\n"; - /// We use the same message for all authentication failures because we don't want to give away any unnecessary information for security reasons, - /// only the log will show the exact reason. + /// We use the same message for all authentication failures because we don't want to give away any unnecessary information for security reasons. + /// Only the log ((*), above) will show the exact reason. Note that (*) logs at information level instead of the default error level as + /// authentication failures are not an unusual event. throw Exception(PreformattedMessage{message.str(), "{}: Authentication failed: password is incorrect, or there is no user with such name", std::vector{credentials.getUserName()}}, diff --git a/src/Access/AccessControl.h b/src/Access/AccessControl.h index a91686433ec..a342c5300bf 100644 --- a/src/Access/AccessControl.h +++ b/src/Access/AccessControl.h @@ -9,6 +9,8 @@ #include +#include "config.h" + namespace Poco { diff --git a/src/Access/Authentication.cpp b/src/Access/Authentication.cpp index 8d5d04a4ed2..1d69a659cd6 100644 --- a/src/Access/Authentication.cpp +++ b/src/Access/Authentication.cpp @@ -12,6 +12,7 @@ #include "config.h" + namespace DB { diff --git a/src/Access/AuthenticationData.cpp b/src/Access/AuthenticationData.cpp index 57a1cd756ff..37a4e356af8 100644 --- a/src/Access/AuthenticationData.cpp +++ b/src/Access/AuthenticationData.cpp @@ -1,12 +1,16 @@ #include #include #include +#include #include #include #include #include #include #include +#include +#include +#include #include #include @@ -113,7 +117,8 @@ bool operator ==(const AuthenticationData & lhs, const AuthenticationData & rhs) && (lhs.ssh_keys == rhs.ssh_keys) #endif && (lhs.http_auth_scheme == rhs.http_auth_scheme) - && (lhs.http_auth_server_name == rhs.http_auth_server_name); + && (lhs.http_auth_server_name == rhs.http_auth_server_name) + && (lhs.valid_until == rhs.valid_until); } @@ -384,14 +389,34 @@ std::shared_ptr AuthenticationData::toAST() const throw Exception(ErrorCodes::LOGICAL_ERROR, "AST: Unexpected authentication type {}", toString(auth_type)); } + + if (valid_until) + { + WriteBufferFromOwnString out; + writeDateTimeText(valid_until, out); + + node->valid_until = std::make_shared(out.str()); + } + return node; } AuthenticationData AuthenticationData::fromAST(const ASTAuthenticationData & query, ContextPtr context, bool validate) { + time_t valid_until = 0; + + if (query.valid_until) + { + valid_until = getValidUntilFromAST(query.valid_until, context); + } + if (query.type && query.type == AuthenticationType::NO_PASSWORD) - return AuthenticationData(); + { + AuthenticationData auth_data; + auth_data.setValidUntil(valid_until); + return auth_data; + } /// For this type of authentication we have ASTPublicSSHKey as children for ASTAuthenticationData if (query.type && query.type == AuthenticationType::SSH_KEY) @@ -418,6 +443,7 @@ AuthenticationData AuthenticationData::fromAST(const ASTAuthenticationData & que } auth_data.setSSHKeys(std::move(keys)); + auth_data.setValidUntil(valid_until); return auth_data; #else throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh"); @@ -451,6 +477,8 @@ AuthenticationData AuthenticationData::fromAST(const ASTAuthenticationData & que AuthenticationData auth_data(current_type); + auth_data.setValidUntil(valid_until); + if (validate) context->getAccessControl().checkPasswordComplexityRules(value); @@ -494,6 +522,7 @@ AuthenticationData AuthenticationData::fromAST(const ASTAuthenticationData & que } AuthenticationData auth_data(*query.type); + auth_data.setValidUntil(valid_until); if (query.contains_hash) { diff --git a/src/Access/AuthenticationData.h b/src/Access/AuthenticationData.h index a0c100264f8..2d8d008c925 100644 --- a/src/Access/AuthenticationData.h +++ b/src/Access/AuthenticationData.h @@ -74,6 +74,9 @@ public: const String & getHTTPAuthenticationServerName() const { return http_auth_server_name; } void setHTTPAuthenticationServerName(const String & name) { http_auth_server_name = name; } + time_t getValidUntil() const { return valid_until; } + void setValidUntil(time_t valid_until_) { valid_until = valid_until_; } + friend bool operator ==(const AuthenticationData & lhs, const AuthenticationData & rhs); friend bool operator !=(const AuthenticationData & lhs, const AuthenticationData & rhs) { return !(lhs == rhs); } @@ -106,6 +109,7 @@ private: /// HTTP authentication properties String http_auth_server_name; HTTPAuthenticationScheme http_auth_scheme = HTTPAuthenticationScheme::BASIC; + time_t valid_until = 0; }; } diff --git a/src/Access/Common/AccessType.h b/src/Access/Common/AccessType.h index e9f24a8c685..ec543104167 100644 --- a/src/Access/Common/AccessType.h +++ b/src/Access/Common/AccessType.h @@ -99,6 +99,8 @@ enum class AccessType : uint8_t M(CREATE_ARBITRARY_TEMPORARY_TABLE, "", GLOBAL, CREATE) /* allows to create and manipulate temporary tables with arbitrary table engine */\ M(CREATE_FUNCTION, "", GLOBAL, CREATE) /* allows to execute CREATE FUNCTION */ \ + M(CREATE_WORKLOAD, "", GLOBAL, CREATE) /* allows to execute CREATE WORKLOAD */ \ + M(CREATE_RESOURCE, "", GLOBAL, CREATE) /* allows to execute CREATE RESOURCE */ \ M(CREATE_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) /* allows to execute CREATE NAMED COLLECTION */ \ M(CREATE, "", GROUP, ALL) /* allows to execute {CREATE|ATTACH} */ \ \ @@ -108,6 +110,8 @@ enum class AccessType : uint8_t implicitly enabled by the grant DROP_TABLE */\ M(DROP_DICTIONARY, "", DICTIONARY, DROP) /* allows to execute {DROP|DETACH} DICTIONARY */\ M(DROP_FUNCTION, "", GLOBAL, DROP) /* allows to execute DROP FUNCTION */\ + M(DROP_WORKLOAD, "", GLOBAL, DROP) /* allows to execute DROP WORKLOAD */\ + M(DROP_RESOURCE, "", GLOBAL, DROP) /* allows to execute DROP RESOURCE */\ M(DROP_NAMED_COLLECTION, "", NAMED_COLLECTION, NAMED_COLLECTION_ADMIN) /* allows to execute DROP NAMED COLLECTION */\ M(DROP, "", GROUP, ALL) /* allows to execute {DROP|DETACH} */\ \ @@ -159,6 +163,7 @@ enum class AccessType : uint8_t M(SYSTEM_SHUTDOWN, "SYSTEM KILL, SHUTDOWN", GLOBAL, SYSTEM) \ M(SYSTEM_DROP_DNS_CACHE, "SYSTEM DROP DNS, DROP DNS CACHE, DROP DNS", GLOBAL, SYSTEM_DROP_CACHE) \ M(SYSTEM_DROP_CONNECTIONS_CACHE, "SYSTEM DROP CONNECTIONS CACHE, DROP CONNECTIONS CACHE", GLOBAL, SYSTEM_DROP_CACHE) \ + M(SYSTEM_PREWARM_MARK_CACHE, "SYSTEM PREWARM MARK, PREWARM MARK CACHE, PREWARM MARKS", GLOBAL, SYSTEM_DROP_CACHE) \ M(SYSTEM_DROP_MARK_CACHE, "SYSTEM DROP MARK, DROP MARK CACHE, DROP MARKS", GLOBAL, SYSTEM_DROP_CACHE) \ M(SYSTEM_DROP_UNCOMPRESSED_CACHE, "SYSTEM DROP UNCOMPRESSED, DROP UNCOMPRESSED CACHE, DROP UNCOMPRESSED", GLOBAL, SYSTEM_DROP_CACHE) \ M(SYSTEM_DROP_MMAP_CACHE, "SYSTEM DROP MMAP, DROP MMAP CACHE, DROP MMAP", GLOBAL, SYSTEM_DROP_CACHE) \ @@ -193,6 +198,7 @@ enum class AccessType : uint8_t M(SYSTEM_SENDS, "SYSTEM STOP SENDS, SYSTEM START SENDS, STOP SENDS, START SENDS", GROUP, SYSTEM) \ M(SYSTEM_REPLICATION_QUEUES, "SYSTEM STOP REPLICATION QUEUES, SYSTEM START REPLICATION QUEUES, STOP REPLICATION QUEUES, START REPLICATION QUEUES", TABLE, SYSTEM) \ M(SYSTEM_VIRTUAL_PARTS_UPDATE, "SYSTEM STOP VIRTUAL PARTS UPDATE, SYSTEM START VIRTUAL PARTS UPDATE, STOP VIRTUAL PARTS UPDATE, START VIRTUAL PARTS UPDATE", TABLE, SYSTEM) \ + M(SYSTEM_REDUCE_BLOCKING_PARTS, "SYSTEM STOP REDUCE BLOCKING PARTS, SYSTEM START REDUCE BLOCKING PARTS, STOP REDUCE BLOCKING PARTS, START REDUCE BLOCKING PARTS", TABLE, SYSTEM) \ M(SYSTEM_DROP_REPLICA, "DROP REPLICA", TABLE, SYSTEM) \ M(SYSTEM_SYNC_REPLICA, "SYNC REPLICA", TABLE, SYSTEM) \ M(SYSTEM_REPLICA_READINESS, "SYSTEM REPLICA READY, SYSTEM REPLICA UNREADY", GLOBAL, SYSTEM) \ @@ -237,6 +243,9 @@ enum class AccessType : uint8_t M(S3, "", GLOBAL, SOURCES) \ M(HIVE, "", GLOBAL, SOURCES) \ M(AZURE, "", GLOBAL, SOURCES) \ + M(KAFKA, "", GLOBAL, SOURCES) \ + M(NATS, "", GLOBAL, SOURCES) \ + M(RABBITMQ, "", GLOBAL, SOURCES) \ M(SOURCES, "", GROUP, ALL) \ \ M(CLUSTER, "", GLOBAL, ALL) /* ON CLUSTER queries */ \ diff --git a/src/Access/ContextAccess.cpp b/src/Access/ContextAccess.cpp index 949fd37e403..06e89d78339 100644 --- a/src/Access/ContextAccess.cpp +++ b/src/Access/ContextAccess.cpp @@ -52,7 +52,10 @@ namespace {AccessType::HDFS, "HDFS"}, {AccessType::S3, "S3"}, {AccessType::HIVE, "Hive"}, - {AccessType::AZURE, "AzureBlobStorage"} + {AccessType::AZURE, "AzureBlobStorage"}, + {AccessType::KAFKA, "Kafka"}, + {AccessType::NATS, "NATS"}, + {AccessType::RABBITMQ, "RabbitMQ"} }; @@ -701,15 +704,17 @@ bool ContextAccess::checkAccessImplHelper(const ContextPtr & context, AccessFlag const AccessFlags dictionary_ddl = AccessType::CREATE_DICTIONARY | AccessType::DROP_DICTIONARY; const AccessFlags function_ddl = AccessType::CREATE_FUNCTION | AccessType::DROP_FUNCTION; + const AccessFlags workload_ddl = AccessType::CREATE_WORKLOAD | AccessType::DROP_WORKLOAD; + const AccessFlags resource_ddl = AccessType::CREATE_RESOURCE | AccessType::DROP_RESOURCE; const AccessFlags table_and_dictionary_ddl = table_ddl | dictionary_ddl; const AccessFlags table_and_dictionary_and_function_ddl = table_ddl | dictionary_ddl | function_ddl; const AccessFlags write_table_access = AccessType::INSERT | AccessType::OPTIMIZE; const AccessFlags write_dcl_access = AccessType::ACCESS_MANAGEMENT - AccessType::SHOW_ACCESS; - const AccessFlags not_readonly_flags = write_table_access | table_and_dictionary_and_function_ddl | write_dcl_access | AccessType::SYSTEM | AccessType::KILL_QUERY; + const AccessFlags not_readonly_flags = write_table_access | table_and_dictionary_and_function_ddl | workload_ddl | resource_ddl | write_dcl_access | AccessType::SYSTEM | AccessType::KILL_QUERY; const AccessFlags not_readonly_1_flags = AccessType::CREATE_TEMPORARY_TABLE; - const AccessFlags ddl_flags = table_ddl | dictionary_ddl | function_ddl; + const AccessFlags ddl_flags = table_ddl | dictionary_ddl | function_ddl | workload_ddl | resource_ddl; const AccessFlags introspection_flags = AccessType::INTROSPECTION; }; static const PrecalculatedFlags precalc; diff --git a/src/Access/Credentials.h b/src/Access/Credentials.h index f220b8d2c48..b21b7e6921f 100644 --- a/src/Access/Credentials.h +++ b/src/Access/Credentials.h @@ -15,6 +15,9 @@ public: explicit Credentials() = default; explicit Credentials(const String & user_name_); + Credentials(const Credentials &) = default; + Credentials(Credentials &&) = default; + virtual ~Credentials() = default; const String & getUserName() const; diff --git a/src/Access/IAccessStorage.cpp b/src/Access/IAccessStorage.cpp index 3249d89ba87..72e0933e214 100644 --- a/src/Access/IAccessStorage.cpp +++ b/src/Access/IAccessStorage.cpp @@ -554,7 +554,7 @@ std::optional IAccessStorage::authenticateImpl( continue; } - if (areCredentialsValid(user->getName(), user->valid_until, auth_method, credentials, external_authenticators, auth_result.settings)) + if (areCredentialsValid(user->getName(), auth_method, credentials, external_authenticators, auth_result.settings)) { auth_result.authentication_data = auth_method; return auth_result; @@ -579,7 +579,6 @@ std::optional IAccessStorage::authenticateImpl( bool IAccessStorage::areCredentialsValid( const std::string & user_name, - time_t valid_until, const AuthenticationData & authentication_method, const Credentials & credentials, const ExternalAuthenticators & external_authenticators, @@ -591,6 +590,7 @@ bool IAccessStorage::areCredentialsValid( if (credentials.getUserName() != user_name) return false; + auto valid_until = authentication_method.getValidUntil(); if (valid_until) { const time_t now = std::chrono::system_clock::to_time_t(std::chrono::system_clock::now()); diff --git a/src/Access/IAccessStorage.h b/src/Access/IAccessStorage.h index 84cbdd0a751..4e2b27a1864 100644 --- a/src/Access/IAccessStorage.h +++ b/src/Access/IAccessStorage.h @@ -236,7 +236,6 @@ protected: bool allow_plaintext_password) const; virtual bool areCredentialsValid( const std::string & user_name, - time_t valid_until, const AuthenticationData & authentication_method, const Credentials & credentials, const ExternalAuthenticators & external_authenticators, diff --git a/src/Access/RoleCache.h b/src/Access/RoleCache.h index 75d1fd32685..b707a05346f 100644 --- a/src/Access/RoleCache.h +++ b/src/Access/RoleCache.h @@ -22,6 +22,10 @@ public: const std::vector & current_roles, const std::vector & current_roles_with_admin_option); + std::shared_ptr getEnabledRoles( + boost::container::flat_set current_roles, + boost::container::flat_set current_roles_with_admin_option); + private: using SubscriptionsOnRoles = std::vector>; diff --git a/src/Access/User.cpp b/src/Access/User.cpp index 887abc213f9..1c92f467003 100644 --- a/src/Access/User.cpp +++ b/src/Access/User.cpp @@ -19,8 +19,7 @@ bool User::equal(const IAccessEntity & other) const return (authentication_methods == other_user.authentication_methods) && (allowed_client_hosts == other_user.allowed_client_hosts) && (access == other_user.access) && (granted_roles == other_user.granted_roles) && (default_roles == other_user.default_roles) - && (settings == other_user.settings) && (grantees == other_user.grantees) && (default_database == other_user.default_database) - && (valid_until == other_user.valid_until); + && (settings == other_user.settings) && (grantees == other_user.grantees) && (default_database == other_user.default_database); } void User::setName(const String & name_) @@ -88,7 +87,6 @@ void User::clearAllExceptDependencies() access = {}; settings.removeSettingsKeepProfiles(); default_database = {}; - valid_until = 0; } } diff --git a/src/Access/User.h b/src/Access/User.h index 03d62bf2277..f54e74a305d 100644 --- a/src/Access/User.h +++ b/src/Access/User.h @@ -23,7 +23,6 @@ struct User : public IAccessEntity SettingsProfileElements settings; RolesOrUsersSet grantees = RolesOrUsersSet::AllTag{}; String default_database; - time_t valid_until = 0; bool equal(const IAccessEntity & other) const override; std::shared_ptr clone() const override { return cloneImpl(); } diff --git a/src/Access/tests/gtest_access_rights_ops.cpp b/src/Access/tests/gtest_access_rights_ops.cpp index 902fc949840..41567905a10 100644 --- a/src/Access/tests/gtest_access_rights_ops.cpp +++ b/src/Access/tests/gtest_access_rights_ops.cpp @@ -284,7 +284,8 @@ TEST(AccessRights, Union) "CREATE DICTIONARY, DROP DATABASE, DROP TABLE, DROP VIEW, DROP DICTIONARY, UNDROP TABLE, " "TRUNCATE, OPTIMIZE, BACKUP, CREATE ROW POLICY, ALTER ROW POLICY, DROP ROW POLICY, " "SHOW ROW POLICIES, SYSTEM MERGES, SYSTEM TTL MERGES, SYSTEM FETCHES, " - "SYSTEM MOVES, SYSTEM PULLING REPLICATION LOG, SYSTEM CLEANUP, SYSTEM VIEWS, SYSTEM SENDS, SYSTEM REPLICATION QUEUES, SYSTEM VIRTUAL PARTS UPDATE, " + "SYSTEM MOVES, SYSTEM PULLING REPLICATION LOG, SYSTEM CLEANUP, SYSTEM VIEWS, SYSTEM SENDS, " + "SYSTEM REPLICATION QUEUES, SYSTEM VIRTUAL PARTS UPDATE, SYSTEM REDUCE BLOCKING PARTS, " "SYSTEM DROP REPLICA, SYSTEM SYNC REPLICA, SYSTEM RESTART REPLICA, " "SYSTEM RESTORE REPLICA, SYSTEM WAIT LOADING PARTS, SYSTEM SYNC DATABASE REPLICA, SYSTEM FLUSH DISTRIBUTED, " "SYSTEM UNLOAD PRIMARY KEY, dictGet ON db1.*, GRANT TABLE ENGINE ON db1, " diff --git a/src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp b/src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp index 86f7661e53f..061a1e519e1 100644 --- a/src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp +++ b/src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp @@ -59,13 +59,13 @@ constexpr size_t group_array_sorted_sort_strategy_max_elements_threshold = 10000 template struct GroupArraySortedData { + static constexpr bool is_value_generic_field = std::is_same_v; + using Allocator = MixedAlignedArenaAllocator; - using Array = PODArray; + using Array = typename std::conditional_t, PODArray>; static constexpr size_t partial_sort_max_elements_factor = 2; - static constexpr bool is_value_generic_field = std::is_same_v; - Array values; static bool compare(const T & lhs, const T & rhs) @@ -144,7 +144,7 @@ struct GroupArraySortedData } if (values.size() > max_elements) - values.resize(max_elements, arena); + resize(max_elements, arena); } ALWAYS_INLINE void partialSortAndLimitIfNeeded(size_t max_elements, Arena * arena) @@ -153,7 +153,23 @@ struct GroupArraySortedData return; ::nth_element(values.begin(), values.begin() + max_elements, values.end(), Comparator()); - values.resize(max_elements, arena); + resize(max_elements, arena); + } + + ALWAYS_INLINE void resize(size_t n, Arena * arena) + { + if constexpr (is_value_generic_field) + values.resize(n); + else + values.resize(n, arena); + } + + ALWAYS_INLINE void push_back(T && element, Arena * arena) + { + if constexpr (is_value_generic_field) + values.push_back(element); + else + values.push_back(element, arena); } ALWAYS_INLINE void addElement(T && element, size_t max_elements, Arena * arena) @@ -171,12 +187,12 @@ struct GroupArraySortedData return; } - values.push_back(std::move(element), arena); + push_back(std::move(element), arena); std::push_heap(values.begin(), values.end(), Comparator()); } else { - values.push_back(std::move(element), arena); + push_back(std::move(element), arena); partialSortAndLimitIfNeeded(max_elements, arena); } } @@ -210,14 +226,6 @@ struct GroupArraySortedData result_array_data[result_array_data_insert_begin + i] = values[i]; } } - - ~GroupArraySortedData() - { - for (auto & value : values) - { - value.~T(); - } - } }; template @@ -313,14 +321,12 @@ public: throw Exception(ErrorCodes::TOO_LARGE_ARRAY_SIZE, "Too large array size, it should not exceed {}", max_elements); auto & values = this->data(place).values; - values.resize_exact(size, arena); - if constexpr (std::is_same_v) + if constexpr (Data::is_value_generic_field) { + values.resize(size); for (Field & element : values) { - /// We must initialize the Field type since some internal functions (like operator=) use them - new (&element) Field; bool has_value = false; readBinary(has_value, buf); if (has_value) @@ -329,6 +335,7 @@ public: } else { + values.resize_exact(size, arena); if constexpr (std::endian::native == std::endian::little) { buf.readStrict(reinterpret_cast(values.data()), size * sizeof(values[0])); diff --git a/src/AggregateFunctions/AggregateFunctionQuantile.h b/src/AggregateFunctions/AggregateFunctionQuantile.h index 423fd4bc569..aa6755f237d 100644 --- a/src/AggregateFunctions/AggregateFunctionQuantile.h +++ b/src/AggregateFunctions/AggregateFunctionQuantile.h @@ -312,6 +312,9 @@ struct NameQuantilesExactInclusive { static constexpr auto name = "quantilesExac struct NameQuantileExactWeighted { static constexpr auto name = "quantileExactWeighted"; }; struct NameQuantilesExactWeighted { static constexpr auto name = "quantilesExactWeighted"; }; +struct NameQuantileExactWeightedInterpolated { static constexpr auto name = "quantileExactWeightedInterpolated"; }; +struct NameQuantilesExactWeightedInterpolated { static constexpr auto name = "quantilesExactWeightedInterpolated"; }; + struct NameQuantileInterpolatedWeighted { static constexpr auto name = "quantileInterpolatedWeighted"; }; struct NameQuantilesInterpolatedWeighted { static constexpr auto name = "quantilesInterpolatedWeighted"; }; diff --git a/src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp b/src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp index 469abdf45a2..116b04bf4ba 100644 --- a/src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp +++ b/src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp @@ -1,13 +1,14 @@ -#include #include +#include #include +#include #include #include -#include - #include #include +#include + namespace DB { @@ -29,7 +30,7 @@ namespace * It uses O(distinct(N)) memory. Can be naturally applied for values with weight. * In case of many identical values, it can be more efficient than QuantileExact even when weight is not used. */ -template +template struct QuantileExactWeighted { struct Int128Hash @@ -46,6 +47,7 @@ struct QuantileExactWeighted /// When creating, the hash table must be small. using Map = HashMapWithStackMemory; + using Pair = typename Map::value_type; Map map; @@ -58,8 +60,18 @@ struct QuantileExactWeighted void add(const Value & x, Weight weight) { - if (!isNaN(x)) - map[x] += weight; + if constexpr (!interpolated) + { + /// Keep compatibility for function quantilesExactWeighted. + if (!isNaN(x)) + map[x] += weight; + } + else + { + /// Ignore values with zero weight in function quantilesExactWeightedInterpolated. + if (!isNaN(x) && weight) + map[x] += weight; + } } void merge(const QuantileExactWeighted & rhs) @@ -85,6 +97,43 @@ struct QuantileExactWeighted /// Get the value of the `level` quantile. The level must be between 0 and 1. Value get(Float64 level) const + { + if constexpr (interpolated) + return getInterpolatedImpl(level); + else + return getImpl(level); + } + + /// Get the `size` values of `levels` quantiles. Write `size` results starting with `result` address. + /// indices - an array of index levels such that the corresponding elements will go in ascending order. + void getMany(const Float64 * levels, const size_t * indices, size_t num_levels, Value * result) const + { + if constexpr (interpolated) + getManyInterpolatedImpl(levels, indices, num_levels, result); + else + getManyImpl(levels, indices, num_levels, result); + } + + Float64 getFloat(Float64 level) const + { + if constexpr (interpolated) + return getFloatInterpolatedImpl(level); + else + return getFloatImpl(level); + } + + void getManyFloat(const Float64 * levels, const size_t * indices, size_t num_levels, Float64 * result) const + { + if constexpr (interpolated) + getManyFloatInterpolatedImpl(levels, indices, num_levels, result); + else + getManyFloatImpl(levels, indices, num_levels, result); + } + +private: + /// get implementation without interpolation + Value getImpl(Float64 level) const + requires(!interpolated) { size_t size = map.size(); @@ -92,7 +141,6 @@ struct QuantileExactWeighted return std::numeric_limits::quiet_NaN(); /// Copy the data to a temporary array to get the element you need in order. - using Pair = typename Map::value_type; std::unique_ptr array_holder(new Pair[size]); Pair * array = array_holder.get(); @@ -135,9 +183,9 @@ struct QuantileExactWeighted return it->first; } - /// Get the `size` values of `levels` quantiles. Write `size` results starting with `result` address. - /// indices - an array of index levels such that the corresponding elements will go in ascending order. - void getMany(const Float64 * levels, const size_t * indices, size_t num_levels, Value * result) const + /// getMany implementation without interpolation + void getManyImpl(const Float64 * levels, const size_t * indices, size_t num_levels, Value * result) const + requires(!interpolated) { size_t size = map.size(); @@ -149,7 +197,6 @@ struct QuantileExactWeighted } /// Copy the data to a temporary array to get the element you need in order. - using Pair = typename Map::value_type; std::unique_ptr array_holder(new Pair[size]); Pair * array = array_holder.get(); @@ -197,23 +244,165 @@ struct QuantileExactWeighted } } - /// The same, but in the case of an empty state, NaN is returned. - Float64 getFloat(Float64) const + /// getFloat implementation without interpolation + Float64 getFloatImpl(Float64) const + requires(!interpolated) { throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Method getFloat is not implemented for QuantileExact"); } - void getManyFloat(const Float64 *, const size_t *, size_t, Float64 *) const + /// getManyFloat implementation without interpolation + void getManyFloatImpl(const Float64 *, const size_t *, size_t, Float64 *) const + requires(!interpolated) { throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Method getManyFloat is not implemented for QuantileExact"); } + + /// get implementation with interpolation + Value getInterpolatedImpl(Float64 level) const + requires(interpolated) + { + size_t size = map.size(); + if (0 == size) + return Value(); + + Float64 res = getFloatInterpolatedImpl(level); + if constexpr (is_decimal) + return Value(static_cast(res)); + else + return static_cast(res); + } + + /// getMany implementation with interpolation + void getManyInterpolatedImpl(const Float64 * levels, const size_t * indices, size_t num_levels, Value * result) const + requires(interpolated) + { + size_t size = map.size(); + if (0 == size) + { + for (size_t i = 0; i < num_levels; ++i) + result[i] = Value(); + return; + } + + std::unique_ptr res_holder(new Float64[num_levels]); + Float64 * res = res_holder.get(); + getManyFloatInterpolatedImpl(levels, indices, num_levels, res); + for (size_t i = 0; i < num_levels; ++i) + { + if constexpr (is_decimal) + result[i] = Value(static_cast(res[i])); + else + result[i] = Value(res[i]); + } + } + + /// getFloat implementation with interpolation + Float64 getFloatInterpolatedImpl(Float64 level) const + requires(interpolated) + { + size_t size = map.size(); + + if (0 == size) + return std::numeric_limits::quiet_NaN(); + + /// Copy the data to a temporary array to get the element you need in order. + std::unique_ptr array_holder(new Pair[size]); + Pair * array = array_holder.get(); + + size_t i = 0; + for (const auto & pair : map) + { + array[i] = pair.getValue(); + ++i; + } + + ::sort(array, array + size, [](const Pair & a, const Pair & b) { return a.first < b.first; }); + std::partial_sum(array, array + size, array, [](const Pair & acc, const Pair & p) { return Pair(p.first, acc.second + p.second); }); + Weight max_position = array[size - 1].second - 1; + Float64 position = max_position * level; + return quantileInterpolated(array, size, position); + } + + /// getManyFloat implementation with interpolation + void getManyFloatInterpolatedImpl(const Float64 * levels, const size_t * indices, size_t num_levels, Float64 * result) const + requires(interpolated) + { + size_t size = map.size(); + if (0 == size) + { + for (size_t i = 0; i < num_levels; ++i) + result[i] = std::numeric_limits::quiet_NaN(); + return; + } + + /// Copy the data to a temporary array to get the element you need in order. + std::unique_ptr array_holder(new Pair[size]); + Pair * array = array_holder.get(); + + size_t i = 0; + for (const auto & pair : map) + { + array[i] = pair.getValue(); + ++i; + } + + ::sort(array, array + size, [](const Pair & a, const Pair & b) { return a.first < b.first; }); + std::partial_sum(array, array + size, array, [](Pair acc, Pair & p) { return Pair(p.first, acc.second + p.second); }); + Weight max_position = array[size - 1].second - 1; + + for (size_t j = 0; j < num_levels; ++j) + { + Float64 position = max_position * levels[indices[j]]; + result[indices[j]] = quantileInterpolated(array, size, position); + } + } + + /// Calculate quantile, using linear interpolation between two closest values + Float64 NO_SANITIZE_UNDEFINED quantileInterpolated(const Pair * array, size_t size, Float64 position) const + requires(interpolated) + { + size_t lower = static_cast(std::floor(position)); + size_t higher = static_cast(std::ceil(position)); + + const auto * lower_it = std::lower_bound(array, array + size, lower + 1, [](const Pair & a, size_t b) { return a.second < b; }); + const auto * higher_it = std::lower_bound(array, array + size, higher + 1, [](const Pair & a, size_t b) { return a.second < b; }); + if (lower_it == array + size) + lower_it = array + size - 1; + if (higher_it == array + size) + higher_it = array + size - 1; + + UnderlyingType lower_key = lower_it->first; + UnderlyingType higher_key = higher_it->first; + + if (lower == higher || lower_key == higher_key) + return static_cast(lower_key); + + return (static_cast(higher) - position) * lower_key + (position - static_cast(lower)) * higher_key; + } }; -template using FuncQuantileExactWeighted = AggregateFunctionQuantile, NameQuantileExactWeighted, true, void, false, false>; -template using FuncQuantilesExactWeighted = AggregateFunctionQuantile, NameQuantilesExactWeighted, true, void, true, false>; +template +using FuncQuantileExactWeighted = AggregateFunctionQuantile< + Value, + QuantileExactWeighted, + std::conditional_t, + true, + std::conditional_t, + false, + false>; +template +using FuncQuantilesExactWeighted = AggregateFunctionQuantile< + Value, + QuantileExactWeighted, + std::conditional_t, + true, + std::conditional_t, + true, + false>; -template